Hrzic Franko, Movahhedi Mohammadreza, Lavoie-Gagne Ophelie, Kiapour Ata
Musculoskeletal Digital Innovation and Informatics (MDI²) Program, Department of Orthopaedic and Sports Medicine, Boston Children's Hospital, Harvard Medical School, Boston MA, USA.
Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000, Croatia.
Sci Rep. 2025 Aug 28;15(1):31788. doi: 10.1038/s41598-025-17174-z.
It is well known that machine learning models require a high amount of annotated data to obtain optimal performance. Labelling Computed Tomography (CT) data can be a particularly challenging task due to its volumetric nature and often missing and/or incomplete associated meta-data. Even inspecting one CT scan requires additional computer software, or in the case of programming languages-additional programming libraries. This study proposes a simple, yet effective approach based on 2D X-ray-like estimation of 3D CT scans for body region identification. Although body region is commonly associated with the CT scan, it often describes only the focused major body region neglecting other anatomical regions present in the observed CT. In the proposed approach, estimated 2D images were utilized to identify 14 distinct body regions, providing valuable information for constructing a high-quality medical dataset. To evaluate the effectiveness of the proposed method, it was compared against 2.5D, 3D and foundation model (MI2) based approaches. Our approach outperformed the others, where it came on top with statistical significance and F1-Score for the best-performing model EffNet-B0 of 0.980 ± 0.016 in comparison to the 0.840 ± 0.114 (2.5D DenseNet-161), 0.854 ± 0.096 (3D VoxCNN), and 0.852 ± 0.104 (MI2 foundation model). The utilized dataset comprised three different clinical centers and counted 15,622 CT scans (44,135 labels).
众所周知，机器学习模型需要大量带注释的数据才能获得最佳性能。由于计算机断层扫描（CT）数据的体数据性质以及常常缺失和/或不完整的相关元数据，对其进行标注可能是一项特别具有挑战性的任务。即使检查一次CT扫描也需要额外的计算机软件，或者在编程语言的情况下还需要额外的编程库。本研究提出了一种基于对3D CT扫描进行类似2D X光估计的简单而有效的方法来识别身体区域。虽然身体区域通常与CT扫描相关联，但它通常只描述聚焦的主要身体区域，而忽略了观察到的CT中存在的其他解剖区域。在所提出的方法中，利用估计的2D图像来识别14个不同的身体区域，为构建高质量的医学数据集提供有价值的信息。为了评估所提出方法的有效性，将其与基于2.5D、3D和基础模型（MI2）的方法进行了比较。我们的方法优于其他方法，在性能最佳的模型EffNet-B0方面，以统计学显著性和F1分数位居榜首，F1分数为0.980±0.016，相比之下，2.5D DenseNet-161的F1分数为0.840±0.114，3D VoxCNN的F1分数为0.854±0.096，MI2基础模型的F1分数为0.852±0.104。所使用的数据集包括三个不同的临床中心，共有15622次CT扫描（44135个标签）。
