Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Fully automatic ROI extraction and edge-based segmentation of radius and ulna bones from hand radiographs(PWN-Polish Scientific Publishers bbe@ibib.waw.pl, 2017) Simu, S.; Lal, S.; Nagarsekar, P.; Naik, A.Bone age is a reliable measure of person's growth and maturation of skeleton. The difference between chronological age and bone age indicates presence of endocrinological problems. The automated bone age assessment system (ABAA) based on Tanner and Whitehouse method (TW3) requires monitoring the growth of radius, ulna and short bones (phalanges) of left hand. In this paper, a detailed analysis of two bones in the bone age assessment system namely, radius and ulna is presented. We propose an automatic extraction method for the region of interest (ROI) of radius and ulna bones from a left hand radiograph (RUROI). We also propose an improved edge-based segmentation technique for those bones. Quantitative and qualitative results of the proposed segmentation technique are evaluated and compared with other state-of-the-art segmentation techniques. Medical experts have also validated the qualitative results of proposed segmentation technique. Experimental results reveal that these proposed techniques provide better segmentation accuracy as compared to the other state-of-the-art segmentation techniques. © 2017 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of SciencesItem A study about evolutionary and non-evolutionary segmentation techniques on hand radiographs for bone age assessment(Elsevier Ltd, 2017) Simu, S.; Lal, S.In this paper, a study and performance comparison of various evolutionary and non-evolutionary segmentation techniques on digital hand radiographs for bone age assessment is presented. The segmented hand bones are of vital importance in process of automated bone age assessment (ABAA). Bone age assessment is a technique of checking the skeletal development and detecting growth disorder in a person. However, it is very difficult to segment out the bone from the soft tissue. The problem arises from overlapping pixel intensities between bone region and soft tissue region and also between soft tissue region and background. Thus there is a requirement for a robust segmentation technique for hand bone segmentation. Taking this into consideration we make a comparison between non-evolutionary and evolutionary segmentation algorithms implemented on hand radiographs to recognize bone borders and shapes. The simulation and experimental results demonstrate that multiplicative intrinsic component optimization (MICO) algorithm provides better results as compared to other existing evolutionary and non-evolutionary algorithms. © 2016 Elsevier LtdItem Fully automatic segmentation of phalanges from hand radiographs for bone age assessment(Taylor and Francis Ltd., 2019) Simu, S.; Lal, S.; Fadte, K.; Harlapur, A.Segmentation of bones from hand radiograph is an important step in automated bone age assessment (ABAA) system. Main challenges in the segmentation of bones are the intensity inhomogeneity caused by the irregular distribution of X-rays and the overlapping pixel intensities between the bone and soft tissue. Hence, there is a need to develop a robust segmentation technique to tackle the problems associated with the hand radiographs. This paper proposes a fully automatic technique for segmentation of phalanges from left-hand radiograph for bone age assessment. The proposed technique is divided into five stages which are pre-processing, extraction of Phalangeal region of interest, edge preservation, segmentation of phalanges and post-processing. Quantitative and qualitative results of proposed segmentation technique are evaluated and compared with other state-of-the-art segmentation methods. Qualitative results of proposed segmentation technique are also validated by different medical experts. The segmentation accuracy achieved by proposed segmentation technique is 94%. The proposed technique can be used for development of fully ABAA of a person for better accuracy. © 2017, © 2017 Informa UK Limited, trading as Taylor & Francis Group.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 LiverNet: efficient and robust deep learning model for automatic diagnosis of sub-types of liver hepatocellular carcinoma cancer from H&E stained liver histopathology images(Springer Science and Business Media Deutschland GmbH, 2021) Aatresh, A.A.; Alabhya, K.; Lal, S.; Kini, J.; Saxena, P.P.Purpose: Liver cancer is one of the most common types of cancers in Asia with a high mortality rate. A common method for liver cancer diagnosis is the manual examination of histopathology images. Due to its laborious nature, we focus on alternate deep learning methods for automatic diagnosis, providing significant advantages over manual methods. In this paper, we propose a novel deep learning framework to perform multi-class cancer classification of liver hepatocellular carcinoma (HCC) tumor histopathology images which shows improvements in inference speed and classification quality over other competitive methods. Method: The BreastNet architecture proposed by Togacar et al. shows great promise in using convolutional block attention modules (CBAM) for effective cancer classification in H&E stained breast histopathology images. As part of our experiments with this framework, we have studied the addition of atrous spatial pyramid pooling (ASPP) blocks to effectively capture multi-scale features in H&E stained liver histopathology data. We classify liver histopathology data into four classes, namely the non-cancerous class, low sub-type liver HCC tumor, medium sub-type liver HCC tumor, and high sub-type liver HCC tumor. To prove the robustness and efficacy of our models, we have shown results for two liver histopathology datasets—a novel KMC dataset and the TCGA dataset. Results: Our proposed architecture outperforms state-of-the-art architectures for multi-class cancer classification of HCC histopathology images, not just in terms of quality of classification, but also in computational efficiency on the novel proposed KMC liver data and the publicly available TCGA-LIHC dataset. We have considered precision, recall, F1-score, intersection over union (IoU), accuracy, number of parameters, and FLOPs as metrics for comparison. The results of our meticulous experiments have shown improved classification performance along with added efficiency. LiverNet has been observed to outperform all other frameworks in all metrics under comparison with an approximate improvement of 2 % in accuracy and F1-score on the KMC and TCGA-LIHC datasets. Conclusion: To the best of our knowledge, our work is among the first to provide concrete proof and demonstrate results for a successful deep learning architecture to handle multi-class HCC histopathology image classification among various sub-types of liver HCC tumor. Our method shows a high accuracy of 90.93 % on the proposed KMC liver dataset requiring only 0.5739 million parameters and 1.1934 million floating point operations per second. © 2021, CARS.Item Efficient deep learning architecture with dimension-wise pyramid pooling for nuclei segmentation of histopathology images(Elsevier Ltd, 2021) Aatresh, A.A.; Yatgiri, R.P.; Chanchal, A.K.; Kumar, A.; Ravi, A.; Das, D.; Raghavendra, B.S.; Lal, S.; Kini, J.Image segmentation remains to be one of the most vital tasks in the area of computer vision and more so in the case of medical image processing. Image segmentation quality is the main metric that is often considered with memory and computation efficiency overlooked, limiting the use of power hungry models for practical use. In this paper, we propose a novel framework (Kidney-SegNet) that combines the effectiveness of an attention based encoder-decoder architecture with atrous spatial pyramid pooling with highly efficient dimension-wise convolutions. The segmentation results of the proposed Kidney-SegNet architecture have been shown to outperform existing state-of-the-art deep learning methods by evaluating them on two publicly available kidney and TNBC breast H&E stained histopathology image datasets. Further, our simulation experiments also reveal that the computational complexity and memory requirement of our proposed architecture is very efficient compared to existing deep learning state-of-the-art methods for the task of nuclei segmentation of H&E stained histopathology images. The source code of our implementation will be available at https://github.com/Aaatresh/Kidney-SegNet. © 2021 Elsevier LtdItem High-resolution deep transferred ASPPU-Net for nuclei segmentation of histopathology images(Springer Science and Business Media Deutschland GmbH, 2021) Chanchal, A.K.; Lal, S.; Kini, J.Purpose: Increasing cancer disease incidence worldwide has become a major public health issue. Manual histopathological analysis is a common diagnostic method for cancer detection. Due to the complex structure and wide variability in the texture of histopathology images, it has been challenging for pathologists to diagnose manually those images. Automatic segmentation of histopathology images to diagnose cancer disease is a continuous exploration field in recent times. Segmentation and analysis for diagnosis of histopathology images by using an efficient deep learning algorithm are the purpose of the proposed method. Method: To improve the segmentation performance, we proposed a deep learning framework that consists of a high-resolution encoder path, an atrous spatial pyramid pooling bottleneck module, and a powerful decoder. Compared to the benchmark segmentation models having a deep and thin path, our network is wide and deep that effectively leverages the strength of residual learning as well as encoder–decoder architecture. Results: We performed careful experimentation and analysis on three publically available datasets namely kidney dataset, Triple Negative Breast Cancer (TNBC) dataset, and MoNuSeg histopathology image dataset. We have used the two most preferred performance metrics called F1 score and aggregated Jaccard index (AJI) to evaluate the performance of the proposed model. The measured values of F1 score and AJI score are (0.9684, 0.9394), (0.8419, 0.7282), and (0.8344, 0.7169) on the kidney dataset, TNBC histopathology dataset, and MoNuSeg dataset, respectively. ConclusionItem A novel dataset and efficient deep learning framework for automated grading of renal cell carcinoma from kidney histopathology images(Nature Research, 2023) Chanchal, A.K.; Lal, S.; Kumar, R.; Kwak, J.T.; Kini, J.Trends of kidney cancer cases worldwide are expected to increase persistently and this inspires the modification of the traditional diagnosis system to respond to future challenges. Renal Cell Carcinoma (RCC) is the most common kidney cancer and responsible for 80–85% of all renal tumors. This study proposed a robust and computationally efficient fully automated Renal Cell Carcinoma Grading Network (RCCGNet) from kidney histopathology images. The proposed RCCGNet contains a shared channel residual (SCR) block which allows the network to learn feature maps associated with different versions of the input with two parallel paths. The SCR block shares the information between two different layers and operates the shared data separately by providing beneficial supplements to each other. As a part of this study, we also introduced a new dataset for the grading of RCC with five different grades. We obtained 722 Hematoxylin & Eosin (H &E) stained slides of different patients and associated grades from the Department of Pathology, Kasturba Medical College (KMC), Mangalore, India. We performed comparable experiments which include deep learning models trained from scratch as well as transfer learning techniques using pre-trained weights of the ImageNet. To show the proposed model is generalized and independent of the dataset, we experimented with one additional well-established data called BreakHis dataset for eight class-classification. The experimental result shows that proposed RCCGNet is superior in comparison with the eight most recent classification methods on the proposed dataset as well as BreakHis dataset in terms of prediction accuracy and computational complexity. © 2023, The Author(s).Item ProsGradNet: An effective and structured CNN approach for prostate cancer grading from histopathology images(Elsevier Ltd, 2025) Prabhu, A.; Sravya, N.; Lal, S.; Kini, J.Prostate cancer (PCa) is one of the most prevalent and potentially fatal malignancies affecting men globally. The incidence of prostate cancer is expected to double by 2040, posing significant health challenges. This anticipated increase underscores the urgent need for early and precise diagnosis to facilitate effective treatment and management. Histopathological analysis using Gleason grading system plays a pivotal role in clinical decision making by classifying cancer subtypes based on their cellular characteristics. This paper proposes a novel deep CNN model named as Prostate Grading Network (ProsGradNet), for the automatic grading of PCa from histopathological images. Central to the approach is the novel Context Guided Shared Channel Residual (CGSCR) block, that introduces structured methods for channel splitting and clustering, by varying group sizes. By grouping channels into 2, 4, and 8, it prioritizes deeper layer features, enhancing local semantic content and abstract feature representation. This methodological advancement significantly boosts classification accuracy, achieving an impressive 92.88% on Prostate Gleason dataset, outperforming other CNN models. To demonstrate the generalizability of ProsGradNet over different datasets, experiments are performed on Kasturba Medical College (KMC) Kidney dataset as well. The results further confirm the superiority of the proposed ProsGradNet model, with a classification accuracy of 92.68% on the KMC Kidney dataset. This demonstrates the model's potential to be applied effectively across various histopathological datasets, making it a valuable tool to fight against cancer. © 2025 Elsevier LtdItem Development and evaluation of deep neural networks for the classification of subtypes of renal cell carcinoma from kidney histopathology images(Nature Research, 2025) Chanchal, A.K.; Lal, S.; Suresh, S.Kidney cancer is a leading cause of cancer-related mortality, with renal cell carcinoma (RCC) being the most prevalent form, accounting for 80–85% of all renal tumors. Traditional diagnosis of kidney cancer requires manual examination and analysis of histopathology images, which is time-consuming, error-prone, and depends on the pathologist’s expertise. Recently, deep learning algorithms have gained significant attention in histopathology image analysis. In this study, we developed an efficient and robust deep learning architecture called RenalNet for the classification of subtypes of RCC from kidney histopathology images. The RenalNet is designed to capture cross-channel and inter-spatial features at three different scales simultaneously and combine them together. Cross-channel features refer to the relationships and dependencies between different data channels, while inter-spatial features refer to patterns within small spatial regions. The architecture contains a CNN module called multiple channel residual transformation (MCRT), to focus on the most relevant morphological features of RCC by fusing the information from multiple paths. Further, to improve the network’s representation power, a CNN module called Group Convolutional Deep Localization (GCDL) has been introduced, which effectively integrates three different feature descriptors. As a part of this study, we also introduced a novel benchmark dataset for the classification of subtypes of RCC from kidney histopathology images. We obtained digital hematoxylin and eosin (H&E) stained WSIs from The Cancer Genome Atlas (TCGA) and acquired region of interest (ROIs) under the supervision of experienced pathologists resulted in the creation of patches. To demonstrate that the proposed model is generalized and independent of the dataset, it has experimented on three well-known datasets. Compared to the best-performing state-of-the-art model, RenalNet achieves accuracies of 91.67%, 97.14%, and 97.24% on three different datasets. Additionally, the proposed method significantly reduces the number of parameters and FLOPs, demonstrating computationally efficient with 2.71 × FLOPs & 0.2131 × parameters. © The Author(s) 2025.