Fujioka Tomoyuki, Kubota Kazunori, Mori Mio, Kikuchi Yuka, Katsuta Leona, Kimura Mizuki, Yamaga Emi, Adachi Mio, Oda Goshi, Nakagawa Tsuyoshi, Kitazume Yoshio, Tateishi Ukihide
Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan.
Department of Radiology, Dokkyo Medical University, 880 Kitakobayashi, Mibu, Shimotsugagun, Tochigi 321-0293, Japan.
Diagnostics (Basel). 2020 Jul 4;10(7):456. doi: 10.3390/diagnostics10070456.
We aimed to use generative adversarial network (GAN)-based anomaly detection to diagnose images of normal tissue, benign masses, or malignant masses on breast ultrasound. We retrospectively collected 531 normal breast ultrasound images from 69 patients. Data augmentation was performed and 6372 (531 × 12) images were available for training. Efficient GAN-based anomaly detection was used to construct a computational model to detect anomalous lesions in images and calculate abnormalities as an anomaly score. Images of 51 normal tissues, 48 benign masses, and 72 malignant masses were analyzed for the test data. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of this anomaly detection model were calculated. Malignant masses had significantly higher anomaly scores than benign masses ( < 0.001), and benign masses had significantly higher scores than normal tissues ( < 0.001). Our anomaly detection model had high sensitivities, specificities, and AUC values for distinguishing normal tissues from benign and malignant masses, with even greater values for distinguishing normal tissues from malignant masses. GAN-based anomaly detection shows high performance for the detection and diagnosis of anomalous lesions in breast ultrasound images.
我们旨在使用基于生成对抗网络（GAN）的异常检测技术来诊断乳腺超声检查中的正常组织、良性肿块或恶性肿块图像。我们回顾性收集了69例患者的531张正常乳腺超声图像。进行了数据增强，共有6372（531×12）张图像可用于训练。使用基于高效GAN的异常检测构建计算模型，以检测图像中的异常病变并将异常计算为异常分数。对51张正常组织、48个良性肿块和72个恶性肿块的图像进行测试数据分析。计算了该异常检测模型的灵敏度、特异性和受试者操作特征曲线下面积（AUC）。恶性肿块的异常分数显著高于良性肿块（<0.001），良性肿块的分数显著高于正常组织（<0.001）。我们的异常检测模型在区分正常组织与良性和恶性肿块方面具有较高的灵敏度、特异性和AUC值，在区分正常组织与恶性肿块方面的值更高。基于GAN的异常检测在乳腺超声图像中异常病变的检测和诊断方面表现出高性能。
