arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.17157cs.CVq-bio.TO
收藏

在深度学习中建立全切片图像预测与诊断证据子区域之间的因果关系

Establishing Causal Relationship Between Whole Slide Image Predictions and Diagnostic Evidence Subregions in Deep Learning

Northeastern University(东北大学);Chinese Academy of Sciences(中国科学院)

Tianhang Nan, Yong Ding, Hao Quan, Deliang Li, Lisha Li, Guanghong Zhao, Xiaoyu Cui

AI总结:

本文提出CI-MIL方法,通过特征蒸馏与随机傅里叶特征空间中的重加权校正特征分布偏差,在不依赖像素级标注的情况下建立WSI诊断与证据子区域间的因果关系,并在两个病理数据集上取得领先性能。

摘要:

由于缺乏细粒度标注指导,当前的多实例学习(Multiple Instance Learning, MIL)难以像全监督学习那样,在全切片图像(Whole Slide Image, WSI)诊断与证据子图像之间建立稳健的因果关系,因此大量噪声图像可能削弱网络的预测能力。所提出的因果推断多实例学习(Causal Inference Multiple Instance Learning, CI-MIL)利用分布外泛化来减少MIL网络对子图像的识别混淆,且无需像素级标注。具体而言,引入特征蒸馏以粗略识别病变图像块的特征表示;随后,在随机傅里叶特征空间中,对这些特征进行重新加权以最小化互相关,从而有效校正特征分布偏差。这些过程降低了将预测结果追溯回图像块时的不确定性。由于网络能够更清晰地识别预测诊断与诊断证据图像之间的因果关系,预测诊断变得更加直接和可靠。实验结果表明,CI-MIL优于现有最先进方法,在Camelyon16数据集(乳腺癌)上达到92.25%的准确率和95.28%的AUC,在TCGA-NSCLC数据集(非小细胞肺癌)上达到94.29%的准确率和98.07%的AUC。此外,CI-MIL展现出优越的可解释性,其所选区域与真实标注高度一致,有望为病理学家提供更可靠的诊断辅助。

英文摘要:

Due to the lack of fine-grained annotation guidance, current Multiple Instance Learning (MIL) struggles to establish a robust causal relationship between Whole Slide Image (WSI) diagnosis and evidence sub-images, just like fully supervised learning. So many noisy images can undermine the network's prediction. The proposed Causal Inference Multiple Instance Learning (CI-MIL), uses out-of-distribution generalization to reduce the recognition confusion of sub-images by MIL network, without requiring pixelwise annotations. Specifically, feature distillation is introduced to roughly identify the feature representation of lesion patches. Then, in the random Fourier feature space, these features are re-weighted to minimize the cross-correlation, effectively correcting the feature distribution deviation. These processes reduce the uncertainty when tracing the prediction results back to patches. Predicted diagnoses are more direct and reliable because the causal relationship between them and diagnostic evidence images is more clearly recognized by the network. Experimental results demonstrate that CI-MIL outperforms state-of-the-art methods, achieving 92.25% accuracy and 95.28% AUC on the Camelyon16 dataset (breast cancer), while 94.29% accuracy and 98.07% AUC on the TCGA-NSCLC dataset (non-small cell lung cancer). Additionally, CI-MIL exhibits superior interpretability, as its selected regions demonstrate high consistency with ground truth annotations, promising more reliable diagnostic assistance for pathologists.

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。

↑