arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.00640physics.med-ph
收藏

基于人工智能的定量PET分割方法需要客观的基于任务的评估

Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET

Ziping Liu, Joyce C. Mhlanga, Barry A. Siegel, Abhinav K. Jha

AI总结:

本文通过ECOG-ACRIN 6668/RTOG 0235多中心临床试验数据,证明用Dice分数评估AI-based PET分割方法与基于MTV/TLG量化准确性的任务评估结果不一致,从而强调需要客观的基于任务的评估方法。

摘要:

基于人工智能(AI)的方法在肿瘤正电子发射断层扫描(PET)图像分割中展现出巨大前景。对于这些方法的临床转化,评估其在临床相关任务上的表现至关重要。然而,这些方法通常使用的评估指标可能与任务表现不相关。其中一个广泛使用的指标是Dice分数,这是一种衡量估计分割与参考标准(例如手动分割)之间空间重叠度的品质因数。在这项工作中,我们研究了使用Dice分数评估基于AI的分割方法是否与在临床任务上评估得出相似的解释,这些临床任务是从非小细胞肺癌患者的PET图像中量化原发肿瘤的代谢肿瘤体积(MTV)和总病灶糖酵解(TLG)。该研究通过使用ECOG-ACRIN 6668/RTOG 0235多中心临床试验数据进行回顾性分析来完成。具体来说,我们使用Dice分数以及量化MTV/TLG的准确性,评估了一种常用的基于AI的分割方法的不同结构。我们的结果表明,使用Dice分数进行评估可能导致与使用基于任务的品质因数进行评估所得结果不一致的发现。因此,我们的研究强调了基于人工智能的定量PET分割方法需要客观的基于任务的评估。

英文摘要:

Artificial intelligence (AI)-based methods are showing substantial promise in segmenting oncologic positron emission tomography (PET) images. For clinical translation of these methods, assessing their performance on clinically relevant tasks is important. However, these methods are typically evaluated using metrics that may not correlate with the task performance. One such widely used metric is the Dice score, a figure of merit that measures the spatial overlap between the estimated segmentation and a reference standard (e.g., manual segmentation). In this work, we investigated whether evaluating AI-based segmentation methods using Dice scores yields a similar interpretation as evaluation on the clinical tasks of quantifying metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of primary tumor from PET images of patients with non-small cell lung cancer. The investigation was conducted via a retrospective analysis with the ECOG-ACRIN 6668/RTOG 0235 multi-center clinical trial data. Specifically, we evaluated different structures of a commonly used AI-based segmentation method using both Dice scores and the accuracy in quantifying MTV/TLG. Our results show that evaluation using Dice scores can lead to findings that are inconsistent with evaluation using the task-based figure of merit. Thus, our study motivates the need for objective task-based evaluation of AI-based segmentation methods for quantitative PET.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑