Mahesh Gour
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
Mahesh Gour has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
Sweta Jain
Department of Computer Science and Engineering MANIT Bhopal India
3 shared publications- Sweta Jain
Department of Computer Science and Engineering, Maulana Azad National Institute of Technology, Bhopal, Madhya Pradesh, India
3 shared publications Sushree Sangeeta Behera
Indian Institute of Technology Indore, India
2 shared publicationsVivek Kanhangad
Indian Institute of Technology Indore, India
2 shared publications- Ana Filipa Sequeira
Universidade do Porto
1 shared publication Christoph Busch
Norwegian Biometrics Laboratory, NTNU, Norway
1 shared publication
Latest Publications
- 30 May 2024
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 34 (4)
Robust nuclei segmentation with encoder‐decoder network from the histopathological images
Nuclei segmentation is a prerequisite and an essential step in cancer detection and prognosis. Automatic nuclei segmentation from the histopathological images is challenging due to nuclear overlap, disease types, chromatic stain variability, and cytoplasmic morphology differences. Furthermore, it is demanding to develop a single accurate method for segmenting nuclei of different organs because of the diversity in nuclei size, shape, and appearance across the various organs. To address these challenges, we developed a robust Encoder‐Decoder network for nuclei segmentation from the multi‐organ histopathological images. In this approach, we utilize a pre‐trained EfficientNet‐B4 as an Encoder subnetwork and design a new Decoder subnetwork architecture. Additionally, we have applied morphological operation‐based post‐processing to improve the segmentation results. The performance of our approach has been evaluated on three public datasets, namely, Kumar, TNBC, and CPM‐17 datasets, which contain histopathological images of seven organs, one organ, and four organs, respectively. The proposed method achieved an aggregated Jacquard index of 0.636, 0.611, and 0.706 on Kumar, TNBC, and CPM‐17 datasets, respectively. Our proposed approach also shows superiority over the existing methods.
- 30 May 2024
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 34 (4)
Robust nuclei segmentation with encoder‐decoder network from the histopathological images
Nuclei segmentation is a prerequisite and an essential step in cancer detection and prognosis. Automatic nuclei segmentation from the histopathological images is challenging due to nuclear overlap, disease types, chromatic stain variability, and cytoplasmic morphology differences. Furthermore, it is demanding to develop a single accurate method for segmenting nuclei of different organs because of the diversity in nuclei size, shape, and appearance across the various organs. To address these challenges, we developed a robust Encoder‐Decoder network for nuclei segmentation from the multi‐organ histopathological images. In this approach, we utilize a pre‐trained EfficientNet‐B4 as an Encoder subnetwork and design a new Decoder subnetwork architecture. Additionally, we have applied morphological operation‐based post‐processing to improve the segmentation results. The performance of our approach has been evaluated on three public datasets, namely, Kumar, TNBC, and CPM‐17 datasets, which contain histopathological images of seven organs, one organ, and four organs, respectively. The proposed method achieved an aggregated Jacquard index of 0.636, 0.611, and 0.706 on Kumar, TNBC, and CPM‐17 datasets, respectively. Our proposed approach also shows superiority over the existing methods.
- 20 December 2023
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-10
Histopathological Image Synthesis with Generative Adversarial Networks for Nuclei Segmentation
- 20 December 2023
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-10
Histopathological Image Synthesis with Generative Adversarial Networks for Nuclei Segmentation
- 9 January 2023
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 33 (3) , 1014-1027
XCapsNet: A deep neural network for automated detection of diabetic retinopathy
Diabetic retinopathy (DR) is a retinal condition in which the blood vessels of the retina are damaged. If DR is not detected in its early stage, it can lead to visual impairment and even blindness. For DR diagnosis, ophthalmologists manually examine the condition of the retina using fundus images. This manual way of DR detection is cumbersome, error‐prone, and time‐consuming, and it requires skilled ophthalmologists. To address these issues, we propose a deep learning‐based hybrid model named XCapsNet, which combines the discriminative ability of the Xception and Capsule networks for automated detection of DR from the fundus images. In the proposed approach, we applied the CLAHE image preprocessing technique to improve the discriminative information in fundus images by enhancing the contrast of the images. Furthermore, in the proposed XCapNet model, we utilized the pretrained Xception and CapsNet models to learn the discriminative and hierarchically deep features of the DR fundus images at multiple labels of abstraction for diagnosing the DR disease. The performance of the proposed method is evaluated on the two publicly available APTOS2019 and Messidor datasets. The proposed method achieved a classification accuracy of 83.06% and 98.91% on the APTOS2019 dataset for multiclass and binary‐class classification of DR images, respectively. On the Messidor dataset, the proposed approach achieved an accuracy of 98.33% for the classification of fundus images into DR and Normal classes. Additionally, we have also investigated the performance of different pretrained CNN models for DR detection. The proposed method shows its superiority over the existing methods.
- 9 January 2023
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 33 (3) , 1014-1027
XCapsNet: A deep neural network for automated detection of diabetic retinopathy
Diabetic retinopathy (DR) is a retinal condition in which the blood vessels of the retina are damaged. If DR is not detected in its early stage, it can lead to visual impairment and even blindness. For DR diagnosis, ophthalmologists manually examine the condition of the retina using fundus images. This manual way of DR detection is cumbersome, error‐prone, and time‐consuming, and it requires skilled ophthalmologists. To address these issues, we propose a deep learning‐based hybrid model named XCapsNet, which combines the discriminative ability of the Xception and Capsule networks for automated detection of DR from the fundus images. In the proposed approach, we applied the CLAHE image preprocessing technique to improve the discriminative information in fundus images by enhancing the contrast of the images. Furthermore, in the proposed XCapNet model, we utilized the pretrained Xception and CapsNet models to learn the discriminative and hierarchically deep features of the DR fundus images at multiple labels of abstraction for diagnosing the DR disease. The performance of the proposed method is evaluated on the two publicly available APTOS2019 and Messidor datasets. The proposed method achieved a classification accuracy of 83.06% and 98.91% on the APTOS2019 dataset for multiclass and binary‐class classification of DR images, respectively. On the Messidor dataset, the proposed approach achieved an accuracy of 98.33% for the classification of fundus images into DR and Normal classes. Additionally, we have also investigated the performance of different pretrained CNN models for DR detection. The proposed method shows its superiority over the existing methods.
- 24 July 2022
- Published by Springer Nature
- p. 83-94
Application of Deep Learning Techniques for Prostate Cancer Grading Using Histopathological Images
- 24 July 2022
- Published by Springer Nature
- p. 83-94
Application of Deep Learning Techniques for Prostate Cancer Grading Using Histopathological Images
- 23 November 2021
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 140, 105047
Uncertainty-aware convolutional neural network for COVID-19 X-ray images classification
- 23 November 2021
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 140, 105047
Uncertainty-aware convolutional neural network for COVID-19 X-ray images classification
- 29 March 2020
- Published by Springer Nature
- p. 243-253
DeepRNNetSeg: Deep Residual Neural Network for Nuclei Segmentation on Breast Cancer Histopathological Images
- 29 March 2020
- Published by Springer Nature
- p. 243-253
DeepRNNetSeg: Deep Residual Neural Network for Nuclei Segmentation on Breast Cancer Histopathological Images
- Top Cited Papers
- 14 February 2020
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 30 (3) , 621-635
Residual learning based CNN for breast cancer histopathological image classification
Biopsy is one of the most commonly used modality to identify breast cancer in women, where tissue is removed and studied by the pathologist under the microscope to look for abnormalities in tissue. This technique can be time‐consuming, error‐prone, and provides variable results depending on the expertise level of the pathologist. An automated and efficient approach not only aids in the diagnosis of breast cancer but also reduces human effort. In this paper, we develop an automated approach for the diagnosis of breast cancer tumors using histopathological images. In the proposed approach, we design a residual learning‐based 152‐layered convolutional neural network, named as ResHist for breast cancer histopathological image classification. ResHist model learns rich and discriminative features from the histopathological images and classifies histopathological images into benign and malignant classes. In addition, to enhance the performance of the developed model, we design a data augmentation technique, which is based on stain normalization, image patches generation, and affine transformation. The performance of the proposed approach is evaluated on publicly available BreaKHis dataset. The proposed ResHist model achieves an accuracy of 84.34% and an F1‐score of 90.49% for the classification of histopathological images. Also, this approach achieves an accuracy of 92.52% and F1‐score of 93.45% when data augmentation is employed. The proposed approach outperforms the existing methodologies in the classification of benign and malignant histopathological images. Furthermore, our experimental results demonstrate the superiority of our approach over the pre‐trained networks, namely AlexNet, VGG16, VGG19, GoogleNet, Inception‐v3, ResNet50, and ResNet152 for the classification of histopathological images.
- 14 February 2020
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 30 (3) , 621-635
Top Cited PapersResidual learning based CNN for breast cancer histopathological image classification
Biopsy is one of the most commonly used modality to identify breast cancer in women, where tissue is removed and studied by the pathologist under the microscope to look for abnormalities in tissue. This technique can be time‐consuming, error‐prone, and provides variable results depending on the expertise level of the pathologist. An automated and efficient approach not only aids in the diagnosis of breast cancer but also reduces human effort. In this paper, we develop an automated approach for the diagnosis of breast cancer tumors using histopathological images. In the proposed approach, we design a residual learning‐based 152‐layered convolutional neural network, named as ResHist for breast cancer histopathological image classification. ResHist model learns rich and discriminative features from the histopathological images and classifies histopathological images into benign and malignant classes. In addition, to enhance the performance of the developed model, we design a data augmentation technique, which is based on stain normalization, image patches generation, and affine transformation. The performance of the proposed approach is evaluated on publicly available BreaKHis dataset. The proposed ResHist model achieves an accuracy of 84.34% and an F1‐score of 90.49% for the classification of histopathological images. Also, this approach achieves an accuracy of 92.52% and F1‐score of 93.45% when data augmentation is employed. The proposed approach outperforms the existing methodologies in the classification of benign and malignant histopathological images. Furthermore, our experimental results demonstrate the superiority of our approach over the pre‐trained networks, namely AlexNet, VGG16, VGG19, GoogleNet, Inception‐v3, ResNet50, and ResNet152 for the classification of histopathological images.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 681-687
Periocular recognition in cross-spectral scenario
Periocular recognition has been an active area of research in the past few years. In spite of the advancements made in this area, the cross-spectral matching of visible (VIS) and near-infrared (NIR) periocular images remains a challenge. In this paper, we propose a method based on illumination normalization of VIS and NIR periocular images. Specifically, the approach involves normalizing the images using the difference of Gaussian (DoG) filtering, followed by the computation of a descriptor that captures structural details in the illumination normalized images using histogram of oriented gradients (HOG). Finally, the feature vectors corresponding to the query and the enrolled image are compared using the cosine similarity metric to generate a matching score. Performance of our algorithm has been evaluated on three publicly available benchmark databases of cross-spectral periocular images. Our approach yields significant improvement in performance over the existing approach.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 681-687
Periocular recognition in cross-spectral scenario
Periocular recognition has been an active area of research in the past few years. In spite of the advancements made in this area, the cross-spectral matching of visible (VIS) and near-infrared (NIR) periocular images remains a challenge. In this paper, we propose a method based on illumination normalization of VIS and NIR periocular images. Specifically, the approach involves normalizing the images using the difference of Gaussian (DoG) filtering, followed by the computation of a descriptor that captures structural details in the illumination normalized images using histogram of oriented gradients (HOG). Finally, the feature vectors corresponding to the query and the enrolled image are compared using the cosine similarity metric to generate a matching score. Performance of our algorithm has been evaluated on three publicly available benchmark databases of cross-spectral periocular images. Our approach yields significant improvement in performance over the existing approach.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 725-732
Cross-eyed 2017: Cross-spectral iris/periocular recognition competition
This work presents the 2nd Cross-Spectrum Iris/Periocular Recognition Competition (Cross-Eyed2017). The main goal of the competition is to promote and evaluate advances in cross-spectrum iris and periocular recognition. This second edition registered an increase in the participation numbers ranging from academia to industry: five teams submitted twelve methods for the periocular task and five for the iris task. The benchmark dataset is an enlarged version of the dual-spectrum database containing both iris and periocular images synchronously captured from a distance and within a realistic indoor environment. The evaluation was performed on an undisclosed test-set. Methodology, tested algorithms, and obtained results are reported in this paper identifying the remaining challenges in path forward.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 725-732
Cross-eyed 2017: Cross-spectral iris/periocular recognition competition
This work presents the 2nd Cross-Spectrum Iris/Periocular Recognition Competition (Cross-Eyed2017). The main goal of the competition is to promote and evaluate advances in cross-spectrum iris and periocular recognition. This second edition registered an increase in the participation numbers ranging from academia to industry: five teams submitted twelve methods for the periocular task and five for the iris task. The benchmark dataset is an enlarged version of the dual-spectrum database containing both iris and periocular images synchronously captured from a distance and within a realistic indoor environment. The evaluation was performed on an undisclosed test-set. Methodology, tested algorithms, and obtained results are reported in this paper identifying the remaining challenges in path forward.