Quantification of Retinal Nerve Fibre Layer Thickness on Optical Coherence Tomography with a Deep Learning Segmentation-Free Approach

Abstract

This study describes a segmentation-free deep learning (DL) algorithm for measuring retinal nerve fibre layer (RNFL) thickness on spectral-domain optical coherence tomography (SDOCT). The study included 25,285 B-scans from 1,338 eyes of 706 subjects. Training was done to predict RNFL thickness from raw unsegmented scans using conventional RNFL thickness measurements from good quality images as targets, forcing the DL algorithm to learn its own representation of RNFL. The algorithm was tested in three different sets: (1) images without segmentation errors or artefacts, (2) low-quality images with segmentation errors, and (3) images with other artefacts. In test set 1, segmentation-free RNFL predictions were highly correlated with conventional RNFL thickness (r = 0.983, P < 0.001). In test set 2, segmentation-free predictions had higher correlation with the best available estimate (tests with good quality taken in the same date) compared to those from the conventional algorithm (r = 0.972 vs. r = 0.829, respectively; P < 0.001). Segmentation-free predictions were also better in test set 3 (r = 0.940 vs. r = 0.640, P < 0.001). In conclusion, a novel segmentation-free algorithm to extract RNFL thickness performed similarly to the conventional method in good quality images and better in images with errors or other artefacts.

Radiomics: an overview in lung cancer management—a narrative review

“…However, with the advent and development of deep learning, segmentation may be avoidable altogether, and an algorithm could be created to automatically extract features from an unsegmented image. This is one of the notable distinctions between radiomics and deep learning (33,34).…”

Diagnostik von Erkrankungen des Sehnervenkopfes in Zeiten von künstlicher Intelligenz und Big Data

“…Mit dem DL-Modell, das von Mariottoni et al. vorgeschlagen wurde, ließ sich die RNFL in OCT-Bildern mit schlechter Aufnahmequalität besser messen, als mit der Software des Herstellers [ 21 ]. Neben der RNFL und BMO-MRW zeigen sich bei Fortschreiten eines Glaukoms jedoch auch Änderungen anderer anatomischer Strukturen, die auf dem OCT-Scan der Papille sichtbar sind.…”

A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression

“…Therefore these models can make use of raw SDOCT images without requiring the input of pre-defined features. Along those lines, Mariottoni et al 65 recently demonstrated that a segmentation-free deep learning algorithm could be trained to predict RNFL thickness when assessing a raw OCT B-scan. The segmentation-free predictions were highly correlated with the conventional RNFL thickness ( r = 0.983, P < 0.001), with mean absolute error of approximately 2 µm in good-quality images.…”

“…In addition to RNFL 65 and optic nerve head scans, 66 , 67 deep learning models have also been used to investigate macular scans. 7 , 68 Asaoka et al 7 showed that a deep learning model built from an 8 × 8 macular grid showed superior performance for detecting glaucoma damage compared to macular RNFL thickness or ganglion cell complex measurements.…”