← Back to all news
arXiv Computer Vision By Valentin Boussot, Cedric Hemon, Caroline Lafond, Jean-Claude Nunes, Jean-Louis Dillenseger

When Misalignment Becomes Supervision: Structured Label Noise in Supervised Synthetic CT Generation

Read the original on arXiv Computer Vision →

The paper examines how residual misalignments from registration procedures introduce structured label noise in supervised synthetic CT (sCT) generation. It shows that voxel‑wise metrics are heavily influenced by the consistency between training and evaluation registrations, and that training with anatomically consistent registrations reduces variability and improves robustness. Introducing a perceptual loss based on a pretrained Segment Anything encoder yields sharper, more anatomically coherent sCT and highlights the need for anatomy‑oriented evaluation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 28

DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT

DALE-CT introduces depth‑aware 2D slice encoders that learn an anatomical world model of chest CT scans without 3D or positional supervision. By sampling self‑supervised views across a physical $z$‑axis slab, the encoder captures how anatomy changes between neighboring slices, enabling it to recover slice ordering and distinguish slices by anatomy alone. The model, trained on a large 287k‑scan corpus, achieves state‑of‑the‑art performance on CT‑RATE and is released with full code and evaluation tools.

By Evan W. Damron, Mahmut S. Gokmen, Mitchell A. Klusty, Caroline N. Leach, Emily B. Collier, V. K. Cody Bumgardner
llms
More like this →
arXiv AI
Sep 16

Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation

The paper presents the first systematic evaluation of out‑of‑distribution generalization for congenital heart disease (CHD) segmentation, using the ImageCHD cohort as a held‑out target. It compares several segmentation architectures under different training regimes, showing that in‑distribution performance is a poor predictor of cross‑cohort robustness: nnU‑Net drops from 0.77 to 0.51 Dice, while SwinUNETR maintains higher performance at 0.67 Dice. Limited target‑domain adaptation with only 11 labeled ImageCHD cases boosts all SwinUNETR variants above 0.76 Dice, highlighting the importance of explicit cross‑dataset testing.

By Aniketh Vijesh, Shrisharanyan Vasu, Abhijit Ramesh, Clare Pomeroy-Ward, Harikrishnan Anil Maya, Sarin Xavier, Mahesh Kappanayil, Gilad Gressel
computer-visionfine-tuning
More like this →