Banerjee Rohan, Mujib Rakhshanda, Sanyal Prayas, Chakraborti Tapabrata, Saha Sanjoy Kumar
Jadavpur University, Kolkata, India.
Heritage Institute of Technology, Kolkata, India.
Med Biol Eng Comput. 2025 Apr;63(4):959-974. doi: 10.1007/s11517-024-03250-5. Epub 2024 Dec 14.
It has been shown in recent years that a range of optical diseases have early manifestation in retinal fundus images. It is becoming increasingly important to separate the regions of interest (RoI) upfront in the automated classification pipeline in order to ensure the alignment of the disease diagnosis with clinically relevant visual features. In this work, we introduce Pan-Ret, a semi-supervised framework which starts with locating the abnormalities in the biomedically relevant RoIs of a retinal image in an "annotation-agnostic" fashion. It does so by leveraging an anomaly detection setup using parallel autoencoders that are trained only on healthy population initially. Then, the anomalous images are separated based on the RoIs using a fully interpretable classifier like support vector machine (SVM). Experimental results show that the proposed approach yields an overall F1-score of 0.95 and 0.96 in detecting abnormalities on two different public datasets covering a diverse range of retinal diseases including diabetic retinopathy, hypertensive retinopathy, glaucoma, age-related macular degeneration, and several more in a staged manner. Thus, the work presents a milestone towards a pan-retinal disease diagnostic pipeline that can not only cater to the current set of disease classes, but has the capacity of adding further classes down the line. This is due to an anomaly detection style one-class learning setup of the deep autoencoder piece of the proposed pipeline, thus improving the generalizability of this approach compared to usual fully supervised competitors. This is also expected to increase the practical translational potential of Pan-Ret in a real-life scalable clinical setting.
近年来的研究表明，一系列眼部疾病在视网膜眼底图像中会有早期表现。在自动分类流程中预先分离出感兴趣区域（RoI）变得越来越重要，以确保疾病诊断与临床相关视觉特征相匹配。在这项工作中，我们引入了Pan-Ret，这是一个半监督框架，它以“无需标注”的方式开始定位视网膜图像中与生物医学相关的RoI中的异常。它通过利用一种异常检测设置来实现，该设置使用并行自动编码器，这些编码器最初仅在健康人群上进行训练。然后，使用支持向量机（SVM）等完全可解释的分类器根据RoI分离出异常图像。实验结果表明，在两个不同的公共数据集上检测异常时（这些数据集涵盖了包括糖尿病性视网膜病变、高血压性视网膜病变、青光眼、年龄相关性黄斑变性等多种视网膜疾病），所提出的方法以分阶段的方式分别产生了0.95和0.96的总体F1分数。因此，这项工作朝着全视网膜疾病诊断流程迈出了里程碑式的一步，该流程不仅可以适应当前的疾病类别集，而且有能力在未来增加更多类别。这是由于所提出的管道中深度自动编码器部分采用了异常检测风格的单类学习设置，因此与通常的完全监督竞争对手相比，提高了这种方法的通用性。这也有望增加Pan-Ret在实际可扩展临床环境中的实际转化潜力。
