Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item GAN-Based Encoder-Decoder Model for Multi-Label Diagnostic Scan Classification and Automated Radiology Report Generation(CRC Press, 2024) Kumar, R.; Karthik, K.; Kamath S․, S.S.X-ray imaging is one of the most popular diagnostic imaging techniques and plays a critical role in the diagnosis and treatment process. Given the huge volume of patients and scans performed in most hospitals each day, the current practice of manual analysis of such scan images by experienced radiologists is a time-consuming and often error-prone process, worsened by the cognitive burden experienced by the radiologists. Conventional diagnostic reports written by radiologists after radiological image capture contain radiography-specific keywords (tags), observations of different body parts in the image (findings), and the actual diagnosis (impression). Automated multi-label classification of X-ray scans for disease prediction, and generation of an associated textual diagnostic scan report can ease the burden for radiologists, while also enabling fast, localized, and explanatory analysis. In this work, GAN-MLC, a CNN-LSTM description generator model trained in the adversarial setup, is proposed for the multi-label classification of X-ray images and improved feature learning for capturing disease-specific findings. Experiments performed on the NIH Chest X-ray Dataset revealed that the proposed GAN-MLC outperformed CNN-based models by a significant margin of more than seven percent. For the text diagnostic report generation task, the GAN-MLC achieved promising BLEU scores and was more robust against overfitting issues. © 2024 selection and editorial matter, Bhanu Chander, Koppala Guravaiah, B. Anoop, and G. Kumaravelan; individual chapters, the contributors.Item Automated microaneurysms detection for early diagnosis of diabetic retinopathy: A Comprehensive review(Elsevier B.V., 2021) Mayya, V.; Kamath S․, S.S.; Kulkarni, U.Diabetic retinopathy (DR), a chronic disease in which the retina is damaged due to small vessel damage caused by diabetes mellitus, is one of the leading causes of vision impairment in diabetic patients. Detection of the earliest clinical sign of the advent of DR is a critical requirement for intervention and effective treatment. Ophthalmologists are trained to identify DR, based on examining specific minute changes in the eye - microaneurysms, retinal haemorrhages, macular edema and changes in the retinal blood vessels. Segmentation of microaneurysms (MA) is a critical requirement for the early diagnosis of DR and has been the primary focus of the research community over the past few years. In this work, a systematic review of existing literature is carried out to examine the diagnostic use of automated MA detection and segmentation for early DR diagnosis. We mainly focus on existing early DR diagnosis techniques to understand their strengths and weaknesses. Though early diagnosis is performed using colour fundus photography, fluorescein angiography or optical coherence tomography angiography images, our study is limited to colour fundus based techniques. The early DR diagnosis methodologies reviewed in this article can be broadly classified into classical image processing, conventional machine learning (ML), and deep learning (DL) based techniques. Though significant progress has been achieved in these three classes of early DR diagnosis, several challenges and gaps still exist, underscoring a considerable scope for the development of fully automated, user-friendly early DR diagnosis and grading systems. We discuss in detail the challenges that need to be addressed in designing such effective, efficient, and robust algorithms for early DR diagnosis systems and also the ample scope for future research in this area. © 2021Item Applications of Machine Learning in Diabetic Foot Ulcer Diagnosis using Multimodal Images: A Review(International Association of Engineers, 2023) Mayya, V.; Tummala, V.; Reddy, C.U.; Mishra, P.; Boddu, R.; Olivia, D.; Kamath S․, S.S.Diabetes related complications such as Diabetic Foot Ulcers (DFU) may necessitate recurrent hospitalisations and expensive treatments. Uncontrolled diabetes can result in severe DFUs, resulting in amputation of lower limbs or feet, prolonged debilitation and diminished quality of life. Early diagnosis and proactive management are reported to significantly enhance the prognosis and reduce the onset of further complications. In this study, research works on developing clinical decision support systems (CDSS) for the identification and segmentation of DFU are systematically reviewed. The techniques employed range from traditional image processing techniques to approaches based on deep learning (DL). A taxonomy of DFU CDSSs is presented, categorised into two groups: RGB-based techniques and thermal imaging-based approaches. To the best of our knowledge, this is the first attempt at a comprehensive study of CDSSs for DFU related investigative tasks, based on different imaging modalities. We also delve into the difficulties experienced in the process of creating efficient, reliable, and accurate models for the early detection of DFU, and highlight the vast potential for further research in this emerging domain. © (2023), (International Association of Engineers). All Rights Reserved.Item Nature-inspired query optimisation models for medical information retrieval with relevance feedback(Inderscience Publishers, 2023) Jayasimha, A.; Mudambi, R.; Kamath S․, S.S.Medical information retrieval (MedIR) involves retrieving relevant medical-related information from a set of medical documents for a particular user query. As the volume of medical records grows, the challenging problem is determining those documents which best suiting a given query by considering user satisfaction. Statistical term weighting and probabilistic approaches for this purpose have several limitations. The gap between information need and user query can be addressed through query optimisation and relevance feedback. In this paper, we propose a document retrieval framework that incorporates query optimisation using techniques like genetic algorithm, particle swarm optimisation (PSO), and global swarm optimisation (GSO). Further, we use relevance feedback methods to reformulate the user query. The proposed techniques are applied to datasets with predefined relevance judgments to perform quantitative validation. Experimental results using the relevance judgements available in the University of Glasgow's Medline collection underscored the significant improvement achieved using BM25 scores as the fitness function. © 2023 Inderscience Enterprises Ltd.Item Multi-task deep neural network models for learning COVID-19 disease representations from multimodal data(Inderscience Publishers, 2023) Mayya, V.; Karthik, K.; Karadka, K.P.; Kamath S․, S.S.Over the continued course of the COVID-19 pandemic, a significant volume of expert-written diagnosis reports has been accumulated that capture a multitude of symptoms and observations on diagnosed COVID-19 cases, along with expert-validated chest X-ray scans. The utility of rich, latent information embedded in such unstructured expert-written diagnosis reports and its importance as a source of valuable disease-specific information has been explored to a very limited extent. In this work, a convolutional attention-based dense (CAD) neural model for COVID-19 prediction is proposed. The model is trained on the rich disease-specific parameters extracted from chest X-ray images and expert-written diagnostic text reports to support an evidence-based diagnosis. Scalability is ensured by incorporating content based learning models for automatically generating diagnosis reports of identified COVID-19 cases, reducing radiologists' cognitive burden. Experimental evaluation showed that multimodal patient data plays a vital role in diagnosing early-stage cases, thus helping hasten the diagnosis process. © 2023 Inderscience Enterprises Ltd.Item MSDNet: a deep neural ensemble model for abnormality detection and classification of plain radiographs(Springer Science and Business Media Deutschland GmbH, 2023) Karthik, K.; Kamath S․, S.S.Modern medical diagnostic techniques facilitate accurate diagnosis and treatment recommendations in healthcare. Such diagnostics procedures are performed daily in large numbers, thus, the clinical interpretation workload of radiologists is very high. Identification of abnormalities is a predominantly manual task that is performed by radiologists before the medical scans are available to the patient’s referring doctor for further recommendations. On the other hand, for a radiologist to delineate the imaging study’s findings/observations as a textual report is also a tedious task. Automated methods for radiographic image examination for identifying abnormalities and generating reliable radiology report are thus a fundamental requirement in clinical workflow management applications. In this work, we present an automated approach for abnormality classification, localization and diagnostic report retrieval for identified abnormalities. We propose MSDNet, an ensemble of Convolutional Neural models for abnormality classification, which combines the features of multiple CNN models to enhance abnormality classification performance. The proposed model also is designed to localize and visualize the detected abnormality on the radiograph image, based on an abnormal region detection algorithm to further optimize the diagnosis quality. Furthermore, the extracted features generated by MSDNet are used to automatically generate the diagnosis text report using an automatic content-based report retrieval algorithm. The upper extremity musculo-skeletal images from the MURA dataset and chest X-ray images from Indiana dataset were used for the experimental evaluation of the proposed approach. The proposed model achieved promising results, with an accuracy of 82.69%, showing its significant impact on alleviating radiologists’ cognitive load, thus improving the overall efficiency. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.