Subhashis Banerjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Subhashis Banerjee has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Sushmita Mitra
Machine Intelligence Unit, Indian Statistical Institute, Kolkata, India
10 shared publications - Robin Strand
Department of Information Technology, Centre for Image Analysis, Uppsala University, Uppsala, Sweden
4 shared publications - B. Uma Shankar
Machine Intelligence Unit, Indian Statistical Institute, Kolkata, India
3 shared publications Ashis Kumar Dhara
Department of Electrical Engineering, National Institute of Technology Durgapur, Durgapur, India
2 shared publications- Ashis Kumar Dhara
Electrical Engineering Department, National Institute of Technology Durgapur, Durgapur, India
2 shared publications B. Uma Shankar
2 shared publications
Latest Publications
- Open Access
- 22 April 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-12
Streamlining neuroradiology workflow with AI for improved cerebrovascular structure monitoring
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.
- 22 April 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-12
Open AccessStreamlining neuroradiology workflow with AI for improved cerebrovascular structure monitoring
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.
- 16 December 2023
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-14
ASE-Net for Segmentation of Post-Operative Glioblastoma and Patient-Specific Fine-Tuning for Segmentation Refinement of Follow-Up MRI Scans
- 16 December 2023
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-14
ASE-Net for Segmentation of Post-Operative Glioblastoma and Patient-Specific Fine-Tuning for Segmentation Refinement of Follow-Up MRI Scans
- Open Access
- 7 July 2023
- Published by Springer Nature in Research Square
Streamlining Neuroradiology Workflow with AI for Improved Cerebrovascular Structure Monitoring
The use of radiological imaging to examine intracranial blood vessels is critical for both preoperative planning and postoperative follow-up. Automated segmentation of cerebrovascular anatomy from Time-Of-Flight Magnetic Resonance Angiography (TOFMRA) can provide radiologists with a more detailed and precise view of these vessels. In this paper, we introduce 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 voxelwise 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 different 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.
- 7 July 2023
- Published by Springer Nature in Research Square
Open AccessStreamlining Neuroradiology Workflow with AI for Improved Cerebrovascular Structure Monitoring
The use of radiological imaging to examine intracranial blood vessels is critical for both preoperative planning and postoperative follow-up. Automated segmentation of cerebrovascular anatomy from Time-Of-Flight Magnetic Resonance Angiography (TOFMRA) can provide radiologists with a more detailed and precise view of these vessels. In this paper, we introduce 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 voxelwise 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 different 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.
- 27 April 2023
- Published by Springer Nature
- p. 190-200
Deep Active Learning for Glioblastoma Quantification
- 27 April 2023
- Published by Springer Nature
- p. 190-200
Deep Active Learning for Glioblastoma Quantification
- 3 April 2023
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12464, 804-807
Deep curriculum learning for follow-up MRI registration in glioblastoma
This paper presents a weakly supervised deep convolutional neural network-based approach to perform voxel-level 3D registration between subsequent follow-up MRI scans of the same patient. To handle the large deformation in the surrounding brain tissues due to the tumor’s mass effect we proposed curriculum learning-based training for the network. Weak supervision helps the network to concentrate more focus on the tumor region and resection cavity through a saliency detection network. Qualitative and quantitative experimental results show the proposed registration network outperformed two popular state-of-the-art methods.
- 3 April 2023
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12464, 804-807
Deep curriculum learning for follow-up MRI registration in glioblastoma
This paper presents a weakly supervised deep convolutional neural network-based approach to perform voxel-level 3D registration between subsequent follow-up MRI scans of the same patient. To handle the large deformation in the surrounding brain tissues due to the tumor’s mass effect we proposed curriculum learning-based training for the network. Weak supervision helps the network to concentrate more focus on the tumor region and resection cavity through a saliency detection network. Qualitative and quantitative experimental results show the proposed registration network outperformed two popular state-of-the-art methods.
- Open Access
- 18 June 2021
- Published by MDPI AG in Electronics
- Vol. 10 (12) , 1463
DeepSGP: Deep Learning for Gene Selection and Survival Group Prediction in Glioblastoma
Glioblastoma Multiforme (GBM) is an aggressive form of glioma, exhibiting very poor survival. Genomic input, in the form of RNA sequencing data (RNA-seq), is expected to provide vital information about the characteristics of the genes that affect the Overall Survival (OS) of patients. This could have a significant impact on treatment planning. We present a new Autoencoder (AE)-based strategy for the prediction of survival (low or high) of GBM patients, using the RNA-seq data of 129 GBM samples from The Cancer Genome Atlas (TCGA). This is a novel interdisciplinary approach to integrating genomics with deep learning towards survival prediction. First, the Differentially Expressed Genes (DEGs) were selected using EdgeR. These were further reduced using correlation-based analysis. This was followed by the application of ranking with different feature subset selection and feature extraction algorithms, including the AE. In each case, fifty features were selected/extracted, for subsequent prediction with different classifiers. An exhaustive study for survival group prediction, using eight different classifiers with the accuracy and Area Under the Curve (AUC), established the superiority of the AE-based feature extraction method, called DeepSGP. It produced a very high accuracy (0.83) and AUC (0.90). Of the eight classifiers, using the extracted features by DeepSGP, the MLP was the best at Overall Survival (OS) prediction with an accuracy of 0.89 and an AUC of 0.97. The biological significance of the genes extracted by the AE were also analyzed to establish their importance. Finally, the statistical significance of the predicted output of the DeepSGP algorithm was established using the concordance index.
- 18 June 2021
- Published by MDPI AG in Electronics
- Vol. 10 (12) , 1463
Open AccessDeepSGP: Deep Learning for Gene Selection and Survival Group Prediction in Glioblastoma
Glioblastoma Multiforme (GBM) is an aggressive form of glioma, exhibiting very poor survival. Genomic input, in the form of RNA sequencing data (RNA-seq), is expected to provide vital information about the characteristics of the genes that affect the Overall Survival (OS) of patients. This could have a significant impact on treatment planning. We present a new Autoencoder (AE)-based strategy for the prediction of survival (low or high) of GBM patients, using the RNA-seq data of 129 GBM samples from The Cancer Genome Atlas (TCGA). This is a novel interdisciplinary approach to integrating genomics with deep learning towards survival prediction. First, the Differentially Expressed Genes (DEGs) were selected using EdgeR. These were further reduced using correlation-based analysis. This was followed by the application of ranking with different feature subset selection and feature extraction algorithms, including the AE. In each case, fifty features were selected/extracted, for subsequent prediction with different classifiers. An exhaustive study for survival group prediction, using eight different classifiers with the accuracy and Area Under the Curve (AUC), established the superiority of the AE-based feature extraction method, called DeepSGP. It produced a very high accuracy (0.83) and AUC (0.90). Of the eight classifiers, using the extracted features by DeepSGP, the MLP was the best at Overall Survival (OS) prediction with an accuracy of 0.89 and an AUC of 0.97. The biological significance of the genes extracted by the AE were also analyzed to establish their importance. Finally, the statistical significance of the predicted output of the DeepSGP algorithm was established using the concordance index.
- Open Access
- 21 June 2020
- Published by Springer Nature in SN Computer Science
- Vol. 1 (4) , 1-14
Glioma Classification Using Deep Radiomics
- 21 June 2020
- Published by Springer Nature in SN Computer Science
- Vol. 1 (4) , 1-14
Open AccessGlioma Classification Using Deep Radiomics
- 19 May 2020
- Published by Springer Nature
- p. 37-49
Ensemble of CNNs for Segmentation of Glioma Sub-regions with Survival Prediction
- 19 May 2020
- Published by Springer Nature
- p. 37-49
Ensemble of CNNs for Segmentation of Glioma Sub-regions with Survival Prediction
- 31 January 2020
- Published by Springer Nature in Soft Computing
- Vol. 24 (17) , 13115-13134
Fuzzy volumetric delineation of brain tumor and survival prediction
- 31 January 2020
- Published by Springer Nature in Soft Computing
- Vol. 24 (17) , 13115-13134
Fuzzy volumetric delineation of brain tumor and survival prediction
- Open Access
- 24 January 2020
- Published by Frontiers Media SA in Frontiers in Computational Neuroscience
- Vol. 14, 3
Novel Volumetric Sub-region Segmentation in Brain Tumors
A novel deep learning based model called Multi-Planar Spatial Convolutional Neural Network (MPS-CNN) is proposed for effective, automated segmentation of different sub-regions viz. peritumoral edema (ED), necrotic core (NCR), enhancing and non-enhancing tumor core (ET/NET), from multi-modal MR images of the brain. An encoder-decoder type CNN model is designed for pixel-wise segmentation of the tumor along three anatomical planes (axial, sagittal, and coronal) at the slice level. These are then combined, by incorporating a consensus fusion strategy with a fully connected Conditional Random Field (CRF) based post-refinement, to produce the final volumetric segmentation of the tumor and its constituent sub-regions. Concepts, such as spatial-pooling and unpooling are used to preserve the spatial locations of the edge pixels, for reducing segmentation error around the boundaries. A new aggregated loss function is also developed for effectively handling data imbalance. The MPS-CNN is trained and validated on the recent Multimodal Brain Tumor Segmentation Challenge (BraTS) 2018 dataset. The Dice scores obtained for the validation set for whole tumor (WT :NCR/NE +ET +ED), tumor core (TC:NCR/NET +ET), and enhancing tumor (ET) are 0.90216, 0.87247, and 0.82445. The proposed MPS-CNN is found to perform the best (based on leaderboard scores) for ET and TC segmentation tasks, in terms of both the quantitative measures (viz. Dice and Hausdorff). In case of the WT segmentation it also achieved the second highest accuracy, with a score which was only 1% less than that of the best performing method.
- 24 January 2020
- Published by Frontiers Media SA in Frontiers in Computational Neuroscience
- Vol. 14, 3
Open AccessNovel Volumetric Sub-region Segmentation in Brain Tumors
A novel deep learning based model called Multi-Planar Spatial Convolutional Neural Network (MPS-CNN) is proposed for effective, automated segmentation of different sub-regions viz. peritumoral edema (ED), necrotic core (NCR), enhancing and non-enhancing tumor core (ET/NET), from multi-modal MR images of the brain. An encoder-decoder type CNN model is designed for pixel-wise segmentation of the tumor along three anatomical planes (axial, sagittal, and coronal) at the slice level. These are then combined, by incorporating a consensus fusion strategy with a fully connected Conditional Random Field (CRF) based post-refinement, to produce the final volumetric segmentation of the tumor and its constituent sub-regions. Concepts, such as spatial-pooling and unpooling are used to preserve the spatial locations of the edge pixels, for reducing segmentation error around the boundaries. A new aggregated loss function is also developed for effectively handling data imbalance. The MPS-CNN is trained and validated on the recent Multimodal Brain Tumor Segmentation Challenge (BraTS) 2018 dataset. The Dice scores obtained for the validation set for whole tumor (WT :NCR/NE +ET +ED), tumor core (TC:NCR/NET +ET), and enhancing tumor (ET) are 0.90216, 0.87247, and 0.82445. The proposed MPS-CNN is found to perform the best (based on leaderboard scores) for ET and TC segmentation tasks, in terms of both the quantitative measures (viz. Dice and Hausdorff). In case of the WT segmentation it also achieved the second highest accuracy, with a score which was only 1% less than that of the best performing method.