Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
9 results
Search Results
Item Dense refinement residual network for road extraction from aerial imagery data(Institute of Electrical and Electronics Engineers Inc., 2019) Eerapu, K.K.; Ashwath, B.; Lal, S.; Dell’Acqua, F.; Narasimha Dhan, A.V.Extraction of roads from high-resolution aerial images with a high degree of accuracy is a prerequisite in various applications. In aerial images, road pixels and background pixels are generally in the ratio of ones-to-tens, which implies a class imbalance problem. Existing semantic segmentation architectures generally do well in road-dominated cases but fail in background-dominated scenarios. This paper proposes a dense refinement residual network (DRR Net) for semantic segmentation of aerial imagery data. The proposed semantic segmentation architecture is composed of multiple DRR modules for the extraction of diversified roads alleviating the class imbalance problem. Each module of the proposed architecture utilizes dense convolutions at various scales only in the encoder for feature learning. Residual connections in each module of the proposed architecture provide the guided learning path by propagating the combined features to subsequent DRR modules. Segmentation maps undergo various levels of refinement based on the number of DRR modules utilized in the architecture. To emphasize more on small object instances, the proposed architecture has been trained with a composite loss function. The qualitative and quantitative results are reported by utilizing the Massachusetts roads dataset. The experimental results report that the proposed architecture provides better results as compared to other recent architectures. © 2019 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.Item NucleiSegNet: Robust deep learning architecture for the nuclei segmentation of liver cancer histopathology images(Elsevier Ltd, 2021) Lal, S.; Das, D.; Alabhya, K.; Kanfade, A.; Kumar, A.; Kini, J.R.The nuclei segmentation of hematoxylin and eosin (H&E) stained histopathology images is an important prerequisite in designing a computer-aided diagnostics (CAD) system for cancer diagnosis and prognosis. Automated nuclei segmentation methods enable the qualitative and quantitative analysis of tens of thousands of nuclei within H&E stained histopathology images. However, a major challenge during nuclei segmentation is the segmentation of variable sized, touching nuclei. To address this challenge, we present NucleiSegNet - a robust deep learning network architecture for the nuclei segmentation of H&E stained liver cancer histopathology images. Our proposed architecture includes three blocks: a robust residual block, a bottleneck block, and an attention decoder block. The robust residual block is a newly proposed block for the efficient extraction of high-level semantic maps. The attention decoder block uses a new attention mechanism for efficient object localization, and it improves the proposed architecture's performance by reducing false positives. When applied to nuclei segmentation tasks, the proposed deep-learning architecture yielded superior results compared to state-of-the-art nuclei segmentation methods. We applied our proposed deep learning architecture for nuclei segmentation to a set of H&E stained histopathology images from two datasets, and our comprehensive results show that our proposed architecture outperforms state-of-the-art methods. As part of this work, we also introduced a new liver dataset (KMC liver dataset) of H&E stained liver cancer histopathology image tiles, containing 80 images with annotated nuclei procured from Kasturba Medical College (KMC), Mangalore, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, India. The proposed model's source code is available at https://github.com/shyamfec/NucleiSegNet. © 2020 Elsevier LtdItem Efficient and robust deep learning architecture for segmentation of kidney and breast histopathology images(Elsevier Ltd, 2021) Chanchal, A.K.; Kumar, A.; Lal, S.; Kini, J.Image segmentation is consistently an important task for computer vision and the analysis of medical images. The analysis and diagnosis of histopathology images by using efficient algorithms that separate hematoxylin and eosin-stained nuclei was the purpose of our proposed method. In this paper, we propose a deep learning model that automatically segments the complex nuclei present in histology images by implementing an effective encoder–decoder architecture with a separable convolution pyramid pooling network (SCPP-Net). The SCPP unit focuses on two aspects: first, it increases the receptive field by varying four different dilation rates, keeping the kernel size fixed, and second, it reduces the trainable parameter by using depth-wise separable convolution. Our deep learning model experimented with three publicly available histopathology image datasets. The proposed SCPP-Net provides better experimental segmentation results compared to other existing deep learning models and is evaluated in terms of F1-score and aggregated Jaccard index. © 2021 Elsevier LtdItem Deep structured residual encoder-decoder network with a novel loss function for nuclei segmentation of kidney and breast histopathology images(Springer, 2022) Chanchal, A.K.; Lal, S.; Kini, J.To improve the process of diagnosis and treatment of cancer disease, automatic segmentation of haematoxylin and eosin (H & E) stained cell nuclei from histopathology images is the first step in digital pathology. The proposed deep structured residual encoder-decoder network (DSREDN) focuses on two aspects: first, it effectively utilized residual connections throughout the network and provides a wide and deep encoder-decoder path, which results to capture relevant context and more localized features. Second, vanished boundary of detected nuclei is addressed by proposing an efficient loss function that better train our proposed model and reduces the false prediction which is undesirable especially in healthcare applications. The proposed architecture experimented on three different publicly available H&E stained histopathological datasets namely: (I) Kidney (RCC) (II) Triple Negative Breast Cancer (TNBC) (III) MoNuSeg-2018. We have considered F1-score, Aggregated Jaccard Index (AJI), the total number of parameters, and FLOPs (Floating point operations), which are mostly preferred performance measure metrics for comparison of nuclei segmentation. The evaluated score of nuclei segmentation indicated that the proposed architecture achieved a considerable margin over five state-of-the-art deep learning models on three different histopathology datasets. Visual segmentation results show that the proposed DSREDN model accurately segment the nuclear regions than those of the state-of-the-art methods. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item O-SegNet: Robust Encoder and Decoder Architecture for Objects Segmentation from Aerial Imagery Data(Institute of Electrical and Electronics Engineers Inc., 2022) Eerapu, K.K.; Lal, S.; Narasimhadhan, A.V.The segmentation of diversified roads and buildings from high-resolution aerial images is essential for various applications, such as urban planning, disaster assessment, traffic congestion management, and up-to-date road maps. However, a major challenge during object segmentation is the segmentation of small-sized, diverse shaped roads, and buildings in dominant background scenarios. We introduce O-SegNet- the robust encoder and decoder architecture for objects segmentation from high-resolution aerial imagery data to address this challenge. The proposed O-SegNet architecture contains Guided-Attention (GA) blocks in the encoder and decoder to focus on salient features by representing the spatial dependencies between features of different scales. Further, GA blocks guide the successive stages of encoder and decoder by interrelating the pixels of the same class. To emphasize more on relevant context, the attention mechanism is provided between encoder and decoder after aggregating the global context via an 8 Level Pyramid Pooling Network (PPN). The qualitative and quantitative results of the proposed and existing semantic segmentation architectures are evaluated by utilizing the dataset provided by Kaiser et al. Further, we show that the proposed O-SegNet architecture outperforms state-of-the-art techniques by accurately preserving the road connectivity and structure of buildings. © 2017 IEEE.Item RSCDNet: A Robust Deep Learning Architecture for Change Detection From Bi-Temporal High Resolution Remote Sensing Images(Institute of Electrical and Electronics Engineers Inc., 2023) Deepanshi; Barkur, R.; Suresh, D.; Lal, S.; Chintala, C.S.; Diwakar, P.G.Accurate change detection from high-resolution satellite and aerial images is of great significance in remote sensing for precise comprehension of Land cover (LC) variations. The current methods compromise with the spatial context; hence, they fail to detect and delineate small change areas and are unable to capture the difference between features of the bi-temporal images. This paper proposes Remote Sensing Change Detection Network (RSCDNet) - a robust end-to-end deep learning architecture for pixel-wise change detection from bi-temporal high-resolution remote-sensing (HRRS) images. The proposed RSCDNet model is based on an encoder-decoder framework integrated with the Modified Self-Attention (MSA) andthe Gated Linear Atrous Spatial Pyramid Pooling (GL-ASPP) blocks; both efficient mechanisms to regulate the field-of-view while finding the most suitable trade-off between accurate localization and context assimilation. The paper documents the design and development of the proposed RSCDNet model and compares its qualitative and quantitative results with state-of-the-art HRRS change detection architectures. The above mentioned novelties in the proposed architecture resulted in an F1-score of 98%, 98%, 88%, and 75% on the four publicly available HRRS datasets namely, Staza-Tisadob, Onera, CD-LEVIR, and WHU. In addition to the improvement in the performance metrics, the strategic connections in the proposed GL-ASPP and MSA units significantly reduce the prediction time per image (PTPI) and provide robustness against perturbations. Experimental results yield that the proposed RSCDNet model outperforms the most recent change detection benchmark models on all four HRRS datasets. © 2017 IEEE.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 FPGA implementation of deep learning architecture for kidney cancer detection from histopathological images(Springer, 2024) Lal, S.; Chanchal, A.K.; Kini, J.; Upadhyay, G.K.Kidney cancer is the most common type of cancer, and designing an automated system to accurately classify the cancer grade is of paramount importance for a better prognosis of the disease from histopathological kidney cancer images. Application of deep learning neural networks (DLNNs) for histopathological image classification is thriving and implementation of these networks on edge devices has been gaining the ground correspondingly due to high computational power and low latency requirements. This paper designs an automated system that classifies histopathological kidney cancer images. For experimentation, we have collected Kidney histopathological images of Non-cancerous, cancerous, and their respective grade of Renal Cell Carcinoma (RCC) from Kasturba Medical College (KMC), Mangalore, Karnataka, India. We have implemented and analyzed performances of deep learning architectures on a Field Programmable Gate Array (FPGA) board. Results yield that the Inception-V3 network provides better accuracy for kidney cancer detection as compared to other deep learning models on Kidney histopathological images. Further, the DenseNet-169 network provides better accuracy for kidney cancer grading as compared to other existing deep learning architecture on the FPGA board. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.Item CAR-BRAINet: Sub-6 GHz aided spatial adaptive beam prediction with multi head attention for heterogeneous vehicular networks(Institute of Physics, 2025) Menon, A.G.; Krishnan, P.; Lal, S.Heterogeneous Vehicular Networks (HetVNets) play a crucial role by integrating different communication technologies, such as sub-6 GHz, mm-wave, and DSRC, to meet the diverse connectivity requirements of 5G/B5G vehicular networks. HetVNet helps address humongous user demands, but maintaining a steady connection in highly mobile, real-world conditions remains challenging. Though ample studies have been conducted on beam prediction models, a dedicated solution for HetVNets has been sparsely explored. Hence, developing a reliable beam prediction model, specifically for HetVNets, is necessary. This paper introduces a lightweight deep learning-based model termed ‘CAR-BRAINet’, which consists of convolutional neural networks with a powerful multi-head attention (MHA) mechanism. Existing literature on beam prediction is primarily studied under a limited, idealised vehicular scenario, often overlooking the real-time complexities and intricacies of vehicular networks. Therefore, this study aims to mimic the complexities of a real-time driving scenario by incorporating key factors, such as prominent MAC protocols (3GPP-C-V2X and IEEE 802.11BD), the effect of Doppler shifts under high velocity and varying distance, and SNR levels, into three high-quality dynamic data sets for urban, rural, and highway vehicular networks. CAR-BRAINet achieves a steady improvement of 11.6467% in spectral efficiency, with a 93.1638% lighter architecture compared to existing methods, resulting in a 94.7103% reduction in prediction time. Therefore, demonstrating a precise beam prediction across all vehicular scenarios, with minimal beam overhead. Thus, this study justifies the effectiveness of CAR-BRAINet in complex HetVNets, offering promising performance without relying on mobile users’ location, angle, and antenna dimensions, thereby reducing redundant sensor latency. © 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.