CoFi: A Fast Coarse-to-Fine Few-Shot Pipeline for Glomerular Basement Membrane Segmentation

TL;DR

CoFi is a fast, coarse-to-fine few-shot segmentation pipeline for electron microscopy images that reduces annotation effort while achieving high accuracy in glomerular basement membrane delineation.

Contribution

Introduces CoFi, a novel efficient pipeline combining lightweight training and SAM-guided refinement for GBM segmentation with minimal annotations.

Findings

Achieved 74.54% Dice coefficient in GBM segmentation.

Operates at 1.9 FPS, enabling real-time analysis.

Reduces annotation and computational burdens compared to traditional methods.

Abstract

Accurate segmentation of the glomerular basement membrane (GBM) in electron microscopy (EM) images is fundamental for quantifying membrane thickness and supporting the diagnosis of various kidney diseases. While supervised deep learning approaches achieve high segmentation accuracy, their reliance on extensive pixel-level annotation renders them impractical for clinical workflows. Few-shot learning can reduce this annotation burden but often struggles to capture the fine structural details necessary for GBM analysis. In this study, we introduce CoFi, a fast and efficient coarse-to-fine few-shot segmentation pipeline designed for GBM delineation in EM images. CoFi first trains a lightweight neural network using only three annotated images to produce an initial coarse segmentation mask. This mask is then automatically processed to generate high-quality point prompts with morphology-aware pruning, which are subsequently used to guide SAM in refining the segmentation. The proposed method achieved exceptional GBM segmentation performance, with a Dice coefficient of 74.54% and an inference speed of 1.9 FPS. We demonstrate that CoFi not only alleviates the annotation and computational burdens associated with conventional methods, but also achieves accurate and reliable segmentation results. The pipeline's speed and annotation efficiency make it well-suited for research and hold strong potential for clinical applications in renal pathology. The pipeline is publicly available at: https://github.com/ddrrnn123/CoFi.