arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.14919eess.IVcs.CV
收藏

通过利用多个分辨率识别和消除细分网络中的偏见

Identifying and Combating Bias in Segmentation Networks by leveraging multiple resolutions

German Center for Neurodegenerative Diseases (DZNE)(德国神经退行性疾病中心(DZNE));Harvard Medical School(哈佛医学院)

Leonie Henschel, David Kügler, Derek S Andrews, Christine W Nordahl, Martin Reuter

摘要:

偏见的探索对深度学习管道在医疗环境中的透明度和适用性具有重大影响,但迄今为止研究得还不够充分。在本文中,我们考虑两个单独的组,训练数据仅在不同的图像分辨率。对于组H,可用的图像和标签处于优选的高分辨率,而对于组L,仅存在弃用的较低分辨率数据。我们分析如何在数据分布中的分辨率偏差传播到系统偏向的预测组L在更高的分辨率。我们的研究结果表明,单分辨率训练设置导致体积组差异的显著损失,这些差异转化为DSC测量的错误分割和低分辨率组的后续分类失败。我们进一步探讨了如何使用不同分辨率的训练数据来对抗这种系统性偏差。具体来说,我们调查的影响,图像resstering,规模增强和分辨率的独立性,并证明偏见可以有效地减少与多分辨率的方法。

英文摘要:

Exploration of bias has significant impact on the transparency and applicability of deep learning pipelines in medical settings, yet is so far woefully understudied. In this paper, we consider two separate groups for which training data is only available at differing image resolutions. For group H, available images and labels are at the preferred high resolution while for group L only deprecated lower resolution data exist. We analyse how this resolution-bias in the data distribution propagates to systematically biased predictions for group L at higher resolutions. Our results demonstrate that single-resolution training settings result in significant loss of volumetric group differences that translate to erroneous segmentations as measured by DSC and subsequent classification failures on the low resolution group. We further explore how training data across resolutions can be used to combat this systematic bias. Specifically, we investigate the effect of image resampling, scale augmentation and resolution independence and demonstrate that biases can effectively be reduced with multi-resolution approaches.

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。

↑