Chen Qian-Qian, Lin Shu-Ting, Ye Jia-Yi, Tong Yun-Fei, Lin Shu, Cai Si-Qing
Department of Radiology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China.
Shanghai Yanghe Huajian Artificial Intelligence Technology Co. Ltd., Shanghai, China.
Front Oncol. 2023 Jun 2;13:1110657. doi: 10.3389/fonc.2023.1110657. eCollection 2023.
In order to explore the relationship between mammographic density of breast mass and its surrounding area and benign or malignant breast, this paper proposes a deep learning model based on C2FTrans to diagnose the breast mass using mammographic density.
This retrospective study included patients who underwent mammographic and pathological examination. Two physicians manually depicted the lesion edges and used a computer to automatically extend and segment the peripheral areas of the lesion (0, 1, 3, and 5 mm, including the lesion). We then obtained the mammary glands' density and the different regions of interest (ROI). A diagnostic model for breast mass lesions based on C2FTrans was constructed based on a 7: 3 ratio between the training and testing sets. Finally, receiver operating characteristic (ROC) curves were plotted. Model performance was assessed using the area under the ROC curve (AUC) with 95% confidence intervals (), sensitivity, and specificity.
In total, 401 lesions (158 benign and 243 malignant) were included in this study. The probability of breast cancer in women was positively correlated with age and mass density and negatively correlated with breast gland classification. The largest correlation was observed for age (r = 0.47). Among all models, the single mass ROI model had the highest specificity (91.8%) with an AUC = 0.823 and the perifocal 5mm ROI model had the highest sensitivity (86.9%) with an AUC = 0.855. In addition, by combining the cephalocaudal and mediolateral oblique views of the perifocal 5 mm ROI model, we obtained the highest AUC (AUC = 0.877 P < 0.001).
Deep learning model of mammographic density can better distinguish benign and malignant mass-type lesions in digital mammography images and may become an auxiliary diagnostic tool for radiologists in the future.
为了探究乳腺肿块及其周围区域的乳腺X线密度与乳腺良恶性之间的关系，本文提出一种基于C2FTrans的深度学习模型，利用乳腺X线密度诊断乳腺肿块。
这项回顾性研究纳入了接受乳腺X线和病理检查的患者。两名医生手动描绘病变边缘，并使用计算机自动扩展和分割病变的周边区域（0、1、3和5毫米，包括病变）。然后我们获得了乳腺密度和不同的感兴趣区域（ROI）。基于训练集和测试集7:3的比例构建了基于C2FTrans的乳腺肿块病变诊断模型。最后，绘制了受试者工作特征（ROC）曲线。使用ROC曲线下面积（AUC）及95%置信区间、灵敏度和特异度评估模型性能。
本研究共纳入401个病变（158个良性和243个恶性）。女性患乳腺癌的概率与年龄和肿块密度呈正相关，与乳腺分类呈负相关。年龄的相关性最大（r = 0.47）。在所有模型中，单肿块ROI模型的特异度最高（91.8%），AUC = 0.823，病灶周围5mm ROI模型的灵敏度最高（86.9%），AUC = 0.855。此外，通过结合病灶周围5mm ROI模型的头尾位和内外侧斜位视图，我们获得了最高的AUC（AUC = 0.877，P < 0.001）。
乳腺X线密度深度学习模型能够更好地区分数字乳腺X线摄影图像中的良恶性肿块型病变，未来可能成为放射科医生的辅助诊断工具。
