BodyGPS: Anatomical Positioning System
This provides a versatile tool for medical imaging tasks like matching and segmentation, but it appears incremental as it builds on existing atlas-based methods with efficiency improvements.
The paper tackles the problem of parsing human anatomy in medical images across different modalities by introducing a foundational model that uses a neural network estimator to map query locations to atlas coordinates, achieving response times of less than 1 ms without additional hardware.
We introduce a new type of foundational model for parsing human anatomy in medical images that works for different modalities. It supports supervised or unsupervised training and can perform matching, registration, classification, or segmentation with or without user interaction. We achieve this by training a neural network estimator that maps query locations to atlas coordinates via regression. Efficiency is improved by sparsely sampling the input, enabling response times of less than 1 ms without additional accelerator hardware. We demonstrate the utility of the algorithm in both CT and MRI modalities.