Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
48 results
Search Results
Item Hearing Loss Prediction using Machine Learning Approaches: Contributions, Limitations and Issues(Institute of Electrical and Electronics Engineers Inc., 2022) Pai, P.K.; Santhi Thilagam, P.S.Hearing, one of the five basic human senses is the ability to perceive sounds and give meaning to them. Hearing loss is a significant health problem affecting children and adults and is growing exponentially. There is a lack of knowledge regarding hearing loss despite enough awareness, resulting in detection and treatment delays. The need for detection at an early stage is significant so that people can take necessary precautions given the limited options for treatment. This paper aims to survey machine learning-based hearing loss prediction. We investigate datasets, machine learning methods, and their outcomes. We also discuss the constraints, difficulties, and intended future works. Based on the results of this survey, we have a greater understanding of the problem's complexity, the obstacles to developing a better system, and the scope of the research, which has led us to concentrate our efforts in the future on analysing data from newborns, infants, and young children. © 2022 IEEE.Item Hearing Loss Prediction in Newborns, Infants and Toddlers using Machine Learning(Institute of Electrical and Electronics Engineers Inc., 2022) Pai, P.K.; Santhi Thilagam, P.S.Hearing is one of the five senses critical to a person's day-to-day functioning. Despite enough awareness, society still has a stigma around hearing loss. It is one of the significant problems in the world today and is increasing exponentially. Early detection and intervention is the way to prevent and treat this problem. This paper focuses on predicting hearing loss in newborns, infants, and toddlers. First, the data is generated for the focused population in cooperation with an audiologist. Then, classification algorithms are applied to the data generated to build predictive models to determine hearing loss. Naïve Bayes, Support Vector Machines, XGBoost and Random Forest are the algorithms used for classification. Two datasets are generated, one with all classes having an equal number of records (balanced) and the other considering the prevalence of loss in population and noise (imbalanced). Maximum accuracy of 100% is obtained for the balanced dataset and 94.10% for the imbalanced dataset from Support Vector Machines. © 2022 IEEE.Item Utilizing Machine Learning for Lung Disease Diagnosis(Institute of Electrical and Electronics Engineers Inc., 2024) Markose, G.C.; Sitaraman, S.R.; Kumar, S.V.; Patel, V.; Mohammed, R.J.; Vaghela, C.For lung issues to be really treated and made due, early location and analysis are fundamental. In healthcare, machine learning (ML) strategies have arisen as an expected innovation with quick development, particularly in the field of clinical diagnostics. To analyze lung diseases, this research investigates the utilization of machine learning calculations. It centers around picture examination, patient information understanding, and the reconciliation of numerous information hotspots for an intensive investigation. This research's principal objective is to explore the chance of utilizing machine learning calculations to foresee and analyze a scope of lung conditions, including lung malignant growth, bronchitis, asthma, sensitivities, and persistent obstructive pneumonic disease (COPD). Proactive mediation depends on expecting the probability of lung issues before they manifest. Utilizing an assortment of machine learning techniques for classification and expectation, the examination assembled a heterogeneous dataset fully intent on laying the preparation for protection healthcare measures. © 2024 IEEE.Item The heart rate is a non-stationary signal, and its variation can contain indicators of current disease or warnings about impending cardiac diseases. The indicators can be present at all times or can occur at random, during certain intervals of the day. However, to study and pinpoint abnormalities in large quantities of data collected over several hours is strenuous and time consuming. Hence, heart rate variation measurement (instantaneous heart rate against time) has become a popular, non-invasive tool for assessing the autonomic nervous system. Computer-based analytical tools for the in-depth study and classification of data over day-long intervals can be very useful in diagnostics. The paper deals with the classification of cardiac rhythms using an artificial neural network and fuzzy relationships. The results indicate a high level of efficacy of the tools used, with an accuracy level of 80-85%. © IFMBE: 2004.(Classification of cardiac abnormalities using heart rate signals) Acharya, A.U.; Kumar, A.; Subbanna Bhat, P.; Lim, C.M.; Iyengar, S.S.; Kannathal, N.; Krishnan, S.M.2004Item Computational fluid dynamic approach to understand the effect of increasing blockage on wall shear stress and region of rupture in arteries blocked by arthesclerotic plaque(UK Simulation Society Clifton Lane Nottingham NG11 8NS, 2016) Hegde, S.S.; Deb, A.; Nagesh, S.Computational bio-mechanics is developing rapidly as a non-invasive tool to assist the medical fraternity to help in both diagnosis and prognosis of human body related issues such as injuries, cardio-vascular dysfunction, atherosclerotic plaque etc. Any system that would help either properly diagnose such problems or assist prognosis would be a boon to the doctors and medical society in general. This project is an attempt to use numerical analysis techniques; in particular, computational fluid dynamics (CFD) to solve hemodynamics related problems. The mathematical modeling of the blood flow in arteries in the presence of successive blockages has been analyzed using CFD technique. Different cases of blockages in terms of percentages have been modeled to study the effect of blockage on wall shear stress values and also the effect of increase in Reynolds number on wall shear stress values. The concept of fluid structure interaction (FSI) has been used to study the effect of increasing von Mises stress on arteries and to determine the region of rupture in arteries. The simulation results are validated using in vivo measurement data from existing literature. © 2016, UK Simulation Society. All rights reserved.Item Perceptually lossless coder for volumetric medical image data(Academic Press Inc. apjcs@harcourt.com, 2017) Chandrika, B.K.; Aparna., P.; Sumam David, S.S.With the development of modern imaging techniques, every medical examination would result in a huge volume of image data. Analysis, storage and/or transmission of these data demands high compression without any loss of diagnostically significant data. Although, various 3-D compression techniques have been proposed, they have not been able to meet the current requirements. This paper proposes a novel method to compress 3-D medical images based on human vision model to remove visually insignificant information. The block matching algorithm applied to exploit the anatomical symmetry remove the spatial redundancies. The results obtained are compared with those of lossless compression techniques. The results show better compression without any degradation in visual quality. The rate-distortion performance of the proposed coders is compared with that of the state-of-the-art lossy coders. The subjective evaluation performed by the medical experts confirms that the visual quality of the reconstructed image is excellent. © 2017Item A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans(Elsevier Ireland Ltd, 2018) Girish, G.N.; Anima, V.A.; Kothari, A.R.; Sudeep, P.V.; Roychowdhury, S.; Rajan, J.(Background and objectives) Retinal cysts are formed by accumulation of fluid in the retina caused by leakages from inflammation or vitreous fractures. Analysis of the retinal cystic spaces holds significance in detection and treatment of several ocular diseases like age-related macular degeneration, diabetic macular edema etc. Thus, segmentation of intra-retinal cysts and quantification of cystic spaces are vital for retinal pathology and severity detection. In the recent years, automated segmentation of intra-retinal cysts using optical coherence tomography B-scans has gained significant importance in the field of retinal image analysis. The objective of this paper is to compare different intra-retinal cyst segmentation algorithms for comparative analysis and benchmarking purposes. (Methods) In this work, we employ a modular approach for standardizing the different segmentation algorithms. Further, we analyze the variations in automated cyst segmentation performances and method scalability across image acquisition systems by using the publicly available cyst segmentation challenge dataset (OPTIMA cyst segmentation challenge). (Results) Several key automated methods are comparatively analyzed using quantitative and qualitative experiments. Our analysis demonstrates the significance of variations in signal-to-noise ratio (SNR), retinal layer morphology and post-processing steps on the automated cyst segmentation processes. (Conclusion) This benchmarking study provides insights towards the scalability of automated processes across vendor-specific imaging modalities to provide guidance for retinal pathology diagnostics and treatment processes. © 2017 Elsevier B.V.Item Segmentation of intima media complex from carotid ultrasound images using wind driven optimization technique(Elsevier Ltd, 2018) Yamanakkanavar, Y.; Madipalli, P.; Rajan, J.; Kumar, P.K.; Narasimhadhan, A.V.Cardiovascular diseases are the third leading cause of death worldwide. The primitive indication of the possible onset of a cardiovascular disease is atherosclerosis, which is the accumulation of plaque on the arterial wall. The intima-media thickness (IMT) of the common carotid artery is an early marker of the development of cardiovascular disease. The computation of the IMT and the delineation of the carotid plaque are significant predictors for the clinical diagnosis of the risk of stroke. For a robust diagnosis, carotid ultrasound images must be free from speckle noise. To address this problem, we use state-of-the-art despeckling and enhancement methods in this work. Many edge-based methods for IMT estimation have been proposed to overcome the limitations of manual segmentation. In this paper, we present a fully automated region-of-interest (ROI) extraction and a threshold-based segmentation of the intima media complex (IMC) using a wind driven optimization (WDO) technique. A quantitative evaluation is carried out on 90 carotid ultrasound images of two different datasets. The obtained results are compared with those of state-of-the-art techniques such as a model-based approach, a dynamic programming method, and a snake segmentation method. The experimental analysis shows that the proposed method is robust in measuring the IMT in carotid ultrasound images. © 2017 Elsevier LtdItem A novel feature extraction technique for pulmonary sound analysis based on EMD(Elsevier Ireland Ltd, 2018) Mondal, A.; Banerjee, P.; Tang, H.Background and objective: The stethoscope based auscultation technique is a primary diagnostic tool for chest sound analysis. However, the performance of this method is limited due to its dependency on physicians experience, knowledge and also clarity of the signal. To overcome this problem we need an automated computer-aided diagnostic system that will be competent in noisy environment. In this paper, a novel feature extraction technique is introduced for discriminating various pulmonary dysfunctions in an automated way based on pattern recognition algorithms. Method: In this work, the disease correlated relevant characteristics of lung sounds signals are identified in terms of statistical distribution parameters: mean, variance, skewness, and kurtosis. These features are extracted from selective morphological components of the mapped signal in the empirical mode decomposition domain. The feature set is fed to the classifier model to differentiate their corresponding classes. Results: The significance of features developed are validated by conducting several experiments using supervised and unsupervised classifiers. Furthermore, the discriminating power of the proposed features is compared with three types of baseline features. The experimental result is evaluated by statistical analysis and also validated with physicians inference. Conclusions: It is found that the proposed features extraction technique is superior to the baseline methods in terms of classification accuracy, sensitivity and specificity. The developed method gives better results compared to baseline methods in any circumstance. The proposed method gives a higher accuracy of 94.16, sensitivity of 100 and specificity of 93.75 for an artificial neural network classifier. © 2018 Elsevier B.V.Item A visual attention guided unsupervised feature learning for robust vessel delineation in retinal images(Elsevier Ltd, 2018) Srinidhi, C.L.; Aparna., P.; Rajan, J.Background and objective: Accurate segmentation of retinal vessels from color fundus images play a significant role in early diagnosis of various ocular, systemic and neuro-degenerative diseases. Segmenting retinal vessels is challenging due to varying nature of vessel caliber, the proximal presence of pathological lesions, strong central vessel reflex and relatively low contrast images. Most existing methods mainly rely on carefully designed hand-crafted features to model the local geometrical appearance of vasculature structures, which often lacks the discriminative capability in segmenting vessels from a noisy and cluttered background. Methods: We propose a novel visual attention guided unsupervised feature learning (VA-UFL) approach to automatically learn the most discriminative features for segmenting vessels in retinal images. Our VA-UFL approach captures both the knowledge of visual attention mechanism and multi-scale contextual information to selectively visualize the most relevant part of the structure in a given local patch. This allows us to encode a rich hierarchical information into unsupervised filtering learning to generate a set of most discriminative features that aid in the accurate segmentation of vessels, even in the presence of cluttered background. Results: Our proposed method is validated on the five publicly available retinal datasets: DRIVE, STARE, CHASE_DB1, IOSTAR and RC-SLO. The experimental results show that the proposed approach significantly outperformed the state-of-the-art methods in terms of sensitivity, accuracy and area under the receiver operating characteristic curve across all five datasets. Specifically, the method achieved an average sensitivity greater than 0.82, which is 7% higher compared to all existing approaches validated on DRIVE, CHASE_DB1, IOSTAR and RC-SLO datasets, and outperformed even second-human observer. The method is shown to be robust to segmentation of thin vessels, strong central vessel reflex, complex crossover structures and fares well on abnormal cases. Conclusions: The discriminative features learned via visual attention mechanism is superior to hand-crafted features, and it is easily adaptable to various kind of datasets where generous training images are often scarce. Hence, our approach can be easily integrated into large-scale retinal screening programs where the expensive labelled annotation is often unavailable. © 2018 Elsevier Ltd