| 1. |
- Mendrik, AM, et al.
(författare)
-
MRBrainS Challenge: Online Evaluation Framework for Brain Image Segmentation in 3T MRI Scans
- 2015
-
Ingår i: Computational Intelligence and Neuroscience. - : Hindawi Publishing Corporation. - 1687-5265 .- 1687-5273. ; 2015
-
Tidskriftsartikel (refereegranskat)abstract
- Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi)automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65–80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand.
|
|
| 2. |
- Lidayová, Kristína, et al.
(författare)
-
Fast vascular skeleton extraction algorithm
- 2016
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 76, s. 67-75
-
Tidskriftsartikel (refereegranskat)abstract
- Vascular diseases are a common cause of death, particularly in developed countries. Computerized image analysis tools play a potentially important role in diagnosing and quantifying vascular pathologies. Given the size and complexity of modern angiographic data acquisition, fast, automatic and accurate vascular segmentation is a challenging task.In this paper we introduce a fully automatic high-speed vascular skeleton extraction algorithm that is intended as a first step in a complete vascular tree segmentation program. The method takes a 3D unprocessed Computed Tomography Angiography (CTA) scan as input and produces a graph in which the nodes are centrally located artery voxels and the edges represent connections between them. The algorithm works in two passes where the first pass is designed to extract the skeleton of large arteries and the second pass focuses on smaller vascular structures. Each pass consists of three main steps. The first step sets proper parameters automatically using Gaussian curve fitting. In the second step different filters are applied to detect voxels - nodes - that are part of arteries. In the last step the nodes are connected in order to obtain a continuous centerline tree for the entire vasculature. Structures found, that do not belong to the arteries, are removed in a final anatomy-based analysis. The proposed method is computationally efficient with an average execution time of 29s and has been tested on a set of CTA scans of the lower limbs achieving an average overlap rate of 97% and an average detection rate of 71%.
|
|
| 3. |
- Wang, Chunliang, 1980-, et al.
(författare)
-
CT scan range estimation using multiple body parts detection : let PACS learn the CT image content
- 2016
-
Ingår i: International Journal of Computer Assisted Radiology and Surgery. - : Springer. - 1861-6410 .- 1861-6429. ; 11:2, s. 317-325
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: The aim of this study was to develop an efficient CT scan range estimation method that is based on the analysis of image data itself instead of metadata analysis. This makes it possible to quantitatively compare the scan range of two studies. Methods: In our study, 3D stacks are first projected to 2D coronal images via a ray casting-like process. Trained 2D body part classifiers are then used to recognize different body parts in the projected image. The detected candidate regions go into a structure grouping process to eliminate false-positive detections. Finally, the scale and position of the patient relative to the projected figure are estimated based on the detected body parts via a structural voting. The start and end lines of the CT scan are projected to a standard human figure. The position readout is normalized so that the bottom of the feet represents 0.0, and the top of the head is 1.0. Results: Classifiers for 18 body parts were trained using 184 CT scans. The final application was tested on 136 randomly selected heterogeneous CT scans. Ground truth was generated by asking two human observers to mark the start and end positions of each scan on the standard human figure. When compared with the human observers, the mean absolute error of the proposed method is 1.2 % (max: 3.5 %) and 1.6 % (max: 5.4 %) for the start and end positions, respectively. Conclusion: We proposed a scan range estimation method using multiple body parts detection and relative structure position analysis. In our preliminary tests, the proposed method delivered promising results.
|
|
| 4. |
- Wang, Chunliang, 1980-, et al.
(författare)
-
Fast level-set based image segmentation using coherent propagation
- 2014
-
Ingår i: Medical physics (Lancaster). - : John Wiley and Sons Ltd. - 0094-2405. ; 41:7
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: The level-set method is known to require long computation time for 3D image segmentation, which limits its usage in clinical workflow. The goal of this study was to develop a fast level-set algorithm based on the coherent propagation method and explore its character using clinical datasets. Methods: The coherent propagation algorithm allows level set functions to converge faster by forcing the contour to move monotonically according to a predicted developing trend. Repeated temporary backwards propagation, caused by noise or numerical errors, is then avoided. It also makes it possible to detect local convergence, so that the parts of the boundary that have reached their final position can be excluded in subsequent iterations, thus reducing computation time. To compensate for the overshoot error, forward and backward coherent propagation is repeated periodically. This can result in fluctuations of great magnitude in parts of the contour. In this paper, a new gradual convergence scheme using a damping factor is proposed to address this problem. The new algorithm is also generalized to non-narrow band cases. Finally, the coherent propagation approach is combined with a new distance-regularized level set, which eliminates the needs of reinitialization of the distance. Results: Compared with the sparse field method implemented in the widely available ITKSnap software, the proposed algorithm is about 10 times faster when used for brain segmentation and about 100 times faster for aorta segmentation. Using a multiresolution approach, the new method achieved 50 times speed-up in liver segmentation. The Dice coefficient between the proposed method and the sparse field method is above 99% in most cases. Conclusions: A generalized coherent propagation algorithm for level set evolution yielded substantial improvement in processing time with both synthetic datasets and medical images.
|
|
| 5. |
- Chen, Heping, et al.
(författare)
-
Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation
- 2021
-
Ingår i: Frontiers in Neuroscience. - : Frontiers Media SA. - 1662-4548 .- 1662-453X. ; 15
-
Tidskriftsartikel (refereegranskat)abstract
- Laser speckle contrast imaging (LSCI) is a full-field, high spatiotemporal resolution and low-cost optical technique for measuring blood flow, which has been successfully used for neurovascular imaging. However, due to the low signal-noise ratio and the relatively small sizes, segmenting the cerebral vessels in LSCI has always been a technical challenge. Recently, deep learning has shown its advantages in vascular segmentation. Nonetheless, ground truth by manual labeling is usually required for training the network, which makes it difficult to implement in practice. In this manuscript, we proposed a deep learning-based method for real-time cerebral vessel segmentation of LSCI without ground truth labels, which could be further integrated into intraoperative blood vessel imaging system. Synthetic LSCI images were obtained with a synthesis network from LSCI images and public labeled dataset of Digital Retinal Images for Vessel Extraction, which were then used to train the segmentation network. Using matching strategies to reduce the size discrepancy between retinal images and laser speckle contrast images, we could further significantly improve image synthesis and segmentation performance. In the testing LSCI images of rodent cerebral vessels, the proposed method resulted in a dice similarity coefficient of over 75%.
|
|
| 6. |
- 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.
|
|
| 7. |
- 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.
|
|
| 8. |
- 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.
|
|
| 9. |
- 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.
|
|
| 10. |
- 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.
|
|
