Anatomical Predictions using Subject-Specific Medical Data
This work addresses the need for personalized treatment and analysis in medical imaging by providing subject-specific predictions, though it is incremental as it builds on existing deformation and neural network methods.
The paper tackles the problem of predicting future brain MRI changes for individuals by modeling anatomical changes with a diffeomorphic deformation field predicted via convolutional neural networks, demonstrating good predictions on the ADNI cohort with improvements from external clinical data.
Changes over time in brain anatomy can provide important insight for treatment design or scientific analyses. We present a method that predicts how a brain MRI for an individual will change over time. We model changes using a diffeomorphic deformation field that we predict using function using convolutional neural networks. Given a predicted deformation field, a baseline scan can be warped to give a prediction of the brain scan at a future time. We demonstrate the method using the ADNI cohort, and analyze how performance is affected by model variants and the subject-specific information provided. We show that the model provides good predictions and that external clinical data can improve predictions.