Papers for

radiology workflow managers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Multimodal 3D image alignment shows varied success across medical areas

Benchmarking Intra-Patient 3D Deformable Multimodal Image Registration

Abstract: Multimodal image registration is a key component of many clinical workflows, yet it remains challenging because corresponding anatomical structures often exhibit substantially different image intensities across modalities. In this work, we present a comprehensive benchmark of intra-patient 3D multimodal deformable registration methods across three datasets covering different anatomical regions and difficulty levels, including both synthetic deformation recovery and real clinical scenarios. We evaluate classical optimization-based approaches and modern learning-based methods, including recent deep learning and foundation models, using complementary metrics: Average Dice similarity coefficient (DSC), average 95th-percentile Hausdorff distance (HD95), and a modality-independent structural similarity measure based on the MIND self-similarity context (MIND-SSC). Results show high variability across datasets, with learning-based methods demonstrating superior performance on large synthetic benchmarks, while only limited improvements are observed in real pelvic registration. A key finding of this study is the consistent disagreement between geometric metrics (DSC, HD95) and image-based similarity metrics (MIND-SSC), highlighting that improved overlap does not necessarily imply better global multimodal correspondence. Furthermore, anatomy-guided approaches achieve the highest overlap scores but exhibit degraded performance outside of segmented regions, revealing a trade-off between label-driven alignment and global structural coherence. Overall, our results indicate that no current method achieves robust performance across anatomies and modalities. We demonstrate that intra-patient 3D multimodal registration requires multi-criteria evaluation, including deformation-based metrics, and remains an open problem.

Mon 14 SeptComputer Vision and Pattern RecognitionArtificial Intelligence
The gist
Aligning 3D medical images taken by different machines is important but tricky because the same body parts look different in each image type. The authors tested many methods to line up these images from inside the same patient, covering various body parts and challenges. They found that while learning-based methods work well on synthetic data, real clinical data remains difficult with no method working perfectly everywhere. They also discovered that common ways to measure success don’t always agree, meaning better overlap of labeled areas doesn’t guarantee good matching overall. This means there is still a need for better tools to accurately combine different medical images in 3D.
Open 2609.15669v1