Shen Yiqiu, Wu Nan, Phang Jason, Park Jungkyu, Kim Gene, Moy Linda, Cho Kyunghyun, Geras Krzysztof J
Center for Data Science, New York University, New York, USA.
Department of Radiology, New York University School of Medicine, New York, USA.
Mach Learn Med Imaging. 2019 Oct;11861:18-26. doi: 10.1007/978-3-030-32692-0_3. Epub 2019 Oct 10.
Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.
为自然图像视觉分类任务设计的深度学习模型在医学图像分析中已变得很普遍。然而，医学图像在许多方面与典型自然图像不同，比如分辨率显著更高且感兴趣区域更小。此外，全局结构和局部细节在医学图像分析任务中都起着重要作用。为解决医学图像的这些独特特性，我们提出一种神经网络，它能够利用来自全局显著性图和多个局部图像块的信息对乳腺癌病变进行分类。所提出的模型优于基于ResNet的基线模型，并在筛查乳腺钼靶图像解读中达到了放射科医生级别的性能。尽管我们的模型仅使用图像级标签进行训练，但它能够生成像素级显著性图，这些图可提供可能恶性病变的定位信息。
