Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors
This addresses the need for reliable uncertainty estimates in medical image analysis, which is crucial for clinical decision-making, though it is incremental as it builds on existing PCA-based methods.
The paper tackles the problem of quantifying uncertainty in surface reconstruction for medical images by proposing a probabilistic deep learning approach that incorporates shape priors, achieving improved performance over a deterministic baseline on the UK Biobank dataset for 2D organ delineation.
Surface reconstruction is a vital tool in a wide range of areas of medical image analysis and clinical research. Despite the fact that many methods have proposed solutions to the reconstruction problem, most, due to their deterministic nature, do not directly address the issue of quantifying uncertainty associated with their predictions. We remedy this by proposing a novel probabilistic deep learning approach capable of simultaneous surface reconstruction and associated uncertainty prediction. The method incorporates prior shape information in the form of a principal component analysis (PCA) model. Experiments using the UK Biobank data show that our probabilistic approach outperforms an analogous deterministic PCA-based method in the task of 2D organ delineation and quantifies uncertainty by formulating distributions over predicted surface vertex positions.