Cong Chao, Li Xiaoguang, Zhang Chunlai, Zhang Jing, Sun Kaixiang, Liu Lianluyi, Ambale-Venkatesh Bharath, Chen Xiao, Wang Yi
Department of Radiology, Daping Hospital, Army Medical University, Chongqing, China.
School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing, China.
J Magn Reson Imaging. 2024 Jan;59(1):148-161. doi: 10.1002/jmri.28713. Epub 2023 Apr 4.
Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated.
To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences.
Retrospective.
A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female).
FIELD STRENGTH/SEQUENCE: T1-weighted imaging and dynamic contrast-enhanced MRI (DCE-MRI) with gradient echo sequences, T2-weighted imaging (T2WI) with spin-echo sequences, diffusion-weighted imaging with single-shot echo-planar sequence and at 1.5-T.
A convolutional neural network and long short-term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI-RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE-MRI and non-DCE sequences, respectively.
Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P-value <0.05 was considered statistically significant.
With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE-MRI, the DL-based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE-MRI/T2WI alone, respectively.
The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent-free combination is comparable to DCE-MRI alone and the radiologists' reading in AUC and sensitivity.
Stage 2.
据报道，深度学习（DL）在乳腺磁共振成像（MRI）中是可行的。然而，DL方法在多参数磁共振成像（mpMRI）联合用于乳腺癌检测方面的有效性尚未得到充分研究。
利用多序列特征提取与组合，实现一种用于乳腺癌分类和检测的DL方法。
回顾性研究。
共569例本地病例作为内部队列（年龄50.2±11.2岁；100%为女性），分为训练组（218例）、验证组（73例）和测试组（278例）；125例来自公共数据集的病例作为外部队列（年龄53.6±11.5岁；100%为女性）。
场强/序列：采用梯度回波序列的T1加权成像和动态对比增强MRI（DCE-MRI），采用自旋回波序列的T2加权成像（T2WI），采用单次激发回波平面序列的扩散加权成像，场强为1.5T。
采用卷积神经网络和长短期记忆级联网络进行病变分类，以组织病理学作为内部/外部队列中恶性和良性类别的金标准，对侧乳房作为健康类别。由三位独立的放射科医生评估乳腺影像报告和数据系统（BI-RADS）分类作为比较，并采用类激活图对内部队列中的病变进行定位。分别用DCE-MRI和非DCE序列评估分类和定位性能。
病变分类的敏感性、特异性、曲线下面积（AUC）、德龙检验和科恩kappa系数。定位的敏感性和均方误差。P值<0.05被认为具有统计学意义。
通过优化的mpMRI组合，内部/外部队列中的病变分类AUC分别为0.98/0.91，敏感性分别为0.96/0.83。在没有DCE-MRI的情况下，基于DL的方法优于放射科医生的读片结果（AUC为0.96对0.90）。仅使用DCE-MRI/T2WI时，病变定位的敏感性分别为0.97/0.93。
DL方法在内部/外部队列中实现了较高的病变检测准确率。无对比剂组合的分类性能在AUC和敏感性方面与单独使用DCE-MRI及放射科医生的读片结果相当。
3级。
2级。
