Region-Weighted Losses and Model Fusion for Cross-Modal PET Attenuation Correction
Not on the map. Why?
Abstract (arXiv)
We describe our approach to the Big Cross-Modal Attenuation Correction (BIC-MAC) challenge, which asks for a pseudo-CT in Hounsfield Units to be synthesized from Non-Attenuation-Corrected PET (NAC-PET), DIXON MRI and a topogram, and scores both the pseudo-CT and the Attenuation-Corrected PET (AC-PET) reconstructed from it. Three ideas carried our improvements over the organizers' 3D U-Net baseline. The loss matters more than the architecture: we compute the L1 error in the Carney attenuation-coefficient (μ) space that the CT metric itself uses, weighted by anatomical region. Only once that loss was in place did the unregistered DIXON MRI work as extra input channels. A fixed convex combination of two independently trained models then beat both of its members on three of the four metrics and ranks first overall on the public validation leaderboard.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 12 references that are in the map. First posted on arXiv 22 Aug 2026.
Builds on
8 of 12 references.
References · 8
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
- 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
- 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
- 2022TotalSegmentator: robust segmentation of 104 anatomical structures in CT imagescited by 613
Built on by
Not cited yet.