164.111.127.22
dgid:
enl:
npi:0
-Advertisement-
Retina

New study highlights OCT’s pivotal role in eye disease monitoring

Posted on

The integration of machine learning (ML) and deep learning (DL) techniques with optical coherence tomography (OCT) enhances diagnostic accuracy and efficiency, suggesting a future where continuous learning systems could predict eye pathologies through subtle changes in OCT images, thereby reducing the workload of eye care professionals, according to a new study that reviewed the role of OCT-derived images in detecting, characterizing, and monitoring eye diseases.

The comprehensive review analyzed the application of ML and DL techniques in OCT imaging for ocular disease detection. The findings highlighted that while ML-based decision support systems grapple with feature abundance and significance determination, DL-based systems offer a more streamlined, plug-and-play approach. Pre-trained deep networks have proven effective for classification tasks involving complex OCT images. These networks not only facilitate the reduction of ophthalmologists’ and retina specialists’ workloads but also hold the potential for developing continuous learning systems capable of predicting ocular pathologies through subtle image changes.

The authors concluded that OCT-derived imaging, coupled with advanced ML and DL techniques, is paving the way for more accurate, efficient, and predictive ophthalmic care, heralding a new era in the early detection and management of eye diseases.

Reference
Akpinar MH, Sengur A, Faust O, et al. Artificial intelligence in retinal screening using OCT images: A review of the last decade (2013-2023). Comput Methods Programs Biomed. 2024;254:108253. doi: 10.1016/j.cmpb.2024.108253. Epub ahead of print. PMID: 38861878.

-Advertisement-
-Advertisement-
-Advertisement-
-Advertisement-
-Advertisement-
-Advertisement-