EU-Net: Efficient U-shaped Deep Convolutional Neural Network for Colon Polyps Segmentation Shreerudra Pratik, Pallabi Sharma, Debaraj Rana, Bunil Kumar Balabantaray Icepe 2024 6th International Conference on Energy Power and Environment Towards Indigenous Energy Utilization, 2024 Deep learning has emerged as a transformative approach in the realm of polyp segmentation within colonoscopy images. In the pursuit of advancing this segmentation approach, this study introduces a novel deep learning architecture that synergistically combines the concept of EfficientNet-B7 and U-Net and propose a new architecture named EU-Net. The EfficientNet-B7, recognized for its scalable and powerful feature extraction capabilities, serves as the encoder of EU-Net. In contrast, the U-Net, renowned for its capability in biomedical image segmentation, functions as the decoder. The prime contribution of the proposed model lies in the analysis of different attention mechanisms before the concatenation of skip connection and the upsampling feature. This attention mechanism enhances the model’s focus, ensuring it retains critical regions within images, thereby boosting the accuracy of segmentation tasks. Furthermore, the EU-Net model is enriched with dilated convolutions, enabling it to capture multi-scale context without the loss of resolution, a paramount feature for detecting polyps of varying sizes. The proposed model was rigorously evaluated using the CVC-ClinicDB, a benchmark database for colonoscopy image analysis. The proposed model achieves an IoU of 0.8863. Preliminary results showcase a substantial improvement in segmentation performance, highlighting the potential of the proposed Eu-Net in advancing colorectal cancer prevention efforts.
Li-SegPNet: Encoder-Decoder Mode Lightweight Segmentation Network for Colorectal Polyps Analysis Pallabi Sharma, Anmol Gautam, Pallab Maji, Ram Bilas Pachori, Bunil Kumar Balabantaray IEEE Transactions on Biomedical Engineering, 2023 Objective: One of the fundamental and crucial tasks for the automated diagnosis of colorectal cancer is the segmentation of the acute gastrointestinal lesions, most commonly colorectal polyps. Therefore, in this work, we present a novel lightweight encoder-decoder mode of architecture with the attention mechanism to address this challenging task. Methods: The proposed Li-SegPNet architecture harnesses cross-dimensional interaction in feature maps with novel encoder block with modified triplet attention. We have used atrous spatial pyramid pooling to handle the problem of segmenting objects at multiple scales. We also address the semantic gap between the encoder and decoder through a modified skip connection using attention gating. Results: We applied our model to colonoscopy still images and trained and validated it on two publicly available datasets, Kvasir-SEG and CVC-ClinicDB. We achieve mean Intersection-Over-Union (mIoU) and dice scores of 0.88, 0.9058 and 0.8969, 0.9372 on Kvasir-SEG and CVC-ClinicDB, respectively. We analyze the generalizability of Li-SegPNet by testing it on two independent previously unseen datasets, Hyper-Kvasir and EndoTect 2020, and establish the model efficiency in cross-dataset evaluation. We employ multi-scale testing to examine the model performance on different sizes of polyps. Li-SegPNet performs best on medium-sized polyps with a mIoU and dice score of 0.9086 and 0.9137, respectively on the Kvasir-SEG dataset and 0.9425, 0.9434 of mIoU and dice score, respectively on CVC-ClinicDB. Conclusion: The experimental results convey that we establish a new benchmark on these four datasets for the segmentation of polyps. Significance: The proposed model can be used as a new benchmark model for polyps segmentation. Lesser parameters in comparison to other models give the edge in the applicability of the proposed Li-SegPNet model in real-time clinical analysis.
LPNet: A lightweight CNN with discrete wavelet pooling strategies for colon polyps classification Pallabi Sharma, Dipankar Das, Anmol Gautam, Bunil Kumar Balabantaray International Journal of Imaging Systems and Technology, 2023 The traditional process of disease diagnosis from medical images follows a manual process, which is tedious and arduous. A computer‐aided diagnosis (CADs) system can work as an assistive tool to improve the diagnosis process. In this pursuit, this article introduces a unique architecture LPNet for classifying colon polyps from the colonoscopy video frames. Colon polyps are abnormal growth of cells in the colon wall. Over time, untreated colon polyps may cause colorectal cancer. Different convolutional neural networks (CNNs) based systems have been developed in recent years. However, CNN uses pooling to reduce the number of parameters and expand the receptive field. On the other hand, pooling results in data loss and is deleterious to subsequent processes. Pooling strategies based on discrete wavelet operations have been proposed in our architecture as a solution to this problem, with the promise of achieving a better trade‐off between receptive field size and computing efficiency. The overall performance of this model is superior to the others, according to experimental results on a colonoscopy dataset. LPNet with bio‐orthogonal wavelet achieved the highest performance with an accuracy of 93.55%. It outperforms the other state‐of‐the‐art (SOTA) CNN models for the polyps classification task, and it is lightweight in terms of the number of learnable parameters compared with them, making the model easily deployable in edge devices.
An Ensemble-Based Deep Convolutional Neural Network for Computer-Aided Polyps Identification From Colonoscopy Pallabi Sharma, Bunil Kumar Balabantaray, Kangkana Bora, Saurav Mallik, Kunio Kasugai, et al. Frontiers in Genetics, 2022 Colorectal cancer (CRC) is the third leading cause of cancer death globally. Early detection and removal of precancerous polyps can significantly reduce the chance of CRC patient death. Currently, the polyp detection rate mainly depends on the skill and expertise of gastroenterologists. Over time, unidentified polyps can develop into cancer. Machine learning has recently emerged as a powerful method in assisting clinical diagnosis. Several classification models have been proposed to identify polyps, but their performance has not been comparable to an expert endoscopist yet. Here, we propose a multiple classifier consultation strategy to create an effective and powerful classifier for polyp identification. This strategy benefits from recent findings that different classification models can better learn and extract various information within the image. Therefore, our Ensemble classifier can derive a more consequential decision than each individual classifier. The extracted combined information inherits the ResNet’s advantage of residual connection, while it also extracts objects when covered by occlusions through depth-wise separable convolution layer of the Xception model. Here, we applied our strategy to still frames extracted from a colonoscopy video. It outperformed other state-of-the-art techniques with a performance measure greater than 95% in each of the algorithm parameters. Our method will help researchers and gastroenterologists develop clinically applicable, computational-guided tools for colonoscopy screening. It may be extended to other clinical diagnoses that rely on image.
Melanoma Detection using Advanced Deep Neural Network Pallabi Sharma, Anmol Gautam, Rajashree Nayak, Bunil Kumar Balabantaray 4th International Conference on Energy Power and Environment Icepe 2022, 2022 Melanoma is a type of skin cancer that starts in the cells (melanocytes) that govern the color of your skin. Melanoma is the most lethal one among all other skin diseases and the only reason for 77% deaths due to skin cancer. The best way to reduce these deaths is to detect cancer at its early stages so it can be treated and cured with minor treatment or surgeries. To speed up and improve the process of early detection, we propose an automatic classification method for melanoma cancer using an advanced deep neural network. Deep learning models require a large dataset to work efficiently, but due to limited time and the heavy workload of doctors, there is a lack of annotated skin can-cer images. Therefore, the proposed model introduces adversarial training for achieving better accuracy even with a small amount of data. The model removes unnecessary details and noise from the image and amplifies the depth and gradient in the dimensions and the shade of the image. This proposed adversarial method uses the gradients of the loss with respect to the input image to create a new adversarial example image that maximizes the loss for an input image. The synthetically generated images are used in the classification system for training and testing purposes. A comparative analysis of training with an adversarial approach and without an adversarial approach on different pre-trained models, namely VGG16, VGG19, Densenet121, and Resnet101, is also introduced in this work. ResNet101 with adversarial training has shown a state-of-the-art accuracy performance of 84.77% for melanoma classification. Therefore, the proposed approach can be considered an efficient method for classifying benign and malignant melanoma.
SAU-NET: Scale Aware Polyp Segmentation using Encoder-Decoder Network Anmol Gautam, Suchana Das, Pallabi Sharma, Pallab Maji, Bunil Kumar Balabantaray 2022 IEEE Region 10 Symposium Tensymp 2022, 2022 Colorectal Cancer has become a major cause of death in recent times. To improve the chances of survival, detecting early signs and identifying polyps in a routine examination is necessary. In this pursuit, an automatic computer-aided diagnosis (CAD) system to detect early signs of the disease onset is crucial. Deep Learning is at the base of recent advances in CAD systems, and its successes in CAD encourage it to be used in colorectal cancer analysis. Efficient segmentation of polyps from the colonoscopy images can aid radiologists immensely in the task of polyps identification and analysis. Therefore, this paper proposes an encoder-decoder-based architecture to segment polyps. Our proposed model takes into account multi-scale features that are present in the images. For efficient feature extraction, residual encoder blocks and Squeeze and Excitation modules are used to enhance channel inter-dependencies. Again, a residual dense decoder is used to improve the reconstruction in the decoder module. During the encoding stage, spatial information loss leads to a semantic gap between encoder and decoder. To handle this, a modified skip connection is proposed to bridge the semantic gap between the encoder and the corresponding decoder. The proposed model achieved an 85.15% dice score, 74.26% IoU, and 83.88% mean IoU on the Kvasir-SEG dataset. The results show that the proposed model can segment polyps more efficiently than many other popular models in the literature. Comparatively, fewer parameters in the proposed model prevail it efficient in real-time use.
WMCF-Net: Wavelet pooling-based multiscale contextual fusion network for polyp classification S Pratik, P Sharma, DR Nayak, BK Balabantaray Biomedical Signal Processing and Control 107, 107727 , 2025 2025 Citations: 4
MSPolypNet: A residual multi-scale semantic approach for polyps segmentation S Pratik, P Sharma, BK Balabantaray, RB Pachori Computers and Electrical Engineering 123, 110224 , 2025 2025 Citations: 2
EU-Net: Efficient U-shaped Deep Convolutional Neural Network for Colon Polyps Segmentation S Pratik, P Sharma, D Rana, BK Balabantaray 2024 6th International Conference on Energy, Power and Environment (ICEPE), 1-5 , 2024 2024 Citations: 1
A survey on cancer detection via convolutional neural networks: Current challenges and future directions P Sharma, DR Nayak, BK Balabantaray, M Tanveer, R Nayak Neural Networks 169, 637-659 , 2024 2024 Citations: 113
LPNet: A lightweight CNN with discrete wavelet pooling strategies for colon polyps classification P Sharma, D Das, A Gautam, BK Balabantaray International Journal of Imaging Systems and Technology , 2022 2022 Citations: 10
Li-segpnet: Encoder-decoder mode lightweight segmentation network for colorectal polyps analysis P Sharma, A Gautam, P Maji, RB Pachori, BK Balabantaray IEEE Transactions on Biomedical Engineering 70 (4), 1330-1339 , 2022 2022 Citations: 56
SAU-NET: Scale aware polyp segmentation using encoder-decoder network A Gautam, S Das, P Sharma, P Maji, BK Balabantaray 2022 IEEE Region 10 Symposium (TENSYMP), 1-5 , 2022 2022 Citations: 11
U-Shaped Xception-Residual Network for Polyps Region Segmentation P Sharma, BK Balabantary, P Rangababu Proceedings of International Conference on Frontiers in Computing and … , 2022 2022
Melanoma detection using advanced deep neural network P Sharma, A Gautam, R Nayak, BK Balabantaray 2022 4th international conference on energy, power and environment (ICEPE), 1-5 , 2022 2022 Citations: 15
An ensemble-based deep convolutional neural network for computer-aided polyps identification from colonoscopy P Sharma, BK Balabantaray, K Bora, S Mallik, K Kasugai, Z Zhao Frontiers in Genetics 13, 844391 , 2022 2022 Citations: 58
Identification of significant frames from colonoscopy video: An approach towardsearly detection of colorectal cancer P Sharma, K Bora, BK Balabantaray 2020 International Conference on Computational Performance Evaluation (ComPE … , 2020 2020 Citations: 5
Two Stage Classification with CNN for Colorectal Cancer Detection. P Sharma, K Bora, BK Balabantaray Oncologie (Tech Science Press) 22 (3) , 2020 2020 Citations: 26
Classification of brain mri using deep learning techniques P Sharma, I Wahlang, S Sanyal, AK Maji Soft Computing: Theories and Applications: Proceedings of SoCTA 2018, 559-569 , 2020 2020 Citations: 14
Deep learning techniques for classification of brain MRI I Wahlang, P Sharma, S Sanyal, G Saha, AK Maji International Journal of Intelligent Systems Technologies and Applications … , 2020 2020 Citations: 25
A comparative study on segmentation techniques for brain tumor mri I Wahlang, P Sharma, SM Nasreen, AK Maji, G Saha Information and Communication Technology for Competitive Strategies … , 2018 2018 Citations: 15
Brain tumor classification techniques using mri: a study I Wahlang, P Sharma, G Saha, AK Maji Research Journal of Pharmacy and Technology 11 (10), 4764-4770 , 2018 2018 Citations: 18
Assessing the awareness level of breast and cervical cancer: a cross-sectional study in northeast India K Bora, N Rajbongshi, LB Mahanta, P Sharma, D Dutta International Journal of Medical Science and Public Health 5 (10), 1 , 2016 2016 Citations: 11
MOST CITED SCHOLAR PUBLICATIONS
A survey on cancer detection via convolutional neural networks: Current challenges and future directions P Sharma, DR Nayak, BK Balabantaray, M Tanveer, R Nayak Neural Networks 169, 637-659 , 2024 2024 Citations: 113
An ensemble-based deep convolutional neural network for computer-aided polyps identification from colonoscopy P Sharma, BK Balabantaray, K Bora, S Mallik, K Kasugai, Z Zhao Frontiers in Genetics 13, 844391 , 2022 2022 Citations: 58
Li-segpnet: Encoder-decoder mode lightweight segmentation network for colorectal polyps analysis P Sharma, A Gautam, P Maji, RB Pachori, BK Balabantaray IEEE Transactions on Biomedical Engineering 70 (4), 1330-1339 , 2022 2022 Citations: 56
Two Stage Classification with CNN for Colorectal Cancer Detection. P Sharma, K Bora, BK Balabantaray Oncologie (Tech Science Press) 22 (3) , 2020 2020 Citations: 26
Deep learning techniques for classification of brain MRI I Wahlang, P Sharma, S Sanyal, G Saha, AK Maji International Journal of Intelligent Systems Technologies and Applications … , 2020 2020 Citations: 25
Brain tumor classification techniques using mri: a study I Wahlang, P Sharma, G Saha, AK Maji Research Journal of Pharmacy and Technology 11 (10), 4764-4770 , 2018 2018 Citations: 18
Melanoma detection using advanced deep neural network P Sharma, A Gautam, R Nayak, BK Balabantaray 2022 4th international conference on energy, power and environment (ICEPE), 1-5 , 2022 2022 Citations: 15
A comparative study on segmentation techniques for brain tumor mri I Wahlang, P Sharma, SM Nasreen, AK Maji, G Saha Information and Communication Technology for Competitive Strategies … , 2018 2018 Citations: 15
Classification of brain mri using deep learning techniques P Sharma, I Wahlang, S Sanyal, AK Maji Soft Computing: Theories and Applications: Proceedings of SoCTA 2018, 559-569 , 2020 2020 Citations: 14
SAU-NET: Scale aware polyp segmentation using encoder-decoder network A Gautam, S Das, P Sharma, P Maji, BK Balabantaray 2022 IEEE Region 10 Symposium (TENSYMP), 1-5 , 2022 2022 Citations: 11
Assessing the awareness level of breast and cervical cancer: a cross-sectional study in northeast India K Bora, N Rajbongshi, LB Mahanta, P Sharma, D Dutta International Journal of Medical Science and Public Health 5 (10), 1 , 2016 2016 Citations: 11
LPNet: A lightweight CNN with discrete wavelet pooling strategies for colon polyps classification P Sharma, D Das, A Gautam, BK Balabantaray International Journal of Imaging Systems and Technology , 2022 2022 Citations: 10
Identification of significant frames from colonoscopy video: An approach towardsearly detection of colorectal cancer P Sharma, K Bora, BK Balabantaray 2020 International Conference on Computational Performance Evaluation (ComPE … , 2020 2020 Citations: 5
WMCF-Net: Wavelet pooling-based multiscale contextual fusion network for polyp classification S Pratik, P Sharma, DR Nayak, BK Balabantaray Biomedical Signal Processing and Control 107, 107727 , 2025 2025 Citations: 4
MSPolypNet: A residual multi-scale semantic approach for polyps segmentation S Pratik, P Sharma, BK Balabantaray, RB Pachori Computers and Electrical Engineering 123, 110224 , 2025 2025 Citations: 2
EU-Net: Efficient U-shaped Deep Convolutional Neural Network for Colon Polyps Segmentation S Pratik, P Sharma, D Rana, BK Balabantaray 2024 6th International Conference on Energy, Power and Environment (ICEPE), 1-5 , 2024 2024 Citations: 1
U-Shaped Xception-Residual Network for Polyps Region Segmentation P Sharma, BK Balabantary, P Rangababu Proceedings of International Conference on Frontiers in Computing and … , 2022 2022
