← Back to all news
arXiv AI By David Corral Fontecha, Juan Miranda Bautista, Pablo Menendez Fern\'andez-Miranda, Sergio Rubio-Mart\'in, Lara Lloret Iglesias, Jose A. Vega

Physically Aware Radiomics Without Interpolation: Disentangling Voxel Geometry and Signal Modification in CT and MRI

Read the original on arXiv AI →

The study introduces a voxel-spacing-aware radiomic framework that incorporates physical geometry into texture computation without resampling, modifying PyRadiomics to preserve native image signals. Four extraction configurations—native non-resampled (NR), isotropic resampling (RS), voxel-spacing-aware (VS), and fake-isotropic preprocessing (FK)—were compared across 685 CT pulmonary nodules and 209 MRI breast cases, evaluating 196 radiomic descriptors. Results show that VS closely matches NR (median ICC(A,1) ≈0.998) while RS and FK exhibit lower agreement, indicating that spacing metadata alone can significantly influence radiomic features.

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 AI.

Related stories

arXiv AI
Jun 3

Sparse-View Lung Nodule Volumetry from Digitally Reconstructed Radiographs via AReT: Anatomy-Regularized TensoRF

arXiv:2606. 02639v1 Announce Type: cross Abstract: We identify and resolve a previously unreported failure mode in TensoRF when applied to X-ray attenuation fields: the default density shift of -10, originally introduced for RGB scene reconstruction, suppresses density gradients and prevents sparse-view medical reconstruction regardless of learning rate or regularization strategy.

By Spoorthi M, Suja Palaniswamy
efficiencysafety
More like this →
arXiv Computer Vision
Aug 28

Parameter-Efficient pretrained-CT-to-MRI Transfer for Rectal Cancer Segmentation: Performance-Calibration Trade-offs

The paper introduces SWIFT, a Swin V2‑based model pretrained on 10,444 3D CT volumes and fine‑tuned for rectal cancer segmentation on T2‑weighted MRI. Four configurations—full fine‑tuning (SWIFT), decoder compression (SWIFTe), low‑rank adaptation (SWIFTe‑LoRA), and a LoRA‑decoder ensemble (SWIFTe‑LDE4)—were evaluated on 247 cases, showing that SWIFTe reduces parameters by 70.1% while improving tumor detection and radiomic agreement. The study also demonstrates a trade‑off between detection and boundary agreement, and highlights that SWIFTe‑LDE4 achieves the lowest calibration errors after temperature scaling.

By Aneesh Rangnekar, Jorge Tapias Gomez, Joseph O Deasy, Harini Veeraraghavan
computer-visionfine-tuningbenchmarks
More like this →