Chłopowiec Adam R, Karanowski Konrad, Skrzypczak Tomasz, Grzesiuk Mateusz, Chłopowiec Adrian B, Tabakov Martin
Department of Artificial Intelligence, Wroclaw University of Science and Technology, Wybrzeże Wyspianskiego 27, 50-370 Wroclaw, Poland.
Faculty of Medicine, Wroclaw Medical University, Wybrzeże Ludwika Pasteura 1, 50-367 Wroclaw, Poland.
Diagnostics (Basel). 2023 May 29;13(11):1904. doi: 10.3390/diagnostics13111904.
Multiple studies presented satisfactory performances for the treatment of various ocular diseases. To date, there has been no study that describes a multiclass model, medically accurate, and trained on large diverse dataset. No study has addressed a class imbalance problem in one giant dataset originating from multiple large diverse eye fundus image collections. To ensure a real-life clinical environment and mitigate the problem of biased medical image data, 22 publicly available datasets were merged. To secure medical validity only Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD) and Glaucoma (GL) were included. The state-of-the-art models ConvNext, RegNet and ResNet were utilized. In the resulting dataset, there were 86,415 normal, 3787 GL, 632 AMD and 34,379 DR fundus images. ConvNextTiny achieved the best results in terms of recognizing most of the examined eye diseases with the most metrics. The overall accuracy was 80.46 ± 1.48. Specific accuracy values were: 80.01 ± 1.10 for normal eye fundus, 97.20 ± 0.66 for GL, 98.14 ± 0.31 for AMD, 80.66 ± 1.27 for DR. A suitable screening model for the most prevalent retinal diseases in ageing societies was designed. The model was developed on a diverse, combined large dataset which made the obtained results less biased and more generalizable.
多项研究在各种眼部疾病的治疗方面表现令人满意。迄今为止，尚无研究描述一种多类模型，该模型在医学上准确无误，且是在大量多样的数据集中进行训练的。没有研究解决过源自多个大型多样眼底图像集的一个巨型数据集中的类别不平衡问题。为确保真实的临床环境并减轻医学图像数据偏差问题，合并了22个公开可用的数据集。为确保医学有效性，仅纳入了糖尿病性视网膜病变（DR）、年龄相关性黄斑变性（AMD）和青光眼（GL）。使用了最先进的模型ConvNext、RegNet和ResNet。在所得数据集中，有86415张正常眼底图像、3787张青光眼图像、632张年龄相关性黄斑变性图像和34379张糖尿病性视网膜病变眼底图像。ConvNextTiny在以大多数指标识别大多数所检查的眼部疾病方面取得了最佳结果。总体准确率为80.46±1.48。具体准确率值分别为：正常眼底为80.01±1.10，青光眼为97.20±0.66，年龄相关性黄斑变性为98.14±0.31，糖尿病性视网膜病变为80.66±1.27。设计了一种适用于老龄化社会中最常见视网膜疾病的筛查模型。该模型是在一个多样的、组合的大型数据集上开发的，这使得所获得的结果偏差更小且更具普遍性。
