A Machine Learning Framework for the Quantification of Experimental Uveitis in Murine OCT
Authors:
Preprint
- 7 March 2023
- preprint
- Published by Optica Publishing Group in Optica Open
Abstract
This paper presents methods for the detection and assessment of non-infectious uveitis, a leading cause of vision loss in working age adults. In the first part, we propose a classification model that can accurately predict the presence of uveitis and differentiate between different stages of the disease using optical coherence tomography (OCT) images. We utilize the Grad-CAM visualization technique to elucidate the decision-making process of the classifier and gain deeper insights into the results obtained. In the second part, we apply and compare three methods for the detection of detached particles in the retina that are indicative of uveitis. The first is a fully supervised detection method, the second is an unsupervised technique, and the third is a weakly supervised segmentation that produces per-pixel masks as output. The segmentation model is used as a backbone for a fully automated pipeline that can segment small particles of uveitis in 2D slices of the retina, reconstruct the volume, and produce centroids as points distribution in space. The number of particles in retinas is used to grade the disease, and point process analysis on centroids in (3D) shows clustering patterns in the distribution of the particles on the retina.Keywords
All Related Versions
- Published version: Biomedical Optics Express, 14 (7), 3413.
This publication has 20 references indexed in Scilit:
- Deep learning in glaucoma with optical coherence tomography: a reviewEye, 2020
- Monocular human pose estimation: A survey of deep learning-based methodsComputer Vision and Image Understanding, 2020
- Utility of Deep Learning Methods for Referability Classification of Age-Related Macular DegenerationJAMA Ophthalmology, 2018
- Clinically applicable deep learning for diagnosis and referral in retinal diseaseNature Medicine, 2018
- Deep Learning Is Effective for Classifying Normal versus Age-Related Macular Degeneration OCT ImagesOphthalmology Retina, 2017
- Multiple objects detection in biological images using a marked point process frameworkMethods, 2017
- Deep Residual Learning for Image Recognition2016
- Automated Analysis of Anterior Chamber Inflammation by Spectral-Domain Optical Coherence TomographyOphthalmology, 2015
- Adaptive-weighted bilateral filtering and other pre-processing techniques for optical coherence tomographyComputerized Medical Imaging and Graphics, 2014
- Rodent Models of Experimental Autoimmune Uveitis2012