Image To Tree with Recursive Prompting
Abstract
Extracting complex structures from grid-based data is a common key step in automated medical image analysis. The conventional solution to recovering tree-structured geometries typically involves computing the minimal cost path through intermediate representations derived from segmentation masks. However, this methodology has significant limitations in the context of projective imaging of tree-structured 3D anatomical data such as coronary arteries, since there are often overlapping branches in the 2D projection. In this work, we propose a novel approach to predicting tree connectivity structure which reformulates the task as an optimization problem over individual steps of a recursive process. We design and train a two-stage model which leverages the UNet and Transformer architectures and introduces an image-based prompting technique. Our proposed method achieves compelling results on a pair of synthetic datasets, and outperforms a shortest-path baseline.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2023
- DOI:
- 10.48550/arXiv.2301.00447
- arXiv:
- arXiv:2301.00447
- Bibcode:
- 2023arXiv230100447B
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning
- E-Print:
- 12 pages, 5 figures