Wayfinding artificial intelligence to detect clinically meaningful spots of retinal diseases: Artificial intelligence to help retina specialists in real world practice

• Published in: PloS one Vol. 18; no. 3; p. e0283214
• Main Authors: Shiihara, Hideki, Sonoda, Shozo, Terasaki, Hiroto, Fujiwara, Kazuki, Funatsu, Ryoh, Shiba, Yousuke, Kumagai, Yoshiki, Honda, Naoto, Sakamoto, Taiji
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 27.03.2023; Public Library of Science (PLoS)
• Subjects: Abnormalities; Algorithms; Ambiguity; Analysis; Artificial Intelligence; Biology and Life Sciences; Clinical medicine; Color vision; Computer and Information Sciences; Deep learning; Diabetic retinopathy; Diagnosis; Entropy; Epithelium; Evaluation; Humans; Image segmentation; Localization; Machine learning; Mathematical models; Medical diagnosis; Medical imaging; Medicine and Health Sciences; Membranes; Navigation behavior; Ophthalmology; Optical Coherence Tomography; Physical Sciences; Probability distribution; Research and Analysis Methods; Retina; Retina - diagnostic imaging; Retinal Diseases; Retinal Pigment Epithelium; Risk factors; Tomography; Tomography, Optical Coherence - methods; Wayfinding; Japan
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0283214

To aim of this study is to develop an artificial intelligence (AI) that aids in the thought process by providing retinal clinicians with clinically meaningful or abnormal findings rather than just a final diagnosis, i.e., a "wayfinding AI." Spectral domain optical coherence tomography B-scan images were classified into 189 normal and 111 diseased eyes. These were automatically segmented using a deep-learning based boundary-layer detection model. During segmentation, the AI model calculates the probability of the boundary surface of the layer for each A-scan. If this probability distribution is not biased toward a single point, layer detection is defined as ambiguous. This ambiguity was calculated using entropy, and a value referred to as the ambiguity index was calculated for each OCT image. The ability of the ambiguity index to classify normal and diseased images and the presence or absence of abnormalities in each layer of the retina were evaluated based on the area under the curve (AUC). A heatmap, i.e., an ambiguity-map, of each layer, that changes the color according to the ambiguity index value, was also created. The ambiguity index of the overall retina of the normal and disease-affected images (mean ± SD) were 1.76 ± 0.10 and 2.06 ± 0.22, respectively, with a significant difference (p < 0.05). The AUC used to distinguish normal and disease-affected images using the ambiguity index was 0.93, and was 0.588 for the internal limiting membrane boundary, 0.902 for the nerve fiber layer/ganglion cell layer boundary, 0.920 for the inner plexiform layer/inner nuclear layer boundary, 0.882 for the outer plexiform layer/outer nuclear layer boundary, 0.926 for the ellipsoid zone line, and 0.866 for the retinal pigment epithelium/Bruch's membrane boundary. Three representative cases reveal the usefulness of an ambiguity map. The present AI algorithm can pinpoint abnormal retinal lesions in OCT images, and its localization is known at a glance when using an ambiguity map. This will help diagnose the processes of clinicians as a wayfinding tool.