针对精子重叠和染色杂质难题，提出无监督分割方法SpeHeatal
SpeHeatal: A Cluster-Enhanced Segmentation Method for Sperm Morphology Analysis
- 基于连通性、一致性与距离设计聚类算法Con2Dis，精准分割重叠尾部
- 结合SAM模型与定制拼接技术，实现头尾完整分割，准确率显著提升
- 无需标注数据，特别适合复杂精子图像分析，临床诊断价值高
精确评估精子形态对男科诊断至关重要，但精子图像分割面临巨大挑战。现有方法依赖大量标注数据，难以处理精子重叠及染色杂质问题。本文从几何角度分析重叠尾部问题，提出新型聚类算法Con2Dis，综合考虑连通性、一致性与距离三个关键因素，有效分割重叠尾部。在此基础上，提出无监督方法SpeHeatal，用于完整分割精子头和尾。该方法利用Segment Anything Model(SAM)生成精子头掩码并过滤染色杂质，通过Con2Dis分割尾部，并采用定制掩码拼接技术构建完整精子掩码。实验表明，SpeHeatal在处理重叠精子图像时表现优异，显著优于现有方法。
原文摘要 · Abstract (English)
The accurate assessment of sperm morphology is crucial in andrological diagnostics, where the segmentation of sperm images presents significant challenges. Existing approaches frequently rely on large annotated datasets and often struggle with the segmentation of overlapping sperm and the presence of dye impurities. To address these challenges, this paper first analyzes the issue of overlapping sperm tails from a geometric perspective and introduces a novel clustering algorithm, Con2Dis, which effectively segments overlapping tails by considering three essential factors: CONnectivity, CONformity, and DIStance. Building on this foundation, we propose an unsupervised method, SpeHeatal, designed for the comprehensive segmentation of the SPErm HEAd and TAiL. SpeHeatal employs the Segment Anything Model(SAM) to generate masks for sperm heads while filtering out dye impurities, utilizes Con2Dis to segment tails, and then applies a tailored mask splicing technique to produce complete sperm masks. Experimental results underscore the superior performance of SpeHeatal, particularly in handling images with overlapping sperm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。