IPSM-Bench: A New Intermediate Phase Segmentation Benchmark in Microstructure Images of Zinc-Based Absorbable Biomaterials

2026-06-09

AI Summary

This study addresses the challenges of intermediate phase segmentation in microstructural images of zinc-based absorbable biomaterials, which include scarce annotations, low contrast, densely packed small targets, and high morphological heterogeneity. To tackle these issues, the authors introduce IPSM-Bench, the first high-quality benchmark dataset specifically curated for zinc alloy intermediate phase segmentation, and propose SCoP-SAM—a novel method that integrates spatial context priors derived from gradient structure and grayscale features into the full encoder–decoder pipeline of the Segment Anything Model (SAM). The proposed approach substantially enhances segmentation accuracy and generalization capability, achieving state-of-the-art performance on IPSM-Bench and demonstrating robust effectiveness across multiple public alloy datasets, thereby advancing the analysis of zinc alloy microstructures.

Abstract

Zinc-based alloys are indispensable emerging absorbable metallic biomaterials, and their macroscopic performance is governed by microstructural characteristics. Intermediate phases-key microstructural constituents-are pivotal in regulating mechanical and functional properties. However, intermediate phase segmentation in zinc alloy microstructures faces formidable challenges: scarce annotated datasets, low contrast, difficulty detecting small targets, and heterogeneous morphologies. To this end, we construct IPSM-Bench, the largest high-quality dataset for zinc-alloy intermediate phase segmentation. Furthermore, we propose SCoP-SAM, a new Spatial Context Prior-guided SAM method that leverages the gradient structure and grayscale properties of intermediate phases to capture spatial context priors and incorporates them into the entire SAM encoding-decoding process, improving segmentation performance. Based on the proposed IPSM-Bench, we establish a new benchmark for intermediate phase segmentation to systematically evaluate state-of-the-art (SOTA) methods and advance research on zinc alloy microstructure analysis. Extensive experiments on IPSM-Bench and additional public alloy benchmarks demonstrate that our SCoP-SAM not only achieves SOTA performance for zinc-alloy intermediate phase segmentation but also generalizes remarkably well to other alloy scenarios.

Problem

• intermediate phase segmentation
• zinc-based biomaterials
• microstructure images
• low contrast
• small target detection

Innovation

• intermediate phase segmentation
• zinc-based biomaterials
• spatial context prior
• SCoP-SAM
• microstructure analysis