Fast inference in classification of optical coherence tomography (OCT) images for real-time retinal disease diagnosis
Fast inference in classification of optical coherence tomography (OCT) images for real-time retinal disease diagnosis
By
Amin Rahmani, Mehdi Ghatee
has been accepted in “Biomedical Signal Processing and Control“.
Highlights
- Novel energy based early exiting schema.
- Novel method of early exit detection using distribution fitting.
- Real-time OCT classification on low computation devices.
Abstract
Background:
The increasing prevalence of retinal diseases highlights the need for more ophthalmology specialists, as existing diagnostic methods struggle to efficiently screen a growing patient population. Recent advancements in artificial intelligence, particularly in deep learning, offer a promising solution.
Aims:
In light of the rising demand for telehealth services and precise diagnostic systems, we aim to develop a deep-learning framework for classifying Optical Coherence Tomography (OCT) images. This framework is designed to be used by ophthalmologists on cost-effective, low-computation devices such as smartphones.
Materials and Methods:
We present an energy-based early-exiting deep learning framework to optimize computational efficiency for OCT classification. This framework integrates an early exit module along with a distribution-based decision-making algorithm for inference time. The modules will raise exit numbers from earlier layers of the backbone network.
Results:
Our ResNet-18 and ResNet-50 models achieved an impressive 100% accuracy in under 0.1 s on the OCT2017 dataset, averaging 0.77 GMacs per sample. In testing on a second dataset comprising 3,231 samples, we maintained an F-score of 1 while successfully reducing computational overhead. Furthermore, the model exhibited excellent performance on smartphones, averaging 0.618 s per sample with just 6 MB of memory usage.
Conclusion:
We have developed deep-learning models that enhance inference speed, reduce computational costs, and maintain high accuracy. This framework has the potential to support ophthalmologists in diagnosing retinal diseases using smartphones or serve as a valuable telehealth monitoring tool.
Graphical abstract
Keywords
Dynamic routing
Early exiting
Deep learning
Energy based model
OCT classification
Ref: https://doi.org/10.1016/j.bspc.2024.107365
The full version of the paper “Fast inference in classification of optical coherence tomography (OCT) images for real-time retinal disease diagnosis” by Amin Rahmani & Mehdi Ghatee is now available online in “Biomedical Signal Processing and Control”. It can be downloaded by clicking the following Share Link before February 16, 2025. No sign up, registration, or fees are required.
Share Link: