| 1. |
- 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.
|
|
| 2. |
- Auer, M., et al.
(författare)
-
A methodology to study the morphologic changes in lesions during in vitro angioplasty using MRI and image processing
- 2008
-
Ingår i: Medical Image Analysis. - : Elsevier BV. - 1361-8415 .- 1361-8423. ; 12:2, s. 163-173
-
Tidskriftsartikel (refereegranskat)abstract
- The assessment of morphologic changes in atherosclerotic lesions during interventional procedures such as transluminal balloon angioplasty is an issue of highest clinical importance. We propose a methodology that allows realistic 3D morphomechanical modeling of the vessel, the plaque and the lumen at different stages of in vitro angioplasty. We elaborate on a novel device designed to guide angioplasty under controlled experimental conditions. The device allows to reproduce in vivo conditions as good as possible, i.e. axial in situ pre-stretch, 100 mmHg intraluminal pressure, 37 degrees C Tyrode solution, balloon inflation without external constraints using a high-pressure syringe and contrast medium. With a standard 1.5 T MR-system we accomplish multi-spectral images at different stages of the angioplasty experiment. After MR image acquisition the specimen is used for histopathological analysis and biomechanical tests. A segmentation process is used to generate NURBS-based 3D geometric models of the individual vessel and plaque components at different balloon pressures. Tissue components are segmented automatically using generalized gradient vector flow active contours. We investigated 10 human femoral arteries. The effects of balloon compression on the individual artery components is particularly described for two obstructed arteries with an intact collagenous cap, a pronounced lipid pool and with calcification. In both arteries we observe a significant increase in lumen area after angioplasty. Dissection between intima and media and reduction of the lipid pool are primary mechanisms of dilatation. This methodology provides a basis for studying plaque biomechanics under supra-physiological loading conditions. It has the potential to improve and validate finite element models of atherosclerotic plaques which may allow a better prediction of angioplasty procedures.
|
|
| 3. |
- Bilic, Patrick, et al.
(författare)
-
The Liver Tumor Segmentation Benchmark (LiTS)
- 2023
-
Ingår i: Medical Image Analysis. - : Elsevier BV. - 1361-8415 .- 1361-8423. ; 84, s. 102680-
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.
|
|
| 4. |
- Bustamante, Mariana, 1983-, et al.
(författare)
-
Automated multi-atlas segmentation of cardiac 4D flow MRI
- 2018
-
Ingår i: Medical Image Analysis. - : Elsevier. - 1361-8415 .- 1361-8423. ; 49, s. 128-140
-
Tidskriftsartikel (refereegranskat)abstract
- Four-dimensional (4D) flow magnetic resonance imaging (4D Flow MRI) enables acquisition of time-resolved three-directional velocity data in the entire heart and all major thoracic vessels. The segmentation of these tissues is typically performed using semi-automatic methods. Some of which primarily rely on the velocity data and result in a segmentation of the vessels only during the systolic phases. Other methods, mostly applied on the heart, rely on separately acquired balanced Steady State Free Precession (b-SSFP) MR images, after which the segmentations are superimposed on the 4D Flow MRI. While b-SSFP images typically cover the whole cardiac cycle and have good contrast, they suffer from a number of problems, such as large slice thickness, limited coverage of the cardiac anatomy, and being prone to displacement errors caused by respiratory motion. To address these limitations we propose a multi-atlas segmentation method, which relies only on 4D Flow MRI data, to automatically generate four-dimensional segmentations that include the entire thoracic cardiovascular system present in these datasets. The approach was evaluated on 4D Flow MR datasets from a cohort of 27 healthy volunteers and 83 patients with mildly impaired systolic left-ventricular function. Comparison of manual and automatic segmentations of the cardiac chambers at end-systolic and end-diastolic timeframes showed agreements comparable to those previously reported for automatic segmentation methods of b-SSFP MR images. Furthermore, automatic segmentation of the entire thoracic cardiovascular system improves visualization of 4D Flow MRI and facilitates computation of hemodynamic parameters.
|
|
| 5. |
- Chen, Boqi, et al.
(författare)
-
Generative appearance replay for continual unsupervised domain adaptation
- 2023
-
Ingår i: Medical Image Analysis. - : Elsevier. - 1361-8415 .- 1361-8423. ; 89, s. 102924-102924
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple different domains, and may not contain labels for training. Certain settings, for instance medical applications, often involve further restrictions that prohibit retention of previously seen data due to privacy regulations. In this work, to address such challenges, we study unsupervised segmentation in continual learning scenarios that involve domain shift. To that end, we introduce GarDA (Generative Appearance Replay for continual Domain Adaptation), a generative-replay based approach that can adapt a segmentation model sequentially to new domains with unlabeled data. In contrast to single-step unsupervised domain adaptation (UDA), continual adaptation to a sequence of domains enables leveraging and consolidation of information from multiple domains. Unlike previous approaches in incremental UDA, our method does not require access to previously seen data, making it applicable in many practical scenarios. We evaluate GarDA on three datasets with different organs and modalities, where it substantially outperforms existing techniques. Our code is available at: https://github.com/histocartography/generative-appearance-replay.Previous article in issue
|
|
| 6. |
- de Bel, Thomas, et al.
(författare)
-
Residual cyclegan for robust domain transformation of histopathological tissue slides
- 2021
-
Ingår i: Medical Image Analysis. - : Elsevier. - 1361-8415 .- 1361-8423. ; 70
-
Tidskriftsartikel (refereegranskat)abstract
- Variation between stains in histopathology is commonplace across different medical centers. This can have a significant effect on the reliability of machine learning algorithms. In this paper, we propose to reduce performance variability by using-consistent generative adversarial (CycleGAN) networks to remove staining variation. We improve upon the regular CycleGAN by incorporating residual learning. We comprehensively evaluate the performance of our stain transformation method and compare its usefulness in addition to extensive data augmentation to enhance the robustness of tissue segmentation algorithms. Our steps are as follows: first, we train a model to perform segmentation on tissue slides from a single source center, while heavily applying augmentations to increase robustness to unseen data. Second, we evaluate and compare the segmentation performance on data from other centers, both with and without applying our CycleGAN stain transformation. We compare segmentation performances in a colon tissue segmentation and kidney tissue segmentation task, covering data from 6 different centers. We show that our transformation method improves the overall Dice coefficient by 9% over the non-normalized target data and by 4% over traditional stain transformation in our colon tissue segmentation task. For kidney segmentation, our residual CycleGAN increases performance by 10% over no transformation and around 2% compared to the non-residual CycleGAN. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
|
|
| 7. |
- Dooper, Stephan, et al.
(författare)
-
Gigapixel end-to-end training using streaming and attention
- 2023
-
Ingår i: Medical Image Analysis. - : ELSEVIER. - 1361-8415 .- 1361-8423. ; 88
-
Tidskriftsartikel (refereegranskat)abstract
- Current hardware limitations make it impossible to train convolutional neural networks on gigapixel image inputs directly. Recent developments in weakly supervised learning, such as attention-gated multiple instance learning, have shown promising results, but often use multi-stage or patch-wise training strategies risking suboptimal feature extraction, which can negatively impact performance. In this paper, we propose to train a ResNet-34 encoder with an attention-gated classification head in an end-to-end fashion, which we call StreamingCLAM, using a streaming implementation of convolutional layers. This allows us to train end-to-end on 4-gigapixel microscopic images using only slide-level labels.We achieve a mean area under the receiver operating characteristic curve of 0.9757 for metastatic breast cancer detection (CAMELYON16), close to fully supervised approaches using pixel-level annotations. Our model can also detect MYC-gene translocation in histologic slides of diffuse large B-cell lymphoma, achieving a mean area under the ROC curve of 0.8259. Furthermore, we show that our model offers a degree of interpretability through the attention mechanism.
|
|
| 8. |
- Eklund, Anders, et al.
(författare)
-
Medical Image Processing on the GPU : Past, Present and Future
- 2013
-
Ingår i: Medical Image Analysis. - : Elsevier. - 1361-8415 .- 1361-8423. ; 17:8, s. 1073-1094
-
Forskningsöversikt (refereegranskat)abstract
- Graphics processing units (GPUs) are used today in a wide range of applications, mainly because they can dramatically accelerate parallel computing, are affordable and energy efficient. In the field of medical imaging, GPUs are in some cases crucial for enabling practical use of computationally demanding algorithms. This review presents the past and present work on GPU accelerated medical image processing, and is meant to serve as an overview and introduction to existing GPU implementations. The review covers GPU acceleration of basic image processing operations (filtering, interpolation, histogram estimation and distance transforms), the most commonly used algorithms in medical imaging (image registration, image segmentation and image denoising) and algorithms that are specific to individual modalities (CT, PET, SPECT, MRI, fMRI, DTI, ultrasound, optical imaging and microscopy). The review ends by highlighting some future possibilities and challenges.
|
|
| 9. |
|
|
| 10. |
- Hansson, Mattias, et al.
(författare)
-
Segmentation of B-mode cardiac ultrasound data by Bayesian Probability Maps
- 2014
-
Ingår i: Medical Image Analysis. - : Elsevier. - 1361-8415 .- 1361-8423. ; 18:7, s. 1184-1199
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper we present a model for describing the position distribution of the endocardium in the two-chamber apical long-axis view of the heart in clinical B-mode ultrasound cycles. We propose a novel Bayesian formulation, including priors for spatial and temporal smoothness, and preferred shapes and position. The shape model takes into account both endocardium, atrial region and apex. The likelihood is built using a statistical signal model, which attempts to closely model a censored signal. In addition, the use of a censored Gamma mixture model with unknown censoring point, to handle artefacts resulting from left-censoring of the in US clinical B-mode, is to our knowledge novel. The posterior density is sampled by the Gibbs method to estimate the expected latent variable representation of the endocardium, which we call the Bayesian Probability Map; the map describes the probability of pixels being classified as being within the endocardium. The regularization parameters of the model are estimated by cross-validation, and the results are compared against the two-chamber apical model of Chen et al.
|
|
