单时点分割模型在纵向病灶分析中因定位偏移导致性能崩溃
Unstable Prompts, Unreliable Segmentations: A Challenge for Longitudinal Lesion Analysis
- 通过人为偏移病灶位置，验证模型对中心定位的强依赖性
- 随扫描配准误差增大，随访图像分割准确率急剧下降
- 提示需构建端到端纵向分析模型，而非串行单时点工具
纵向病灶分析对肿瘤诊疗至关重要，但自动化工具常面临时间一致性挑战。尽管通用病灶分割模型已有进展，但多针对单一时点设计。本文评估了ULS23分割模型在纵向场景下的表现。基于公开的基线与随访CT数据集，研究发现两个关键且相互关联的失败模式：随访图像因扫描间配准误差导致分割质量显著下降，进而引发病灶对应关系失效。为系统探究此脆弱性，我们进行受控实验，人工将输入体数据相对于真实病灶中心进行偏移。结果表明，模型性能高度依赖于病灶居中的假设；当病灶偏移足够大时，分割准确率骤降。这些发现揭示了将单时点模型应用于纵向数据的根本局限。结论指出，可靠的肿瘤追踪需从串联单功能工具转向专为时间分析设计的端到端集成模型。
原文摘要 · Abstract (English)
Longitudinal lesion analysis is crucial for oncological care, yet automated tools often struggle with temporal consistency. While universal lesion segmentation models have advanced, they are typically designed for single time points. This paper investigates the performance of the ULS23 segmentation model in a longitudinal context. Using a public clinical dataset of baseline and follow-up CT scans, we evaluated the model's ability to segment and track lesions over time. We identified two critical, interconnected failure modes: a sharp degradation in segmentation quality in follow-up cases due to inter-scan registration errors, and a subsequent breakdown of the lesion correspondence process. To systematically probe this vulnerability, we conducted a controlled experiment where we artificially displaced the input volume relative to the true lesion center. Our results demonstrate that the model's performance is highly dependent on its assumption of a centered lesion; segmentation accuracy collapses when the lesion is sufficiently displaced. These findings reveal a fundamental limitation of applying single-timepoint models to longitudinal data. We conclude that robust oncological tracking requires a paradigm shift away from cascading single-purpose tools towards integrated, end-to-end models inherently designed for temporal analysis.
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。