analiza aiqbench
This research presents a unified 3D framework using domain-adversarial learning to align CT and MRI data for robust pancreas segmentation, addressing the challenge of modality-specific intensity distributions. By training a shared encoder-decoder architecture, the study achieves high Dice scores on whole-organ segmentation while enabling label-efficient transfer to subregion tasks without requiring additional annotations for one modality. The approach demonstrates that learning unified anatomical representations can significantly improve generalization across heterogeneous medical imaging datasets.
Unified CT and MRI Pancreas Segmentation for Label-Efficient Cross-Modality Subregion Transfer
arXiv:2609.13043v1 Announce Type: cross Abstract: Robust medical image segmentation across imaging modalities is challenging because of large differences in appearance and intensity distributions. Models trained on a single modality often show substantial performance drops when applied to unseen domains. In this work, we develop a unified 3D pancreas segmentation framework that applies domain-adversarial learning to 4,604 heterogeneous CT and MRI scans to learn anatomical representations. A shared nnU-Net encoder-decoder is trained for whole-pancreas segmentation, with a latent domain discriminator encouraging CT-MRI feature alignment. The learned encoder is subsequently transferred to pancreatic head-body-tail segmentation using limited MRI-only subregion annotations. An average Dice score of 87.31% on the in-distribution test set and Dice scores ranging from 84.20% to 88.09% across external OOD datasets were achieved in whole pancreas segmentation. Dice scores of 80.53% on MRI and 83.05% on CT were achieved for downstream subregion segmentation, without using CT subregion annotations. These results demonstrate that a unified anatomical representation can support both cross-modality pancreas segmentation and label-efficient downstream transfer.
Abstract:Robust medical image segmentation across imaging modalities is challenging because of large differences in appearance and intensity distributions. Models trained on a single modality often show substantial performance drops when applied to unseen domains. In this work, we develop a unified 3D pancreas segmentation framework that applies domain-adversarial learning to 4,604 heterogeneous CT and MRI scans to learn anatomical representations. A shared nnU-Net encoder-decoder is trained for whole-pancreas segmentation, with a latent domain discriminator encouraging CT-MRI feature alignment. The learned encoder is subsequently transferred to pancreatic head-body-tail segmentation using limited MRI-only subregion annotations. An average Dice score of 87.31% on the in-distribution test set and Dice scores ranging from 84.20% to 88.09% across external OOD datasets were achieved in whole pancreas segmentation. Dice scores of 80.53% on MRI and 83.05% on CT were achieved for downstream subregion segmentation, without using CT subregion annotations. These results demonstrate that a unified anatomical representation can support both cross-modality pancreas segmentation and label-efficient downstream transfer.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.13043 [cs.CV]
(or arXiv:2609.13043v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.13043 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 261 cuvinte
Subiecte conexe
XtalPi Holdings Limited: XtalPi Holdings Announces 2026 Interim Results
finanznachrichten.de · 19 aug. 2026
From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model
arXiv · 21 aug. 2026
[AINews] The Future of Latent Space
Latent Space · 25 sept. 2026
New AI framework matches scans to standard pathology tests
Quantum Zeitgeist · 3 sept. 2026