Aug 2026· Medical Physics (Lancaster)· Vol 53 9, pp.
e70653
· 1 citation· 51 references
Computer ScienceMedicine
TL;DR
NA-UNETR effectively balances local precision and global context, enabling accurate segmentation of thin, low-contrast LAD structures and demonstrates a robust and computationally efficient framework for substructure-level cardiac segmentation in radiotherapy planning.
Abstract
Background
Accurate segmentation of the left anterior descending (LAD) artery in 3D free-breathing, non-contrast CT is critical for cardiac dose sparing in thoracic radiotherapy. The task is inherently difficult because the LAD is extremely small, exhibits poor soft-tissue contrast, and varies substantially across patients. Even manual contours show limited inter-observer agreement on non-contrast CT, underscoring the ambiguity of the vessel boundaries.
Purpose
To develop a transformer-based segmentation framework that enhances LAD delineation in low-contrast, imbalanced CT using local-global context modeling and uncertainty-guided optimization.
Methods
We propose NA-UNETR, a 3D transformer-based segmentation model with neighborhood attention (NA) and Dilated NA (DiNA) blocks that jointly capture fine structural detail and long-range context. To address the limited availability of annotated LAD artery data, the model is pretrained on 1000 CTA volumes representing general coronary anatomy and then fine-tuned using a parameter-efficient adaptation strategy on 20 free-breathing institutional CT scans of the LAD artery. A composite Dice-Focal and Hausdorff loss, dynamically balanced via homoscedastic uncertainty, improves overlap and boundary accuracy. Preprocessing included intensity clipping, contrast enhancement, and artery-centric sampling, and postprocessing refined morphology.
Results
NA-UNETR achieved comparable performance to SOTA with improved efficiency and boundary properties. It reached 45.64% Dice, 38.16 mm HD95, and 10.01 mm ASD, improving Dice by 3.10 percentage points over nnU-Net and reducing HD95 by 2.96 mm relative to Swin UNETR, while showing the strongest boundary accuracy among all models and demonstrating improved geometric and centerline stability. On ImageCAS, it achieved 79.49% Dice, 8.89 mm HD95, and 1.02 mm ASD. Ablations confirmed that residual blocks, variable kernels, and uncertainty-weighted loss each contributed to performance stability and boundary precision.
Conclusions
NA-UNETR effectively balances local precision and global context, enabling accurate segmentation of thin, low-contrast LAD structures. Its integration of NA, uncertainty-weighted loss, and LoRA-based fine-tuning demonstrates a robust and computationally efficient framework for substructure-level cardiac segmentation in radiotherapy planning.
This work proposes a novel two-stage segmentation framework that provides a favorable trade-off between segmentation accuracy and inference efficiency, supporting its potential for practical clinical deployment.
Chen Zhou, Wenjing Han, Yueming Wu et al.· Computerized Medical Imaging...· 0 citations
The proposed anatomy-informed multi-task framework improves lesion segmentation, reduces false positives, and generalizes robustly across multiple cohorts, and introduces a prototype-based inference strategy that uses feature-space similarity to suppress morphologically confusing false positives.
Zhuo-Wei Xu, Tian-Yi Liu, Long Bai et al.· Medical Image Analysis· 0 citations
Accurate segmentation of coronary arteries in X-ray angiography videos is essential for quantitative coronary analysis and image-guided interventions. However, accurate segmentation remains challenging because coronary vessels are thin and exhibit low contrast, while the presence of catheters, guidewires, and complex a...
A modality-routed 3D cardiac segmentation pipeline that combines TotalSegmentator-initialized nnU-Netv2 models with site-characterized, label-preserving appearance augmentation is proposed, suggesting that site-motivated appearance augmentation is a practical strategy for improving cross-site robustness in limited-data...
Tanishqua H Mudaliar, Justin D. Li, Daniel Lin et al.· 0 citations
B-MIM is introduced, a modification of the iBOT objective that stochastically reduces global semantic alignment to prioritize local patch reconstruction and suggests that reducing global semantic pressure during pretraining enhances generalization to intricate anatomical structures.
S. González, Karen Sanchez, J. M. Saavedra et al.· 0 citations
F focal-modulation-driven global context with deformable-convolution-based local adaptation produces boundary-refined pancreatic tumor segmentations on CT, which improves boundary fidelity and provides a transparent layer of review that may support treatment planning and longitudinal monitoring.
V. M. Firos, P. J. A. Alphonse, Ugo Fiore et al.· Machine Vision and Applicati...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.