Automated carotid artery atherosclerotic inflammation segmentation in PET using MSR-Net
Abstract
Objective. To develop an automated method for segmentation and uptake quantification of carotid atherosclerotic inflammation on 64Cu-CANF-comb PET while accounting for partial-volume and tissue-fraction effects. Approach. Synthetic carotid PET images with known fractional-volume ground truth were generated by combining MR-derived high-resolution activity maps with GATE Monte Carlo simulation incorporating major PET physical processes and matched to the Biograph mMR acquisition and reconstruction. A two-stage network first localized the carotid vessel wall from T1-weighted MR and then estimated voxel-wise inflammation fraction from masked PET. Both stages used a multiscale residual (MSR) convolutional backbone. Performance was compared with U-Net, Transformer U-Net, DUCK-Net, and iterative Yang partial-volume correction. Main results. In a two-alternative forced-choice study, five nuclear-medicine physicians identified real images with 54% accuracy (54/100; Wilson 95% CI 0.44-0.63; exact binomial p = 0.48). On 184 simulated test slices from five held-out patients, the proposed method achieved a weighted DSC of 0.79, compared with 0.73 for U-Net, 0.69 for Transformer U-Net, and 0.75 for DUCK-Net, with corresponding HD values of 1.85, 2.29, 2.32, and 2.23 voxels. Patient-cluster bootstrap comparisons favored the proposed method for DSC and HD against all three baselines (Holm-corrected p <= 0.031). Overall ENRMSE was 0.24 versus 0.59, 0.68, and 0.59 for the three DL baselines and 0.57 for iterative Yang. In seven patients, corrected SUV showed a positive association with MR-derived lipid-rich/necrotic core with hemorrhage. Significance. The proposed framework improved carotid PET segmentation and uptake quantification under simulated conditions. The patient analysis is preliminary and requires external validation with biological reference standards before clinical deployment.
Related
- Comparative Evaluation of Carotid Artery Hemodynamics: Patient-Specific CFD Simulations vs. 4D flow MRI
- Fully automated diaphragm segmentation on routine 2D-cine and 3D thoracic MRI: multireader validation
- Effects of Deep Learning Architecture and Pretraining on Automated Vocal Fold Segmentation in Ex Vivo High-Speed Phonation Images
- Attention-guided super-resolution of 4D flow MRI in carotid arteries
- Using Graph Neural Networks for the segmentation of overlapping objects in high granularity calorimeters
BibTeX
@misc{li2026automated,
title = {{Automated carotid artery atherosclerotic inflammation segmentation in PET using MSR-Net}},
author = {Ran Li and Abhinav K. Jha and Jie Zheng and Richard Laforest and Yongjian Liu and Mohamed Zayed and Tyler J. Fraum and Barry A. Siegel and Malak Itani and Joyce C. Mhlanga and Pamela K. Woodard},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.15245},
eprint = {2610.15245},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.15245},
}
RIS
TY - UNPB
TI - Automated carotid artery atherosclerotic inflammation segmentation in PET using MSR-Net
AU - Ran Li
AU - Abhinav K. Jha
AU - Jie Zheng
AU - Richard Laforest
AU - Yongjian Liu
AU - Mohamed Zayed
AU - Tyler J. Fraum
AU - Barry A. Siegel
AU - Malak Itani
AU - Joyce C. Mhlanga
AU - Pamela K. Woodard
PY - 2026
DA - 2026/10/11
PB - arXiv
DO - 10.48550/arxiv.2610.15245
UR - https://arxiv.org/abs/2610.15245
AB - Objective. To develop an automated method for segmentation and uptake quantification of carotid atherosclerotic inflammation on 64Cu-CANF-comb PET while accounting for partial-volume and tissue-fraction effects. Approach. Synthetic carotid PET images with known fractional-volume ground truth were generated by combining MR-derived high-resolution activity maps with GATE Monte Carlo simulation incorporating major PET physical processes and matched to the Biograph mMR acquisition and reconstruction. A two-stage network first localized the carotid vessel wall from T1-weighted MR and then estimated voxel-wise inflammation fraction from masked PET. Both stages used a multiscale residual (MSR) convolutional backbone. Performance was compared with U-Net, Transformer U-Net, DUCK-Net, and iterative Yang partial-volume correction. Main results. In a two-alternative forced-choice study, five nuclear-medicine physicians identified real images with 54% accuracy (54/100; Wilson 95% CI 0.44-0.63; exact binomial p = 0.48). On 184 simulated test slices from five held-out patients, the proposed method achieved a weighted DSC of 0.79, compared with 0.73 for U-Net, 0.69 for Transformer U-Net, and 0.75 for DUCK-Net, with corresponding HD values of 1.85, 2.29, 2.32, and 2.23 voxels. Patient-cluster bootstrap comparisons favored the proposed method for DSC and HD against all three baselines (Holm-corrected p <= 0.031). Overall ENRMSE was 0.24 versus 0.59, 0.68, and 0.59 for the three DL baselines and 0.57 for iterative Yang. In seven patients, corrected SUV showed a positive association with MR-derived lipid-rich/necrotic core with hemorrhage. Significance. The proposed framework improved carotid PET segmentation and uptake quantification under simulated conditions. The patient analysis is preliminary and requires external validation with biological reference standards before clinical deployment.
ER -