用对抗注意力提升肺病诊断公平性，缓解性别偏差问题。
Fair Lung Disease Diagnosis from Chest CT via Gender-Adversarial Attention Multiple Instance Learning
- 基于卷积神经网络的多实例学习，自动筛选关键切片
- 在四个类别上平均宏F1达0.685，最高单折0.759
- 特别适合关注医疗公平性和模型鲁棒性的研究者
我们提出一种面向胸部CT图像的多类别肺病诊断公平性框架，用于参加CVPR 2026年PHAROS-AIF-MIH研讨会的公平疾病诊断挑战赛。任务需将CT扫描分为四类：健康、新冠、腺癌和鳞状细胞癌，评估指标为按性别划分的宏F1均值，明确惩罚性别不公的预测结果。针对跨数百切片的病灶信号稀疏及疾病类别与性别组合下的严重人口统计学失衡问题，我们设计了一种基于ConvNeXt主干的注意力多实例学习模型，无需切片级标注即可识别诊断相关切片，并引入梯度反转层（GRL）以对抗性方式抑制表征中的性别预测结构。训练中采用焦点损失加标签平滑，按（疾病类别，性别）联合分层进行交叉验证，并对最稀缺子组进行针对性过采样。推理阶段通过五折模型集成、水平翻转测试时增强与软对数投票，结合留出集阈值优化提升鲁棒性。最终模型在验证集上平均得分0.685（标准差0.030），最佳单折达0.759。所有训练与推理代码已公开于https://github.com/ADE-17/cvpr-fair-chest-ct。
原文摘要 · Abstract (English)
We present a fairness-aware framework for multi-class lung disease diagnosis from chest CT volumes, developed for the Fair Disease Diagnosis Challenge at the PHAROS-AIF-MIH Workshop (CVPR 2026). The challenge requires classifying CT scans into four categories -- Healthy, COVID-19, Adenocarcinoma, and Squamous Cell Carcinoma -- with performance measured as the average of per-gender macro F1 scores, explicitly penalizing gender-inequitable predictions. Our approach addresses two core difficulties: the sparse pathological signal across hundreds of slices, and a severe demographic imbalance compounded across disease class and gender. We propose an attention-based Multiple Instance Learning (MIL) model on a ConvNeXt backbone that learns to identify diagnostically relevant slices without slice-level supervision, augmented with a Gradient Reversal Layer (GRL) that adversarially suppresses gender-predictive structure in the learned scan representation. Training incorporates focal loss with label smoothing, stratified cross-validation over joint (class, gender) strata, and targeted oversampling of the most underrepresented subgroup. At inference, all five-fold checkpoints are ensembled with horizontal-flip test-time augmentation via soft logit voting and out-of-the-fold threshold optimization for robustness. Our model achieves a mean validation competition score of 0.685 (std - 0.030), with the best single fold reaching 0.759. All training and inference code is publicly available at https://github.com/ADE-17/cvpr-fair-chest-ct
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。