Semi-Supervised Retinal Vessel Segmentation via SAM-Based Teacher-Student Distillation with Topology-Aware Loss

OBJECTIVE: Accurate retinal vessel segmentation is critical for early diagnosis and monitoring of ocular and systemic diseases. However, deep learning methods are often limited by scarce pixel-level annotations and the inability of standard loss functions to preserve vascular topology, leading to fragmented vessel predictions. APPROACH: We propose SAM-KD a semi-supervised framework that adapts the Segment Anything Model (SAM) for retinal vessel segmentation through a two-stage teacher-student distillation strategy. A LoRA-adapted SAM ViT-B teacher and a lightweight TinyViT-5M student are first trained on limited labeled data. The frozen teacher then generates soft pseudo-labels for unlabeled images, guiding the student through feature-level and logit-level distillation. To improve structural continuity, we introduce a graph-based connectivity loss (L conn ) that penalizes topological discrepancies based on Betti numbers and skeleton length. MAIN RESULTS: Experiments on three public benchmarks (STARE, CHASEDB1, and HRF) using only 20% labeled data show that SAM-KD outperforms other baselines across both pixel-level metrics (Dice, sensitivity, MCC) and topological metrics (clDice, ∆b 0 , ∆b 1 ). On HRF, the proposed connectivity loss reduces ∆b 1 by 46% compared with the strongest semi-supervised baseline (38.2 vs. 71.5). The distilled TinyViT-5M student (5.4 M parameters) achieves inference in 12 ms per image with 4.9 GB VRAM, providing a 5.8× speedup and 2.9× lower memory usage than the teacher, with only a 1.1-point Dice reduction. CONCLUSION: SAM-KD provides an effective and annotation-efficient solution for retinal vessel segmentation by combining foundation model adaptation, hierarchical distillation, and topology-aware supervision. Its lightweight design makes it suitable for real-time clinical deployment in resource-constrained environments.

Authors

Institutions

Publication Details

Journal
Physiological Measurement
Published
2026-11-17
DOI
https://doi.org/10.1088/1361-6579/aec350
Primary Topic
Retinal Imaging and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Semi-Supervised Retinal Vessel Segmentation via SAM-Based Teacher-Student Distillation with Topology-Aware Loss

Duc Tri Phan
2 links
Physiological Measurement
Retinal Imaging and Analysis
article

Semi-Supervised Retinal Vessel Segmentation via SAM-Based Teacher-Student Distillation with Topology-Aware Loss

Duc Tri Phan
article en

Abstract

OBJECTIVE: Accurate retinal vessel segmentation is critical for early diagnosis and monitoring of ocular and systemic diseases. However, deep learning methods are often limited by scarce pixel-level annotations and the inability of standard loss functions to preserve vascular topology, leading to fragmented vessel predictions. APPROACH: We propose SAM-KD a semi-supervised framework that adapts the Segment Anything Model (SAM) for retinal vessel segmentation through a two-stage teacher-student distillation strategy. A LoRA-adapted SAM ViT-B teacher and a lightweight TinyViT-5M student are first trained on limited labeled data. The frozen teacher then generates soft pseudo-labels for unlabeled images, guiding the student through feature-level and logit-level distillation. To improve structural continuity, we introduce a graph-based connectivity loss (L conn ) that penalizes topological discrepancies based on Betti numbers and skeleton length. MAIN RESULTS: Experiments on three public benchmarks (STARE, CHASEDB1, and HRF) using only 20% labeled data show that SAM-KD outperforms other baselines across both pixel-level metrics (Dice, sensitivity, MCC) and topological metrics (clDice, ∆b 0 , ∆b 1 ). On HRF, the proposed connectivity loss reduces ∆b 1 by 46% compared with the strongest semi-supervised baseline (38.2 vs. 71.5). The distilled TinyViT-5M student (5.4 M parameters) achieves inference in 12 ms per image with 4.9 GB VRAM, providing a 5.8× speedup and 2.9× lower memory usage than the teacher, with only a 1.1-point Dice reduction. CONCLUSION: SAM-KD provides an effective and annotation-efficient solution for retinal vessel segmentation by combining foundation model adaptation, hierarchical distillation, and topology-aware supervision. Its lightweight design makes it suitable for real-time clinical deployment in resource-constrained environments.

Physiological Measurement
Duy Tan University (VN)
Retinal Imaging and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon