零样本学习实现罕见病诊断，无需标注数据也能精准识别眼病。
RURA-Net: A general disease diagnosis method based on Zero-Shot Learning
- 通过孪生网络找相似病，U-Net精分割病灶区域。
- 在外部数据集上准确率达83.95%，优于多数少样本模型。
- 适合标注成本高、数据稀缺的医疗场景，具实用价值。
深度学习模型训练依赖大量标注数据，但医学标注成本高昂，严重制约其在医疗领域的应用。本文提出一种基于零样本学习的通用疾病诊断方法：利用孪生神经网络寻找与目标疾病相似的疾病，通过U-Net模型精确分割关键病灶；再基于ResNet与层次聚类算法，在大量相似疾病样本上训练聚类模型，实现对目标疾病的近似诊断，成功完成零样本学习。为验证模型有效性，我们在CFP模态的眼科疾病数据集上进行评估，使用外部数据集测试，结果显示准确率=0.8395，精确率=0.8094，召回率=0.8463，F1分数=0.8274，AUC=0.9226，各项指标均超过多数少样本与单样本学习模型。结果表明该方法在标注数据稀缺的医疗场景中具有显著潜力和参考价值。
原文摘要 · Abstract (English)
The training of deep learning models relies on a large amount of labeled data. However, the high cost of medical labeling seriously hinders the development of deep learning in the medical field. Our study proposes a general disease diagnosis approach based on Zero-Shot Learning. The Siamese neural network is used to find similar diseases for the target diseases, and the U-Net segmentation model is used to accurately segment the key lesions of the disease. Finally, based on the ResNet-Agglomerative clustering algorithm, a clustering model is trained on a large number of sample data of similar diseases to obtain a approximate diagnosis of the target disease. Zero-Shot Learning of the target disease is then successfully achieved. To evaluate the validity of the model, we validated our method on a dataset of ophthalmic diseases in CFP modality. The external dataset was used to test its performance, and the accuracy=0.8395, precision=0.8094, recall=0.8463, F1 Score=0.8274, AUC=0.9226, which exceeded the indexes of most Few-Shot Learning and One-Shot Learning models. It proves that our method has great potential and reference value in the medical field, where annotation data is usually scarce and expensive to obtain.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。