METHODS: Patients with pathology-confirmed invasive breast cancer treated with adjuvant radiotherapy following breast-conserving surgery in four centers were included. From 2019 to 2020, a total of 230 patients from four nationwide centers in China were screened, of whom 208 were enrolled for DL modeling, and 22 patients from another three centers formed the external testing cohort. The subset of the internal testing cohort (n = 42) formed the internal correlation testing cohort for correlation analysis. The outline of the ipsilateral breast was marked with a lead wire before the scanning. Then, a DL model based on the High-Resolution Net was developed to detect the lead wire marker in each slice of the CT images automatically, and an in-house model was applied to segment the ipsilateral lung region. The mean and standard deviation of the distance error, the average precision, and average recall were used to measure the performance of the lead wire marker detection model. Based on these DL model results, we proposed an organ feature, and the Pearson correlation coefficient was calculated between the proposed organ feature and ipsilateral lung volume receiving 20 Gray (Gy) or more (V20).
RESULTS: For the lead wire marker detection model, the mean and standard deviation of the distance error, AP (5 mm) and AR (5 mm) reached 3.415 ± 4.529, 0.860, 0.883, and 4.189 ± 8.390, 0.848, 0.830 in the internal testing cohort and external testing cohort, respectively. The proposed organ feature calculated from the detected marker correlated with ipsilateral lung V20 (Pearson correlation coefficient, 0.542 with p < 0.001 in the internal correlation testing cohort and 0.554 with p = 0.008 in the external testing cohort).
CONCLUSIONS: The proposed artificial Intelligence-based CT organ feature was correlated with normal lung dose in adjuvant radiotherapy following breast-conserving surgery in patients with invasive breast cancer.
BACKGROUND: NCT05609058 (08/11/2022).
方法:纳入4个中心经病理证实的浸润性乳腺癌保乳术后辅助放疗患者。从2019年到2020年,共筛查了来自中国四个全国性中心的230名患者,其中208人注册了DL建模,来自另外三个中心的22名患者组成了外部测试队列。内部测试队列的子集(n=42)形成用于相关性分析的内部相关性测试队列。扫描前用导线标记同侧乳房的轮廓。然后,开发了基于高分辨率网络的DL模型,以自动检测CT图像的每个切片中的引线标记,并应用内部模型分割同侧肺区域。距离误差的平均值和标准偏差,平均精度,和平均召回率被用来衡量引线标记检测模型的性能。基于这些DL模型结果,我们提出了一个器官特征,计算出建议的器官特征与接受20Gray(Gy)或更多(V20)的同侧肺容积之间的Pearson相关系数。
结果:对于引线标记检测模型,距离误差的平均值和标准偏差,在内部测试队列和外部测试队列中,AP(5mm)和AR(5mm)分别达到3.415±4.529、0.860、0.883和4.189±8.390、0.848、0.830,分别。根据检测到的与同侧肺V20相关的标记物计算出的拟议器官特征(Pearson相关系数,0.542,内部相关性测试队列中p<0.001,外部测试队列中p=0.008的0.554)。
结论:提出的基于人工智能的CT器官特征与浸润性乳腺癌患者保乳手术后辅助放疗的正常肺剂量相关。
背景:NCT05609058(2022年8月11日)。