用混沌变换替代随机掩码，提升医学图像自监督学习效果
Attention-Based Chaotic Self-Supervision for Medical Image Classification
- 用混沌变换破坏图像，让模型逆向重建以学习鲁棒特征
- 在皮肤癌和糖尿病视网膜病变数据集上准确率超90%、F1值超74%
- 适合需要少标注数据的医疗图像分类任务
医学图像分类的深度学习模型通常依赖大规模标注数据或ImageNet预训练。自监督学习（SSL）成为替代方案，但常见的掩码自编码器（MAE）可能因随机掩码破坏精细诊断特征。本文提出新型自监督预训练策略——混沌去噪自编码器（CDAE）。不采用掩码，而是对输入图像施加混沌变换，让自编码器重建原图，迫使编码器通过“逆混沌”学习鲁棒的领域特异性特征。此外，设计注意力融合机制，结合CDAE训练的编码器与标准编码器，兼顾通用与领域特征。在ISIC 2018（皮肤病变）和APTO 2019（糖尿病视网膜病变）两个公开数据集上评估，模型在ISIC 2018上达到0.9221准确率和0.8530 F1-macro，在APTO 2019上达0.8644准确率和0.7433 F1-macro，验证了方法有效性。
原文摘要 · Abstract (English)
Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful alternative, yet common methods like masked autoencoders (MAEs) may inadvertently destroy fine-grained diagnostic features by using random masking. In this paper, we propose a novel SSL pre-training strategy, the Chaotic Denoising Autoencoder (CDAE). Instead of masking, we apply a chaotic transformation to the input image, tasking an autoencoder to reconstruct the original. We hypothesize this forces the encoder to learn robust, domain-specific features by "inverting the chaos". Furthermore, we propose an attentive fusion mechanism that combines features from our CDAE-trained encoder with a standard encoder, leveraging the strengths of both general and domain-specific representations. Our method is evaluated on two public medical datasets: ISIC 2018 (skin lesions) and APTOS 2019 (diabetic retinopathy). The proposed model achieves high performance, with an accuracy of 0.9221 and an F1-macro of 0.8530 on ISIC 2018, and an accuracy of 0.8644 and F1-macro of 0.7433 on APTOS 2019, demonstrating the efficacy of our approach.
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。