用多视角注意力模型提升乳腺癌分类准确率
MamT$^4$: Multi-view Attention Networks for Mammography Cancer Classification
- 设计多视图注意力网络，综合四张乳腺影像进行诊断决策
- 在越南数字乳腺数据集上达84.0%的ROC-AUC和56.0%的F1分数
- 结合自研图像裁剪模型，提升病灶区域聚焦能力
本研究提出一种名为MamT$^4$的新方法，用于同时分析四张乳腺钼靶影像：单侧乳腺的一张视图及同侧另一视图、对侧乳腺两张视图。该方法模拟放射科医生全面审阅患者全套影像的实践。研究还提出基于ResNet-34的U-Net图像裁剪模型，有效去除图像伪影并聚焦乳腺区域。据我们所知，该方法在经裁剪预处理的越南数字乳腺影像数据集（VinDr-Mammo）上，首次实现84.0 ± 1.7的ROC-AUC与56.0 ± 1.3的F1分数。
原文摘要 · Abstract (English)
In this study, we introduce a novel method, called MamT$^4$, which is used for simultaneous analysis of four mammography images. A decision is made based on one image of a breast, with attention also devoted to three additional images: another view of the same breast and two images of the other breast. This approach enables the algorithm to closely replicate the practice of a radiologist who reviews the entire set of mammograms for a patient. Furthermore, this paper emphasizes the preprocessing of images, specifically proposing a cropping model (U-Net based on ResNet-34) to help the method remove image artifacts and focus on the breast region. To the best of our knowledge, this study is the first to achieve a ROC-AUC of 84.0 $\pm$ 1.7 and an F1 score of 56.0 $\pm$ 1.3 on an independent test dataset of Vietnam digital mammography (VinDr-Mammo), which is preprocessed with the cropping model.
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。