arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.05798cs.CVcs.AIcs.LG
收藏

多视图超复数学习用于乳腺癌筛查

Multi-View Hypercomplex Learning for Breast Cancer Screening

Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome(信息工程、电子与电信系(DIET),罗马萨皮恩扎大学)

Eleonora Lopez, Eleonora Grassucci, Danilo Comminiello

AI总结:

针对多视图乳腺癌筛查,提出基于参数化超复数神经网络的多视图超复数学习范式,通过超复数代数捕获视图间关系,提出PHResNets、PHYBOnet和PHYSEnet架构,性能优于现有方法并具泛化性。

摘要:

放射科医生通过联合分析所有四个视图来解读乳腺X线摄影检查,因为视图之间的相关性对于准确诊断至关重要。近期方法采用专用融合模块来捕获这些依赖关系,但这些方法常常受到视图主导、训练不稳定和计算开销的阻碍。为了解决这些挑战,我们引入了多视图超复数学习,这是一种基于参数化超复数神经网络(PHNNs)的新型多视图乳腺癌分类学习范式。得益于超复数代数,我们的模型能够内在捕获视图内和视图间的关系。我们提出了用于双视图检查的PHResNets,以及两种互补的四视图架构:PHYBOnet(针对效率优化)和PHYSEnet(针对准确性优化)。大量实验表明,我们的方法持续优于最先进的多视图模型,同时还能泛化到其他放射影像模态和任务,如胸部X光片的疾病分类和多模态脑肿瘤分割。完整代码和预训练模型可在 https://github.com/ispamm/PHBreast 获取。

英文摘要:

Radiologists interpret mammography exams by jointly analyzing all four views, as correlations among them are crucial for accurate diagnosis. Recent methods employ dedicated fusion blocks to capture such dependencies, but these are often hindered by view dominance, training instability, and computational overhead. To address these challenges, we introduce multi-view hypercomplex learning, a novel learning paradigm for multi-view breast cancer classification based on parameterized hypercomplex neural networks (PHNNs). Thanks to hypercomplex algebra, our models intrinsically capture both intra- and inter-view relations. We propose PHResNets for two-view exams and two complementary four-view architectures: PHYBOnet, optimized for efficiency, and PHYSEnet, optimized for accuracy. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art multi-view models, while also generalizing across radiographic modalities and tasks such as disease classification from chest X-rays and multimodal brain tumor segmentation. Full code and pretrained models are available at https://github.com/ispamm/PHBreast.

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。

↑