Early prediction of neoadjuvant chemotherapy response for advanced breast cancer using PET/MRI image deep learning.
Early prediction of neoadjuvant chemotherapy response for advanced breast cancer using PET/MRI image deep learning.
复制标题
DOI：
10.1038/s41598-020-77875-5
复制
发表时间：
2020-12-03
影响因子：
4.6
通讯作者：
Woo SK
中科院分区：
文献类型：
--
作者：
Choi JH;Kim HA;Kim W;Lim I;Lee I;Byun BH;Noh WC;Seong MK;Lee SS;Kim BI;Choi CW;Lim SM;Woo SK
本研究旨在探讨正电子发射断层扫描/计算机断层扫描（PET/CT）和磁共振成像（MRI）对晚期乳腺癌新辅助化疗（NAC）病理反应的预测效力。介绍了乳腺PET/MRI图像深度学习模型，并与传统方法进行了比较。在第一个NAC周期之前和之后，对晚期乳腺癌患者的PET/CT和MRI参数进行了评价[n = 56;所有女性;中位年龄为49（范围26-66）岁]。最大标准化摄取值（SUVmax）、代谢性肿瘤体积（MTV）和总病变糖酵解（TLG）与相应的基线值（分别为SUV 0、MTV 0和TLG 0）和中期PET图像（分别为SUV 1、MTV 1和TLG 1）一起获得。从基线和中期弥散MR图像（分别为ADC 0和ADC 1）获得平均表观弥散系数。测量基线和中期参数之间的差异（ΔSUV、ΔMTV、ΔTLG和ΔADC）。对HER 2阴性和三阴性组进行亚组分析。卷积神经网络（CNN）的数据集，被分配为训练数据集（80%）和测试数据集（20%），从基线（PET 0，MRI 0）和中期（PET 1，MRI 1）图像中裁剪。化疗3个周期后，采用米勒和佩恩系统评估组织学反应。接受者工作特征曲线分析用于评估区分应答者和无应答者的性能。有6名应答者（11%）和50名无应答者（89%）。ΔSUV的曲线下面积（AUC）最高，为0.805（95% CI 0.677-0.899）。对于HER 2阴性亚型，ΔSUV的AUC最高，为0.879（95% CI 0.722-0.965）。应用CNN后AUC改善（SUV 0：PET 0 = 0.652：0.886，SUV 1：PET 1 = 0.687：0.980和ADC 1：MRI 1 = 0.537：0.701），ADC 0除外（ADC 0：MRI 0 = 0.703：0.602）。PET/MRI图像深度学习模型可以预测晚期乳腺癌患者对NAC的病理反应。
This study aimed to investigate the predictive efficacy of positron emission tomography/computed tomography (PET/CT) and magnetic resonance imaging (MRI) for the pathological response of advanced breast cancer to neoadjuvant chemotherapy (NAC). The breast PET/MRI image deep learning model was introduced and compared with the conventional methods. PET/CT and MRI parameters were evaluated before and after the first NAC cycle in patients with advanced breast cancer [n = 56; all women; median age, 49 (range 26–66) years]. The maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were obtained with the corresponding baseline values (SUV0, MTV0, and TLG0, respectively) and interim PET images (SUV1, MTV1, and TLG1, respectively). Mean apparent diffusion coefficients were obtained from baseline and interim diffusion MR images (ADC0 and ADC1, respectively). The differences between the baseline and interim parameters were measured (ΔSUV, ΔMTV, ΔTLG, and ΔADC). Subgroup analysis was performed for the HER2-negative and triple-negative groups. Datasets for convolutional neural network (CNN), assigned as training (80%) and test datasets (20%), were cropped from the baseline (PET0, MRI0) and interim (PET1, MRI1) images. Histopathologic responses were assessed using the Miller and Payne system, after three cycles of chemotherapy. Receiver operating characteristic curve analysis was used to assess the performance of the differentiating responders and non-responders. There were six responders (11%) and 50 non-responders (89%). The area under the curve (AUC) was the highest for ΔSUV at 0.805 (95% CI 0.677–0.899). The AUC was the highest for ΔSUV at 0.879 (95% CI 0.722–0.965) for the HER2-negative subtype. AUC improved following CNN application (SUV0:PET0 = 0.652:0.886, SUV1:PET1 = 0.687:0.980, and ADC1:MRI1 = 0.537:0.701), except for ADC0 (ADC0:MRI0 = 0.703:0.602). PET/MRI image deep learning model can predict pathological responses to NAC in patients with advanced breast cancer.
登录
查看更多内容
DOI：
10.1148/rg.2017160130
发表时间：
2017-03
期刊：
Radiographics : a review publication of the Radiological Society of North America, Inc
影响因子：
--
作者：
Erickson BJ;Korfiatis P;Akkus Z;Kline TL
通讯作者：
Kline TL
影响因子：
3.9
作者：
Koolen, Bas B.;Pengel, Kenneth E.;Olmos, Renato A. Valdes
通讯作者：
Olmos, Renato A. Valdes
影响因子：
3.2
作者：
Gao, Wen;Guo, Ning;Dong, Ting
通讯作者：
Dong, Ting
影响因子：
9.3
作者：
Hatt, Mathieu;Groheux, David;Cheze-Le Rest, Catherine
通讯作者：
Cheze-Le Rest, Catherine
影响因子：
3.9
作者：
Ogston, KN;Miller, ID;Heys, SD
通讯作者：
Heys, SD