LOCTseg: A lightweight fully convolutional network for end-to-end optical coherence tomography segmentation

• Published in: Computers in biology and medicine Vol. 150; p. 106174
• Main Authors: Parra-Mora, Esther, da Silva Cruz, Luís A.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01-11-2022; Elsevier Limited
• Subjects: Algorithms; Datasets; Deep learning; Epiretinal membrane; Fully convolutional networks; Image acquisition; Image processing; Image resolution; Image segmentation; Lightweight; Lightweight architecture; Macular pucker; Medical image segmentation; Medical imaging; Multiple sclerosis; Optical Coherence Tomography; Retina; Retinal layers segmentation; Tomography; Deep learning; Fully convolutional networks; Epiretinal membrane; Optical coherence tomography; Lightweight architecture; Medical image segmentation; Macular pucker; Retinal layers segmentation
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.106174

This article presents a novel end-to-end automatic solution for semantic segmentation of optical coherence tomography (OCT) images. OCT is a non-invasive imaging technology widely used in clinical practice due to its ability to acquire high-resolution cross-sectional images of the ocular fundus. Due to the large variability of the retinal structures, OCT segmentation is usually carried out manually and requires expert knowledge. This study introduces a novel fully convolutional network (FCN) architecture designated by LOCTSeg, for end-to-end automatic segmentation of diagnostic markers in OCT b-scans. LOCTSeg is a lightweight deep FCN optimized for balancing performance and efficiency. Unlike state-of-the-art FCNs used in image segmentation, LOCTSeg achieves competitive inference speed without sacrificing segmentation accuracy. The proposed LOCTSeg is evaluated on two publicly available benchmarking datasets: (1) annotated retinal OCT image database (AROI) comprising 1136 images, and (2) healthy controls and multiple sclerosis lesions (HCMS) consisting of 1715 images. Moreover, we evaluated the proposed LOCTSeg with a private dataset of 250 OCT b-scans acquired from epiretinal membrane (ERM) and healthy patients. Results of the evaluation demonstrate empirically the effectiveness of the proposed algorithm, which improves the state-of-the-art Dice score from 69% to 73% and from 91% to 92% on AROI and HCMS datasets, respectively. Furthermore, LOCTSeg outperforms comparable lightweight FCNs’ Dice score by margins between 4% and 15% on ERM segmentation.
•Fully convolutional networks are the state-of-the-art for image semantic segmentation.•We introduce LOCTSeg, a new fully automated end-to-end and low-complexity network for OCT b-scan segmentation.•Segmentation of retinal layers, fluids, and epiretinal membranes from OCT b-scans is an active area of research.•The method achieves high performance with faster inference time and fewer computational requirements.•The proposed lightweight architecture improved state-of-the-art performance on two public datasets.