Fleximind improves medical image alignment using combined pretrained and local features
FlexiMIND: Combined Pretrained Vision Features and Local Structure for Training-Free Deformable Medical Image Registration
Computer Vision and Pattern Recognition
Summary
Matching images of the same body part taken by different scans is hard because the pictures look different. The authors created FlexiMIND, which uses both smart features learned from general images and detailed local texture descriptors to align medical images without any extra training. They tested it on several types of scans and found it works well, especially at fixing big errors. This tool can help doctors compare different medical images accurately without needing lots of additional data or training.
What this means in practice
- •For medical imaging engineers: Align medical images from different scans more accurately without requiring new training data or labels.
- •For radiology software developers: Integrate non-learning-based registration methods using pretrained encoders to improve robustness in multi-modality medical image alignment.
Authors
Mojtaba Safari, Mingzhe Hu, Shansong Wang, Suyang Xi, Joshua Lorenz, Sean Pitroda, Aytekin Oto, Ralph R. Weichselbaum, Xiaofeng Yang
Abstract
Objective. Deformable image registration remains challenging because corresponding anatomy may exhibit different intensity relationships. Hand-crafted modality-robust descriptors such as Modality-Independent Neighborhood Descriptor with Self-Similarity Context (MIND-SSC) and features from pretrained vision encoders provide distinct representations for correspondence estimation, but how they should be combined remains unclear. We investigate whether tighter integration improves registration over a sequential, scale-separated design. Approach. We introduce FlexiMIND, a training-free and label-free two-stage framework in which frozen FlexiCT-2D encoder features establish contextual correspondence and MIND-SSC refines the deformation within ConvexAdam. Five alternative feature-coupling strategies were evaluated under a protocol across CT-CT (DIR-Lab 4DCT 4DCT, 10 cases), MR-MR (ACDC, 50 patients), and MR-CT (Learn2Reg Abdomen MR-CT, 8 pairs) registration. Performance was assessed using target registration error (TRE), Dice similarity coefficient (Dice), SDlogJ, and local folding. Main results. FlexiMIND achieved a TRE of 1.27 mm on DIR-Lab 4DCT, a DSC of 0.807 on ACDC, and an organ-averaged DSC of 0.825 on Abdomen MR-CT. Across 15 coupling-strategy dataset comparisons, only four outperformed the reference method, with a maximum absolute improvement of 0.0043 in Dice, whereas degradation reached 20.6 % in TRE and 37.9 % in Dice. Changes in registration accuracy were closely associated with changes in deformation-field regularity, and strategies that better preserved regularity generally remained closest to the reference performance. Landmark-level analysis showed that the pretrained encoder stage primarily reduced large correspondence errors rather than uniformly improving local precision. Code is available upon acceptance at https://github.com/mosaf/FlexiMIND.