Skip to main content
QUICK REVIEW

[论文解读] Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans

Ling Zhang, Yu Shi|arXiv (Cornell University)|Aug 24, 2020
Pancreatic and Hepatic Oncology Research参考文献 18被引用 5
一句话总结

本文提出一种自学习框架,用于利用多机构、多期相、部分标注的CT扫描进行胰腺导管腺癌(PDAC)分割。通过利用两个专用教师模型生成伪标注,并通过助教模型优化血管边界,学生模型实现了0.71的Dice分数——与放射科医生之间的变异程度相当,并相较于nnUNet等强基线模型实现了6.3%的绝对性能提升。

ABSTRACT

Accurate and automated tumor segmentation is highly desired since it has the great potential to increase the efficiency and reproducibility of computing more complete tumor measurements and imaging biomarkers, comparing to (often partial) human measurements. This is probably the only viable means to enable the large-scale clinical oncology patient studies that utilize medical imaging. Deep learning approaches have shown robust segmentation performances for certain types of tumors, e.g., brain tumors in MRI imaging, when a training dataset with plenty of pixel-level fully-annotated tumor images is available. However, more than often, we are facing the challenge that only (very) limited annotations are feasible to acquire, especially for hard tumors. Pancreatic ductal adenocarcinoma (PDAC) segmentation is one of the most challenging tumor segmentation tasks, yet critically important for clinical needs. Previous work on PDAC segmentation is limited to the moderate amounts of annotated patient images (n<300) from venous or venous+arterial phase CT scans. Based on a new self-learning framework, we propose to train the PDAC segmentation model using a much larger quantity of patients (n~=1,000), with a mix of annotated and un-annotated venous or multi-phase CT images. Pseudo annotations are generated by combining two teacher models with different PDAC segmentation specialties on unannotated images, and can be further refined by a teaching assistant model that identifies associated vessels around the pancreas. A student model is trained on both manual and pseudo annotated multi-phase images. Experiment results show that our proposed method provides an absolute improvement of 6.3% Dice score over the strong baseline of nnUNet trained on annotated images, achieving the performance (Dice = 0.71) similar to the inter-observer variability between radiologists.

研究动机与目标

  • 开发一种稳健的全自动PDAC分割方法,能够处理有限的专家标注。
  • 在肿瘤边界不清晰、图像对比度低的复杂多期相CT扫描中提升分割准确性。
  • 通过减少对耗时的人工分割的依赖,实现大规模肿瘤学研究。
  • 实现与放射科医生之间观察者间变异程度相当的性能。
  • 通过自学习框架利用未标注数据,使模型训练规模超越小规模标注数据集的限制。

提出的方法

  • 采用双教师自学习框架,利用两个具有不同优势的专用PDAC分割模型,为未标注的多期相CT扫描生成伪标注。
  • 训练一个助教模型,以识别并从胰腺中排除血管结构(如门静脉、脾静脉),从而提高分割准确性。
  • 学生模型在人工标注图像与教师模型和助教模型生成的优化伪标注组合上进行训练。
  • 该框架整合了多期相CT数据(非增强、动脉期、静脉期),以增强肿瘤可见性并提升模型泛化能力。
  • 采用五折交叉验证策略评估性能,Dice系数为主要评价指标。
  • 在包含约1,000名患者的大型多机构数据集上验证该方法,涵盖标注与未标注病例。

实验结果

研究问题

  • RQ1当仅有有限的专家标注时,自学习框架是否能有效提升PDAC分割性能?
  • RQ2整合多个具有互补专长的教师模型,是否能提升在复杂、低对比度CT扫描中的分割准确性?
  • RQ3专注于血管结构排除的助教模型,是否能改善PDAC分割中的肿瘤边界勾画?
  • RQ4所提出的方法是否能达到与放射科医生之间观察者间变异程度相当的性能?
  • RQ5当在部分标注的多期相CT数据上训练时,学生模型是否能超越nnUNet等强基线模型的性能?

主要发现

  • 所提方法在测试集上达到0.755的中位Dice分数,显著优于在完全标注数据上训练的基线模型nnUNet。
  • 在引入由助教模型优化的伪标注后,学生模型达到0.709的Dice分数,相较于nnUNet基线实现6.3%的绝对性能提升。
  • 该方法实现0.71的Dice分数,与放射科医生之间的观察者间变异范围(0.697–0.710)相当,表明达到放射科医生水平的性能。
  • 使用三相CT(非增强、动脉期、静脉期)将分割性能提升至0.646,超过以往最先进结果。
  • 助教模型有效减少了假阳性,通过准确识别并排除胰腺及肿瘤分割中的血管结构。
  • 定性结果表明,学生模型在边界勾画方面表现更优,尤其在大而形状不规则的肿瘤以及靠近复杂血管结构的肿瘤中。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。