DINOv3 with Test-Time Calibration for Automated Carotid Intima-Media Thickness Measurement on CUBS v1
Authors: Zhenpeng Zhang, Jinwei Lu, Yurui Dong, Bo Yuan
Organizations: School of Basic Medical Sciences, Fudan University, Shanghai 200032, China · Fudan University, Shanghai, China · Institute of Medical Genetics and Genomics, Fudan University, Shanghai 200032, China
Carotid intima-media thickness (CIMT) measured from B-mode ultrasound is an established vascular biomarker for atherosclerosis and cardiovascular risk stratification. Although a wide range of computerized methods have been proposed for carotid boundary delineation and CIMT estimation, robust and transferable deep models that jointly address segmentation and measurement remain underexplored, particularly in the era of vision foundation models. Motivated by recent advances in adapting DINOv3 to medical segmentation and exploiting DINOv3 in test-time optimization pipelines, we investigate a DINOv3-based framework for carotid intima-media complex segmentation and subsequent CIMT measurement on the Carotid Ultrasound Boundary Study (CUBS) v1 dataset. Our pipeline predicts the intima-media band at a fixed image resolution, extracts upper and lower boundaries column-wise, corrects for image resizing using the per-image calibration factor provided by CUBS, and reports CIMT in physical units. Across three patient-level test splits, our method achieved a mean test Dice of 0.7739 ± 0.0037 and IoU of 0.6384 ± 0.0044. The mean CIMT absolute error was 181.16 ± 11.57 μm, with a mean Pearson correlation of 0.480 ± 0.259. In a held-out validation subset (n=28), test-time threshold calibration reduced the mean absolute CIMT error from 141.0 μm at the default threshold to 101.1 μm at the measurement-optimized threshold, while simultaneously reducing systematic bias toward zero. Relative to the error ranges reported in the original CUBS benchmark for classical computerized methods, these results place a DINOv3-based approach within the clinically relevant ∼0.1 mm measurement regime. Together, our findings support the feasibility of using vision foundation models for interpretable, calibration-aware CIMT measurement.
Figures & tables
Figure 1: End-to-end CIMT measurement workflow. The segmented intima-media band is converted into upper and lower boundaries, transformed into a column-wise thickness profile, and finally converted from resized-pixel units to physical units using calibration-factor correction.
Figure 2: Quantitative performance summary of the proposed DINOv3-based CIMT measurement system. The figure highlights absolute measurement error, systematic bias, agreement behavior, and the improvement obtained by test-time calibration.
Figure 3: Additional qualitative evidence for DINOv3-based CIMT measurement. The top panel summarizes the effect of threshold calibration on representative cases, while the lower panels provide complementary visual evidence of model response patterns and challenging residual-error cases.
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
The tortuosity of corneal nerve fibers are used as indication for different diseases. Current state-of-the-art methods for grading the tortuosity heavily rely on expensive segmentation maps of these nerve fibers. In this paper, we demonstrate that self-supervised pretrained features from ImageNet are transferable to the domain of in vivo confocal microscopy. We show that DINO should not be disregarded as a deep learning model for medical imaging, although it was superseded by two later versions. After careful fine-tuning, DINO improves upon the state-of-the-art in terms of accuracy (84,25%) and sensitivity (77,97%). Our fine-tuned model focuses on the key morphological elements in grading without the use of segmentation maps.
Kim Ouan, Noémie Moreau, Katarzyna Bozek
Faculty of Mathematics and Natural Sciences, University of Cologne, Germany · Institute for Biomedical Informatics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Germany · Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital Cologne, University of Cologne, Germany +1
Accurate coronary artery segmentation on coronary computed tomography angiography (CCTA) is essential for diagnosing coronary artery disease. Deep networks are conventionally trained and evaluated with the Dice coefficient, but volume-overlap metrics are poorly suited to thin, tubular anatomy: since most voxels belong to a few thickproximal segments, a missing distal branch barely affects Dice despite severely disrupting the connectivity required for clinical use. We introduce a surface metric that matches predicted and reference surface points via bipartite assignment under a localized, vessel-radius tolerance, reporting precision, recall, and F1 with decoupled false positives (spurious branches) and false negatives (missed branches) a distinction the symmetric Dice cannot make. With it we show that a strong Dice-trained baseline omits far more vessel surface than it hallucinates, an asymmetry its high Dice hides. Building on this, we propose a differentiable surface loss that simultaneously suppresses spurious mass and recovers absent structure, validated by fine-tuning three backbones (nnU-Net, SwinUNETR, NexToU) on two public benchmarks (Image-CAS, ASOCA). Against a matched-epoch control, it significantly improves surface F1 by recovering missed distal vessels at comparable Dice. Our findings argue for measuring and optimizing the vessel surface, not the volume it overlaps. Code
Rafael Velasquez, Esther Puyol-Antón, Pablo Arbeláez
Universidad de los Andes, Bogotá, Colombia · School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK