| 1. |
|
|
| 2. |
- Banerjee, Subhashis, et al.
(författare)
-
Deep Curriculum Learning for Follow-up MRI Registration in Glioblastoma
- 2023
-
Ingår i: Medical Imaging 2023. - : SPIE -Society of Photo-Optical Instrumentation Engineers. - 9781510660335 - 9781510660342
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a weakly supervised deep convolutional neural network-based approach to perform voxel-level3D registration between subsequent follow-up MRI scans of the same patient. To handle the large deformation inthe surrounding brain tissues due to the tumor’s mass effect we proposed curriculum learning-based training forthe network. Weak supervision helps the network to concentrate more focus on the tumor region and resectioncavity through a saliency detection network. Qualitative and quantitative experimental results show the proposedregistration network outperformed two popular state-of-the-art methods.
|
|
| 3. |
- Banerjee, Subhashis, et al.
(författare)
-
Lifelong Learning with Dynamic Convolutions for Glioma Segmentation from Multi-Modal MRI
- 2023
-
Ingår i: Medical imaging 2023. - : SPIE - International Society for Optical Engineering. - 9781510660335 - 9781510660342
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a novel solution for catastrophic forgetting in lifelong learning (LL) using Dynamic Convolution Neural Network (Dy-CNN). The proposed dynamic convolution layer can adapt convolution filters by learning kernel coefficients or weights based on the input image. The suitability of the proposed Dy-CNN in a lifelong sequential learning-based scenario with multi-modal MR images is experimentally demonstrated for the segmentation of Glioma tumors from multi-modal MR images. Experimental results demonstrated the superiority of the Dy-CNN-based segmenting network in terms of learning through multi-modal MRI images and better convergence of lifelong learning-based training.
|
|
| 4. |
- Banerjee, Subhashis, et al.
(författare)
-
Segmentation of Intracranial Aneurysm Remnant in MRA using Dual-Attention Atrous Net
- 2021
-
Ingår i: 25th International Conference on Pattern Recognition (ICPR). - 9781728188089 ; , s. 9265-9272
-
Konferensbidrag (refereegranskat)abstract
- Due to the advancement of non-invasive medical imaging modalities like Magnetic Resonance Angiography (MRA), an increasing number of Intracranial Aneurysm (IA) cases are being reported in recent years. The IAs are typically treated by so-called endovascular coiling, where blood flow in the IA is prevented by embolization with a platinum coil. Accurate quantification of the IA Remnant (IAR), i.e. the volume with blood flow present post treatment is the utmost important factor in choosing the right treatment planning. This is typically done by manually segmenting the aneurysm remnant from the MRA volume. Since manual segmentation of volumetric images is a labour-intensive and error-prone process, development of an automatic volumetric segmentation method is required. Segmentation of small structures such as IA, that may largely vary in size, shape, and location is considered extremely difficult. Similar intensity distribution of IAs and surrounding blood vessels makes it more challenging and susceptible to false positive. In this paper we propose a novel 3D CNN architecture called Dual-Attention Atrous Net (DAtt-ANet), which can efficiently segment IAR volumes from MRA images by reconciling features at different scales using the proposed Parallel Atrous Unit (PAU) along with the use of self-attention mechanism for extracting fine-grained features and intra-class correlation. The proposed DAtt-ANet model is trained and evaluated on a clinical MRA image dataset of IAR consisting of 46 subjects. We compared the proposed DAtt-ANet with five state-of-the-art CNN models based on their segmentation performance. The proposed DAtt-ANet outperformed all other methods and was able to achieve a five-fold cross-validation DICE score of 0.73 +/- 0.06.
|
|
| 5. |
- Banerjee, Subhashis, et al.
(författare)
-
Streamlining neuroradiology workflow with AI for improved cerebrovascular structure monitoring
- 2024
-
Ingår i: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 14:1
-
Tidskriftsartikel (refereegranskat)abstract
- Radiological imaging to examine intracranial blood vessels is critical for preoperative planning and postoperative follow-up. Automated segmentation of cerebrovascular anatomy from Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) can provide radiologists with a more detailed and precise view of these vessels. This paper introduces a domain generalized artificial intelligence (AI) solution for volumetric monitoring of cerebrovascular structures from multi-center MRAs. Our approach utilizes a multi-task deep convolutional neural network (CNN) with a topology-aware loss function to learn voxel-wise segmentation of the cerebrovascular tree. We use Decorrelation Loss to achieve domain regularization for the encoder network and auxiliary tasks to provide additional regularization and enable the encoder to learn higher-level intermediate representations for improved performance. We compare our method to six state-of-the-art 3D vessel segmentation methods using retrospective TOF-MRA datasets from multiple private and public data sources scanned at six hospitals, with and without vascular pathologies. The proposed model achieved the best scores in all the qualitative performance measures. Furthermore, we have developed an AI-assisted Graphical User Interface (GUI) based on our research to assist radiologists in their daily work and establish a more efficient work process that saves time.
|
|
| 6. |
- Banerjee, Subhashis, et al.
(författare)
-
Topology-Aware Learning for Volumetric Cerebrovascular Segmentation
- 2022
-
Ingår i: 2022 IEEE International Symposium on Biomedical Imaging (IEEE ISBI 2022). - : IEEE. - 9781665429238 ; , s. 1-4
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a topology-aware learning strategy for volumetric segmentation of intracranial cerebrovascular structures. We propose a multi-task deep CNN along with a topology-aware loss function for this purpose. Along with the main task (i.e. segmentation), we train the model to learn two related auxiliary tasks viz. learning the distance transform for the voxels on the surface of the vascular tree and learning the vessel centerline. This provides additional regularization and allows the encoder to learn higher-level intermediate representations to boost the performance of the main task. We compare the proposed method with six state-of-the-art deep learning-based 3D vessel segmentation methods, by using a public Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) dataset. Experimental results demonstrate that the proposed method has the best performance in this particular context.
|
|
| 7. |
- Daoud, Adel, 1981, et al.
(författare)
-
Using Satellite Images and Deep Learning to Measure Health and Living Standards in India
- 2023
-
Ingår i: Social Indicators Research. - : SPRINGER. - 0303-8300 .- 1573-0921. ; 167:1-3, s. 475-505
-
Tidskriftsartikel (refereegranskat)abstract
- Using deep learning with satellite images enhances our understanding of human development at a granular spatial and temporal level. Most studies have focused on Africa and on a narrow set of asset-based indicators. This article leverages georeferenced village-level census data from across 40% of the population of India to train deep models that predicts 16 indicators of human well-being from Landsat 7 imagery. Based on the principles of transfer learning, the census-based model is used as a feature extractor to train another model that predicts an even larger set of developmental variables—over 90 variables—included in two rounds of the National Family Health Survey (NFHS). The census-based-feature-extractor model outperforms the current standard in the literature for most of these NFHS variables. Overall, the results show that combining satellite data with Indian Census data unlocks rich information for training deep models that track human development at an unprecedented geographical and temporal resolution.
|
|
| 8. |
- Kundu, Swagata, et al.
(författare)
-
3-D Attention-SEV-Net for Segmentation of Post-operative Glioblastoma with Interactive Correction of Over-Segmentation
- 2023
-
Ingår i: Pattern Recognition and Machine Intelligence, PREMI 2023. - : Springer. - 9783031451690 - 9783031451706 ; , s. 380-387
-
Konferensbidrag (refereegranskat)abstract
- Accurate localization and volumetric quantification of postoperative glioblastoma are of profound importance for clinical applications like post-surgery treatment planning, monitoring of tumor regrowth, and radiotherapy map planning. Manual delineation consumes more time and error prone thus automated 3-D quantification of brain tumors using deep learning algorithms from MRI scans has been used in recent years. The shortcoming with automated segmentation is that it often over-segments or under-segments the tumor regions. An interactive deep-learning tool will enable radiologists to correct the over-segmented and under-segmented voxels. In this paper, we proposed a network named Attention-SEV-Net which outperforms state-of-the-art network architectures. We also developed an interactive graphical user interface, where the initial 3-D segmentation of contrast-enhanced tumor can be interactively corrected to remove falsely detected isolated tumor regions. Attention-SEV-Net is trained with BraTS-2021 training data set and tested on Uppsala University post-operative glioblastoma dataset. The methodology outperformed state-of-the-art networks like U-Net, VNet, Attention U-Net and Residual U-Net. The mean dice score achieved is 0.6682 and the mean Hausdorff distance-95 got is 8.96mm for the Uppsala University dataset.
|
|
| 9. |
- Kundu, Swagata, et al.
(författare)
-
ASE-Net for Segmentation of Post-operative Glioblastoma and Patient-specific Fine-tuning for Segmentation Refinement of Follow-up MRI Scans
- 2024
-
Ingår i: SN computer science. - : Springer. - 2661-8907. ; 5:106
-
Tidskriftsartikel (refereegranskat)abstract
- Volumetric quantification of tumors is usually done manually by radiologists requiring precious medical time and suffering from inter-observer variability. An automatic tool for accurate volume quantification of post-operative glioblastoma would reduce the workload of radiologists and improve the quality of follow-up monitoring and patient care. This paper deals with the 3-D segmentation of post-operative glioblastoma using channel squeeze and excitation based attention gated network (ASE-Net). The proposed deep neural network has a 3-D encoder and decoder based architecture with channel squeeze and excitation (CSE) blocks and attention blocks. The CSE block reduces the dependency on space information and put more emphasize on the channel information. The attention block suppresses the feature maps of irrelevant background and helps highlighting the relevant feature maps. The Uppsala university data set used has post-operative follow-up MRI scans for fifteen patients. A patient specific fine-tuning approach is used to improve the segmentation results for each patient. ASE-Net is also cross-validated with BraTS-2021 data set. The mean dice score of five-fold cross validation results with BraTS-2021 data set for enhanced tumor is 0.8244. The proposed network outperforms the competing networks like U-Net, Attention U-Net and Res U-Net. On the Uppsala University glioblastoma data set, the mean Dice score obtained with the proposed network is 0.7084, Hausdorff Distance-95 is 7.14 and the mean volumetric similarity achieved is 0.8579. With fine-tuning the pre-trained network, the mean dice score improved to 0.7368, Hausdorff Distance-95 decreased to 6.10 and volumetric similarity improved to 0.8736. ASE-Net outperforms the competing networks and can be used for volumetric quantification of post-operative glioblastoma from follow-up MRI scans. The network significantly reduces the probability of over segmentation.
|
|
| 10. |
- Mehta, Raghav, et al.
(författare)
-
QU-BraTS : MICCAI BraTS 2020 Challenge on QuantifyingUncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
- 2022
-
Ingår i: Journal of Machine Learning for Biomedical Imaging. - 2766-905X. ; , s. 1-54
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning (DL) models have provided the state-of-the-art performance in a wide variety of medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder the translation of DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties, could enable clinical review of the most uncertain regions, thereby building trust and paving the way towards clinical translation. Recently, a number of uncertainty estimation methods have been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019-2020 task on uncertainty quantification (QU-BraTS), and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions, and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentages of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, and hence highlight the need for uncertainty quantification in medical image analyses. Our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS
|
|
