Medical Image Classification
Medical image classification uses machine learning to automatically categorize medical images (e.g., X-rays, MRIs) for diagnosis and treatment planning. Current research emphasizes improving model generalizability across diverse datasets and handling challenges like class imbalance and noisy labels, often employing convolutional neural networks (CNNs), vision transformers (ViTs), and foundation models adapted for medical data. These advancements aim to enhance diagnostic accuracy, efficiency, and accessibility, particularly in resource-constrained settings, while also addressing issues of model interpretability and fairness.
Papers
Interpreting and Correcting Medical Image Classification with PIP-Net
Meike Nauta, Johannes H. Hegeman, Jeroen Geerdink, Jörg Schlötterer, Maurice van Keulen, Christin Seifert
Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition
Jia-Xin Zhuang, Jiabin Cai, Jianguo Zhang, Wei-shi Zheng, Ruixuan Wang
Label-noise-tolerant medical image classification via self-attention and self-supervised learning
Hongyang Jiang, Mengdi Gao, Yan Hu, Qiushi Ren, Zhaoheng Xie, Jiang Liu
MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification
Dequan Wang, Xiaosong Wang, Lilong Wang, Mengzhang Li, Qian Da, Xiaoqiang Liu, Xiangyu Gao, Jun Shen, Junjun He, Tian Shen, Qi Duan, Jie Zhao, Kang Li, Yu Qiao, Shaoting Zhang