自监督特征在医学图像分类任务中的可迁移性如何？
How Transferable Are Self-supervised Features in Medical Image Classification Tasks?
AI总结：
本文评估了ImageNet自监督预训练特征在医学图像分类任务中的可迁移性，并提出了融合多模型预训练嵌入的端到端迁移学习方法DVME，显著提升了下游任务性能。
摘要：
迁移学习已成为缓解医学分类任务中标注数据缺乏的标准做法。尽管使用有监督 ImageNet 预训练特征对下游任务进行微调的方法直接且在许多研究中被广泛探讨，但对自监督预训练有用性的研究却很少。本文通过评估在选定的医学分类任务上，使用三种自监督技术（SimCLR、SwAV 和 DINO）预训练特征初始化的模型的性能，来评估 ImageNet 自监督预训练的可迁移性。所选任务涵盖前哨腋窝淋巴结图像中的肿瘤检测、眼底图像中的糖尿病视网膜病变分类，以及胸部 X 光图像中的多种病理状况分类。我们证明，自监督预训练模型比其有监督对应模型产生更丰富的嵌入，从线性评估和微调的角度来看，这有利于下游任务。例如，在数据极小子集上的线性评估中，我们观察到糖尿病视网膜病变分类任务的 Kappa 分数提高了 14.79%，肿瘤分类任务的 AUC 提高了 5.4%，肺炎检测的 AUC 提高了 7.03%，胸部 X 光中病理状况检测的 AUC 提高了 9.4%。此外，我们引入了 Dynamic Visual Meta-Embedding (DVME) 作为一种端到端的迁移学习方法，融合多个模型的预训练嵌入。我们表明，与使用单一预训练模型的方法相比，DVME 获得的集合表示显著提升了选定任务的性能，并且可以推广到预训练模型的任意组合。
英文摘要：
Transfer learning has become a standard practice to mitigate the lack of labeled data in medical classification tasks. Whereas finetuning a downstream task using supervised ImageNet pretrained features is straightforward and extensively investigated in many works, there is little study on the usefulness of self-supervised pretraining. In this paper, we assess the transferability of ImageNet self-supervisedpretraining by evaluating the performance of models initialized with pretrained features from three self-supervised techniques (SimCLR, SwAV, and DINO) on selected medical classification tasks. The chosen tasks cover tumor detection in sentinel axillary lymph node images, diabetic retinopathy classification in fundus images, and multiple pathological condition classification in chest X-ray images. We demonstrate that self-supervised pretrained models yield richer embeddings than their supervised counterpart, which benefits downstream tasks in view of both linear evaluation and finetuning. For example, in view of linear evaluation at acritically small subset of the data, we see an improvement up to 14.79% in Kappa score in the diabetic retinopathy classification task, 5.4% in AUC in the tumor classification task, 7.03% AUC in the pneumonia detection, and 9.4% in AUC in the detection of pathological conditions in chest X-ray. In addition, we introduce Dynamic Visual Meta-Embedding (DVME) as an end-to-end transfer learning approach that fuses pretrained embeddings from multiple models. We show that the collective representation obtained by DVME leads to a significant improvement in the performance of selected tasks compared to using a single pretrained model approach and can be generalized to any combination of pretrained models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
