Retinal layer segmentation in rodent OCT images: Local intensity profiles & fully convolutional neural networks. (January 2021)

• Record Type: Journal Article
• Authors: Morales, Sandra; Colomer, Adrián; Mossi, José M.; del Amor, Rocío; Woldbye, David; Klemp, Kristian; Larsen, Michael; Naranjo, Valery
• Is Part Of: Computer methods and programs in biomedicine. Volume 198(2021)
• Publication Date: 2021-01
• Subjects: Optical coherence tomography -- Rodent OCT -- Rat OCT -- Layer segmentation -- Convolutional neural networks -- Intensity profile; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105788
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Two approaches to detect retinal layers in rat OCT images are presented. One approach is based on classical image processing and the other on deep learning. Both methods significantly outperform a commercial image segmentation software. Deep-learning-based method obtains promising results on unseen databases. A new rat OCT database with expert-reviewed segmentations is publicly available. Abstract: Background and Objective: Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented. Methods: One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture. Results: After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons. Conclusions: Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images.