Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item Evolution of LiverNet 2.x: Architectures for automated liver cancer grade classification from H&E stained liver histopathological images(Springer, 2024) Chanchal, A.K.; Lal, S.; Barnwal, D.; Sinha, P.; Arvavasu, S.; Kini, J.Recently, the automation of disease identification has been quite popular in the field of medical diagnosis. The rise of Convolutional Neural Networks (CNNs) for training and generalizing medical image data has proven to be quite efficient in detecting and identifying the types and sub-types of various diseases. Since the classification of large datasets of Hematoxylin & Eosin (H&E) stained histopathology images by experts can be expensive and time-consuming, automated processes using deep learning have been encouraged for the past decade. This paper introduces LiverNet 2.x model by modifying the previously encountered LiverNet architecture. The proposed model uses two different improvements of the Atrous Spatial Pyramid Pooling (ASPP) block to extract the clinically defined features of hepatocellular carcinoma (HCC) from liver histopathology images. LiverNet 2.0 uses a modified form of ASPP block known as DenseASPP, where all the atrous convolution outputs are densely connected. Whereas LiverNet 2.1 uses fewer concatenations while maintaining a large receptive field by stacking the dilated convolutional blocks in a tree-like fashion. This paper also discusses the trade-off between LiverNet 2.0 and LiverNet 2.1 in terms of accuracy and computational complexity. All comparison model and the proposed model is trained and tested on the patches of two different histopathological datasets. The experimental results show that the proposed model performs better compared to reference models. For the KMC Liver dataset, LiverNet 2.0 and LiverNet 2.1 achieved an accuracy of 97.50% and 97.14% respectively. Accuracy of 94.37% and 97.14% for the TCGA Liver dataset are achieved. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item RMDNet-Deep Learning Paradigms for Effective Malware Detection and Classification(Institute of Electrical and Electronics Engineers Inc., 2024) S, S.; Lal, S.; Pratap Singh, M.; Raghavendra, B.S.Malware analysis and detection are still essential for maintaining the security of networks and computer systems, even as the threat landscape shifts. Traditional approaches are insufficient to keep pace with the rapidly evolving nature of malware. Artificial Intelligence (AI) assumes a significant role in propelling its design to unprecedented levels. Various Machine Learning (ML) based malware detection systems have been developed to combat the ever-changing characteristics of malware. Consequently, there is a growing interest in exploring advanced techniques that leverage the power of Deep Learning (DL) to effectively analyze and detect malicious software. DL models demonstrate enhanced capabilities for analyzing extensive sequences of system calls. This paper proposes a Robust Malware Detection Network (RMDNet) for effective malware detection and classification. The proposed RMDNet model branches the input and performs depth-wise convolution and concatenation operations. The experimental results of the proposed RMDNet and existing DL models are evaluated on 48240 malware and binary visualization image dataset with RGB format. Also on the multi-class malimg and dumpware-10 datasets with grayscale format. The experimental results on each of these datasets demonstrate that the proposed RMDNet model can effectively and accurately categorize malware, outperforming the most recent benchmark DL algorithms. © 2013 IEEE.Item NBDNet: A Deep Learning Algorithm for Despeckling of SAR Data(Springer, 2024) Kevala, V.D.; Lal, S.In the recent years, remote sensing has gained high momentum in varied applications. Satellite imaging and processing is one of the most sorted techniques followed by researchers. Synthetic aperture radar (SAR) images are popular among the remote sensing community due to its capability of imaging in all weather conditions. The practical applications of SAR data is limited due to presence of speckle noise. In the past, deep learning methods are developed to despeckle the SAR images. This paper proposes a convolutional neural network based non-blind denoising network (NBDNet) for the despeckling of SAR images. In the proposed NBDNet model, attention blocks are introduced to preserve the structural and texture details of the captured scene globally. Further, squeeze and excitation module and convolutional block attention module have been used in the proposed NBDNet to capture the minute structural information of the artefacts. The experimental results of proposed NBDNet and benchmark algorithms are evaluated on synthetic UC merced land-use images and real SAR images. Quantitative and visual results of of proposed NBDNet yield better texture and structural detail preservation as compared to benchmark algorithms on both datasets. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.Item Development of Robust CNN Architecture for Grading and Classification of Renal Cell Carcinoma Histology Images(Institute of Electrical and Electronics Engineers Inc., 2025) Chanchal, C.A.; Lal, S.; Suresh, S.Kidney cancer is a commonly diagnosed cancer disease in recent years, and Renal Cell Carcinoma (RCC) is the most common kidney cancer responsible for 80% to 85% of all renal tumors. The diagnosis of kidney cancer requires manual examination and analysis of histopathological images of the affected tissue. This process is time-consuming, prone to human error, and highly depends on the expertise of a pathologist. Early detection and grading of kidney cancer tissues enable doctors and practitioners to decide the further course of treatment. Therefore, quick and precise analysis of kidney cancer tissue images is extremely important for proper diagnosis. Recently, deep learning algorithms have proved to be very efficient and accurate in histopathology image analysis. In this paper, we propose a computationally efficient deep-learning architecture based on convolutional neural networks (CNNs) to automate the grading and classification task for kidney cancer tissue. The proposed Robust CNN (RoCNN) architecture is capable of learning features at varying convolutional filter sizes because of the inception modules employed in it. Squeeze and Extract (SE) blocks are used to remove unnecessary contributions from noisy channels and improve model accuracy. Concatenating samples from three different parts of architecture allows for the encompassing of varied features, further improving grading and classification accuracy. To demonstrate that the proposed model is generalized and independent of the dataset, it has experimented on two well-known datasets, the KMC kidney dataset of five different grades and the TCGA dataset of four classes. Compared to the best-performing state-of-the-art model the accuracy of RoCNN shows a significant improvement of about 4.22% and 3.01% for both datasets respectively. © 2013 IEEE.Item An Efficient Parallel Branch Network for Multi-Class Classification of Prostate Cancer From Histopathological Images(John Wiley and Sons Inc, 2025) Srivastava, V.; Prabhu, A.; Sravya, S.; Vibha Damodara, K.; Lal, S.; Kini, J.Prostate cancer is one of the prevalent forms of cancer, posing a significant health concern for men. Accurate detection and classification of prostate cancer are crucial for effective diagnosis and treatment planning. Histopathological images play a pivotal role in identifying prostate cancer by enabling pathologists to identify cellular abnormalities and tumor characteristics. With the rapid advancements in deep learning, Convolutional Neural Networks (CNNs) have emerged as a powerful tool for tackling complex computer vision tasks, including object detection, classification, and segmentation. This paper proposes a Parallel Branch Network (PBN), a CNN architecture specifically designed for the automatic classification of prostate cancer into its subtypes from histopathological images. The paper introduces a novel Efficient Residual (ER) block that enhances feature representation using residual learning and multi-scale feature extraction. By utilizing multiple branches with different filter reduction ratios and dense attention mechanisms, the block captures diverse features while preserving essential information. The proposed PBN model achieved a classification accuracy of 93.16% on the Prostate Gleason dataset, outperforming all other comparison models. © 2025 Wiley Periodicals LLC.