Prediction of lymphoma response to CAR T cells by deep learning-based image analysis.
Prediction of lymphoma response to CAR T cells by deep learning-based image analysis.
复制标题
DOI：
10.1371/journal.pone.0282573
复制
发表时间：
2023
期刊：
影响因子：
3.7
通讯作者：
中科院分区：
文献类型：
--
作者：
临床预后评分系统在预测淋巴瘤治疗结果方面的效用有限。因此，我们测试了基于深度学习（DL）的图像分析方法在治疗前诊断计算机断层扫描（dCT）、低剂量CT（lCT）和18 F-氟脱氧葡萄糖正电子发射断层扫描（FDG-PET）图像上的可行性，以及基于规则的推理，以预测B细胞淋巴瘤对嵌合抗原受体（CAR）T细胞疗法的治疗反应。分析了来自39名用CD 19定向CAR T细胞治疗的B细胞淋巴瘤成人患者的770个淋巴结病变的治疗前图像。使用预先训练的神经网络模型进行迁移学习，然后针对特定任务进行重新训练，用于根据单独的dCT、lCT和FDG-PET图像预测病变水平的治疗反应。通过将基于规则的推理应用于病变水平的预测结果，进行患者水平的反应分析。还将患者水平缓解预测与基于弥漫性大B细胞淋巴瘤国际预后指数（IPI）的预测进行了比较。基于单次全dCT切片输入的病变水平反应预测的平均准确度为0.82 ± 0.05，灵敏度为0.87 ± 0.07，特异性为0.77 ± 0.12，AUC为0.91 ± 0.03。使用“多数60%”规则，使用治疗后12个月患者缓解作为参考标准，dCT患者水平缓解预测的准确性为0.81，灵敏度为0.75，特异性为0.88，优于基于IPI风险因素的缓解预测（准确性为0.54，灵敏度为0.38，特异性为0.61（p = 0.046））。使用基于DL的图像分析和基于规则的推理从治疗前医学图像预测B细胞淋巴瘤的治疗结果是可行的。这种方法可以在启动CAR T细胞治疗之前为决策提供临床有用的预后信息。
Clinical prognostic scoring systems have limited utility for predicting treatment outcomes in lymphomas. We therefore tested the feasibility of a deep-learning (DL)-based image analysis methodology on pre-treatment diagnostic computed tomography (dCT), low-dose CT (lCT), and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) images and rule-based reasoning to predict treatment response to chimeric antigen receptor (CAR) T-cell therapy in B-cell lymphomas. Pre-treatment images of 770 lymph node lesions from 39 adult patients with B-cell lymphomas treated with CD19-directed CAR T-cells were analyzed. Transfer learning using a pre-trained neural network model, then retrained for a specific task, was used to predict lesion-level treatment responses from separate dCT, lCT, and FDG-PET images. Patient-level response analysis was performed by applying rule-based reasoning to lesion-level prediction results. Patient-level response prediction was also compared to prediction based on the international prognostic index (IPI) for diffuse large B-cell lymphoma. The average accuracy of lesion-level response prediction based on single whole dCT slice-based input was 0.82+0.05 with sensitivity 0.87+0.07, specificity 0.77+0.12, and AUC 0.91+0.03. Patient-level response prediction from dCT, using the “Majority 60%” rule, had accuracy 0.81, sensitivity 0.75, and specificity 0.88 using 12-month post-treatment patient response as the reference standard and outperformed response prediction based on IPI risk factors (accuracy 0.54, sensitivity 0.38, and specificity 0.61 (p = 0.046)). Prediction of treatment outcome in B-cell lymphomas from pre-treatment medical images using DL-based image analysis and rule-based reasoning is feasible. This approach can potentially provide clinically useful prognostic information for decision-making in advance of initiating CAR T-cell therapy.
登录
查看更多内容
DOI：
10.1073/pnas.1806579115
发表时间：
2018-08-14
影响因子：
11.1
作者：
Mei S;Montanari A;Nguyen PM
通讯作者：
Nguyen PM
DOI：
10.1056/nejmoa1707447
发表时间：
2017-12-28
期刊：
The New England journal of medicine
影响因子：
--
作者：
Neelapu SS;Locke FL;Bartlett NL;Lekakis LJ;Miklos DB;Jacobson CA;Braunschweig I;Oluwole OO;Siddiqi T;Lin Y;Timmerman JM;Stiff PJ;Friedberg JW;Flinn IW;Goy A;Hill BT;Smith MR;Deol A;Farooq U;McSweeney P;Munoz J;Avivi I;Castro JE;Westin JR;Chavez JC;Ghobadi A;Komanduri KV;Levy R;Jacobsen ED;Witzig TE;Reagan P;Bot A;Rossi J;Navale L;Jiang Y;Aycock J;Elias M;Chang D;Wiezorek J;Go WY
通讯作者：
Go WY
影响因子：
10.6
作者：
Sari, Can Taylan;Gunduz-Demir, Cigdem
通讯作者：
Gunduz-Demir, Cigdem
影响因子：
4.6
作者：
Minh Tuan Nguyen;Binh Van Nguyen;Kim, Kiseon
通讯作者：
Kim, Kiseon
影响因子：
3
作者：
Naito, Tatsuhiko;Nagashima, Yu;Shimizu, Jun
通讯作者：
Shimizu, Jun