胸部X光片长尾多标签分类的技巧集合
Bag of Tricks for Long-Tailed Multi-Label Classification on Chest X-Rays
AI总结：
针对胸部X光片长尾多标签分类难题，本文整合数据增强、特征提取、分类器、损失再加权及外部数据等策略，并结合测试时增强与集成，在CXR-LT竞赛测试集上取得0.349 mAP、前五名。
摘要：
由于胸部放射影像本身具有长尾和多标签特性，其临床分类对标准机器学习算法而言尤其具有挑战性。然而，很少有研究同时考虑类别不平衡与标签共现所带来的耦合挑战，这限制了它们在真实场景中提升胸部X光片（CXR）诊断价值的能力。此外，随着预训练技术的普及，如何将这些新范式融入现有框架仍缺乏系统性研究。本技术报告简要介绍了我们在ICCV CVAMD 2023 CXR-LT竞赛中的解决方案。我们通过实验探究了整合多种先进设计对CXR诊断的有效性，这些设计涉及数据增强、特征提取器、分类器设计、损失函数再加权、外部数据补充等方面。此外，我们通过简单的测试时数据增强和模型集成提升了性能。我们的框架最终在竞赛测试集上取得0.349 mAP，位列前五名。
英文摘要：
Clinical classification of chest radiography is particularly challenging for standard machine learning algorithms due to its inherent long-tailed and multi-label nature. However, few attempts take into account the coupled challenges posed by both the class imbalance and label co-occurrence, which hinders their value to boost the diagnosis on chest X-rays (CXRs) in the real-world scenarios. Besides, with the prevalence of pretraining techniques, how to incorporate these new paradigms into the current framework lacks of the systematical study. This technical report presents a brief description of our solution in the ICCV CVAMD 2023 CXR-LT Competition. We empirically explored the effectiveness for CXR diagnosis with the integration of several advanced designs about data augmentation, feature extractor, classifier design, loss function reweighting, exogenous data replenishment, etc. In addition, we improve the performance through simple test-time data augmentation and ensemble. Our framework finally achieves 0.349 mAP on the competition test set, ranking in the top five.
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。
