Conpro improves vessel segmentation using contrast projection pretraining
ConPro: Contrast Projection Pretraining for Label-Efficient Vessel Segmentation in DSA Sequences
Computer Vision and Pattern Recognition
Summary
Labeling blood vessels in medical images is very time-consuming, but these images naturally show how contrast dye flows through vessels. The authors designed a new way to teach a computer to find vessels by looking at how contrast changes over time, instead of just static pictures. Their method, called ConPro, learns from unlabeled videos and helps the computer do better even with few labeled examples. This makes it easier to train computer programs to identify blood vessels accurately in diagnostic images.
What this means in practice
- •For medical imaging software developers: Improve vessel segmentation in angiography by pretraining models with contrast projection to reduce need for labeled data and boost accuracy.
- •For radiology ai integration teams: Integrate pretrained vessel segmentation models into clinical workflows to speed up image annotation and improve diagnostic support.
Authors
Xinge Guo, Yuanhao Wang, Liqi Shu, Yang Liu, Min Xu
Abstract
Dense vessel annotation in digital subtraction angiography (DSA) is labor-intensive, yet every unlabeled sequence records how contrast passes through the vessels. Semi-supervised methods take their targets from the current model, and generic self-supervised pretexts reconstruct static appearance, so this signal goes unused. We propose ConPro, a self-supervised pretraining scheme whose target is a contrast projection, the normalized drop of every pixel below its temporal median over the sequence. On DIAS and DSCA, with 10%, 20% and 50% of the training cases labeled, ConPro improves on training from scratch at every label fraction and is the best of the compared methods on DSCA at 20% and 50% labels. Controlled comparisons show that the gain comes from the target. A temporal-median target with the same input, loss and budget stays at scratch level, and using the projection directly instead of learning it, as an input channel or a pseudo-label, helps little or hurts. ConPro provides pretrained weights without changing the segmentation architecture, so it combines with semi-supervised training, and UniMatch, the strongest baseline, gains 0.5 to 2.0 Dice and 0.9 to 2.3 clDice at every label fraction when started from ConPro weights, reaching 75.4 Dice on DIAS and 81.3 on DSCA.