| 1. |
|
|
| 2. |
|
|
| 3. |
- Smedby, Örjan, et al.
(författare)
-
Measures of continuity of care. A register-based correlation study.
- 1986
-
Ingår i: Medical Care. - 0025-7079 .- 1537-1948. ; 24:6, s. 511-518
-
Tidskriftsartikel (refereegranskat)abstract
- In an empirical study using data from a health center in Sweden, correlation coefficients were computed among nine different measures of continuity of care, five of them visit-based and four individual-based. Generally, the correlations were high. This may be due, in part, to the similar behavior of the measures for people making few visits. The correlations were also quite high, however, when the sample was restricted to people with many visits. Several measures display a significant dependence on utilization level. The results suggest that, for general purposes, the measure COC should be preferred among the individual-based measures and fraction-of-care continuity among the visit-based measures. On grounds of flexibility and ease of interpretation, the authors recommend fraction-of-care measures.
|
|
| 4. |
- Aalto, Anne, et al.
(författare)
-
Brain magnetic resonance imaging does not contribute to the diagnosis of chronic neuroborreliosis
- 2007
-
Ingår i: Acta Radiologica. - : SAGE Publications. - 0284-1851 .- 1600-0455. ; 48:7, s. 755-762
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Borrelia infections, especially chronic neuroborreliosis ( NB), may cause considerable diagnostic problems. This diagnosis is based on symptoms and findings in the cerebrospinal fluid but is not always conclusive. Purpose: To evaluate brain magnetic resonance imaging ( MRI) in chronic NB, to compare the findings with healthy controls, and to correlate MRI findings with disease duration. Material and Methods: Sixteen well- characterized patients with chronic NB and 16 matched controls were examined in a 1.5T scanner with a standard head coil. T1- ( with and without gadolinium), T2-, and diffusion- weighted imaging plus fluid- attenuated inversion recovery ( FLAIR) imaging were used. Results: White matter lesions and lesions in the basal ganglia were seen in 12 patients and 10 controls ( no significant difference). Subependymal lesions were detected in patients down to the age of 25 and in the controls down to the age of 43. The number of lesions was correlated to age both in patients ( rho=0.83, P < 0.01) and in controls ( rho=0.61, P < 0.05), but not to the duration of disease. Most lesions were detected with FLAIR, but many also with T2- weighted imaging. Conclusion: A number of MRI findings were detected in patients with chronic NB, although the findings were unspecific when compared with matched controls and did not correlate with disease duration. However, subependymal lesions may constitute a potential finding in chronic NB.
|
|
| 5. |
|
|
| 6. |
- Ahle, Margareta, 1966-
(författare)
-
Necrotising Enterocolitis : epidemiology and imaging
- 2017
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Necrotising enterocolitis (NEC) is a potentially devastating intestinal inflammation of multifactorial aetiology in premature or otherwise vulnerable neonates. Because of the broad spectrum of presentations, diagnosis and timing of surgical intervention may be challenging, and imaging needs to be an integrated part of management.The first four studies included in this thesis used routinely collected, nationwide register data to describe the incidence of NEC in Sweden 1987‒2009, its variation with time, seasonality, space-time clustering, and associations with maternal, gestational, and perinatal factors, and the risk of intestinal failure in the aftermath of the disease.Early infant survival increased dramatically during the study period. The incidence rate of NEC was 0.34 per 1,000 live births, rising from 0.26 per 1,000 live births in the first six years of the study period to 0.57 in the last five. The incidence rates in the lowest birth weights were 100‒160 times those of the entire birth cohort. Seasonal variation was found, as well as space-time clustering in association with delivery hospitals but not with maternal residential municipalities.Comparing NEC cases with matched controls, some factors, positively associated with NEC, were isoimmunisation, fetal distress, caesarean section, persistent ductus arteriosus, cardiac and gastrointestinal malformations, and chromosomal abnormalities. Negative associations included maternal pre-eclampsia, maternal urinary infection, and premature rupture of the membranes. Intestinal failure occurred in 6% of NEC cases and 0.4% of controls, with the highest incidence towards the end of the study period.The last study investigated current practices and perceptions of imaging in the management of NEC, as reported by involved specialists. There was great consensus on most issues. Areas in need of further study seem mainly related to imaging routines, the use of ultrasound, and indications for surgery.Developing alongside the progress of neonatal care, NEC is a complex, multifactorial disease, with shifting patterns of predisposing and precipitating causes, and potentially serious long-term complications. The findings of seasonal variation, spacetime clustering, and negative associations with antenatal exposure to infectious agents, fit into the growing understanding of the central role of bacteria and immunological processes in normal maturation of the intestinal canal as well as in the pathogenesis of NEC. Imaging in the management of NEC may be developed through future studies combining multiple diagnostic parameters in relation to clinical outcome.
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Andersson, Mats, et al.
(författare)
-
Adaptiv filtering of 4D-heart CT for image denoising and patient safety
- 2010
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- The aim of this medical image science project is to increase patient safety in terms of improved image quality and reduced exposure to ionizing radiation in CT. The means to achieve these goals is to develop and evaluate an efficient adaptive filtering (denoising/image enhancement) method that fully explores true 4D image acquisition modes. Four-dimensional (4D) medical image data are captured as a time sequence of image volumes. During 4D image acquisition, a 3D image of the patient is recorded at regular time intervals. The resulting data will consequently have three spatial dimensions and one temporal dimension. Increasing the dimensionality of the data impose a major increase the computational demands. The initial linear filtering which is the cornerstone in all adaptive image enhancement algorithms increase exponentially with the dimensionality. On the other hand the potential gain in Signal to Noise Ratio (SNR) also increase exponentially with the dimensionality. This means that the same gain in noise reduction that can be attained by performing the adaptive filtering in 3D as opposed to 2D can be expected to occur once more by moving from 3D to 4D. The initial tests on on both synthetic and clinical 4D images has resulted in a significant reduction of the noise level and an increased detail compared to 2D and 3D methods. When tuning the parameters for adaptive filtering is extremely important to attain maximal diagnostic value which not necessarily coincide with an an eye pleasing image for a layman. Although this application focus on CT the resulting adaptive filtering methods will be beneficial for a wide range of 3D/4D medical imaging modalities e.g. shorter acquisition time in MRI and improved elimination of noise in 3D or 4D ultrasound datasets.
|
|
| 11. |
- Andersson, Malin, et al.
(författare)
-
How to measure renal artery stenosis - a retrospective comparison of morphological measurement approaches in relation to hemodynamic significance
- 2015
-
Ingår i: BMC Medical Imaging. - : BioMed Central. - 1471-2342. ; 15
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Although it is well known that renal artery stenosis may cause renovascular hypertension, it is unclear how the degree of stenosis should best be measured in morphological images. The aim of this study was to determine which morphological measures from Computed Tomography Angiography (CTA) and Magnetic Resonance Angiography (MRA) are best in predicting whether a renal artery stenosis is hemodynamically significant or not. Methods: Forty-seven patients with hypertension and a clinical suspicion of renovascular hypertension were examined with CTA, MRA, captopril-enhanced renography (CER) and captopril test (Ctest). CTA and MRA images of the renal arteries were analyzed by two readers using interactive vessel segmentation software. The measures included minimum diameter, minimum area, diameter reduction and area reduction. In addition, two radiologists visually judged the diameter reduction without automated segmentation. The results were then compared using limits of agreement and intra-class correlation, and correlated with the results from CER combined with Ctest (which were used as standard of reference) using receiver operating characteristics (ROC) analysis. Results: A total of 68 kidneys had all three investigations (CTA, MRA and CER + Ctest), where 11 kidneys (16.2 %) got a positive result on the CER + Ctest. The greatest area under ROC curve (AUROC) was found for the area reduction on MRA, with a value of 0.91 (95 % confidence interval 0.82-0.99), excluding accessory renal arteries. As comparison, the AUROC for the radiologists' visual assessments on CTA and MRA were 0.90 (0.82-0.98) and 0.91 (0.83-0.99) respectively. None of the differences were statistically significant. Conclusions: No significant differences were found between the morphological measures in their ability to predict hemodynamically significant stenosis, but a tendency of MRA having higher AUROC than CTA. There was no significant difference between measurements made by the radiologists and measurements made with fuzzy connectedness segmentation. Further studies are required to definitely identify the optimal measurement approach.
|
|
| 12. |
- Andersson, Thord, et al.
(författare)
-
Consistent intensity inhomogeneity correction in water-fat MRI
- 2015
-
Ingår i: Journal of Magnetic Resonance Imaging. - : Wiley-Blackwell. - 1053-1807 .- 1522-2586. ; 42:2
-
Tidskriftsartikel (refereegranskat)abstract
- PURPOSE: To quantitatively and qualitatively evaluate the water-signal performance of the consistent intensity inhomogeneity correction (CIIC) method to correct for intensity inhomogeneitiesMETHODS: Water-fat volumes were acquired using 1.5 Tesla (T) and 3.0T symmetrically sampled 2-point Dixon three-dimensional MRI. Two datasets: (i) 10 muscle tissue regions of interest (ROIs) from 10 subjects acquired with both 1.5T and 3.0T whole-body MRI. (ii) Seven liver tissue ROIs from 36 patients imaged using 1.5T MRI at six time points after Gd-EOB-DTPA injection. The performance of CIIC was evaluated quantitatively by analyzing its impact on the dispersion and bias of the water image ROI intensities, and qualitatively using side-by-side image comparisons.RESULTS: CIIC significantly ( P1.5T≤2.3×10-4,P3.0T≤1.0×10-6) decreased the nonphysiological intensity variance while preserving the average intensity levels. The side-by-side comparisons showed improved intensity consistency ( Pint≤10-6) while not introducing artifacts ( Part=0.024) nor changed appearances ( Papp≤10-6).CONCLUSION: CIIC improves the spatiotemporal intensity consistency in regions of a homogenous tissue type.
|
|
| 13. |
|
|
| 14. |
|
|
| 15. |
- Astaraki, Mehdi, PhD Student, 1984-, et al.
(författare)
-
A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images
- 2021
-
Ingår i: Frontiers in Oncology. - : Frontiers Media SA. - 2234-943X. ; 11
-
Tidskriftsartikel (refereegranskat)abstract
- Objectives: Both radiomics and deep learning methods have shown great promise in predicting lesion malignancy in various image-based oncology studies. However, it is still unclear which method to choose for a specific clinical problem given the access to the same amount of training data. In this study, we try to compare the performance of a series of carefully selected conventional radiomics methods, end-to-end deep learning models, and deep-feature based radiomics pipelines for pulmonary nodule malignancy prediction on an open database that consists of 1297 manually delineated lung nodules.Methods: Conventional radiomics analysis was conducted by extracting standard handcrafted features from target nodule images. Several end-to-end deep classifier networks, including VGG, ResNet, DenseNet, and EfficientNet were employed to identify lung nodule malignancy as well. In addition to the baseline implementations, we also investigated the importance of feature selection and class balancing, as well as separating the features learned in the nodule target region and the background/context region. By pooling the radiomics and deep features together in a hybrid feature set, we investigated the compatibility of these two sets with respect to malignancy prediction.Results: The best baseline conventional radiomics model, deep learning model, and deep-feature based radiomics model achieved AUROC values (mean ± standard deviations) of 0.792 ± 0.025, 0.801 ± 0.018, and 0.817 ± 0.032, respectively through 5-fold cross-validation analyses. However, after trying out several optimization techniques, such as feature selection and data balancing, as well as adding context features, the corresponding best radiomics, end-to-end deep learning, and deep-feature based models achieved AUROC values of 0.921 ± 0.010, 0.824 ± 0.021, and 0.936 ± 0.011, respectively. We achieved the best prediction accuracy from the hybrid feature set (AUROC: 0.938 ± 0.010).Conclusion: The end-to-end deep-learning model outperforms conventional radiomics out of the box without much fine-tuning. On the other hand, fine-tuning the models lead to significant improvements in the prediction performance where the conventional and deep-feature based radiomics models achieved comparable results. The hybrid radiomics method seems to be the most promising model for lung nodule malignancy prediction in this comparative study.
|
|
| 16. |
- Astaraki, Mehdi, PhD Student, 1984-
(författare)
-
Advanced Machine Learning Methods for Oncological Image Analysis
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Cancer is a major public health problem, accounting for an estimated 10 million deaths worldwide in 2020 alone. Rapid advances in the field of image acquisition and hardware development over the past three decades have resulted in the development of modern medical imaging modalities that can capture high-resolution anatomical, physiological, functional, and metabolic quantitative information from cancerous organs. Therefore, the applications of medical imaging have become increasingly crucial in the clinical routines of oncology, providing screening, diagnosis, treatment monitoring, and non/minimally-invasive evaluation of disease prognosis. The essential need for medical images, however, has resulted in the acquisition of a tremendous number of imaging scans. Considering the growing role of medical imaging data on one side and the challenges of manually examining such an abundance of data on the other side, the development of computerized tools to automatically or semi-automatically examine the image data has attracted considerable interest. Hence, a variety of machine learning tools have been developed for oncological image analysis, aiming to assist clinicians with repetitive tasks in their workflow.This thesis aims to contribute to the field of oncological image analysis by proposing new ways of quantifying tumor characteristics from medical image data. Specifically, this thesis consists of six studies, the first two of which focus on introducing novel methods for tumor segmentation. The last four studies aim to develop quantitative imaging biomarkers for cancer diagnosis and prognosis.The main objective of Study I is to develop a deep learning pipeline capable of capturing the appearance of lung pathologies, including lung tumors, and integrating this pipeline into the segmentation networks to leverage the segmentation accuracy. The proposed pipeline was tested on several comprehensive datasets, and the numerical quantifications show the superiority of the proposed prior-aware DL framework compared to the state of the art. Study II aims to address a crucial challenge faced by supervised segmentation models: dependency on the large-scale labeled dataset. In this study, an unsupervised segmentation approach is proposed based on the concept of image inpainting to segment lung and head-neck tumors in images from single and multiple modalities. The proposed autoinpainting pipeline shows great potential in synthesizing high-quality tumor-free images and outperforms a family of well-established unsupervised models in terms of segmentation accuracy.Studies III and IV aim to automatically discriminate the benign from the malignant pulmonary nodules by analyzing the low-dose computed tomography (LDCT) scans. In Study III, a dual-pathway deep classification framework is proposed to simultaneously take into account the local intra-nodule heterogeneities and the global contextual information. Study IV seeks to compare the discriminative power of a series of carefully selected conventional radiomics methods, end-to-end Deep Learning (DL) models, and deep features-based radiomics analysis on the same dataset. The numerical analyses show the potential of fusing the learned deep features into radiomic features for boosting the classification power.Study V focuses on the early assessment of lung tumor response to the applied treatments by proposing a novel feature set that can be interpreted physiologically. This feature set was employed to quantify the changes in the tumor characteristics from longitudinal PET-CT scans in order to predict the overall survival status of the patients two years after the last session of treatments. The discriminative power of the introduced imaging biomarkers was compared against the conventional radiomics, and the quantitative evaluations verified the superiority of the proposed feature set. Whereas Study V focuses on a binary survival prediction task, Study VI addresses the prediction of survival rate in patients diagnosed with lung and head-neck cancer by investigating the potential of spherical convolutional neural networks and comparing their performance against other types of features, including radiomics. While comparable results were achieved in intra-dataset analyses, the proposed spherical-based features show more predictive power in inter-dataset analyses.In summary, the six studies incorporate different imaging modalities and a wide range of image processing and machine-learning techniques in the methods developed for the quantitative assessment of tumor characteristics and contribute to the essential procedures of cancer diagnosis and prognosis.
|
|
| 17. |
- Astaraki, Mehdi, PhD Student, 1984-, et al.
(författare)
-
Benign-malignant pulmonary nodule classification in low-dose CT with convolutional features
- 2021
-
Ingår i: Physica medica (Testo stampato). - : Elsevier BV. - 1120-1797 .- 1724-191X. ; 83, s. 146-153
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Low-Dose Computed Tomography (LDCT) is the most common imaging modality for lung cancer diagnosis. The presence of nodules in the scans does not necessarily portend lung cancer, as there is an intricate relationship between nodule characteristics and lung cancer. Therefore, benign-malignant pulmonary nodule classification at early detection is a crucial step to improve diagnosis and prolong patient survival. The aim of this study is to propose a method for predicting nodule malignancy based on deep abstract features.Methods: To efficiently capture both intra-nodule heterogeneities and contextual information of the pulmonary nodules, a dual pathway model was developed to integrate the intra-nodule characteristics with contextual attributes. The proposed approach was implemented with both supervised and unsupervised learning schemes. A random forest model was added as a second component on top of the networks to generate the classification results. The discrimination power of the model was evaluated by calculating the Area Under the Receiver Operating Characteristic Curve (AUROC) metric. Results: Experiments on 1297 manually segmented nodules show that the integration of context and target supervised deep features have a great potential for accurate prediction, resulting in a discrimination power of 0.936 in terms of AUROC, which outperformed the classification performance of the Kaggle 2017 challenge winner.Conclusion: Empirical results demonstrate that integrating nodule target and context images into a unified network improves the discrimination power, outperforming the conventional single pathway convolutional neural networks.
|
|
| 18. |
- Astaraki, Mehdi, PhD Student, 1984-, et al.
(författare)
-
Early survival prediction in non-small cell lung cancer from PET/CT images using an intra-tumor partitioning method
- 2019
-
Ingår i: Physica medica (Testo stampato). - : Elsevier BV. - 1120-1797 .- 1724-191X. ; 60, s. 58-65
-
Tidskriftsartikel (refereegranskat)abstract
- PurposeTo explore prognostic and predictive values of a novel quantitative feature set describing intra-tumor heterogeneity in patients with lung cancer treated with concurrent and sequential chemoradiotherapy.MethodsLongitudinal PET-CT images of 30 patients with non-small cell lung cancer were analysed. To describe tumor cell heterogeneity, the tumors were partitioned into one to ten concentric regions depending on their sizes, and, for each region, the change in average intensity between the two scans was calculated for PET and CT images separately to form the proposed feature set. To validate the prognostic value of the proposed method, radiomics analysis was performed and a combination of the proposed novel feature set and the classic radiomic features was evaluated. A feature selection algorithm was utilized to identify the optimal features, and a linear support vector machine was trained for the task of overall survival prediction in terms of area under the receiver operating characteristic curve (AUROC).ResultsThe proposed novel feature set was found to be prognostic and even outperformed the radiomics approach with a significant difference (AUROCSALoP = 0.90 vs. AUROCradiomic = 0.71) when feature selection was not employed, whereas with feature selection, a combination of the novel feature set and radiomics led to the highest prognostic values.ConclusionA novel feature set designed for capturing intra-tumor heterogeneity was introduced. Judging by their prognostic power, the proposed features have a promising potential for early survival prediction.
|
|
| 19. |
- Astaraki, Mehdi, PhD Student, 1984-, et al.
(författare)
-
Multimodal brain tumor segmentation with normal appearance autoencoder
- 2019
-
Ingår i: International MICCAI Brainlesion Workshop. - Cham : Springer Nature. ; , s. 316-323
-
Konferensbidrag (refereegranskat)abstract
- We propose a hybrid segmentation pipeline based on the autoencoders’ capability of anomaly detection. To this end, we, first, introduce a new augmentation technique to generate synthetic paired images. Gaining advantage from the paired images, we propose a Normal Appearance Autoencoder (NAA) that is able to remove tumors and thus reconstruct realistic-looking, tumor-free images. After estimating the regions where the abnormalities potentially exist, a segmentation network is guided toward the candidate region. We tested the proposed pipeline on the BraTS 2019 database. The preliminary results indicate that the proposed model improved the segmentation accuracy of brain tumor subregions compared to the U-Net model.
|
|
| 20. |
- Astaraki, Mehdi, PhD Student, 1984-, et al.
(författare)
-
Normal appearance autoencoder for lung cancer detection and segmentation
- 2019
-
Ingår i: International Conference on Medical Image Computing and Computer-Assisted Intervention. - Cham : Springer Nature. ; , s. 249-256
-
Konferensbidrag (refereegranskat)abstract
- One of the major differences between medical doctor training and machine learning is that doctors are trained to recognize normal/healthy anatomy first. Knowing the healthy appearance of anatomy structures helps doctors to make better judgement when some abnormality shows up in an image. In this study, we propose a normal appearance autoencoder (NAA), that removes abnormalities from a diseased image. This autoencoder is semi-automatically trained using another partial convolutional in-paint network that is trained using healthy subjects only. The output of the autoencoder is then fed to a segmentation net in addition to the original input image, i.e. the latter gets both the diseased image and a simulated healthy image where the lesion is artificially removed. By getting access to knowledge of how the abnormal region is supposed to look, we hypothesized that the segmentation network could perform better than just being shown the original slice. We tested the proposed network on the LIDC-IDRI dataset for lung cancer detection and segmentation. The preliminary results show the NAA approach improved segmentation accuracy substantially in comparison with the conventional U-Net architecture.
|
|
| 21. |
|
|
| 22. |
- Astaraki, Mehdi, PhD Student, 1984-, et al.
(författare)
-
Prior-aware autoencoders for lung pathology segmentation
- 2022
-
Ingår i: Medical Image Analysis. - : Elsevier BV. - 1361-8415 .- 1361-8423. ; 80, s. 102491-
-
Tidskriftsartikel (refereegranskat)abstract
- Segmentation of lung pathology in Computed Tomography (CT) images is of great importance for lung disease screening. However, the presence of different types of lung pathologies with a wide range of heterogeneities in size, shape, location, and texture, on one side, and their visual similarity with respect to surrounding tissues, on the other side, make it challenging to perform reliable automatic lesion seg-mentation. To leverage segmentation performance, we propose a deep learning framework comprising a Normal Appearance Autoencoder (NAA) model to learn the distribution of healthy lung regions and re-construct pathology-free images from the corresponding pathological inputs by replacing the pathological regions with the characteristics of healthy tissues. Detected regions that represent prior information re-garding the shape and location of pathologies are then integrated into a segmentation network to guide the attention of the model into more meaningful delineations. The proposed pipeline was tested on three types of lung pathologies, including pulmonary nodules, Non-Small Cell Lung Cancer (NSCLC), and Covid-19 lesion on five comprehensive datasets. The results show the superiority of the proposed prior model, which outperformed the baseline segmentation models in all the cases with significant margins. On av-erage, adding the prior model improved the Dice coefficient for the segmentation of lung nodules by 0.038, NSCLCs by 0.101, and Covid-19 lesions by 0.041. We conclude that the proposed NAA model pro-duces reliable prior knowledge regarding the lung pathologies, and integrating such knowledge into a prior segmentation network leads to more accurate delineations.
|
|
| 23. |
|
|
| 24. |
|
|
| 25. |
- Bendazzoli, Simone, et al.
(författare)
-
Automatic rat brain segmentation from MRI using statistical shape models and random forest
- 2019
-
Ingår i: MEDICAL IMAGING 2019. - : SPIE-INT SOC OPTICAL ENGINEERING. - 9781510625464 - 9781510625457
-
Konferensbidrag (refereegranskat)abstract
- In MRI neuroimaging, the shimming procedure is used before image acquisition to correct for inhomogeneity of the static magnetic field within the brain. To correctly adjust the field, the brain's location and edges must first be identified from quickly-acquired low resolution data. This process is currently carried out manually by an operator, which can be time-consuming and not always accurate. In this work, we implement a quick and automatic technique for brain segmentation to be potentially used during the shimming. Our method is based on two main steps. First, a random forest classifier is used to get a preliminary segmentation from an input MRI image. Subsequently, a statistical shape model of the brain, which was previously generated from ground-truth segmentations, is fitted to the output of the classifier to obtain a model-based segmentation mask. In this way, a-priori knowledge on the brain's shape is included in the segmentation pipeline. The proposed methodology was tested on low resolution images of rat brains and further validated on rabbit brain images of higher resolution. Our results suggest that the present method is promising for the desired purpose in terms of time efficiency, segmentation accuracy and repeatability. Moreover, the use of shape modeling was shown to be particularly useful when handling low-resolution data, which could lead to erroneous classifications when using only machine learning-based methods.
|
|
| 26. |
|
|
| 27. |
- Bendazzoli, Simone, et al.
(författare)
-
Lung vessel connectivity map as anatomical prior knowledge for deep learning-based lung lobe segmentation
- 2024
-
Ingår i: Journal of Medical Imaging. - : SPIE-Intl Soc Optical Eng. - 2329-4302 .- 2329-4310. ; 11:4
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose Our study investigates the potential benefits of incorporating prior anatomical knowledge into a deep learning (DL) method designed for the automated segmentation of lung lobes in chest CT scans. Approach We introduce an automated DL-based approach that leverages anatomical information from the lung's vascular system to guide and enhance the segmentation process. This involves utilizing a lung vessel connectivity (LVC) map, which encodes relevant lung vessel anatomical data. Our study explores the performance of three different neural network architectures within the nnU-Net framework: a standalone U-Net, a multitasking U-Net, and a cascade U-Net. Results Experimental findings suggest that the inclusion of LVC information in the DL model can lead to improved segmentation accuracy, particularly, in the challenging boundary regions of expiration chest CT volumes. Furthermore, our study demonstrates the potential for LVC to enhance the model's generalization capabilities. Finally, the method's robustness is evaluated through the segmentation of lung lobes in 10 cases of COVID-19, demonstrating its applicability in the presence of pulmonary diseases. Conclusions Incorporating prior anatomical information, such as LVC, into the DL model shows promise for enhancing segmentation performance, particularly in the boundary regions. However, the extent of this improvement has limitations, prompting further exploration of its practical applicability.
|
|
| 28. |
- Bernard, Olivier, et al.
(författare)
-
Standardized evaluation system for left ventricular segmentation algorithms in 3D echocardiography.
- 2016
-
Ingår i: IEEE Transactions on Medical Imaging. - : Institute of Electrical and Electronics Engineers (IEEE). - 0278-0062 .- 1558-254X. ; 35:4, s. 967-977
-
Tidskriftsartikel (refereegranskat)abstract
- Real-time 3D Echocardiography (RT3DE) has been proven to be an accurate tool for left ventricular (LV) volume assessment. However, identification of the LV endocardium remains a challenging task, mainly because of the low tissue/blood contrast of the images combined with typical artifacts. Several semi and fully automatic algorithms have been proposed for segmenting the endocardium in RT3DE data in order to extract relevant clinical indices, but a systematic and fair comparison between such methods has so far been impossible due to the lack of a publicly available common database. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms developed to segment the LV border in RT3DE. A database consisting of 45 multivendor cardiac ultrasound recordings acquired at different centers with corresponding reference measurements from 3 experts are made available. The algorithms from nine research groups were quantitatively evaluated and compared using the proposed online platform. The results showed that the best methods produce promising results with respect to the experts' measurements for the extraction of clinical indices, and that they offer good segmentation precision in terms of mean distance error in the context of the experts' variability range. The platform remains open for new submissions.
|
|
| 29. |
- Blystad, Ida, 1972-
(författare)
-
Clinical Applications of Synthetic MRI of the Brain
- 2017
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Magnetic Resonance Imaging (MRI) has a high soft-tissue contrast with a high sensitivity for detecting pathological changes in the brain. Conventional MRI is a time-consuming method with multiple scans that relies on the visual assessment of the neuroradiologist. Synthetic MRI uses one scan to produce conventional images, but also quantitative maps based on relaxometry, that can be used to quantitatively analyse tissue properties and pathological changes. The studies presented here apply the use of synthetic MRI of the brain in different clinical settings.In the first study, synthetic MR images were compared to conventional MR images in 22 patients. The contrast, the contrast-to-noise ratio, and the diagnostic quality were assessed. Image quality was perceived to be inferior in the synthetic images, but synthetic images agreed with the clinical diagnoses to the same extent as the conventional images.Patients with early multiple sclerosis were analysed in the second study. In patients with multiple sclerosis, contrast-enhancing white matter lesions are a sign of active disease and can indicate a need for a change in therapy. Gadolinium-based contrast agents are used to detect active lesions, but concern has been raised regarding the long-term effects of repeated use of gadolinium. In this study, relaxometry was used to evaluate whether pre-contrast injection tissue-relaxation rates and proton density can identify active lesions without gadolinium. The findings suggest that active lesions often have relaxation times and proton density that differ from non-enhancing lesions, but with some overlap. This makes it difficult to replace gadolinium-based contrast agent injection with synthetic MRI in the monitoring of MS patients.Malignant gliomas are primary brain tumours with contrast enhancement due to a defective blood-brain barrier. However, they also grow in an infiltrative, diffuse manner, making it difficult to clearly delineate them from surrounding normal brain tissue in the diagnostic workup, at surgery, and during follow-up. The contrast-enhancing part of the tumour is easily visualised, but not the diffuse infiltration. In studies three and four, synthetic MRI was used to analyse the peritumoral area of malignant gliomas, and revealed quantitative findings regarding peritumoral relaxation changes and non-visible contrast enhancement suggestive of non-visible infiltrative tumour growth.In conclusion, synthetic MRI provides quantitative information about the brain tissue and this could improve the diagnosis and treatment for patients.
|
|
| 30. |
- Blystad, Ida, et al.
(författare)
-
Quantitative MRI for Analysis of Active Multiple Sclerosis Lesions without Gadolinium-Based Contrast Agent
- 2016
-
Ingår i: American Journal of Neuroradiology. - : American Society of Neuroradiology (ASNR). - 0195-6108 .- 1936-959X. ; 37:1, s. 94-100
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND AND PURPOSE: Contrast-enhancing MS lesions are important markers of active inflammation in the diagnostic work-up of MS and in disease monitoring with MR imaging. Because intravenous contrast agents involve an expense and a potential risk of adverse events, it would be desirable to identify active lesions without using a contrast agent. The purpose of this study was to evaluate whether pre-contrast injection tissue-relaxation rates and proton density of MS lesions, by using a new quantitative MR imaging sequence, can identify active lesions.MATERIALS AND METHODS: Forty-four patients with a clinical suspicion of MS were studied. MR imaging with a standard clinical MS protocol and a quantitative MR imaging sequence was performed at inclusion (baseline) and after 1 year. ROIs were placed in MS lesions, classified as nonenhancing or enhancing. Longitudinal and transverse relaxation rates, as well as proton density were obtained from the quantitative MR imaging sequence. Statistical analyses of ROI values were performed by using a mixed linear model, logistic regression, and receiver operating characteristic analysis.RESULTS: Enhancing lesions had a significantly (P < .001) higher mean longitudinal relaxation rate (1.22 ± 0.36 versus 0.89 ± 0.24), a higher mean transverse relaxation rate (9.8 ± 2.6 versus 7.4 ± 1.9), and a lower mean proton density (77 ± 11.2 versus 90 ± 8.4) than nonenhancing lesions. An area under the receiver operating characteristic curve value of 0.832 was obtained.CONCLUSIONS: Contrast-enhancing MS lesions often have proton density and relaxation times that differ from those in nonenhancing lesions, with lower proton density and shorter relaxation times in enhancing lesions compared with nonenhancing lesions.
|
|
| 31. |
- Blystad, Ida, 1972-, et al.
(författare)
-
Quantitative MRI for analysis of peritumoral edema in malignant gliomas
- 2017
-
Ingår i: PLOS ONE. - : Public Library of Science. - 1932-6203. ; 12:5
-
Tidskriftsartikel (refereegranskat)abstract
- Background and purpose Damage to the blood-brain barrier with subsequent contrast enhancement is a hallmark of glioblastoma. Non-enhancing tumor invasion into the peritumoral edema is, however, not usually visible on conventional magnetic resonance imaging. New quantitative techniques using relaxometry offer additional information about tissue properties. The aim of this study was to evaluate longitudinal relaxation R-1, transverse relaxation R-2, and proton density in the peritumoral edema in a group of patients with malignant glioma before surgery to assess whether relaxometry can detect changes not visible on conventional images. Methods In a prospective study, 24 patients with suspected malignant glioma were examined before surgery. A standard MRI protocol was used with the addition of a quantitative MR method (MAGIC), which measured R-1, R-2, and proton density. The diagnosis of malignant glioma was confirmed after biopsy/surgery. In 19 patients synthetic MR images were then created from the MAGIC scan, and ROIs were placed in the peritumoral edema to obtain the quantitative values. Dynamic susceptibility contrast perfusion was used to obtain cerebral blood volume (rCBV) data of the peritumoral edema. Voxel-based statistical analysis was performed using a mixed linear model. Results R-1, R-2, and rCBV decrease with increasing distance from the contrast-enhancing part of the tumor. There is a significant increase in R1 gradient after contrast agent injection (P<.0001). There is a heterogeneous pattern of relaxation values in the peritumoral edema adjacent to the contrast-enhancing part of the tumor. Conclusion Quantitative analysis with relaxometry of peritumoral edema in malignant gliomas detects tissue changes not visualized on conventional MR images. The finding of decreasing R-1 and R-2 means shorter relaxation times closer to the tumor, which could reflect tumor invasion into the peritumoral edema. However, these findings need to be validated in the future.
|
|
| 32. |
|
|
| 33. |
- Blystad, Ida, 1972-, et al.
(författare)
-
Quantitative MRI using relaxometry in malignant gliomas detects contrast enhancement in peritumoral oedema
- 2020
-
Ingår i: Scientific Reports. - : Springer Nature. - 2045-2322. ; 10:1
-
Tidskriftsartikel (refereegranskat)abstract
- Malignant gliomas are primary brain tumours with an infiltrative growth pattern, often with contrast enhancement on magnetic resonance imaging (MRI). However, it is well known that tumour infiltration extends beyond the visible contrast enhancement. The aim of this study was to investigate if there is contrast enhancement not detected visually in the peritumoral oedema of malignant gliomas by using relaxometry with synthetic MRI. 25 patients who had brain tumours with a radiological appearance of malignant glioma were prospectively included. A quantitative MR-sequence measuring longitudinal relaxation (R-1), transverse relaxation (R-2) and proton density (PD), was added to the standard MRI protocol before surgery. Five patients were excluded, and in 20 patients, synthetic MR images were created from the quantitative scans. Manual regions of interest (ROIs) outlined the visibly contrast-enhancing border of the tumours and the peritumoral area. Contrast enhancement was quantified by subtraction of native images from post GD-images, creating an R-1-difference-map. The quantitative R-1-difference-maps showed significant contrast enhancement in the peritumoral area (0.047) compared to normal appearing white matter (0.032), p = 0.048. Relaxometry detects contrast enhancement in the peritumoral area of malignant gliomas. This could represent infiltrative tumour growth.
|
|
| 34. |
- Blystad, Ida, et al.
(författare)
-
Synthetic MRI of the brain in a clinical setting
- 2012
-
Ingår i: Acta Radiologica. - : Sage Publications. - 0284-1851 .- 1600-0455. ; 53:10, s. 1158-1163
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND:Conventional magnetic resonance imaging (MRI) has relatively long scan times for routine examinations, and the signal intensity of the images is related to the specific MR scanner settings. Due to scanner imperfections and automatic optimizations, it is impossible to compare images in terms of absolute image intensity. Synthetic MRI, a method to generate conventional images based on MR quantification, potentially both decreases examination time and enables quantitative measurements.PURPOSE:To evaluate synthetic MRI of the brain in a clinical setting by assessment of the contrast, the contrast-to-noise ratio (CNR), and the diagnostic quality compared with conventional MR images.MATERIAL AND METHODS:Twenty-two patients had synthetic imaging added to their clinical MR examination. In each patient, 12 regions of interest were placed in the brain images to measure contrast and CNR. Furthermore, general image quality, probable diagnosis, and lesion conspicuity were investigated.RESULTS:Synthetic T1-weighted turbo spin echo and T2-weighted turbo spin echo images had higher contrast but also a higher level of noise, resulting in a similar CNR compared with conventional images. Synthetic T2-weighted FLAIR images had lower contrast and a higher level of noise, which led to a lower CNR. Synthetic images were generally assessed to be of inferior image quality, but agreed with the clinical diagnosis to the same extent as the conventional images. Lesion conspicuity was higher in the synthetic T1-weighted images, which also had a better agreement with the clinical diagnoses than the conventional T1-weighted images.CONCLUSION:Synthetic MR can potentially shorten the MR examination time. Even though the image quality is perceived to be inferior, synthetic images agreed with the clinical diagnosis to the same extent as the conventional images in this study.
|
|
| 35. |
|
|
| 36. |
- Borgen, Lars, et al.
(författare)
-
Application of adaptive non-linear 2D and 3D postprocessing filters for reduced dose abdominal CT
- 2012
-
Ingår i: Acta Radiologica. - : Informa Healthcare / Wiley-Blackwell / Royal Society of Medicine Press. - 0284-1851 .- 1600-0455. ; 53:3, s. 335-342
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Abdominal computed tomography (an is a frequently performed imaging procedure, resulting in considerable radiation doses to the patient population. Postprocessing filters are one of several dose reduction measures that might help to reduce radiation doses without loss of image quality. less thanbrgreater than less thanbrgreater thanPurpose: To assess and compare the effect of two- and three-dimensional (2D, 3D) non-linear adaptive filters on reduced dose abdominal CT images. less thanbrgreater than less thanbrgreater thanMaterial and Methods: Two baseline abdominal CT image series with a volume computer tomography dose index (CTDI (vol)) of 12 mGy and 6 mGy were acquired for 12 patients. Reduced dose images were postprocessed with 2D and 3D filters. Six radiologists performed blinded randomized, side-by-side image quality assessments. Objective noise was measured. Data were analyzed using visual grading regression and mixed linear models. less thanbrgreater than less thanbrgreater thanResults: All image quality criteria were rated as superior for 3D filtered images compared to reduced dose baseline and 2D filtered images (P andlt; 0.01). Standard dose images had better image quality than reduced dose 3D filtered images (P andlt; 0.01), but similar image noise. For patients with body mass index (BMI) andlt; 30 kg/m(2) however, 3D filtered images were rated significantly better than normal dose images for two image criteria (P andlt; 0.05), while no significant difference was found for the remaining three image criteria (P andgt; 0.05). There were no significant variations of objective noise between standard dose and 2D or 3D filtered images. less thanbrgreater than less thanbrgreater thanConclusion: The quality of 3D filtered reduced dose abdominal CT images is superior compared to reduced dose unfiltered and 2D filtered images. For patients with BMI andlt; 30 kg/m(2), 3D filtered images are comparable to standard dose images.
|
|
| 37. |
- Brismar, Torkel, et al.
(författare)
-
Liver Vessel Enhancement by Gd-BOPTA and Gc-EOB-DTPA – a Comparison in Healthy Volunteers.
- 2009
-
Ingår i: Acta Radiologica. - : Informa Healthcare. - 0284-1851 .- 1600-0455. ; 50:7, s. 709-715
-
Tidskriftsartikel (refereegranskat)abstract
- Background: A thorough understanding of magnetic resonance (MR) contrast media dynamics makes it possible to choose the optimal contrast media for each investigation. Differences in visualizing hepatobiliary function between Gd-BOPTA and Gd-EOB-DTPA have previously been demonstrated, but less has been published regarding differences in liver vessel visualization.Purpose: To compare the liver vessel and liver parenchymal enhancement dynamics of Gd-BOPTA (MultiHance®) and Gd-EOB-DTPA (Primovist®). Material and Methods: The signal intensity of the liver parenchyma, the common hepatic artery, the middle hepatic vein, and a segmental branch of the right portal vein, was obtained in 10 healthy volunteers before contrast media administration, during arterial and portal venous phases, and 10, 20, 30, 40 and 130 minutes after intravenous contrast medium injection, but due to scanner limitations not during the hepatic venous phase. Results: Maximum enhancement of liver parenchyma was observed from the portal venous phase until 130 minutes after Gd-BOPTA administration and from 10 minutes to 40 minutes after Gd-EOB-DTPA. There was no difference in maximum enhancement of liver parenchyma between the two contrast media. When using Gd-BOPTA, the vascular contrast enhancement was still apparent 40 minutes after injection, but had vanished 10 minutes after Gd-EOB-DTPA injection. The maximum difference in signal intensity between the vessels and the liver parenchyma was significantly greater with Gd-BOPTA than with Gd-EOB-DTPA (p<0.0001). Conclusion: At the dosage used in this study Gd-BOPTA yields higher maximum enhancement of the hepatic artery, portal vein and middle hepatic vein during the arterial and the portal venous phase and during the delayed phases than Gd-EOB-DTPA does, whereas there is no difference in liver parenchymal enhancement between the two contrast agents.
|
|
| 38. |
|
|
| 39. |
- Brusini, Irene, et al.
(författare)
-
Changes in brain architecture are consistent with altered fear processing in domestic rabbits
- 2018
-
Ingår i: Proceedings of the National Academy of Sciences of the United States of America. - : National Academy of Sciences. - 0027-8424 .- 1091-6490. ; 115:28, s. 7380-7385
-
Tidskriftsartikel (refereegranskat)abstract
- The most characteristic feature of domestic animals is their change in behavior associated with selection for tameness. Here we show, using high-resolution brain magnetic resonance imaging in wild and domestic rabbits, that domestication reduced amygdala volume and enlarged medial prefrontal cortex volume, supporting that areas driving fear have lost volume while areas modulating negative affect have gained volume during domestication. In contrast to the localized gray matter alterations, white matter anisotropy was reduced in the corona radiata, corpus callosum, and the subcortical white matter. This suggests a compromised white matter structural integrity in projection and association fibers affecting both afferent and efferent neural flow, consistent with reduced neural processing. We propose that compared with their wild ancestors, domestic rabbits are less fearful and have an attenuated flight response because of these changes in brain architecture.
|
|
| 40. |
|
|
| 41. |
|
|
| 42. |
- Brusini, Irene
(författare)
-
Methods for the analysis and characterization of brain morphology from MRI images
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Brain magnetic resonance imaging (MRI) is an imaging modality that produces detailed images of the brain without using any ionizing radiation. From a structural MRI scan, it is possible to extract morphological properties of different brain regions, such as their volume and shape. These measures can both allow a better understanding of how the brain changes due to multiple factors (e.g., environmental and pathological) and contribute to the identification of new imaging biomarkers of neurological and psychiatric diseases. The overall goal of the present thesis is to advance the knowledge on how brain MRI image processing can be effectively used to analyze and characterize brain structure.The first two works presented in this thesis are animal studies that primarily aim to use MRI data for analyzing differences between groups of interest. In Paper I, MRI scans from wild and domestic rabbits were processed to identify structural brain differences between these two groups. Domestication was found to significantly reshape brain structure in terms of both regional gray matter volume and white matter integrity. In Paper II, rat brain MRI scans were used to train a brain age prediction model. This model was then tested on both controls and a group of rats that underwent long-term environmental enrichment and dietary restriction. This healthy lifestyle intervention was shown to significantly affect the predicted brain age trajectories by slowing the rats' aging process compared to controls. Furthermore, brain age predicted on young adult rats was found to have a significant effect on survival.Papers III to V are human studies that propose deep learning-based methods for segmenting brain structures that can be severely affected by neurodegeneration. In particular, Papers III and IV focus on U-Net-based 2D segmentation of the corpus callosum (CC) in multiple sclerosis (MS) patients. In both studies, good segmentation accuracy was obtained and a significant correlation was found between CC area and the patient's level of cognitive and physical disability. Additionally, in Paper IV, shape analysis of the segmented CC revealed a significant association between disability and both CC thickness and bending angle. Conversely, in Paper V, a novel method for automatic segmentation of the hippocampus is proposed, which consists of embedding a statistical shape prior as context information into a U-Net-based framework. The inclusion of shape information was shown to significantly improve segmentation accuracy when testing the method on a new unseen cohort (i.e., different from the one used for training). Furthermore, good performance was observed across three different diagnostic groups (healthy controls, subjects with mild cognitive impairment and Alzheimer's patients) that were characterized by different levels of hippocampal atrophy.In summary, the studies presented in this thesis support the great value of MRI image analysis for the advancement of neuroscientific knowledge, and their contribution is mostly two-fold. First, by applying well-established processing methods on datasets that had not yet been explored in the literature, it was possible to characterize specific brain changes and disentangle relevant problems of a clinical or biological nature. Second, a technical contribution is provided by modifying and extending already-existing brain image processing methods to achieve good performance on new datasets.
|
|
| 43. |
- Brusini, Irene, et al.
(författare)
-
MRI-derived brain age as a biomarker of ageing in rats : validation using a healthy lifestyle intervention
- 2022
-
Ingår i: Neurobiology of Aging. - : Elsevier BV. - 0197-4580 .- 1558-1497. ; 109, s. 204-215
-
Tidskriftsartikel (refereegranskat)abstract
- The difference between brain age predicted from MRI and chronological age (the so-called BrainAGE) has been proposed as an ageing biomarker. We analyse its cross-species potential by testing it on rats undergoing an ageing modulation intervention. Our rat brain age prediction model combined Gaussian process regression with a classifier and achieved a mean absolute error (MAE) of 4.87 weeks using cross-validation on a longitudinal dataset of 31 normal ageing rats. It was then tested on two groups of 24 rats (MAE = 9.89 weeks, correlation coefficient = 0.86): controls vs. a group under long-term environmental enrichment and dietary restriction (EEDR). Using a linear mixed-effects model, BrainAGE was found to increase more slowly with chronological age in EEDR rats ( p = 0 . 015 for the interaction term). Cox re-gression showed that older BrainAGE at 5 months was associated with higher mortality risk ( p = 0 . 03 ). Our findings suggest that lifestyle-related prevention approaches may help to slow down brain ageing in rodents and the potential of BrainAGE as a predictor of age-related health outcomes.
|
|
| 44. |
- Brusini, Irene, et al.
(författare)
-
Shape Information Improves the Cross-Cohort Performance of Deep Learning-Based Segmentation of the Hippocampus
- 2020
-
Ingår i: Frontiers in Neuroscience. - : Frontiers Media S.A.. - 1662-4548 .- 1662-453X. ; 14
-
Tidskriftsartikel (refereegranskat)abstract
- Performing an accurate segmentation of the hippocampus from brain magnetic resonance images is a crucial task in neuroimaging research, since its structural integrity is strongly related to several neurodegenerative disorders, including Alzheimer's disease (AD). Some automatic segmentation tools are already being used, but, in recent years, new deep learning (DL)-based methods have been proven to be much more accurate in various medical image segmentation tasks. In this work, we propose a DL-based hippocampus segmentation framework that embeds statistical shape of the hippocampus as context information into the deep neural network (DNN). The inclusion of shape information is achieved with three main steps: (1) a U-Net-based segmentation, (2) a shape model estimation, and (3) a second U-Net-based segmentation which uses both the original input data and the fitted shape model. The trained DL architectures were tested on image data of three diagnostic groups [AD patients, subjects with mild cognitive impairment (MCI) and controls] from two cohorts (ADNI and AddNeuroMed). Both intra-cohort validation and cross-cohort validation were performed and compared with the conventional U-net architecture and some variations with other types of context information (i.e., autocontext and tissue-class context). Our results suggest that adding shape information can improve the segmentation accuracy in cross-cohort validation, i.e., when DNNs are trained on one cohort and applied to another. However, no significant benefit is observed in intra-cohort validation, i.e., training and testing DNNs on images from the same cohort. Moreover, compared to other types of context information, the use of shape context was shown to be the most successful in increasing the accuracy, while keeping the computational time in the order of a few minutes.
|
|
| 45. |
- Brusini, Irene, et al.
(författare)
-
Voxel-Wise Clustering of Tractography Data for Building Atlases of Local Fiber Geometry
- 2019
-
Konferensbidrag (refereegranskat)abstract
- This paper aims at proposing a method to generate atlases of white matter fibers’ geometry that consider local orientation and curvature of fibers extracted from tractography data. Tractography was performed on diffusion magnetic resonance images from a set of healthy subjects and each tract was characterized voxel-wise by its curvature and Frenet–Serret frame, based on which similar tracts could be clustered separately for each voxel and each subject. Finally, the centroids of the clusters identified in all subjects were clustered to create the final atlas. The proposed clustering technique showed promising results in identifying voxel-wise distributions of curvature and orientation. Two tractography algorithms (one deterministic and one probabilistic) were tested for the present work, obtaining two different atlases. A high agreement between the two atlases was found in several brain regions. This suggests that more advanced tractography methods might only be required for some specific regions in the brain. In addition, the probabilistic approach resulted in the identification of a higher number of fiber orientations in various white matter areas, suggesting it to be more adequate for investigating complex fiber configurations in the proposed framework as compared to deterministic tractography.
|
|
| 46. |
- Buizza, Giulia, et al.
(författare)
-
Early tumor response prediction for lung cancer patients using novel longitudinal pattern features from sequential PET/CT image scans
- 2018
-
Ingår i: Physica medica (Testo stampato). - : ELSEVIER SCI LTD. - 1120-1797 .- 1724-191X. ; 54, s. 21-29
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: A new set of quantitative features that capture intensity changes in PET/CT images over time and space is proposed for assessing the tumor response early during chemoradiotherapy. The hypothesis whether the new features, combined with machine learning, improve outcome prediction is tested. Methods: The proposed method is based on dividing the tumor volume into successive zones depending on the distance to the tumor border. Mean intensity changes are computed within each zone, for CT and PET scans separately, and used as image features for tumor response assessment. Doing so, tumors are described by accounting for temporal and spatial changes at the same time. Using linear support vector machines, the new features were tested on 30 non-small cell lung cancer patients who underwent sequential or concurrent chemoradiotherapy. Prediction of 2-years overall survival was based on two PET-CT scans, acquired before the start and during the first 3 weeks of treatment. The predictive power of the newly proposed longitudinal pattern features was compared to that of previously proposed radiomics features and radiobiological parameters. Results: The highest areas under the receiver operating characteristic curves were 0.98 and 0.93 for patients treated with sequential and concurrent chemoradiotherapy, respectively. Results showed an overall comparable performance with respect to radiomics features and radiobiological parameters. Conclusions: A novel set of quantitative image features, based on underlying tumor physiology, was computed from PET/CT scans and successfully employed to distinguish between early responders and non-responders to chemoradiotherapy.
|
|
| 47. |
- Bäcklin, Emelie, et al.
(författare)
-
Pulmonary volumes and signs of chronic airflow limitation in quantitative computed tomography
- 2024
-
Ingår i: Clinical Physiology and Functional Imaging. - : Wiley. - 1475-0961 .- 1475-097X. ; 44:4, s. 340-348
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundComputed tomography (CT) offers pulmonary volumetric quantification but is not commonly used in healthy individuals due to radiation concerns. Chronic airflow limitation (CAL) is one of the diagnostic criteria for chronic obstructive pulmonary disease (COPD), where early diagnosis is important. Our aim was to present reference values for chest CT volumetric and radiodensity measurements and explore their potential in detecting early signs of CAL.MethodsFrom the population-based Swedish CArdioPulmonarybioImage Study (SCAPIS), 294 participants aged 50–64, were categorized into non-CAL (n = 258) and CAL (n = 36) groups based on spirometry. From inspiratory and expiratory CT images we compared lung volumes, mean lung density (MLD), percentage of low attenuation volume (LAV%) and LAV cluster volume between groups, and against reference values from static pulmonary function test (PFT).ResultsThe CAL group exhibited larger lung volumes, higher LAV%, increased LAV cluster volume and lower MLD compared to the non-CAL group. Lung volumes significantly deviated from PFT values. Expiratory measurements yielded more reliable results for identifying CAL compared to inspiratory. Using a cut-off value of 0.6 for expiratory LAV%, we achieved sensitivity, specificity and positive/negative predictive values of 72%, 85% and 40%/96%, respectively.ConclusionWe present volumetric reference values from inspiratory and expiratory chest CT images for a middle-aged healthy cohort. These results are not directly comparable to those from PFTs. Measures of MLD and LAV can be valuable in the evaluation of suspected CAL. Further validation and refinement are necessary to demonstrate its potential as a decision support tool for early detection of COPD.
|
|
| 48. |
- Carina, Stenman, 1964-
(författare)
-
Standardized ultrasonography with cine-loop documentation : diagnostic variability in liver and kidney examinations
- 2015
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Background: Ultrasound examination of the abdomen is often a first choice at radiology departments due to the lack of ionizing radiation. For diagnostic accuracy and economic benefits there has been a need for new routines in this area that incorporate the benefits of an radiographer or sonographer performing a multitude of ultrasound examinations following strictly standardized examination protocols and documentation forms made by cine-loops that will give the radiologist access to all relevant information needed for an accurate postexamination diagnosis.Aim: The overall objective of this thesis was to evaluate the diagnostic variability in examinations of the kidneys and liver that use a standardized ultrasound method along with video documentation of the entire examination and off-line review by radiologists. More specifically, we wanted to compare the agreement between readers and between operators.Design and method: This thesis is based on four quantitative studies using standardized protocols for kidney, liver and gallbladder examinations. In paper I, including 64 patients, and paper IV, including 98 patients, the patients were prospectively enrolled and the examinations were retrospectively reviewed. The patients in papers I and IV were examined by one radiographer (sonographer) and one radiologist during the same session. In paper I, findings using the standardized ultrasound method were compared with traditional bedside assessments by a radiologist. In paper IV, the patients were examined using only the standardized method. In paper II, including 98 patients, and in paper III, including 115 patients, the patients were examined by one sonographer using the standardized method and the examinations were reviewed by two or three radiologists.Results: In paper I, no significant systematic differences were found between the findings using the standardized method and the traditional bedside assessment.Paper II showed good intra- and inter-observer agreement between three experienced radiologists when reviewing examinations conducted using the standardized method.In paper III we verified good inter-observer agreement between two radiologists reviewing ultrasound examinations using the standardized technique in patients who had undergone surgery for colorectal cancer. Intravenous contrast was used and the injection of contrast medium increased the visibility of liver lesions.In paper IV, we observed that using a standardized cine-loop technique, there was a slightly better inter-operator agreement than inter-reader agreement.Conclusion: The satisfactory agreement shown in all four studies suggests that the new workflow method using standardized ultrasound examinations and stored cine-loops, performed by a radiographer or sonographer and analyzed off-line by a radiologist, is a promising technique. The results are less affected when a radiologist examiner is replaced by a radiographer or sonographer than when the reviewer is replaced by a different radiologist.
|
|
| 49. |
- Chang, Yongjun, et al.
(författare)
-
Effects of preprocessing in slice-level classification of interstitial lung disease based on deep convolutional networks
- 2018
-
Ingår i: VipIMAGE 2017. - Cham : Springer Netherlands. - 9783319681948 ; , s. 624-629
-
Konferensbidrag (refereegranskat)abstract
- Several preprocessing methods are applied to the automatic classification of interstitial lung disease (ILD). The proposed methods are used for the inputs to an established convolutional neural network in order to investigate the effect of those preprocessing techniques to slice-level classification accuracy. Experimental results demonstrate that the proposed preprocessing methods and a deep learning approach outperformed the case of the original images input to deep learning without preprocessing.
|
|
| 50. |
- Chowdhury, Manish, et al.
(författare)
-
An Efficient Radiographic Image Retrieval System Using Convolutional Neural Network
- 2016
-
Ingår i: 2016 23rd International Conference on Pattern Recognition (ICPR). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781509048472 ; , s. 3134-3139
-
Konferensbidrag (refereegranskat)abstract
- Content-Based Medical Image Retrieval (CBMIR) is an important research field in the context of medical data management. In this paper we propose a novel CBMIR system for the automatic retrieval of radiographic images. Our approach employs a Convolutional Neural Network (CNN) to obtain high- level image representations that enable a coarse retrieval of images that are in correspondence to a query image. The retrieved set of images is refined via a non-parametric estimation of putative classes for the query image, which are used to filter out potential outliers in favour of more relevant images belonging to those classes. The refined set of images is finally re-ranked using Edge Histogram Descriptor, i.e. a low-level edge-based image descriptor that allows to capture finer similarities between the retrieved set of images and the query image. To improve the computational efficiency of the system, we employ dimensionality reduction via Principal Component Analysis (PCA). Experiments were carried out to evaluate the effectiveness of the proposed system on medical data from the “Image Retrieval in Medical Applications” (IRMA) benchmark database. The obtained results show the effectiveness of the proposed CBMIR system in the field of medical image retrieval.
|
|
