Skeleton-Guided Instance Separation for Fine-Grained Segmentation in Microscopy

TL;DR

This paper introduces A2B-IS, a novel one-stage microscopy instance segmentation framework that uses skeleton-guided features and semi-supervised learning to improve accuracy in complex, overlapping cell images.

Contribution

The paper presents a new one-stage instance segmentation method with skeleton-guided features, decoupled mask and box predictions, and semi-supervised learning for microscopy images.

Findings

Outperforms state-of-the-art methods on large-scale microscopy datasets.

Reduces computational costs through skeleton-guided anchor placement.

Improves instance separation accuracy in densely packed regions.

Abstract

One of the fundamental challenges in microscopy (MS) image analysis is instance segmentation (IS), particularly when segmenting cluster regions where multiple objects of varying sizes and shapes may be connected or even overlapped in arbitrary orientations. Existing IS methods usually fail in handling such scenarios, as they rely on coarse instance representations such as keypoints and horizontal bounding boxes (h-bboxes). In this paper, we propose a novel one-stage framework named A2B-IS to address this challenge and enhance the accuracy of IS in MS images. Our approach represents each instance with a pixel-level mask map and a rotated bounding box (r-bbox). Unlike two-stage methods that use box proposals for segmentations, our method decouples mask and box predictions, enabling simultaneous processing to streamline the model pipeline. Additionally, we introduce a Gaussian skeleton map to aid the IS task in two key ways: (1) It guides anchor placement, reducing computational costs while improving the model's capacity to learn RoI-aware features by filtering out noise from background regions. (2) It ensures accurate isolation of densely packed instances by rectifying erroneous box predictions near instance boundaries. To further enhance the performance, we integrate two modules into the framework: (1) An Atrous Attention Block (A2B) designed to extract high-resolution feature maps with fine-grained multiscale information, and (2) A Semi-Supervised Learning (SSL) strategy that leverages both labeled and unlabeled images for model training. Our method has been thoroughly validated on two large-scale MS datasets, demonstrating its superiority over most state-of-the-art approaches.