Kaothanthong Natsuda, Wanichwecharungruang Boonsong, Chantangphol Pantid, Pattanapongpaiboon Warisara, Theeramunkong Thanaruk
Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand.
Department of Ophthalmology, Rajavithi Hospital and Rangsit Medical College, Bangkok, Thailand.
Sci Rep. 2024 Dec 28;14(1):31157. doi: 10.1038/s41598-024-82327-5.
Ultrasound biomicroscopy (UBM) is the standard for diagnosing plateau iris, but its limited accessibility in routine clinical settings presents challenges. While anterior segment optical coherence tomography (AS-OCT) is more convenient, its effectiveness in detecting plateau iris is limited. Previous research has demonstrated that combining UBM and AS-OCT image pairs through neural style transfer has improved classification accuracy. However, obtaining paired images is impractical in everyday practice. In this study, we propose a novel semi-supervised approach that eliminates the need for paired images. A generative model learns to distinguish plateau and non-plateau features from UBM images. AS-OCT images are input into the generator, which attempts to transform them into corresponding UBM images. The model's performance is measured by loss values, representing the difficulty of transforming AS-OCT images, which are then used to predict plateau iris. The classification baseline, which applies AS-OCT solely without the style-transfer of UBM information, obtained 52.72% sensitivity, 60.82% specificity, and 57.89% accuracy for external validation; in contrast, the classification with neural style transfer of the image pairs respectively obtained 94.54%, 100.00%, and 98.03%, whereas the semi-supervised approach using loss values classification obtained 93.10%, 93.13%, and 93.12%, respectively. This semi-supervised transfer learning model presents a novel technique for detecting plateau iris with AS-OCT.
超声生物显微镜检查（UBM）是诊断高原虹膜的标准方法，但在常规临床环境中其可及性有限，带来了挑战。虽然眼前节光学相干断层扫描（AS - OCT）更便捷，但其检测高原虹膜的有效性有限。先前的研究表明，通过神经风格迁移将UBM和AS - OCT图像对相结合可提高分类准确率。然而，在日常实践中获取配对图像并不实际。在本研究中，我们提出了一种新颖的半监督方法，该方法无需配对图像。一个生成模型学习从UBM图像中区分高原和非高原特征。将AS - OCT图像输入到生成器中，生成器试图将它们转换为相应的UBM图像。通过损失值来衡量模型的性能，损失值代表转换AS - OCT图像的难度，然后用于预测高原虹膜。仅应用AS - OCT而不进行UBM信息风格迁移的分类基线在外部验证中获得了52.72%的灵敏度、60.82%的特异度和57.89%的准确率；相比之下，图像对的神经风格迁移分类分别获得了94.54%、100.00%和98.03%，而使用损失值分类的半监督方法分别获得了93.10%、93.13%和93.12%。这种半监督迁移学习模型为利用AS - OCT检测高原虹膜提供了一种新技术。
