Diffusion Model based Semi-supervised Learning on Brain Hemorrhage Images for Efficient Midline Shift Quantification
This work addresses the need for efficient and accurate MLS quantification in brain hemorrhage diagnosis, reducing reliance on intensive labeling and poor-performing existing methods, though it is incremental as it builds on semi-supervised and diffusion model techniques.
The authors tackled the problem of accurately measuring brain midline shift (MLS) from head CT scans, a critical factor in clinical diagnosis, by proposing a semi-supervised framework that uses diffusion models and sparse labels. Their method achieved state-of-the-art performance on a real clinical dataset, generating interpretable deformation fields.
Brain midline shift (MLS) is one of the most critical factors to be considered for clinical diagnosis and treatment decision-making for intracranial hemorrhage. Existing computational methods on MLS quantification not only require intensive labeling in millimeter-level measurement but also suffer from poor performance due to their dependence on specific landmarks or simplified anatomical assumptions. In this paper, we propose a novel semi-supervised framework to accurately measure the scale of MLS from head CT scans. We formulate the MLS measurement task as a deformation estimation problem and solve it using a few MLS slices with sparse labels. Meanwhile, with the help of diffusion models, we are able to use a great number of unlabeled MLS data and 2793 non-MLS cases for representation learning and regularization. The extracted representation reflects how the image is different from a non-MLS image and regularization serves an important role in the sparse-to-dense refinement of the deformation field. Our experiment on a real clinical brain hemorrhage dataset has achieved state-of-the-art performance and can generate interpretable deformation fields.