Stowers Casey E, Wu Chengyue, Xu Zhan, Kumar Sidharth, Yam Clinton, Son Jong Bum, Ma Jingfei, Tamir Jonathan I, Rauch Gaiane M, Yankeelov Thomas E
From the Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Tex (C.E.S., C.W., J.I.T., T.E.Y.); Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Tex (S.K., J.I.T.); Livestrong Cancer Institutes, The University of Texas at Austin, Austin, Tex (T.E.Y.); Departments of Imaging Physics (C.W., Z.X., J.B.S., J.M., T.E.Y.), Abdominal Imaging (G.M.R.), Breast Imaging (C.W., G.M.R.), Breast Medical Oncology (C.Y.), Biostatistics (C.W.), and Institute for Data Science in Oncology (C.W.), The University of Texas MD Anderson Cancer Center, Houston, Tex; and Departments of Biomedical Engineering (C.W., T.E.Y.), Diagnostic Medicine (J.I.T., T.E.Y.), and Oncology (T.E.Y.), The University of Texas at Austin, 107 W Dean Keeton St, Stop C0800, Austin, TX 78712.
Radiol Artif Intell. 2025 Jan;7(1):e240124. doi: 10.1148/ryai.240124.
Purpose To combine deep learning and biology-based modeling to predict the response of locally advanced, triple-negative breast cancer before initiating neoadjuvant chemotherapy (NAC). Materials and Methods In this retrospective study, a biology-based mathematical model of tumor response to NAC was constructed and calibrated on a patient-specific basis using imaging data from patients enrolled in the MD Anderson A Robust TNBC Evaluation FraMework to Improve Survival trial (ARTEMIS; ClinicalTrials.gov registration no. NCT02276443) between April 2018 and May 2021. To relate the calibrated parameters in the biology-based model and pretreatment MRI data, a convolutional neural network (CNN) was employed. The CNN predictions of the calibrated model parameters were used to estimate tumor response at the end of NAC. CNN performance in the estimations of total tumor volume (TTV), total tumor cellularity (TTC), and tumor status was evaluated. Model-predicted TTC and TTV measurements were compared with MRI-based measurements using the concordance correlation coefficient and area under the receiver operating characteristic curve (for predicting pathologic complete response at the end of NAC). Results The study included 118 female patients (median age, 51 years [range, 29-78 years]). For comparison of CNN predicted to measured change in TTC and TTV over the course of NAC, the concordance correlation coefficient values were 0.95 (95% CI: 0.90, 0.98) and 0.94 (95% CI: 0.87, 0.97), respectively. CNN-predicted TTC and TTV had an area under the receiver operating characteristic curve of 0.72 (95% CI: 0.34, 0.94) and 0.72 (95% CI: 0.40, 0.95) for predicting tumor status at the time of surgery, respectively. Conclusion Deep learning integrated with a biology-based mathematical model showed good performance in predicting the spatial and temporal evolution of a patient's tumor during NAC using only pre-NAC MRI data. Triple-Negative Breast Cancer, Neoadjuvant Chemotherapy, Convolutional Neural Network, Biology-based Mathematical Model Clinical trial registration no. NCT02276443 ©RSNA, 2024 See also commentary by Mei and Huang in this issue.
目的 结合深度学习和基于生物学的建模方法，在新辅助化疗（NAC）开始前预测局部晚期三阴性乳腺癌的反应。材料与方法 在这项回顾性研究中，构建了一个基于生物学的肿瘤对NAC反应的数学模型，并使用2018年4月至2021年5月期间参加MD安德森稳健三阴性乳腺癌评估框架以提高生存率试验（ARTEMIS；ClinicalTrials.gov注册号：NCT02276443）的患者的影像数据，在患者个体基础上进行校准。为了关联基于生物学模型中的校准参数和治疗前的MRI数据，采用了卷积神经网络（CNN）。校准模型参数的CNN预测用于估计NAC结束时的肿瘤反应。评估了CNN在总肿瘤体积（TTV）、总肿瘤细胞密度（TTC）和肿瘤状态估计中的性能。使用一致性相关系数和受试者工作特征曲线下面积（用于预测NAC结束时的病理完全缓解），将模型预测的TTC和TTV测量值与基于MRI的测量值进行比较。结果 该研究纳入了118名女性患者（中位年龄51岁[范围29 - 78岁]）。对于比较CNN预测的和测量的NAC过程中TTC和TTV的变化，一致性相关系数值分别为0.95（95%CI：0.90，0.98）和0.94（95%CI：0.87，0.97）。对于预测手术时的肿瘤状态，CNN预测的TTC和TTV的受试者工作特征曲线下面积分别为0.72（95%CI：0.34，0.94）和0.72（95%CI：0.40，0.95）。结论 深度学习与基于生物学的数学模型相结合，在仅使用NAC前的MRI数据预测患者肿瘤在NAC期间的时空演变方面表现出良好性能。三阴性乳腺癌、新辅助化疗、卷积神经网络、基于生物学的数学模型 临床试验注册号：NCT02276443 ©RSNA，2024 另见本期梅和黄的评论。
