Adams Jadie, Iyer Krithika, Elhabian Shireen Y
Scientific Computing and Imaging Institute, University of Utah, UT, USA.
Kahlert School of Computing, University of Utah, UT, USA.
Shape Med Imaging (2024). 2025;15275:1-17. Epub 2024 Oct 26.
Anatomical shape analysis plays a pivotal role in clinical research and hypothesis testing, where the relationship between form and function is paramount. Correspondence-based statistical shape modeling (SSM) facilitates population-level morphometrics but requires a cumbersome, potentially bias-inducing construction pipeline. Traditional construction pipelines require manual and computationally expensive steps, hindering their widespread use. Furthermore, such methods utilize templates or assumptions (e.g., linearity) that can bias or limit the expressivity of the variation captured by the constructed SSM. Recent advancements in deep learning have streamlined this process in inference by providing SSM prediction directly from unsegmented medical images. However, the proposed approaches are fully supervised and require utilizing a traditional SSM construction pipeline to create training data, thus inheriting the associated burdens and limitations. To address these challenges, we introduce a weakly supervised deep learning approach to predict SSM from images using point cloud supervision. Specifically, we propose reducing the supervision associated with the state-of-the-art fully Bayesian variational information bottleneck DeepSSM (BVIB-DeepSSM) model. BVIB-DeepSSM is an effective, principled framework for predicting probabilistic anatomical shapes from images with quantification of both aleatoric and epistemic uncertainties. Whereas the original BVIB-DeepSSM method requires strong supervision in the form of ground truth correspondence points, the proposed approach utilizes weak supervision via point cloud surface representations, which are more readily obtainable. Furthermore, the proposed approach learns correspondence in a completely data-driven manner without prior assumptions about the expected variability in shape cohort. Our experiments demonstrate that this approach yields similar accuracy and uncertainty estimation to the fully supervised scenario while substantially enhancing the feasibility of model training for SSM construction.
解剖形状分析在临床研究和假设检验中起着关键作用，其中形态与功能之间的关系至关重要。基于对应关系的统计形状建模（SSM）有助于进行群体水平的形态计量学研究，但需要一个繁琐且可能引入偏差的构建流程。传统的构建流程需要手动操作且计算成本高昂，阻碍了它们的广泛应用。此外，此类方法利用模板或假设（例如线性），这可能会使构建的SSM所捕获的变异的表达产生偏差或受到限制。深度学习的最新进展通过直接从未分割的医学图像进行SSM预测，简化了这一推理过程。然而，所提出的方法是完全监督的，并且需要利用传统的SSM构建流程来创建训练数据，从而继承了相关的负担和局限性。为了应对这些挑战，我们引入了一种弱监督深度学习方法，使用点云监督从图像中预测SSM。具体而言，我们提议减少与最先进的全贝叶斯变分信息瓶颈DeepSSM（BVIB - DeepSSM）模型相关的监督。BVIB - DeepSSM是一个有效的、有原则的框架，用于从图像中预测概率性解剖形状，并对偶然不确定性和认知不确定性进行量化。虽然原始的BVIB - DeepSSM方法需要以真实对应点的形式进行强监督，但所提出的方法通过点云表面表示利用弱监督，这种表示更容易获得。此外，所提出的方法以完全数据驱动的方式学习对应关系，而无需对形状队列中的预期变异性进行先验假设。我们的实验表明，这种方法在与完全监督场景产生相似的准确性和不确定性估计的同时，显著提高了用于SSM构建的模型训练的可行性。
