用CT/MR图像快速推断患者与扫描信息，提升医疗数据可用性。
Extending TotalSegmentator: Predicting Patient and Acquisition Characteristics from CT and MR Images
- 基于3D ResNet-10的多任务模型，直接从影像预测年龄、身高、体重等特征。
- 内部测试中对体重、身高、年龄的平均误差分别低于4.5公斤、4.7厘米、7.2岁。
- 适合影像缺失或不完整的研究场景，支持自动化分析流程构建。
背景：患者信息和扫描元数据对临床决策、图像质量控制及自动化研究流程至关重要，但常缺失或不可靠。目的：开发并评估一个快速开源模型，直接从CT和MR图像预测患者及扫描特征。方法：为CT和MR分别训练了3D ResNet-10集成模型，使用2011至2025年间共57,291例CT和43,200例MR临床检查数据。两模型均预测体重、身高、年龄、性别、对比剂使用情况、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（n=501）和MR（n=636）测试集以及外部CT数据集（n=54）上评估性能。结果：内部CT的平均绝对误差（MAE）分别为体重3.90公斤、身高3.68厘米、年龄4.42年，性别分类F1值0.990；对应MR结果为4.34公斤、4.62厘米、7.13年，F1值0.970。卷积神经网络在两种模态中所有四项核心目标上均优于基于分割的XGBoost基线（校正后P≤0.042）。CT对比剂检测F1为0.963，MR序列类别0.953，对比剂0.823。外部CT测试中MAE为4.45公斤、4.05厘米、5.17年，性别F1值0.971。单次推理耗时20秒（CT）和12秒（MR）。结论：每种模态一个3D多任务模型即可快速恢复异构CT/MR检查中的患者与扫描特征。模型已开源至TotalSegmentator：https://github.com/wasserth/TotalSegmentator。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。