Semantic Latent Space Regression of Diffusion Autoencoders for Vertebral Fracture Grading
This addresses the problem of subjective and data-scarce fracture grading for osteoporosis patients, offering an incremental improvement in interpretability and handling of imbalanced data.
The paper tackles automated grading of vertebral fracture severity from CT scans by proposing a regression approach using a Diffusion Autoencoder trained on unlabelled data, achieving results calibrated to the Genant scale with interpretable visualizations of fracture grades.
Vertebral fractures are a consequence of osteoporosis, with significant health implications for affected patients. Unfortunately, grading their severity using CT exams is hard and subjective, motivating automated grading methods. However, current approaches are hindered by imbalance and scarcity of data and a lack of interpretability. To address these challenges, this paper proposes a novel approach that leverages unlabelled data to train a generative Diffusion Autoencoder (DAE) model as an unsupervised feature extractor. We model fracture grading as a continuous regression, which is more reflective of the smooth progression of fractures. Specifically, we use a binary, supervised fracture classifier to construct a hyperplane in the DAE's latent space. We then regress the severity of the fracture as a function of the distance to this hyperplane, calibrating the results to the Genant scale. Importantly, the generative nature of our method allows us to visualize different grades of a given vertebra, providing interpretability and insight into the features that contribute to automated grading.