Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Utilizing Deep Learning Methods for Cancer Detection through Analysis of MicroRNA Expression Profiles(Institute of Electrical and Electronics Engineers Inc., 2024) Kantamneni, S.; Hegde, P.; Patil, N.Integration of cutting-edge computational methods and genomic data analysis has become crucial in the quest for early cancer diagnosis and enhanced diagnostic accuracy. The genomic sequences of microRNAs (miRNAs), which are important cancer biomarkers, provide important information for this. In this study, we propose a novel deep learning-based framework for cancer detection with a focus on FNNs and a hybrid DNN model with an accuracy of over 90.7%. Our method aims to identify detailed genomic patterns and features that improve the sensitivity and specificity of cancer detection by painstakingly curating and preprocessing large miRNA datasets gathered from various patient cohorts. This research sets the stage for further exploration of deep learning methodologies within the context of miRNA-based cancer detection, promising advancements in personalized diagnosis and prognosis. Our method aims to identify detailed genomic patterns and features that improve the sensitivity and specificity of cancer detection by painstakingly curating and preprocessing large miRNA datasets gathered from various patient cohorts. Our approach seeks to improve sensitivity and specificity by deciphering complex genetic patterns. By utilizing these datasets, we show off the effectiveness of our model and its clinical potential, giving an accuracy of 90.7% for our Hybrid Feedforward and Dense Neural Network model as compared to current state of the art machine learning models. This research promises revolutionary advances in customized oncology, providing a route towards improved diagnostic accuracy and early intervention. It also proves that miRNA expressions values are not sequential in nature. It also lays the groundwork for the development of deep learning in miRNA-based cancer detection. © 2024 IEEE.Item Novel color normalization method for hematoxylin eosin stained histopathology images(Institute of Electrical and Electronics Engineers Inc., 2019) Roy, S.; Lal, S.; Kini, J.R.With the advent of computer-assisted diagnosis (CAD), the accuracy of cancer detection from histopathology images is significantly increased. However, color variation in the CAD system is inevitable due to the variability of stain concentration and manual tissue sectioning. The small variation in color may lead to the misclassification of cancer cells. Therefore, color normalization is a very much essential step prior to segmentation and classification in order to reduce the inter-variability of background color among a set of source images. In this paper, a novel color normalization method is proposed for Hematoxylin and Eosin stained histopathology images. Conventional Reinhard algorithm is modified in our proposed method by incorporating fuzzy logic. Moreover, mathematically, it is proved that our proposed method satisfies all three hypotheses of color normalization. Furthermore, several quality metrics are estimated locally for evaluating the performance of various color normalization methods. The experimental result reveals that our proposed method has outperformed all other benchmark methods. © 2019 IEEE.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 High-Performance Dual-Core Bilateral Surface Optimized PCF SPR Biosensor for Early Detection of Six Distinct Cancer Cells(Springer, 2025) B, N.; Dagar, H.; Krishnan, P.This work presents a photonic crystal fiber (PCF)–based surface plasmon resonance (SPR) biosensor with dual cores and bilateral-surface detection capability to enhance the early identification of cancerous cells. The biosensor processes cell samples including both malignant cancerous cells and healthy normal cells through varying refractive indices. The optimized design of the sensor achieves enhanced wavelength and amplitude sensitivities and identification accuracy in terms of resolution. The bilateral-surface precision PCF SPR biosensor allows for continuous tracking of dynamic biomolecular interactions with the plasmonic region by detecting changes in resonance conditions. The suggested biosensor is evaluated numerically using the finite element method (FEM)–based COMSOL tool. Its performance is assessed for several malignant cells such as MCF7, MDAMB231, PC12, HeLa, Jurkat, and Basal over a refractive index range of 1.360 to 1.401, and they were found to have wavelength sensitivities of 5714.28, 5714.28, 4285.72, 4285.71, 3333.33, and 3000 nm/RIU, respectively. The maximum wavelength sensitivity of 5714.28 nm/RIU is observed for the MCF7 and MDAMB231 cells, and the maximum amplitude sensitivity of 899.248 RIU-1 is achieved for the MCF7 cell. The greatest sensor resolution of 3.33 × 10-5 RIU is achieved for the Basal cell. Therefore, the proposed PCF SPR sensor with its simple geometry and overall high-performance characteristics is a promising candidate for the early detection of six different cancer cells. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.