Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations

Hiba Azeem, Behraj Khan, Tahir Qasim Syed

TL;DR

It is demonstrated that integrating foundation representations with structured clinical priors improves NCCT stroke segmentation and ASPECTS delineation and this method achieves a Dice score of 0.6385 on AISD, outperforming prior CNN and foundation-model baselines.

Abstract

Rapid infarct assessment on non-contrast CT (NCCT) is essential for acute ischemic stroke management. Most deep learning methods perform pixel-wise segmentation without modeling the structured anatomical reasoning underlying ASPECTS scoring, where basal ganglia (BG) and supraganglionic (SG) levels are clinically interpreted in a coupled manner. We propose a clinically aligned framework that combines a frozen DINOv3 backbone with a lightweight decoder and introduce a Territory-Aware Gated Loss (TAGL) to enforce BG-SG consistency during training. This anatomically informed supervision adds no inference-time complexity. Our method achieves a Dice score of 0.6385 on AISD, outperforming prior CNN and foundation-model baselines. On a proprietary ASPECTS dataset, TAGL improves mean Dice from 0.698 to 0.767. These results demonstrate that integrating foundation representations with structured clinical priors improves NCCT stroke segmentation and ASPECTS delineation.

Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations

TL;DR

It is demonstrated that integrating foundation representations with structured clinical priors improves NCCT stroke segmentation and ASPECTS delineation and this method achieves a Dice score of 0.6385 on AISD, outperforming prior CNN and foundation-model baselines.

Abstract

Rapid infarct assessment on non-contrast CT (NCCT) is essential for acute ischemic stroke management. Most deep learning methods perform pixel-wise segmentation without modeling the structured anatomical reasoning underlying ASPECTS scoring, where basal ganglia (BG) and supraganglionic (SG) levels are clinically interpreted in a coupled manner. We propose a clinically aligned framework that combines a frozen DINOv3 backbone with a lightweight decoder and introduce a Territory-Aware Gated Loss (TAGL) to enforce BG-SG consistency during training. This anatomically informed supervision adds no inference-time complexity. Our method achieves a Dice score of 0.6385 on AISD, outperforming prior CNN and foundation-model baselines. On a proprietary ASPECTS dataset, TAGL improves mean Dice from 0.698 to 0.767. These results demonstrate that integrating foundation representations with structured clinical priors improves NCCT stroke segmentation and ASPECTS delineation.
Paper Structure (8 sections, 3 equations, 3 figures, 2 tables)

This paper contains 8 sections, 3 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Experiments
  5. AISD.
  6. Proprietary ASPECTS Dataset.
  7. Results
  8. Conclusion

Figures (3)

  • Figure 1: Overview of the proposed framework. An NCCT slice is processed by a frozen DINOv3 backbone and a multi-scale feature extractor in parallel. Two DPT-style dual-arm decoders process the respective features, and their outputs are fused via a Territory-Aware Gated Loss (TAGL) module before producing the final multi-class segmentation map $\hat{Y}$.
  • Figure 2: Training and validation performance curves. Left: Combined BCE–Dice loss. Right: Corresponding Dice score evolution. Model selection is based on the highest validation Dice.
  • Figure 3: Qualitative segmentation results on the AISD dataset produced by our best-performing model. Examples illustrate typical lesion appearances across challenging NCCT slices, including low-contrast regions and small or fragmented infarcts.