| 1. |
- Arvidsson, Ida, et al.
(författare)
-
Comparison of different augmentation techniques for improved generalization performance for gleason grading
- 2019
-
Ingår i: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). - 9781538636411 ; , s. 923-927
-
Konferensbidrag (refereegranskat)abstract
- The fact that deep learning based algorithms used for digital pathology tend to overfit to the site of the training data is well-known. Since an algorithm that does not generalize is not very useful, we have in this work studied how different data augmentation techniques can reduce this problem but also how data from different sites can be normalized to each other. For both of these approaches we have used cycle generative adversarial networks (GAN); either to generate more examples to train on or to transform images from one site to another. Furthermore, we have investigated to what extent standard augmentation techniques improve the generalization performance. We performed experiments on four datasets with slides from prostate biopsies, stained with HE, detailed annotated with Gleason grades. We obtained results similar to previous studies, with accuracies of 77% for Gleason grading for images from the same site as the training data and 59% for images from other sites. However, we also found out that the use of traditional augmentation techniques gave better performance compared to when using cycle GANs, either to augment the training data or to normalize the test data.
|
|
| 2. |
- Arvidsson, Ida, et al.
(författare)
-
Deep learning prediction of quantitative coronary angiography values using myocardial perfusion images with a CZT camera
- 2023
-
Ingår i: Journal of Nuclear Cardiology. - : Springer Science and Business Media LLC. - 1071-3581 .- 1532-6551. ; 30:1, s. 116-126
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Evaluate the prediction of quantitative coronary angiography (QCA) values from MPI, by means of deep learning. Methods: 546 patients (67% men) undergoing stress 99mTc-tetrofosmin MPI in a CZT camera in the upright and supine position were included (1092 MPIs). Patients were divided into two groups: ICA group included 271 patients who performed an ICA within 6 months of MPI and a control group with 275 patients with low pre-test probability for CAD and a normal MPI. QCA analyses were performed using radiologic software and verified by an expert reader. Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. A deep learning model was trained using a double cross-validation scheme such that all data could be used as test data as well. Results: Area under the receiver-operating characteristic curve for the prediction of QCA, with > 50% narrowing of the artery, by deep learning for the external test cohort: per patient 85% [95% confidence interval (CI) 84%-87%] and per vessel; LAD 74% (CI 72%-76%), RCA 85% (CI 83%-86%), LCx 81% (CI 78%-84%), and average 80% (CI 77%-83%). Conclusion: Deep learning can predict the presence of different QCA percentages of coronary artery stenosis from MPIs.
|
|
| 3. |
- Arvidsson, Ida, et al.
(författare)
-
Detection of left bundle branch block and obstructive coronary artery disease from myocardial perfusion scintigraphy using deep neural networks
- 2021
-
Ingår i: Medical Imaging 2021 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - : SPIE. - 1605-7422. - 9781510640238 ; 11597
-
Konferensbidrag (refereegranskat)abstract
- Myocardial perfusion scintigraphy, which is a non-invasive imaging technique, is one of the most common cardiological examinations performed today, and is used for diagnosis of coronary artery disease. Currently the analysis is performed visually by physicians, but this is both a very time consuming and a subjective approach. These are two of the motivations for why an automatic tool to support the decisions would be useful. We have developed a deep neural network which predicts the occurrence of obstructive coronary artery disease in each of the three major arteries as well as left bundle branch block. Since multiple, or none, of these could have a defect, this is treated as a multi-label classification problem. Due to the highly imbalanced labels, the training loss is weighted accordingly. The prediction is based on two polar maps, captured during stress in upright and supine position, together with additional information such as BMI and angina symptoms. The polar maps are constructed from myocardial perfusion scintigraphy examinations conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). The study includes data from 759 patients. Using 5-fold cross-validation we achieve an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level for the three major arteries, 0.94 on per-patient level and 0.82 for left bundle branch block.
|
|
| 4. |
- Arvidsson, Ida, et al.
(författare)
-
Domain-adversarial neural network for improved generalization performance of gleason grade classification
- 2020
-
Ingår i: Medical Imaging 2020 : Digital Pathology - Digital Pathology. - : SPIE. - 1605-7422. - 9781510634077 ; 11320
-
Konferensbidrag (refereegranskat)abstract
- When training a deep learning model, the dataset used is of great importance to make sure that the model learns relevant features of the data and that it will be able to generalize to new data. However, it is typically difficult to produce a dataset without some bias toward any specific feature. Deep learning models used in histopathology have a tendency to overfit to the stain appearance of the training data - if the model is trained on data from one lab only, it will usually not be able to generalize to data from other labs. The standard technique to overcome this problem is to use color augmentation of the training data which, artificially, generates more variations for the network to learn. In this work we instead test the use of a so called domain-adversarial neural network, which is designed to prevent the model from being biased towards features that in reality are irrelevant such as the origin of an image. To test the technique, four datasets from different hospitals for Gleason grading of prostate cancer are used. We achieve state of the art results for these particular datasets, and furthermore for two of our three test datasets the approach outperforms the use of color augmentation.
|
|
| 5. |
- Arvidsson, Ida, et al.
(författare)
-
Generalization of prostate cancer classification for multiple sites using deep learning
- 2018
-
Ingår i: 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. - 9781538636367 ; 2018-April, s. 191-194
-
Konferensbidrag (refereegranskat)abstract
- Deep learning has the potential to drastically increase the accuracy and efficiency of prostate cancer diagnosis, which would be of uttermost use. Today the diagnosis is determined manually from H&E stained specimens using a light microscope. In this paper several different approaches based on convolutional neural networks for prostate cancer classification are presented and compared, using three different datasets with different origins. The issue that algorithms trained on a certain site might not generalize to other sites, due to for example inevitable stain variations, is highlighted. Two different techniques to overcome this complication are compared; by training the networks using color augmentation and by using digital stain separation. Furthermore, the potential of using an autoencoder to get a more efficient downsampling is investigated, which turned out to be the method giving the best generalization. We achieve accuracies of 95% for classification of benign versus malignant tissue and 81% for Gleason grading for data from the same site as the training data. The corresponding accuracies for images from other sites are in average 88% and 52% respectively.
|
|
| 6. |
- Arvidsson, Ida, et al.
(författare)
-
Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks
- 2021
-
Ingår i: 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR). - : IEEE COMPUTER SOC. - 1051-4651. - 9781728188089 ; , s. 4442-4449
-
Konferensbidrag (refereegranskat)abstract
- For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.
|
|
| 7. |
- Karlsson, Jennie, et al.
(författare)
-
Classification of point-of-care ultrasound in breast imaging using deep learning
- 2023
-
Ingår i: Medical Imaging 2023 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - 2410-9045 .- 1605-7422. - 9781510660359 ; 12465
-
Konferensbidrag (refereegranskat)abstract
- Early detection of breast cancer is important to reduce morbidity and mortality. Access to breast imaging is limited in low- and middle-income countries compared to high-income countries. This contributes to advance-stage breast cancer presentation with poor survival. Pocket-sized portable ultrasound device, also known as point-of-care ultrasound (POCUS), aided by decision support using deep learning-based algorithms for lesion classification could be a cost-effective way to enable access to breast imaging in low-resource settings. A previous study, where using convolutional neural networks (CNN) to classify breast cancer in conventional ultrasound (US) images, showed promising results. The aim of the present study is to classify POCUS breast images. A POCUS data set containing 1100 breast images was collected. To increase the size of the data set, a Cycle-Consistent Adversarial Network (CycleGAN) was trained on US images to generate synthetic POCUS images. A CNN was implemented, trained, validated and tested on POCUS images. To improve performance, the CNN was trained with different combinations of data consisting of POCUS images, US images, CycleGAN-generated POCUS images and spatial augmentation. The best result was achieved by a CNN trained on a combination of POCUS images and CycleGAN-generated POCUS images and augmentation. This combination achieved a 95% confidence interval for AUC between 93.5% - 96.6%.
|
|
| 8. |
- Karlsson, Jennie, et al.
(författare)
-
Machine learning algorithm for classification of breast ultrasound images
- 2022
-
Ingår i: Medical Imaging 2022 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - : SPIE. - 9781510649422 ; 12033
-
Konferensbidrag (refereegranskat)abstract
- Breast cancer is the most common type of cancer globally. Early detection is important for reducing the morbidity and mortality of breast cancer. The aim of this study was to evaluate the performance of different machine learning models to classify malignant or benign lesions on breast ultrasound images. Three different convolutional neural network approaches were implemented: (a) Simple convolutional neural network, (b) transfer learning using pre-trained InceptionV3, ResNet50V2, VGG19 and Xception and (c) deep feature networks based on combinations of the four transfer networks in (b). The data consisted of two breast ultrasound image data sets: (1) an open, single-vendor, data set collected by Cairo University at Baheya Hospital, Egypt, consisting of 437 benign lesions and 210 malignant lesions, where 10% was set to be a test set and the rest was used for training and validation (development) and (2) An in-house, multi-vendor data set collected at Unilabs Mammography Unit, Skåne University Hospital, Sweden, consisting of 13 benign lesions and 265 malignant lesions, was used as an external test set. Both test sets were used for evaluating the networks. The performance measures used were area under the receiver operating characteristic curve (AUC), sensitivity, specificity and weighted accuracy. Holdout, i.e. the splitting of the development data into training and validation data sets just once, was used to find a model with as good performance as possible. 10-fold cross-validation was also performed to provide uncertainty estimates. For the transfer networks which were obtained with holdout, Gradient-weighted Class Activation Mapping was used to generate heat maps indicating which part of the image contributed to the network’s decision. For 10-fold cross-validation it was possible to achieve a mean AUC of 92% and mean sensitivity of 95% for the transfer network based on Xception when testing on the first data set. When testing on the second data set it was possible to obtain a mean AUC of 75% and mean sensitivity of 86% for the combination of ResNet50V2 and Xception.
|
|
| 9. |
- Landgren, Matilda, et al.
(författare)
-
A Measure of Septum Shape Using Shortest Path Segmentation in Echocardiographic Images of LVAD Patients
- 2014
-
Ingår i: Pattern Recognition (ICPR), 2014 22nd International Conference on. - 1051-4651. ; , s. 3398-3403
-
Konferensbidrag (refereegranskat)abstract
- Patients waiting for heart transplantation due to a failing heart can get a left ventricular assist device (LVAD) implanted through open chest surgery. The device consists of a pump that pumps blood from the left ventricle into the aorta. To get the correct rotation speed of the pump, the physicians consider a number of measurements as well as a sequence of echocardiographic images. The important information obtained from the images is the shape of the inter-ventricular septum. For instance, if the septum bulges towards the left ventricle the speed is too high and it might harm the right ventricular function. To get a measure of the shape of the septum, which can be incorporated in a decision support system, we perform a segmentation of the septum using a shortest path method. To reduce user interaction, the user only needs to annotate two anchor points in the first frame. They mark the endpoints of the septum and they are tracked through the sequence with our tracking algorithm. After the segmentation the septum is divided into two regions, the one closest to the right ventricle and the one closest to the left ventricle, and the desired measure is the difference between the areas of these regions divided by the total septum area. The performance of the segmentation algorithm is acceptable and the obtained septum measure corresponds in most cases to the assessments from a physician.
|
|
| 10. |
- Landgren, Matilda, et al.
(författare)
-
An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images
- 2011
-
Ingår i: Lecture Notes in Computer Science. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 0302-9743 .- 1611-3349. - 9783642212277 - 9783642212260 ; 6688, s. 489-500
-
Konferensbidrag (refereegranskat)abstract
- Designing a system for computer aided diagnosis is a complex procedure requiring an understanding of the biology of the disease, insight into hospital workflow and awareness of available technical solutions. This paper aims to show that a valuable system can be designed for diagnosing kidney lesions in children and adolescents from 99m Tc-DMSA scintigraphy images. We present the chain of analysis and provide a discussion of its performance. On a per-lesion basis, the classification reached an ROC-curve area of 0.96 (sensitivity/specificity e.g. 97%/85%) measured using an independent test group consisting of 56 patients with 730 candidate lesions. We conclude that the presented system for diagnostic support has the potential of increasing the quality of care regarding this type of examination.
|
|
| 11. |
- Landgren, Matilda, et al.
(författare)
-
Segmentation of the Left Heart Ventricle in Ultrasound Images Using a Region Based Snake
- 2013
-
Ingår i: Medical Imaging 2013: Image Processing. - : SPIE. - 1996-756X .- 0277-786X. - 9780819494436 ; 8669
-
Konferensbidrag (refereegranskat)abstract
- Ultrasound imaging of the heart is a non-invasive method widely used for different applications. One of them is to measure the blood volume in the left ventricle at different stages of the heart cycle. This demands a proper segmentation of the left ventricle and a (semi-) automated method would decrease intra-variability as well as workload. This paper presents a semi-automated segmentation method that uses a region based snake. To avoid any unwanted concavities in the segmentations due to the cardiac valve we use two anchor points in the snake that are located to the left and to the right of the cardiac valve respectively. For the possibility of segmentations in different stages of the heart cycle these anchor points are tracked through the cycle. This tracking is based both on the resemblance of a region around the anchor points and a prior model of the movement in the y-direction of the anchor points. The region based snake functional is the sum of two terms, a regularizing term and a data term. It is our data term that is region based since it involves the integration of a two-dimensional subdomain of the image plane. A segmentation of the left ventricle is obtained by minimizing the functional which is done by continuously reshaping the contour until the optimal shape and size is obtained. The developed method shows promising results.
|
|
| 12. |
- Lippolis, Giuseppe, et al.
(författare)
-
Automatic registration of multi-modal microscopy images for integrative analysis of prostate tissue sections
- 2013
-
Ingår i: BMC Cancer. - : Springer Science and Business Media LLC. - 1471-2407. ; 13, s. 408-418
-
Tidskriftsartikel (refereegranskat)abstract
- Background Prostate cancer is one of the leading causes of cancer related deaths. For diagnosis, predicting the outcome of the disease, and for assessing potential new biomarkers, pathologists and researchers routinely analyze histological samples. Morphological and molecular information may be integrated by aligning microscopic histological images in a multiplex fashion. This process is usually time-consuming and results in intra- and inter-user variability. The aim of this study is to investigate the feasibility of using modern image analysis methods for automated alignment of microscopic images from differently stained adjacent paraffin sections from prostatic tissue specimens. Methods Tissue samples, obtained from biopsy or radical prostatectomy, were sectioned and stained with either hematoxylin & eosin (H&E), immunohistochemistry for p63 and AMACR or Time Resolved Fluorescence (TRF) for androgen receptor (AR). Image pairs were aligned allowing for translation, rotation and scaling. The registration was performed automatically by first detecting landmarks in both images, using the scale invariant image transform (SIFT), followed by the well-known RANSAC protocol for finding point correspondences and finally aligned by Procrustes fit. The Registration results were evaluated using both visual and quantitative criteria as defined in the text. Results Three experiments were carried out. First, images of consecutive tissue sections stained with H&E and p63/AMACR were successfully aligned in 85 of 88 cases (96.6%). The failures occurred in 3 out of 13 cores with highly aggressive cancer (Gleason score ≥ 8). Second, TRF and H&E image pairs were aligned correctly in 103 out of 106 cases (97%). The third experiment considered the alignment of image pairs with the same staining (H&E) coming from a stack of 4 sections. The success rate for alignment dropped from 93.8% in adjacent sections to 22% for sections furthest away. Conclusions The proposed method is both reliable and fast and therefore well suited for automatic segmentation and analysis of specific areas of interest, combining morphological information with protein expression data from three consecutive tissue sections. Finally, the performance of the algorithm seems to be largely unaffected by the Gleason grade of the prostate tissue samples examined, at least up to Gleason score 7.
|
|
| 13. |
- Läthén, Gunnar, 1981-
(författare)
-
Segmentation Methods for Medical Image Analysis : Blood vessels, multi-scale filtering and level set methods
- 2010
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Image segmentation is the problem of partitioning an image into meaningful parts, often consisting of an object and background. As an important part of many imaging applications, e.g. face recognition, tracking of moving cars and people etc, it is of general interest to design robust and fast segmentation algorithms. However, it is well accepted that there is no general method for solving all segmentation problems. Instead, the algorithms have to be highly adapted to the application in order to achieve good performance. In this thesis, we will study segmentation methods for blood vessels in medical images. The need for accurate segmentation tools in medical applications is driven by the increased capacity of the imaging devices. Common modalities such as CT and MRI generate images which simply cannot be examined manually, due to high resolutions and a large number of image slices. Furthermore, it is very difficult to visualize complex structures in three-dimensional image volumes without cutting away large portions of, perhaps important, data. Tools, such as segmentation, can aid the medical staff in browsing through such large images by highlighting objects of particular importance. In addition, segmentation in particular can output models of organs, tumors, and other structures for further analysis, quantification or simulation.We have divided the segmentation of blood vessels into two parts. First, we model the vessels as a collection of lines and edges (linear structures) and use filtering techniques to detect such structures in an image. Second, the output from this filtering is used as input for segmentation tools. Our contributions mainly lie in the design of a multi-scale filtering and integration scheme for de- tecting vessels of varying widths and the modification of optimization schemes for finding better segmentations than traditional methods do. We validate our ideas on synthetical images mimicking typical blood vessel structures, and show proof-of-concept results on real medical images.
|
|
| 14. |
- Marginean, Felicia, et al.
(författare)
-
An Artificial Intelligence-based Support Tool for Automation and Standardisation of Gleason Grading in Prostate Biopsies
- 2021
-
Ingår i: European Urology Focus. - : Elsevier BV. - 2405-4569. ; 7:5, s. 995-1001
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Gleason grading is the standard diagnostic method for prostate cancer and is essential for determining prognosis and treatment. The dearth of expert pathologists, the inter- and intraobserver variability, as well as the labour intensity of Gleason grading all necessitate the development of a user-friendly tool for robust standardisation.OBJECTIVE: To develop an artificial intelligence (AI) algorithm, based on machine learning and convolutional neural networks, as a tool for improved standardisation in Gleason grading in prostate cancer biopsies.DESIGN, SETTING, AND PARTICIPANTS: A total of 698 prostate biopsy sections from 174 patients were used for training. The training sections were annotated by two senior consultant pathologists. The final algorithm was tested on 37 biopsy sections from 21 patients, with digitised slide images from two different scanners.OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Correlation, sensitivity, and specificity parameters were calculated.RESULTS AND LIMITATIONS: The algorithm shows high accuracy in detecting cancer areas (sensitivity: 100%, specificity: 68%). Compared with the pathologists, the algorithm also performed well in detecting cancer areas (intraclass correlation coefficient [ICC]: 0.99) and assigning the Gleason patterns correctly: Gleason patterns 3 and 4 (ICC: 0.96 and 0.94, respectively), and to a lesser extent, Gleason pattern 5 (ICC: 0.82). Similar results were obtained using two different scanners.CONCLUSIONS: Our AI-based algorithm can reliably detect prostate cancer and quantify the Gleason patterns in core needle biopsies, with similar accuracy as pathologists. The results are reproducible on images from different scanners with a proven low level of intraobserver variability. We believe that this AI tool could be regarded as an efficient and interactive tool for pathologists.PATIENT SUMMARY: We developed a sensitive artificial intelligence tool for prostate biopsies, which detects and grades cancer with similar accuracy to pathologists. This tool holds promise to improve the diagnosis of prostate cancer.
|
|
| 15. |
- Nielsen, Steffen, et al.
(författare)
-
Differential gene expression in primary fibroblasts induced by proton and cobalt-60 beam irradiation
- 2017
-
Ingår i: Acta Oncologica. - 0284-186X .- 1651-226X. ; 56:11, s. 1406-1412
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction: Proton beam therapy delivers a more conformal dose distribution than conventional radiotherapy, thus improving normal tissue sparring. Increasing linear energy transfer (LET) along the proton track increases the relative biological effectiveness (RBE) near the distal edge of the Spread-out Bragg peak (SOBP). The severity of normal tissue side effects following photon beam radiotherapy vary considerably between patients.Aim: The dual study aim was to identify gene expression patterns specific to radiation type and proton beam position, and to assess whether individual radiation sensitivity influences gene expression levels in fibroblast cultures irradiated in vitro.Methods: The study includes 30 primary fibroblast cell cultures from patients previously classified as either radiosensitive or radioresistant. Cells were irradiated at three different positions in the proton beam profile: entrance, mid-SOBP and at the SOBP distal edge. Dose was delivered in three fractions × 3.5 Gy(RBE) (RBE 1.1). Cobalt-60 (Co-60) irradiation was used as reference. Real-time qPCR was performed to determine gene expression levels for 17 genes associated with inflammation response, fibrosis and angiogenesis.Results: Differences in median gene expression levels were observed for multiple genes such as IL6, IL8 and CXCL12. Median IL6 expression was 30%, 24% and 47% lower in entrance, mid-SOBP and SOBP distal edge groups than in Co-60 irradiated cells. No genes were found to be oppositely regulated by different radiation qualities. Radiosensitive patient samples had the strongest regulation of gene expression; irrespective of radiation type.Conclusions: Our findings indicate that the increased LET at the SOBP distal edge position did not generally lead to increased transcriptive response in primary fibroblast cultures. Inflammatory factors were generally less extensively upregulated by proton irradiation compared with Co-60 photon irradiation. These effects may possibly influence the development of normal tissue damage in patients treated with proton beam therapy.
|
|
| 16. |
- Olsson, Carl, et al.
(författare)
-
Extending Continuous Cuts: Anisotropic Metrics and Expansion Moves
- 2009
-
Ingår i: Proceedings of 2009 IEEE 12th International Conference on Computer Vision (ICCV). - 9781424444199 ; , s. 405-412
-
Konferensbidrag (refereegranskat)abstract
- The concept of graph cuts is by now a standard method for all sorts of low level vision problems. Its popularity is largely due to the fact that globally or near globally optimal solutions can be computed using efficient max flow algorithms. On the other hand it has been observed that this method may suffer from metrication errors. Recent work has begun studying continuous versions of graph cuts, which give smaller metrication errors. Another advantage is that continuous cuts are straightforward to parallelize. In this paper we extend the class of functionals that can be optimized in the continuous setting to include anisotropic TV-norms. We show that there is a so called coarea formula for these functionals making it possible to minimize them by solving a convex problem. We also show that the concept of α-expansion moves can be reformulated to fit the continuous formulation, and we derive approximation bounds in analogy with the discrete case. A continuous version of the Potts model for multi-class segmentation problems is presented, and it is shown how to obtain provably good solutions using continuous α-expansions.
|
|
| 17. |
|
|
| 18. |
|
|
| 19. |
|
|
| 20. |
- Oskarsson, Magnus, et al.
(författare)
-
The minimal structure and motion problems with missing data for 1D retina vision
- 2006
-
Ingår i: Journal of Mathematical Imaging and Vision. - : Springer Science and Business Media LLC. - 0924-9907 .- 1573-7683. ; 26:3, s. 327-343
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper we investigate the structure and motion problem for calibrated one-dimensional projections of a two-dimensional environment. The theory of one-dimensional cameras are useful in several areas, e.g. within robotics, autonomous guided vehicles, projection of lines in ordinary vision and vision of vehicles undergoing so called planar motion. In a previous paper the structure and motion problem for all cases with non-missing data was classified and solved. Our aim is here to classify all structure and motion problems, even those with missing data, and to solve them. In the classification we introduce the notion of a prime problem. A prime problem is a minimal problem that does not contain a minimal problem as a sub-problem. We further show that there are infinitely many such prime problems. We give solutions to four prime problems, and using the duality of Carlsson these can be extended to solutions of seven prime problems. Finally we give some experimental results based on synthetic data.
|
|
| 21. |
- Overgaard, Niels Christian, et al.
(författare)
-
An Analysis of Variational Alignment of Curves in Images
- 2005
-
Ingår i: Proc. 5th International Conference on Scale Space and PDE Methods in Computer Vision. - Berlin, Heidelberg : Springer Berlin Heidelberg. ; , s. 480-491
-
Konferensbidrag (refereegranskat)
|
|
| 22. |
- Overgaard, Niels Christian
(författare)
-
Properties of the Pushforward Map on Test Functions, Measures and Distributions
- 2002
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The subject of this thesis is the pushforward map on compactly supported distributions induced by a smooth mapping. Being the adjoint of the natural pullback operation on the class of smooth functions, the pushforward map is always well-defined, and as such it must be regarded as one of the fundamental operations of distribution theory. This thesis has two main aims: The first of these is to give a clear exposition of the properties of the pushforward map associated with a smooth map between open subsets of Euclidean space. The second aim is to investigate the connection between the pushforward by a function f and the asymptotic behavior at infinity of oscillatory integrals with f as phase function. Particular attention will be paid to Palamodov's conjecture (in the category of smooth functions), to which we give some partial answers.
|
|
| 23. |
|
|
| 24. |
- Overgaard, Niels Christian, et al.
(författare)
-
The Variational Origin of Motion by Gaussian Curvature
- 2007
-
Ingår i: Scale Space and Variational Methods in Computer Vision. - Berlin, Heidelberg : Springer. - 9783540728221 - 9783540728238 ; 4485, s. 430-441
-
Konferensbidrag (refereegranskat)abstract
- A variational formulation of an image analysis problem has the nice feature that it is often easier to predict the effect of minimizing a certain energy functional than to interpret the corresponding Euler-Lagrange equations. For example, the equations of motion for an active contour usually contains a mean curvature term, which we know will regularizes the contour because mean curvature is the first variation of curve length, and shorter curves are typically smoother than longer ones.In some applications it may be worth considering Gaussian curvature as a regularizing term instead of mean curvature. The present paper provides a variational principle for this: We show that Gaussian curvature of a regular surface in three-dimensional Euclidean space is the first variation of an energy functional defined on the surface. Some properties of the corresponding motion by Gaussian curvature are pointed out, and a simple example is given, where minimization of this functional yields a nontrivial solution.
|
|
| 25. |
|
|
| 26. |
|
|
| 27. |
|
|
| 28. |
|
|
| 29. |
|
|
| 30. |
- Strandmark, Petter, et al.
(författare)
-
Optimal Levels for the Two-phase, Piecewise Constant Mumford-Shah Functional
- 2009
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Recent results have shown that denoising an image with the Rudin, Osher and Fatemi (ROF) total variation model can be accomplished by solving a series of binary optimization problems. We observe that this fact can be used in the other direction. The procedure is applied to the two-phase, piecewise constant Mumford-Shah functional, where an image is approximated with a function taking only two values. When the difference between the two levels is kept constant, a global optimum can be found efficiently. This allows us to solve the full problem with branch and bound in only one dimension.
|
|
| 31. |
- Strandmark, Petter, et al.
(författare)
-
Optimizing Parametric Total Variation Models
- 2009
-
Ingår i: [Host publication title missing]. ; , s. 2240-2247
-
Konferensbidrag (refereegranskat)abstract
- One of the key factors for the success of recent energy minimization methods is that they seek to compute global solutions. Even for non-convex energy functionals, optimization methods such as graph cuts have proven to produce high-quality solutions by iterative minimization based on large neighborhoods, making them less vulnerable to local minima. Our approach takes this a step further by enlarging the search neighborhood with one dimension. In this paper we consider binary total variation problems that depend on an additional set of parameters. Examples include: (i) the Chan-Vese model that we solve globally (ii) ratio and constrained minimization which can be formulated as parametric problems, and (iii) variants of the Mumford-Shah functional. Our approach is based on a recent theorem of Chambolle which states that solving a one-parameter family of binary problems amounts to solving a single convex variational problem. We prove a generalization of this result and show how it can be applied to parametric optimization.
|
|
| 32. |
- Ståhl, Daniel, et al.
(författare)
-
Automatic Compartment Modelling and Segmentation for Dynamical Renal Scintigraphies
- 2011
-
Ingår i: Lecture Notes in Computer Science. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 1611-3349 .- 0302-9743. - 9783642212260 - 9783642212277 ; 6688, s. 557-568
-
Konferensbidrag (refereegranskat)abstract
- Time-resolved medical data has important applications in a large variety of medical applications. In this paper we study automatic analysis of dynamical renal scintigraphies. The traditional analysis pipeline for dynamical renal scintigraphies is to use manual or semiautomatic methods for segmentation of pixels into physical compartments, extract their corresponding time-activity curves and then compute the parameters that are relevant for medical assessment. In this paper we present a fully automatic system that incorporates spatial smoothing constraints, compartment modelling and positivity constraints to produce an interpretation of the full time-resolved data. The method has been tested on renal dynamical scintigraphies with promising results. It is shown that the method indeed produces more compact representations, while keeping the residual of fit low. The parameters of the time activity curve, such as peak-time and time for half activity from peak, are compared between the previous semiautomatic method and the method presented in this paper. It is also shown how to obtain new and clinically relevant features using our novel system.
|
|
| 33. |
- Tall, Kasper, et al.
(författare)
-
Automatic detection of small areas of Gleason grade 5 in prostate tissue using CNN
- 2019
-
Ingår i: Medical Imaging 2019: Digital Pathology. - : SPIE. - 9781510625594 ; 10956
-
Konferensbidrag (refereegranskat)abstract
- There are several different approaches used to treat prostate cancer, depending on age and general health conditions of the patient but also how severe the cancer is. To determine the latter, Gleason grading is used. The grade is determined by a pathologist, based on structures in histology samples from prostate biopsies. To determine the diagnosis, both the most common Gleason grade but also the highest Gleason grade occurring is used. Since the tumours typically split up the more malignant they are, single cells of Gleason grade 5, the highest and most malignant Gleason grade, can occur intermingled with benign tissue. Therefore, it is of great importance to fid even very small areas of the highest grade. This is what we aim to automatically do in this work. We have trained a convolutional neural network, with a ResNet design, to classify small areas of tissue in high magnification as either Gleason 5 or non-Gleason 5. The dataset used is generated from whole slide images from Skåne University Hospital, and consists in total of 19680 small images with the size 128×128 pixels in 40X. We try to make the algorithm more robust to stain variations, which is a common issue for this type of data, by using colour augmentation. The best accuracy we achieve for classification of Gleason 5 versus non-Gleason 5 images is 92%.
|
|
| 34. |
- Winzell, Filip, et al.
(författare)
-
Systematic Augmentation in HSV Space for Semantic Segmentation of Prostate Biopsies
- 2023
-
Ingår i: Image Analysis : 23rd Scandinavian Conference, SCIA 2023, Proceedings, Part II - 23rd Scandinavian Conference, SCIA 2023, Proceedings, Part II. - 1611-3349 .- 0302-9743. - 9783031314384 - 9783031314377 ; 13886, s. 293-308
-
Konferensbidrag (refereegranskat)abstract
- In recent years, the combination of the digitization of the field of pathology and increased computational power has led to a big increase in research of computer-aided diagnostics using systems based on artificial intelligence (AI). This includes detection and classification of prostate cancer, where several studies have shown great promise in automated prostate cancer grading using deep learning based AI systems. However, there is still work to be done to ensure that these algorithms are invariant to possible variations of the digitized microscopy images they are applied to. A standard method in deep learning to increase the variation of the training data is dataset augmentation. All of these studies apply some augmentation of their data, however, there is a lack of evaluation of different methods and their impact on this crucial part of the AI systems. In this study, we look into different color augmentation methods for the task of segmentation of prostate biopsies. Furthermore, we introduce a novel color augmentation method based on stereographic projection. Our results affirm the importance of studying different augmentation methods and indicate a gain in performance using our method.
|
|
