Structure-Aware OCTA Segmentation for OCTA-Derived Quantitative Analysis of Cerebral Microvascular Perfusion in Ischemic Stroke Authors: Jingmin Luan, Tian Jiang, Xiaohao Sun, Jian Liu, Yao Yu, Xiaojiao Dong, Yang Wang, Yajie Zhang, Zhenhe Ma Published: 2026 ABSTRACT Simple SummaryStroke can weaken vascular signals in optical coherence tomography angiography (OCTA), making vessel segmentation and derived measurements less reliable. We developed a structure-aware cerebral OCTA segmentation method and evaluated it in a photothrombotic mouse model. The method improved overlap, boundary, centerline, and branch-point agreement and was tested under controlled image degradation. In a separate longitudinal analysis, out-of-sample masks showed reduced OCTA-detectable perfusion coverage and apparent vessel length after ischemia, while average vessel diameter changed little. This exploratory preclinical study characterizes OCTA-detectable vascular changes after experimental ischemic stroke. 1. Introduction Ischemic stroke remains a major cause of mortality and long-term neurological disability worldwide [1,2]. Although large-vessel recanalization has improved acute stroke treatment, restoration of macrovascular patency does not necessarily ensure recovery of the cerebral microcirculation [3,4,5]. Persistent microvascular dysfunction may contribute to impaired reperfusion and progression of ischemic injury [6,7]. Penumbral evolution, microvascular constriction, and impaired capillary reflow are central components of acute ischemic injury [8,9,10], while high-resolution optical methods support repeated visualization of microvascular networks [11,12,13,14]. Photothrombotic mouse models combined with OCTA therefore provide a practical platform for longitudinal cerebral microvascular imaging [14,15]. Quantitative indices derived from OCTA can characterize detectable vascular patterns, but their reliability depends on accurate vessel segmentation. Ischemia-related signal attenuation, blurred vessel boundaries, and local signal discontinuities make cerebral OCTA segmentation challenging [16,17,18,19]. Region-overlap metrics such as the Dice coefficient quantify pixel-wise agreement but do not fully characterize boundary displacement, centerline continuity, or bifurcation preservation. These structural errors may affect downstream skeleton-derived measurements, particularly vessel length, branch-point density, and average curvature. Therefore, segmentation of ischemic cerebral OCTA images requires accurate regional delineation together with reliable representation of fine vessels and vascular network structure. In this study, “structural stability” means agreement with the reference annotation in boundary localization [95th-percentile Hausdorff distance (HD95) and average surface distance (ASD)], centerline continuity [centerline Dice (clDice) and centerline precision/recall], branch-point preservation (branch-point F1), and connected-component organization. It does not mean scan–rescan or longitudinal repeatability. Traditional vascular-segmentation methods mainly rely on intensity thresholding and multi-scale vesselness filtering [20,21]. Encoder–decoder convolutional networks and transformer-based architectures subsequently improved feature representation and multi-scale contextual modeling [22,23,24]. General-purpose and medical foundation segmentation models have further provided transferable representations for medical image segmentation [25,26,27,28,29], whereas structure- and boundary-aware networks have introduced task-specific constraints for curvilinear anatomical structures [30,31]. However, the integration of these complementary strategies for ischemic cerebral OCTA, together with their evaluation in relation to downstream vascular quantification, remains limited. To address this need, we developed a structure-aware vessel-segmentation framework based on a lightweight Swin-LiteMedSAM backbone. The framework integrates structure-guided boundary distillation (SBD), a geometry-aware boundary attention mechanism (GBAM), a multi-scale deep supervision strategy (MDSS), and a multi-scale collaborative attention module (MCAM). This study comprised two analytically distinct components. First, a technical segmentation experiment evaluated the proposed method against representative segmentation approaches using subject-level data separation and complementary overlap-, boundary-, centerline-, and bifurcation-sensitive metrics. Second, a separate exploratory longitudinal application used out-of-sample masks generated by sixfold subject-level cross-validation to calculate vascular perfusion density (VPD), vessel length (VL), vessel average diameter (VAD), branch-point density (BPD), and average curvature (AC) in a photothrombotic mouse stroke model. The main contributions of this study are as follows:A structure-aware cerebral OCTA segmentation framework that integrates boundary distillation, geometry-aware attention, multi-scale supervision, and cross-scale feature refinement within Swin-LiteMedSAM.An evaluation protocol combining overlap, boundary, centerline, bifurcation, and connected-component metrics with source-image-level statistics, controlled degradation tests, ablation, and parameter-sensitivity analysis.An exploratory longitudinal pipeline using out-of-sample masks to calculate five OCTA-derived vascular measurements after photothrombotic ischemia. A structure-aware cerebral OCTA segmentation framework that integrates boundary distillation, geometry-aware attention, multi-scale supervision, and cross-scale feature refinement within Swin-LiteMedSAM. A structure-aware cerebral OCTA segmentation framework that integrates boundary distillation, geometry-aware attention, multi-scale supervision, and cross-scale feature refinement within Swin-LiteMedSAM. An evaluation protocol combining overlap, boundary, centerline, bifurcation, and connected-component metrics with source-image-level statistics, controlled degradation tests, ablation, and parameter-sensitivity analysis. An evaluation protocol combining overlap, boundary, centerline, bifurcation, and connected-component metrics with source-image-level statistics, controlled degradation tests, ablation, and parameter-sensitivity analysis. An exploratory longitudinal pipeline using out-of-sample masks to calculate five OCTA-derived vascular measurements after photothrombotic ischemia. An exploratory longitudinal pipeline using out-of-sample masks to calculate five OCTA-derived vascular measurements after photothrombotic ischemia. 2. Related Works 2.1. Fine-Structure Vascular Segmentation Methods and Quantitative Limitations Thin branching vessels are sensitive to noise, low contrast, and local signal loss. Thresholding and vesselness filtering are efficient but vulnerable to these changes [20,21], whereas U-Net and transformer models learn stronger representations [22,23,24]. Dice and intersection over union (IoU) may still miss boundary displacement, centerline breaks, and false connections that alter skeleton-derived length, branch density, and curvature [32,33,34]. Ischemic OCTA therefore requires both region- and structure-sensitive evaluation. 2.2. Structure-Aware, Boundary-Aware, and Multi-Scale Segmentation Strategies Boundary losses improve edge localization, skeleton or topology losses encourage continuity, clDice measures centerline–region agreement, multi-scale supervision helps retain fine vessels, and attention modules refine feature selection [30,31,35,36,37,38]. In the proposed network, SBD supplies annotation-derived guidance during training, GBAM adds geometric boundary cues, MDSS supervises intermediate scales, and MCAM refines cross-scale features. These components are structure-sensitive but do not guarantee topology preservation or biomarker reproducibility. Table 1 compares these strategies and their relevance to ischemic OCTA quantification. 2.3. General-Purpose and Foundation Segmentation Models Foundation models such as SAM and medical lightweight derivatives provide transferable representations and efficient backbones [25,26,27,28,29]. However, their general segmentation objectives are not specific to weak cerebral OCTA boundaries or skeleton-sensitive vascular structures. We therefore retained Swin-LiteMedSAM as the backbone and added OCTA-specific structural constraints rather than using a larger generic architecture. 2.4. OCTA-Based Microvascular Visualization and Quantification Studies OCT/OCTA enables repeated, high-resolution visualization of microvascular networks and supports the measurement of perfusion density, vessel length, vessel diameter, branch density, and tortuosity [13,14,16,39,40,41]. Recent OCTA segmentation studies have explored weak supervision, connectivity-aware modules, and multi-scale feature learning [42,43,44], whereas cerebral OCTA studies have mainly focused on characterizing perfusion-related changes after experimental stroke [15,45,46]. Because reported segmentation performance is strongly influenced by anatomy, the retinal or cerebral layer analyzed, dataset composition, image quality, and annotation protocol, cross-study Dice values should be interpreted as contextual references rather than direct performance rankings. Previous studies have generally examined either segmentation accuracy or biological changes derived from OCTA, with relatively limited attention to the technical reliability of the intermediate segmentation and skeletonization steps. The present study therefore separates the two analytical components: segmentation experiments are used to evaluate the technical performance of the proposed method, while the longitudinal analysis applies out-of-sample masks to provide an exploratory description of OCTA-derived vascular changes after experimental stroke. 3. Materials and Methods To address common degradation issues in ischemic cerebral OCTA images, including reduced vascular contrast, blurred boundaries, and microvascular discontinuities, we construct a fully automated segmentation and quantitative analysis framework. The framework adopts the lightweight prompt-based segmentation model Swin-LiteMedSAM as the backbone network. Multidimensional structural constraints and semantic enhancement mechanisms are introduced to improve the modeling capability for complex degraded vascular morphologies while preserving computational efficiency. Figure 1 shows an overview of this framework. 3.1. Data Acquisition and Preprocessing All procedures were approved by the Institutional Animal Care Committee of Northeastern University and followed the Guide for the Care and Use of Laboratory Animals. The final cohort comprised six adult male C57BL/6 mice (20–30 g); their exact age was unavailable in the original records. Inclusion required successful induction, baseline imaging, complete longitudinal acquisition, and adequate OCTA signal. Prespecified exclusions were failed induction, uncorrectable motion, poor signal, incomplete imaging, or procedure-related death; none of these occurred. The available cohort was used without an a priori sample-size calculation. Photothrombosis was induced under sodium pentobarbital anesthesia (sodium pentobarbital, Sigma-Aldrich, St. Louis, MO, USA) by tail-vein Rose Bengal disodium salt injection (Rose Bengal, Sigma-Aldrich, St. Louis, MO, USA, formulated to 20 mg/mL in physiological saline) and irradiation with a 532 nm solid-state laser (Model MGL-III-5 mW, CNI Laser, Changchun, Jilin, China) for 30 min. OCTA was acquired at baseline and at 0.5, 1, 1.5, 2, 3, 4, 6, 8, and 10 h. A customized swept-source optical coherence tomography system with a central wavelength of 1310 nm, self-developed at Northeastern University at Qinhuangdao, provided 7.5 μm axial and 16 μm lateral resolution over approximately 8 × 7.5 mm; A-scan-wise motion correction and combined differential/decorrelation processing generated OCTA images [39,40,41,47]. Filtered and normalized optical attenuation coefficient (OAC) maps were calculated from structural OCT [48]. Ipsilateral pixels below the subject-specific 25th percentile of the contralateral OAC distribution defined the low-attenuation region of interest (ROI). This rank-based imaging criterion reduced inter-animal signal differences but was not histologically validated and was not interpreted as an ischemic core. 3.2. Annotation and Dataset Construction Reference masks were prepared in Fiji v1.54f (bundled ImageJ 1.54f, National Institutes of Health, Bethesda, MD, USA). One trained researcher annotated each image; a second reviewed vessel continuity, boundaries, fine vessels, artifacts, and bifurcations; and unresolved cases were adjudicated by a senior OCT/OCTA researcher. The consensus mask served as ground truth. Three experts, blinded to animal identity, time point, experimental condition, and annotator identity, rated annotation accuracy, boundary adherence, and topological plausibility on a five-point scale (5, excellent; 4, good; 3, acceptable; 2, poor; 1, unacceptable). Specific scoring criteria are detailed in Table S1 of the Supplementary Materials. Each expert reviewed all 115 original, non-augmented OCTA image–mask pairs; geometrically transformed derivatives were not rescored. The audit was descriptive quality control rather than an objective repeat-annotation study. The mean overall expert score was 4.60 ± 0.35 under the stated criteria. For each animal and time point, the OAC-defined ROI comprised ipsilateral pixels below the 25th percentile of the corresponding contralateral OAC distribution:(1)ROIlow-OAC={x∈Hipsi∣OACx