目的:开发一种VisionTransformer模型,以基于光学相干断层扫描(OCT)图像检测糖尿病性黄斑病变(DM)的不同阶段。
方法:删除质量差的图像后,我们从武汉大学人民医院眼科中心共提取了3319张OCT图像,并将这些图像以7:3的比例随机分为训练集和验证集.回顾性收集2016年至2022年DM患者的所有黄斑横断面扫描OCT图像。DM的OCT阶段之一,包括早期糖尿病性黄斑水肿(DME),先进的DME,严重的DME和萎缩性黄斑病变,被标记在收集的图像上,分别。训练基于VisionTransformer的深度学习(DL)模型以检测DM的四个OCT分级。
结果:我们论文中提出的模型可以提供令人印象深刻的检测性能。我们达到了82.00%的准确率,F1得分为83.11%,受试者工作特征曲线下面积(AUC)为0.96。用于检测四个OCT分级的AUC(即,早期DME,先进的DME,重度DME和萎缩性黄斑病变)分别为0.96、0.95、0.87和0.98,准确率为90.87%,89.96%,94.42%和95.13%,分别,精度为88.46%,80.31%,89.42%和87.74%,分别,灵敏度为87.03%,88.18%,63.39%和89.42%,分别,特异性为93.02%,90.72%,98.40%和96.66%,F1得分为87.74%,84.06%,88.18%和88.57%,分别。
结论:我们基于VisionTransformer的DL模型在检测DM的OCT分级方面表现出相对较高的准确性,这可以帮助患者进行初步筛查,以确定患有严重疾病的人群。这些患者需要进一步检查才能准确诊断,及时治疗,取得良好的视力预后。这些结果强调了人工智能在未来协助临床医生制定DM治疗策略方面的潜力。
To develop a Vision Transformer model to detect different stages of diabetic maculopathy (DM) based on optical coherence tomography (OCT) images.
After removing images with poor quality, a total of 3319 OCT images were extracted from the Eye Center of the Renmin Hospital of Wuhan University and randomly split the images into training and validation sets in a 7:3 ratio. All macular cross-sectional scan OCT images were collected retrospectively from the eyes of DM patients from 2016 to 2022. One of the OCT stages of DM, including early diabetic macular oedema (DME), advanced DME, severe DME and atrophic maculopathy, was labelled on the collected images, respectively. A deep learning (DL) model based on Vision Transformer was trained to detect four OCT grading of DM.
The model proposed in our paper can provide an impressive detection performance. We achieved an accuracy of 82.00%, an F1 score of 83.11%, an area under the receiver operating characteristic curve (AUC) of 0.96. The AUC for the detection of four OCT grading (ie, early DME, advanced DME, severe DME and atrophic maculopathy) was 0.96, 0.95, 0.87 and 0.98, respectively, with an accuracy of 90.87%, 89.96%, 94.42% and 95.13%, respectively, a precision of 88.46%, 80.31%, 89.42% and 87.74%, respectively, a sensitivity of 87.03%, 88.18%, 63.39% and 89.42%, respectively, a specificity of 93.02%, 90.72%, 98.40% and 96.66%, respectively and an F1 score of 87.74%, 84.06%, 88.18% and 88.57%, respectively.
Our DL model based on Vision Transformer demonstrated a relatively high accuracy in the detection of OCT grading of DM, which can help with patients in a preliminary screening to identify groups with serious conditions. These patients need a further test for an accurate diagnosis, and a timely treatment to obtain a good visual prognosis. These results emphasised the potential of artificial intelligence in assisting clinicians in developing therapeutic strategies with DM in the future.