Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
2 results
Search Results
Item Using Image Processing on MRI Scans(Institute of Electrical and Electronics Engineers Inc., 2015) Patil, C.; Mathura, M.G.; Madhumitha, S.; Sumam David, S.; Fernandes, M.; Venugopal, A.; Bhaskaran, B.Alzheimer's disease (AD) is an irreversible and progressive brain disease that gradually destroys memory and thinking skills to an extent that it starts affecting the daily life. It has become the most common cause of dementia among older people. The work presented in this paper evaluates the utility of image processing on the Magnetic Resonance Imaging (MRI) scans to estimate the possibility of an early detection of AD. The total brain atrophy and specifically the hippocampal atrophy are considered strong diagnostic tests for AD. T1 weighted MRIs have been used for the purpose of image processing to evaluate atrophy. The paper demonstrates the applications of several image processing techniques such as K-means clustering, wavelet transform, watershed algorithm and also a customized algorithm tailored for the specific case. It has been implemented on the open source platforms, OpenCV and Qt, which facilitates the implementation and utility of the developed product in the hospitals without requiring any proprietary software. The results obtained from the project could aid the analysis to detect AD along with correlation with the psychiatric results and could thus assist the doctors in detecting AD at an early stage. This could progressively help in understanding and treating AD. © 2015 IEEE.Item Feature-enhanced deep learning technique with soft attention for MRI-based brain tumor classification(Springer Science and Business Media B.V., 2024) Mohanty, B.C.; Subudhi, P.K.; Dash, R.; Mohanty, B.Brain tumor classification using Magnetic Resonance Imaging (MRI) is a pivotal area in medical diagnostics, with the potential to influence early detection and subsequent treatment strategies. Over the years, various machine learning and deep learning models have been proposed to enhance the accuracy of MRI-based tumor detection. In this evolving landscape, this paper introduces a distinctive deep-learning model that harnesses the power of a soft attention mechanism. We employ a meticulously designed Convolutional Neural Network (CNN) comprising four convolution layers. One of the significant innovations in our approach is the method of feature extraction. Instead of extracting features solely from the final layer, as is common in many models, our approach aggregates and combines features from all layers. This ensures that the vital characteristics intrinsic to each layer are not lost but rather amalgamated into a robust and comprehensive feature vector. The incorporation of a soft attention mechanism at the terminal stages ensures that the most salient and clinically relevant features are emphasized, enhancing classification accuracy. To validate the efficacy of our proposed model, we employed standard datasets for training and testing. A comparative analysis with existing state-of-the-art models affirms the superiority and potential of our approach in the realm of MRI-based brain tumor classification. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.