Akinci D'Antonoli Tugba, Berger Lucas K, Indrakanti Ashraya K, Vishwanathan Nathan, Weiss Jakob, Jung Matthias, Berkarda Zeynep, Rau Alexander, Reisert Marco, Küstner Thomas, Walter Alexandra, Merkle Elmar M, Boll Daniel T, Breit Hanns-Christian, Nicoli Andrew Phillip, Segeroth Martin, Cyriac Joshy, Yang Shan, Wasserthal Jakob
Clinic of Radiology and Nuclear Medicine, University Hospital Basel, Petersgraben 4, CH-4031 Basel, Switzerland.
Department of Diagnostic and Interventional Radiology, Faculty of Medicine, Medical Center-University of Freiburg, University of Freiburg, Freiburg, Germany.
Radiology. 2025 Feb;314(2):e241613. doi: 10.1148/radiol.241613.
Background Since the introduction of TotalSegmentator CT, there has been demand for a similar robust automated MRI segmentation tool that can be applied across all MRI sequences and anatomic structures. Purpose To develop and evaluate an automated MRI segmentation model for robust segmentation of major anatomic structures independent of MRI sequence. Materials and Methods In this retrospective study, an nnU-Net model (TotalSegmentator MRI) was trained on MRI and CT scans to segment 80 anatomic structures relevant for use cases such as organ volumetry, disease characterization, surgical planning, and opportunistic screening. Images were randomly sampled from routine clinical studies to represent real-world examples. Dice scores were calculated between the predicted segmentations and expert radiologist segmentations to evaluate model performance on an internal test set and two external test sets and against two publicly available models and TotalSegmentator CT. The Wilcoxon signed rank test was used to compare model performance. The proposed model was applied to a separate internal dataset containing abdominal MRI scans to investigate age-dependent volume changes. Results A total of 1143 scans (616 MRI, 527 CT; median patient age, 61 years [IQR, 50-72 years]) were split into a training set ( = 1088; CT and MRI) and an internal test set ( = 55; MRI only). The two external test sets (AMOS and CHAOS) contained 20 MRI scans each, and the aging-study dataset contained 8672 abdominal MRI scans (median patient age, 59 years [IQR, 45-70 years]). The proposed model had a Dice score of 0.839 for the 80 anatomic structures in the internal test set and outperformed two other models (Dice score of 0.862 vs 0.759 for 40 anatomic structures and 0.838 vs 0.560 for 13 anatomic structures; < .001 for both). On the TotalSegmentator CT test set (89 CT scans), the performance of the proposed model almost matched that of TotalSegmentator CT (Dice score, 0.966 vs 0.970; < .001). The aging study demonstrated a strong correlation between age and organ volume (eg, age and liver volume: ρ = -0.096; < .0001). Conclusion The proposed open-source, easy-to-use model allows for automatic, robust segmentation of 80 structures, extending the capabilities of TotalSegmentator to MRI scans from any MRI sequence. The ready-to-use online tool is available at ; the model, at ; and the dataset, at . © RSNA, 2025 See also the editorial by Kitamura in this issue.
背景 自TotalSegmentator CT推出以来，人们一直需要一种类似的强大的自动MRI分割工具，该工具可应用于所有MRI序列和解剖结构。目的 开发并评估一种自动MRI分割模型，用于独立于MRI序列对主要解剖结构进行强大的分割。材料与方法 在这项回顾性研究中，一个nnU-Net模型（TotalSegmentator MRI）在MRI和CT扫描上进行训练，以分割80个与器官容积测量、疾病特征分析、手术规划和机会性筛查等用例相关的解剖结构。图像从常规临床研究中随机采样，以代表实际案例。计算预测分割结果与专家放射科医生分割结果之间的Dice分数，以评估模型在内部测试集、两个外部测试集上的性能，并与两个公开可用模型和TotalSegmentator CT进行比较。采用Wilcoxon符号秩检验比较模型性能。将所提出的模型应用于一个单独的包含腹部MRI扫描的内部数据集，以研究年龄相关的体积变化。结果 总共1143次扫描（616次MRI，527次CT；患者年龄中位数为61岁[四分位间距，50 - 72岁]）被分为训练集（n = 1088；CT和MRI）和内部测试集（n = 55；仅MRI）。两个外部测试集（AMOS和CHAOS）各包含20次MRI扫描，衰老研究数据集包含8672次腹部MRI扫描（患者年龄中位数为59岁[四分位间距，45 - 70岁]）。所提出的模型在内部测试集中对80个解剖结构的Dice分数为0.839，优于其他两个模型（40个解剖结构的Dice分数分别为0.862对0.759以及13个解剖结构的0.838对0.560；两者均P <.001）。在TotalSegmentator CT测试集（89次CT扫描）上，所提出模型的性能几乎与TotalSegmentator CT相当（Dice分数，0.966对0.970；P <.001）。衰老研究表明年龄与器官体积之间存在强相关性（例如，年龄与肝脏体积：ρ = -0.096；P <.0001）。结论 所提出的开源、易于使用的模型允许对80个结构进行自动、强大的分割，将TotalSegmentator的功能扩展到来自任何MRI序列的MRI扫描。可通过[具体网址1]获取即用型在线工具；通过[具体网址2]获取模型；通过[具体网址3]获取数据集。© RSNA, 2025 另见本期北村的社论。
