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.
Carotid atherosclerosis is a major contributor to ischemic stroke and transient ischemic attack. Conventional ultrasound assessment is commonly based on intima-media thickness, plaque appearance, stenosis degree, and peak systolic velocity, but these morphology- and velocity-based indicators may not fully capture patient-specific vascular risk. This study presents AtheroFlow-XNet, a CUBS-compatible ultrasound morphology and uncertainty-aware learning baseline for carotid intima-media segmentation and preliminary risk prediction. Using the Carotid Ultrasound Boundary Study dataset, manual lumen-intima and media-adventitia boundary annotations were converted into dense intima-media masks for supervised segmentation. Clinical variables were incorporated into an auxiliary risk-prediction branch, and Monte Carlo dropout was used for uncertainty-aware inference. The model was evaluated using a patient-level train-validation-test split with 1,522 training images, 326 validation images, and 328 testing images. The proposed model achieved a Dice coefficient of 0.7930 for LI-MA mask segmentation, a segmentation loss of 0.2359, and an area under the receiver operating characteristic curve of 0.6910 for preliminary risk prediction. Qualitative results showed that predicted masks were generally aligned with manual annotations, while uncertainty maps highlighted ambiguous wall-boundary regions. These results suggest that ultrasound-derived carotid morphology can support automated wall analysis and uncertainty-aware interpretation. Since CUBS does not provide Doppler waveforms or CFD-derived hemodynamic biomarkers, this work should be interpreted as a reproducible morphology-driven baseline. Future work will incorporate Doppler-derived flow profiles, patient-specific vascular reconstruction, and CFD-based wall shear biomarkers.
Aueaphum Aueawatthanaphisut
School of Information, Computer, and Communication Technology Sirindhorn International Institute of Technology, Thammasat University Pathum Thani, Thailand
Accurate segmentation of carotid arteries in ultrasound imaging is critical for stroke risk assessment. However, speckle noise, low contrast, and blurred boundaries remain major challenges. In this paper, we propose a Frequency-Spatial Synergy Network (FSS-Net) to achieve noise-robust and high-precision carotid artery segmentation. The network integrates wavelet transform, multi-domain attention, and edge enhancement into a unified encoder-decoder architecture. Specifically, a Channel-Spatial-Wavelet Attention (CSWA) module is designed to suppress noise and purify semantic features in the frequency domain. A Wavelet-Enhanced Bottleneck (WEB) module is introduced to capture long-range global dependencies efficiently. Furthermore, a Laplacian-Guided Adaptive Edge Fusion (LAEF) module compensates high-frequency details and maintains boundary continuity. Extensive experiments on carotid ultrasound datasets show that FSS-Net achieves a Dice score (DSC) of 96.46% and strong robustness under low SNR conditions, outperforming several state-of-the-art methods. This method realizes accurate segmentation of carotid artery in ultrasonic imaging, effectively identifies carotid atherosclerotic plaque, and is verified by other task (such as segmentation of breast cancer), suggesting that it has good clinical application potential in identifying abnormal tissue masses in ultrasonic images.
Jiawei Liu, Zhijiang Wan, Junhua Hu +5
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
Accurate segmentation of the coronary vessel lumen is a prerequisite for quantitative assessment of atherosclerotic plaque and perivascular adipose tissue in coronary computed tomography angiography (CCTA). Cardiologists rely on semi-automated methods for this task because manual vessel tracing and segmentation are labour-intensive. Although many automated methods have been proposed, their validation remains limited by the lack of large, high-quality publicly available datasets. We provide a new dataset of voxel-wise annotations of the vessel lumen and coronary segments, alongside centerlines, and mesh surfaces for 800 scans from the publicly available ImageCAS dataset. Using this dataset, we benchmark established lumen segmentation methods against inter-observer variability, stratifying performance by disease, image quality, coronary dominance, coronary segment, vessel diameter, and lumen attenuation. These labels allow segmentation accuracy to be described in anatomical and clinical context rather than reported as a single aggregate score. The dataset supports the development and validation of methods for lumen segmentation, plaque and perivascular quantification, and haemodynamic modelling.
Kit M. Bransby, Esther Øksnebjerg, Kristoffer Kjær +7
DTU Compute, Technical University of Denmark, Kongens Lyngby, Denmark · Cardiovascular Research Unit, Copenhagen University Hospital – Rigshospitalet, Copenhagen, Denmark