Fei Michael, McMillan Alan B
Creighton University School of Medicine, Phoenix, AZ, USA.
University of Wisconsin-Madison, Madison, WI, USA.
J Imaging Inform Med. 2025 Aug;38(4):2514-2523. doi: 10.1007/s10278-024-01319-z. Epub 2024 Nov 13.
The advancement of medical image deep learning necessitates tools that can accurately identify body regions from whole-body scans to serve as an essential pre-processing step for downstream tasks. Typically, these deep learning models rely on labeled data and supervised learning, which is labor-intensive. However, the emergence of self-supervised learning is revolutionizing the field by eliminating the need for labels. The purpose of this study was to compare neural network architectures of self-supervised models that produced a body part regression (BPR) slice score to aid in the development of anatomically localized segmentation models. VGG, ResNet, DenseNet, ConvNext, and EfficientNet BPR models were implemented in the MONAI/Pytorch framework. Landmark organs were correlated to slice scores and mean absolute error (MAE) was calculated from the predicted slice and the actual slice of various organ landmarks. Four localized DynUNet segmentation models (thorax, upper abdomen, lower abdomen, and pelvis) were developed using the BPR slice scores. Dice similarity coefficient (DSC) was compared between the localized and baseline segmentation models. The best performing BPR model was the EfficientNet architecture with an overall 3.18 MAE, compared to the VGG baseline model with a MAE of 6.29. The localized segmentation model significantly outperformed the baseline in 16 out of 20 organs with a DSC of 0.88. Enhanced neural networks like EfficientNet have a large performance increase in localizing anatomical structures in a CT compared in BPR task. Utilizing BPR slice score is shown to be effective in anatomically localized segmentation tasks with improved performance.
医学图像深度学习的发展需要能够从全身扫描中准确识别身体区域的工具，作为下游任务的重要预处理步骤。通常，这些深度学习模型依赖于标记数据和监督学习，这是一项劳动密集型工作。然而，自监督学习的出现正在通过消除对标签的需求来彻底改变该领域。本研究的目的是比较产生身体部位回归（BPR）切片分数的自监督模型的神经网络架构，以帮助开发解剖学定位的分割模型。在MONAI/Pytorch框架中实现了VGG、ResNet、DenseNet、ConvNext和EfficientNet BPR模型。将地标器官与切片分数相关联，并根据各种器官地标的预测切片和实际切片计算平均绝对误差（MAE）。使用BPR切片分数开发了四个局部DynUNet分割模型（胸部、上腹部、下腹部和骨盆）。比较了局部分割模型和基线分割模型之间的骰子相似系数（DSC）。表现最佳的BPR模型是EfficientNet架构，总体MAE为3.18，而VGG基线模型的MAE为6.29。在20个器官中的16个器官中，局部分割模型的表现明显优于基线模型，DSC为0.88。与BPR任务相比，像EfficientNet这样的增强神经网络在CT中定位解剖结构方面的性能有了大幅提高。利用BPR切片分数在解剖学定位分割任务中被证明是有效的，性能得到了提高。
