Gatti Anthony A, Blankemeier Louis, Veen Dave Van, Hargreaves Brian, Delp Scott L, Gold Garry E, Kogan Feliks, Chaudhari Akshay S
Department of Radiology at Stanford University, Stanford, CA, 94305, USA.
Department of Electrical Engineering at Stanford University, Stanford, CA, 94305, USA.
medRxiv. 2024 Oct 22:2024.05.06.24306965. doi: 10.1101/2024.05.06.24306965.
Analyzing anatomic shapes of tissues and organs is pivotal for accurate disease diagnostics and clinical decision-making. One prominent disease that depends on anatomic shape analysis is osteoarthritis, which affects 30 million Americans. To advance osteoarthritis diagnostics and prognostics, we introduce , a 3D shape dataset with 9,376 high-resolution, medical-imaging-based 3D shapes of both femur bone and cartilage. Besides data, ShapeMed-Knee includes two benchmarks for assessing reconstruction accuracy and five clinical prediction tasks that assess the utility of learned shape representations. Leveraging ShapeMed-Knee, we develop and evaluate a novel hybrid explicit-implicit neural shape model which achieves up to 40% better reconstruction accuracy than a statistical shape model and two implicit neural shape models. Our hybrid models achieve state-of-the-art performance for preserving cartilage biomarkers (root mean squared error ≤ 0.05 vs. ≤ 0.07, 0.10, and 0.14). Our models are also the first to successfully predict localized structural features of osteoarthritis, outperforming shape models and convolutional neural networks applied to raw magnetic resonance images and segmentations (e.g., osteophyte size and localization 63% accuracy vs. 49-61%). The ShapeMed-Knee dataset provides medical evaluations to reconstruct multiple anatomic surfaces and embed meaningful disease-specific information. ShapeMed-Knee reduces barriers to applying 3D modeling in medicine, and our benchmarks highlight that advancements in 3D modeling can enhance the diagnosis and risk stratification for complex diseases. The dataset, code, and benchmarks are freely accessible.
分析组织和器官的解剖形状对于准确的疾病诊断和临床决策至关重要。一种依赖解剖形状分析的突出疾病是骨关节炎，它影响着3000万美国人。为了推进骨关节炎的诊断和预后评估，我们引入了ShapeMed-Knee，这是一个包含9376个基于医学成像的高分辨率三维形状数据集，涵盖股骨和软骨。除了数据，ShapeMed-Knee还包括两个用于评估重建准确性的基准以及五个临床预测任务，这些任务评估了所学形状表示的效用。利用ShapeMed-Knee，我们开发并评估了一种新型的混合显式-隐式神经形状模型，该模型在重建准确性方面比统计形状模型和两个隐式神经形状模型高出40%。我们的混合模型在保留软骨生物标志物方面达到了当前的最佳性能（均方根误差≤0.05，而其他模型分别为≤0.07、0.10和0.14）。我们的模型也是第一个成功预测骨关节炎局部结构特征的模型，优于应用于原始磁共振图像和分割的形状模型及卷积神经网络（例如，骨赘大小和定位的准确率为63%，而其他模型为49%-61%）。ShapeMed-Knee数据集为重建多个解剖表面并嵌入有意义的疾病特定信息提供了医学评估。ShapeMed-Knee减少了在医学中应用三维建模的障碍，我们的基准突出表明三维建模的进展可以增强对复杂疾病的诊断和风险分层。该数据集、代码和基准均可免费获取。
