Prof. Sujatha Narayanan Unni Profile

Prof. Sujatha Narayanan Unni

Professor at Indian Institute of Technology Madras

SPIE Involvement:

Conference Chair | Author | Editor

Publications (44)

Proceedings Article | 17 April 2024 Poster

Developing a machine-learning-based classification system for detecting choroidal neovascularization (CNV) from optical coherence tomography (OCT) images

Biruktawit Assefa, Sujatha Narayanan Unni

Proceedings Volume 13108, 131080E (2024) https://doi.org/10.1117/12.3028988

Read Abstract +

Choroidal neovascularization (CNV) is a significant complication associated with age-related macular degeneration (AMD), particularly its "wet" or exudative form. In the context of AMD, CNV is the leading cause of severe vision loss and legal blindness. Detecting CNV can prove challenging, particularly in its early stages when symptoms may be subtle, or the abnormal blood vessel growth is minimal. Modern diagnostic tools, such as Optical Coherence Tomography (OCT) and Fluorescein Angiography (FA), have greatly improved our ability to diagnose CNV through comprehensive eye examinations. In this paper, we discuss the classification of normal and CNV affected retina optical coherence tomography (OCT) images, aiming to improve diagnostic reliability and assist medical professionals, working in the field of Ophthalmology. CNV is characterized by the growth of new choroidal vessels into the sub-retinal space through breaks in the Bruch's membrane. Our classification model combines image pre-processing, feature extraction, and image classification techniques. It leverages both traditional machine learning methods like Support Vector Machines (SVM), Random Forest, and AdaBoosting, as well as advanced deep learning architectures like Convolutional Neural Networks (CNN) and the highly regarded VGG16. After an extensive evaluation of model performance, the VGG16-SVM hybrid model emerged as the top performer, achieving an outstanding 99% accuracy rate and an equally impressive 99% precision rate. This result highlights the model's robustness and effectiveness in accurately categorizing images. The superiority of the VGG16-SVM hybrid model can be attributed to VGG16's proficiency in hierarchical feature learning. By combining the strengths of deep learning and traditional machine learning, the model harnesses deep networks' exceptional feature extraction capabilities and the robust classification power of Support Vector Machines (SVM). This synergy results in a more balanced and precise classification performance.

Proceedings Article | 17 April 2024 Poster

Binary classification and spatial localization of breast through polarized Monte Carlo simulation investigation and convolutional neural network modelling

Janaki Ramkumar, Sujatha Narayanan Unni

Proceedings Volume 13108, 131080O (2024) https://doi.org/10.1117/12.3029777

Read Abstract +

Proceedings Article | 17 April 2024 Poster

Study of Intralipid 20% as blood-mimicking fluid for optical imaging applications

Sadbhawna Kushwaha, Sujatha Narayanan Unni

Proceedings Volume 13108, 1310812 (2024) https://doi.org/10.1117/12.3031323

Read Abstract +

Proceedings Article | 17 April 2024 Poster

Development of smart nano-kit for rapid, automated, and ultra-sensitive detection of pesticide traces in agricultural samples

Sujatha Narayanan Unni, Rohit Kumar Sharma, Nishima Wangoo, Maitrayee Trivedi, Kavini V, Sudha Karthik, Vishal Balaji

Proceedings Volume 13108, 131080M (2024) https://doi.org/10.1117/12.3029508

Read Abstract +

Proceedings Article | 17 April 2024 Poster

Hyperspectral signal analysis for classification of leaves utilizing a machine-learning-based algorithm

Jyotisana Meena, Sujatha Narayanan Unni

Proceedings Volume 13108, 131080V (2024) https://doi.org/10.1117/12.3030345

Read Abstract +

Proceedings Article | 20 September 2023 Paper

Chromophore estimation from finite element derived skin tissue models: simulation and experiments

Vysakh Vasudevan, Sujatha Narayanan Unni

Proceedings Volume 12608, 1260811 (2023) https://doi.org/10.1117/12.3007924

KEYWORDS: Tissues, Skin, Reflectivity, Chromophores, Finite element methods, Diffuse reflectance spectroscopy, Algorithm development, Statistical analysis, In vitro testing, Optical properties

Read Abstract +