用异常数据提升医学图像分割精度，无需额外标注或修改模型
Out-of-distribution data supervision towards biomedical semantic segmentation
- 引入异常数据监督机制，无需外部数据或新标注
- 在Lizard数据集上显著减少像素误分类，提升分割效果
- 首次实现仅用异常数据训练出76.1% mIoU的医学分割模型
医学图像分割网络在有限且不完美的医疗数据上训练时，容易出现前景与背景像素误判。受异常数据（OoD）在其他视觉任务中的强表现启发，我们提出数据中心框架Med-OoD，通过引入异常数据监督来解决此问题，且无需外部数据源、特征正则化目标或额外标注。该方法可无缝集成到现有分割网络中，无需修改架构。大量实验表明，Med-OoD能有效防止多种分割网络在医学图像上的像素误分类，并在Lizard数据集上取得显著性能提升。我们还提出一种全新训练范式：完全使用异常数据（无前景类别标签）进行训练，令人惊讶地达到了76.1%的mIoU测试结果。我们希望这一范式能引发对异常数据作用的重新思考。代码已公开于https://github.com/StudioYG/Med-OoD。
原文摘要 · Abstract (English)
Biomedical segmentation networks easily suffer from the unexpected misclassification between foreground and background objects when learning on limited and imperfect medical datasets. Inspired by the strong power of Out-of-Distribution (OoD) data on other visual tasks, we propose a data-centric framework, Med-OoD to address this issue by introducing OoD data supervision into fully-supervised biomedical segmentation with none of the following needs: (i) external data sources, (ii) feature regularization objectives, (iii) additional annotations. Our method can be seamlessly integrated into segmentation networks without any modification on the architectures. Extensive experiments show that Med-OoD largely prevents various segmentation networks from the pixel misclassification on medical images and achieves considerable performance improvements on Lizard dataset. We also present an emerging learning paradigm of training a medical segmentation network completely using OoD data devoid of foreground class labels, surprisingly turning out 76.1% mIoU as test result. We hope this learning paradigm will attract people to rethink the roles of OoD data. Code is made available at https://github.com/StudioYG/Med-OoD.
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。