用置信度标注脑瘤边界，减少医生间差异。
Confidence-Based Annotation Of Brain Tumours In Ultrasound
- 提出稀疏置信度标注法，量化肿瘤边缘不确定性。
- 边缘区域相关性达0.8，软标签训练模型表现更优。
- 适合医学影像标注、降低主观差异，提升模型鲁棒性。
目的：研究超声图像中脑瘤离散分割的挑战，重点关注肿瘤边界处的随机不确定性，尤其是弥漫性肿瘤。提出一种分割协议与方法，通过纳入边界相关不确定性，减少主观性，从而降低标注者认知不确定性。方法：基于计算机视觉与放射学理论设计，提出一种稀疏置信度标注方法。结果：将该方法生成的标注与专业医生的离散标注差异进行对比，发现肿瘤边缘区域存在线性关系，皮尔逊相关系数为0.8。进一步探索下游应用，比较使用置信度标注作为软标签与使用最优离散标注作为硬标签训练网络的效果。在所有评估折中，软标签训练网络的布里尔分数均更优。结论：构建了正式框架，证明了在B型超声中对脑瘤进行离散标注的不可行性。随后提出并验证了一种稀疏置信度标注方法。
原文摘要 · Abstract (English)
Purpose: An investigation of the challenge of annotating discrete segmentations of brain tumours in ultrasound, with a focus on the issue of aleatoric uncertainty along the tumour margin, particularly for diffuse tumours. A segmentation protocol and method is proposed that incorporates this margin-related uncertainty while minimising the interobserver variance through reduced subjectivity, thereby diminishing annotator epistemic uncertainty. Approach: A sparse confidence method for annotation is proposed, based on a protocol designed using computer vision and radiology theory. Results: Output annotations using the proposed method are compared with the corresponding professional discrete annotation variance between the observers. A linear relationship was measured within the tumour margin region, with a Pearson correlation of 0.8. The downstream application was explored, comparing training using confidence annotations as soft labels with using the best discrete annotations as hard labels. In all evaluation folds, the Brier score was superior for the soft-label trained network. Conclusion: A formal framework was constructed to demonstrate the infeasibility of discrete annotation of brain tumours in B-mode ultrasound. Subsequently, a method for sparse confidence-based annotation is proposed and evaluated. Keywords: Brain tumours, ultrasound, confidence, annotation.
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。