发表机构
University Hospital Basel; Iran University of Medical Sciences; Flinders University; University of Debrecen; Univ. Rennes; CLCC Eugène Marquis; INSERM; Bilddiagnostik Basel（巴塞尔大学医院; 伊朗医科大学; 弗林德斯大学; 德布勒森大学; 雷恩大学; 欧仁·马基斯癌症中心; 法国国家健康与医学研究院; 巴塞尔影像诊断中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究扩展TotalSegmentator，训练CT和MR专用3D ResNet-10集成模型，可快速预测患者与采集特征，性能优于基线模型，模型已开源集成至TotalSegmentator。
AI 中文摘要
背景：患者信息和采集元数据对临床决策、图像质量控制及自动化研究流程至关重要，但在影像档案中可能缺失或不可靠。目的：开发并评估一种快速开源模型，可直接从CT和MR图像预测患者与采集特征。材料与方法：针对CT和MR分别训练3D ResNet-10集成模型，训练数据为2011年至2025年采集的57291例CT临床检查和43200例MR临床检查。两个模型均预测体重、身高、年龄、性别、造影剂存在情况、椎体覆盖范围及图像噪声；CT模型额外预测扫描仪制造商、管电压、管电流、卷积核及注射后时间；MR模型预测序列类别。在内部CT测试集（n=501）、内部MR测试集（n=636）及外部CT数据集（n=54）上评估性能。结果：内部CT测试集中，体重、身高、年龄的平均绝对误差（MAE）分别为3.90kg、3.68cm、4.42年，性别F1值为0.990；对应的MR结果分别为4.34kg、4.62cm、7.13年，性别F1值为0.970。在两种模态的四个核心预测目标上，该卷积神经网络（CNN）的表现均优于基于分割结果的XGBoost基线模型（校正后P≤0.042）。CT造影剂的F1值为0.963，MR序列的F1值为0.953，MR造影剂的F1值为0.823。外部CT测试集中，体重、身高、年龄的MAE分别为4.45kg、4.05cm、5.17年，性别F1值为0.971。CPU推理所需时间为CT模型20秒、MR模型12秒。结论：每种模态的一个3D多任务模型可快速从异构CT和MR检查中恢复患者与采集特征，模型已集成至TotalSegmentator。
英文摘要
Background: Patient details and acquisition metadata are important for clinical decisions, image quality control, and automated research pipelines, but may be missing or unreliable in imaging archives. Purpose: To develop and evaluate a fast open-source model that predicts patient and acquisition characteristics directly from CT and MR images. Materials and Methods: Separate 3D ResNet-10 ensembles for CT and MR were trained on 57,291 and 43,200 clinical examinations acquired from 2011 to 2025. Both predicted weight, height, age, sex, contrast presence, vertebral coverage, and image noise. The CT model additionally predicted scanner manufacturer, tube voltage, tube current, convolution kernel, and post-injection time; the MR model predicted sequence class. Performance was evaluated on internal CT (n=501) and MR (n=636) test sets and an external CT dataset (n=54). Results: Internal CT MAEs were 3.90 kg, 3.68 cm, and 4.42 years for weight, height, and age, with sex F1=0.990; corresponding MR results were 4.34 kg, 4.62 cm, 7.13 years, and F1=0.970. The CNN outperformed a segmentation-derived XGBoost baseline for all four core targets in both modalities (adjusted P<=.042). F1 scores were 0.963 for CT contrast, 0.953 for MR sequence, and 0.823 for MR contrast. External CT MAEs were 4.45 kg, 4.05 cm, and 5.17 years, with sex F1=0.971. CPU inference required 20 seconds for CT and 12 seconds for MR. Conclusion: One 3D multitask model per modality can rapidly recover patient and acquisition characteristics from heterogeneous CT and MR examinations. Models are available in TotalSegmentator: https://github.com/wasserth/TotalSegmentator
