Automated carotid artery atherosclerotic inflammation segmentation in PET using MSR-Net
Authors: Ran Li, Abhinav K. Jha, Jie Zheng, Richard Laforest, Yongjian Liu, Mohamed Zayed, Tyler J. Fraum, Barry A. Siegel, +3 more
Organizations: Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, the United States · Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, the United States · Department of Surgery, Washington University in St. Louis, St. Louis, the United States
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.
Figures & tables
Figure 1: Representative simulation example: (a) high-resolution uptake map with a simulated high-uptake region within the vessel wall (left column) and (b) the corresponding synthetic PET image (right column).
Figure 2: Structure of neural network.
Figure 3: (a) Structure of MSR; (b) Structure of Mid-focus Residual Block; (c) Structure of Wide-focus Residual Block; (d) Structure of Residual Block; (e) Structure of double convolution.
Table 3: Segmentation performance across different levels of inflammation-to-background contrast. Values are reported as mean with 95% confidence intervals. The weighted average is computed across contrast intervals with weights proportional to the number of test slices in each interval (32, 98 and 54 slices respectively). Weighted averages were calculated from the underlying unrounded values, so they may differ slightly from values recomputed using the rounded subgroup means shown in the table. The weighted DSC values are 0.73, 0.69, 0.75 and 0.79 for U-Net, Transformer U-Net, DUCK-Net and the proposed method, respectively.
Figure 4: Three representative results corresponding to different contrast ranges using proposed method and the other three DL algorithms. From top to bottom row corresponding to: Contrast = 0.83(low), 1.27(medium), and 1.74(high), respectively.
Figure 5: Focal radiotracer uptake on PET and corresponding carotid plaque-component segmentation on MR images for three representative cases. The MR images are displayed at the same image scale for direct visual comparison. The MR plaque-component segmentation was generated using the previously published two-stage multi-weighted MRI method of Li and others (2023) . In the plaque segmentation, green indicates fresh hemorrhage within 10 days, and red indicates old hemorrhage over 10 days. The mean SUV is measured and shown in the figure.
Figure 6: Association between the percentage volume of LR/NC with hemorrhage and corrected SUVmean (a) and corrected SUVmax (b). Points represent slice-level observations. Solid lines indicate population-level fixed-effect fits from linear mixed-effects models with patient-specific random intercepts, and shaded bands indicate 95% confidence intervals for the fixed-effect mean.
School of Information, Computer, and Communication Technology Sirindhorn International Institute of Technology, Thammasat University Pathum Thani, Thailand
Ji luan Academy, Nanchang University, Nanchang 330031, China · School of Information Engineering, Nanchang University, Nanchang 330031, China · State Key Laboratory of Water Cycle and Water Security, China Institute of Water Resources and Hydropower Research, Beijing 100038, China +4
DTU Compute, Technical University of Denmark, Kongens Lyngby, Denmark · Cardiovascular Research Unit, Copenhagen University Hospital – Rigshospitalet, Copenhagen, Denmark