arXiv 2407.176202024-07-24cs.CVcs.AI

CoMoTo：非配对跨模态病灶蒸馏提升断层合成中的乳腺病灶检测

CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis

Computer Vision and Robotics Institute, University of Girona（赫罗纳大学计算机视觉与机器人研究所）；The Hong Kong University of Science and Technology（香港科技大学）

Muhammad Alberb, Marawan Elbatel, Aya Elgebaly, Ricardo Montoya-del-Angel, Xiaomeng Li, Robert Martí

备注：: ADSMI @ MICCAI 2024

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出CoMoTo框架，利用非配对乳腺X线摄影数据，通过病灶特定知识蒸馏（LsKD）和模态内点对齐（ImPA）增强DBT模型训练，在低数据设置下将平均灵敏度提升7%。

摘要：

数字乳腺断层合成（DBT）是一种先进的乳腺成像模态，与传统乳腺X线摄影相比，具有更优的病灶检测准确性，但代价是读取时间更长。由于数据可用性有限和标注成本高昂，使用深度学习加速DBT病灶检测受到阻碍。解决这一问题的一个可能方案是利用更广泛可用的模态（如乳腺X线摄影）提供的信息，来增强DBT病灶检测。在本文中，我们提出了一个新框架CoMoTo，用于改进DBT中的病灶检测。该框架利用非配对乳腺X线摄影数据来增强DBT模型的训练，通过在推理时消除对乳腺X线摄影的需求提升了实用性。具体而言，我们提出了两个新组件：病灶特定知识蒸馏（LsKD）和模态内点对齐（ImPA）。LsKD选择性地将病灶特征从乳腺X线摄影教师模型蒸馏到DBT学生模型，忽略背景特征。ImPA通过在向学生模型蒸馏知识之前确保教师模型内病灶特征的对齐，进一步丰富了LsKD。我们的全面评估表明，CoMoTo优于传统的预训练和图像级KD，在低数据设置下将平均灵敏度提高了7%。我们的代码可在 https://github.com/Muhammad-Al-Barbary/CoMoTo 获取。

英文摘要：

Digital Breast Tomosynthesis (DBT) is an advanced breast imaging modality that offers superior lesion detection accuracy compared to conventional mammography, albeit at the trade-off of longer reading time. Accelerating lesion detection from DBT using deep learning is hindered by limited data availability and huge annotation costs. A possible solution to this issue could be to leverage the information provided by a more widely available modality, such as mammography, to enhance DBT lesion detection. In this paper, we present a novel framework, CoMoTo, for improving lesion detection in DBT. Our framework leverages unpaired mammography data to enhance the training of a DBT model, improving practicality by eliminating the need for mammography during inference. Specifically, we propose two novel components, Lesion-specific Knowledge Distillation (LsKD) and Intra-modal Point Alignment (ImPA). LsKD selectively distills lesion features from a mammography teacher model to a DBT student model, disregarding background features. ImPA further enriches LsKD by ensuring the alignment of lesion features within the teacher before distilling knowledge to the student. Our comprehensive evaluation shows that CoMoTo is superior to traditional pretraining and image-level KD, improving performance by 7% Mean Sensitivity under low-data setting. Our code is available at https://github.com/Muhammad-Al-Barbary/CoMoTo .

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。