Department of Ophthalmology, Kagoshima University Graduate School of Medical and Dental Sciences, Kagoshima, Japan.
Sonoda Eye Clinic, Kagoshima, Japan.
PLoS One. 2023 Mar 27;18(3):e0283214. doi: 10.1371/journal.pone.0283214. eCollection 2023.
AIM/BACKGROUND: 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.
目的/背景：本研究旨在开发一种人工智能（AI），通过为视网膜临床医生提供有临床意义或异常的发现，而不仅仅是最终诊断，即“导航 AI”，从而辅助他们的思维过程。
对 189 只正常眼和 111 只病变眼的光谱域光相干断层扫描 B 扫描图像进行分类。这些图像使用基于深度学习的边界层检测模型自动分割。在分割过程中，AI 模型计算每个 A 扫描的层边界表面的概率。如果该概率分布不是偏向于单个点，则定义层检测为模糊。使用熵计算这种模糊性，并为每个 OCT 图像计算一个称为模糊指数的数值。基于曲线下面积（AUC）评估模糊指数对正常和病变图像的分类能力，以及视网膜各层的异常存在情况。还创建了一个各层的热图，即模糊图，根据模糊指数值改变颜色。
正常和病变图像的整个视网膜的模糊指数（平均值±标准差）分别为 1.76±0.10 和 2.06±0.22，差异有统计学意义（p<0.05）。使用模糊指数区分正常和病变图像的 AUC 为 0.93，内界膜边界为 0.588，神经纤维层/节细胞层边界为 0.902，内丛状层/内核层边界为 0.920，外丛状层/外核层边界为 0.882，椭圆体带线为 0.926，视网膜色素上皮/布鲁赫膜边界为 0.866。三个有代表性的病例揭示了模糊图的有用性。
本研究中的 AI 算法可以精确定位 OCT 图像中的异常视网膜病变，并且使用模糊图可以一目了然地了解其定位。这将有助于临床医生作为导航工具来诊断疾病。
