To enable deep learning-based computer-aided diagnosis to achieve excellent performance in differentiating benign and malignant breast tumors in ultrasound images, a large number of labeled training samples must be collected. However, it is difficult to acquire sufficient samples due to the high costs of data collection and labeling. Fortunately, breast ultrasound images have two labels from different sources of domain knowledge: the biopsy results are “clean” labels, and the Breast Imaging Reporting and Data System (BI-RADS) score functions as a “noisy” label. Based on these two label types, we propose a multitask classification method based on label distribution correction (MTLC-Net). In our method, we propose different tasks to address the noisy and clean labels. Specifically, we propose a label distribution correction task for noisy labels that includes jointly training the network parameters and soft labels. The model is generalizable and robust by correcting the noisy label distribution based on the BI-RADS score, and it extracts knowledge from the noisy label task to improve the learning in the clean-label task. We conducted extensive comparisons with existing methods. Our method achieved a classification accuracy of 75.8%, a precision of 73.0%, a recall of 80.1% and an F1 score of 0.764—results that are significantly better than those of the existing state-of-the-art methods for differentiating benign and malignant breast tumors in ultrasound images.

为了使基于深度学习的计算机辅助诊断在区分超声图像中的良性和恶性乳腺肿瘤方面获得出色的性能，必须收集大量标记的训练样本。但是，由于数据收集和标记的高昂成本，很难获得足够的样本。幸运的是，乳房超声图像具有来自不同领域知识来源的两个标签：活检结果是“干净”标签，而乳房成像报告和数据系统（BI-RADS）评分则充当“嘈杂”标签。基于这两种标签类型，我们提出了一种基于标签分布校正（MTLC-Net）的多任务分类方法。在我们的方法中，我们提出了不同的任务来解决嘈杂和干净的标签。具体来说，我们提出了一种针对嘈杂标签的标签分布校正任务，其中包括联合训练网络参数和软标签。通过基于BI-RADS分数校正噪声标签分布，该模型具有通用性和鲁棒性，并且该模型从噪声标签任务中提取知识，以改善清洁标签任务中的学习。我们与现有方法进行了广泛的比较。我们的方法实现了75.8％的分类精度，73.0％的精度，80.1％的召回率以及0.764的F1分数，其结果明显优于现有的区分良性和良性的最新方法。超声图像中的恶性乳腺肿瘤。通过基于BI-RADS分数校正噪声标签分布，该模型具有通用性和鲁棒性，并且该模型从噪声标签任务中提取知识，以改善清洁标签任务中的学习。我们与现有方法进行了广泛的比较。我们的方法实现了75.8％的分类精度，73.0％的精度，80.1％的召回率以及0.764的F1分数，其结果明显优于现有的区分良性和良性的最新方法。超声图像中的恶性乳腺肿瘤。通过基于BI-RADS分数校正噪声标签分布，该模型具有通用性和鲁棒性，并且该模型从噪声标签任务中提取知识，以改善清洁标签任务中的学习。我们与现有方法进行了广泛的比较。我们的方法实现了75.8％的分类精度，73.0％的精度，80.1％的召回率以及0.764的F1分数，其结果明显优于现有的区分良性和良性的最新方法。超声图像中的恶性乳腺肿瘤。