文献速递泌尿生殖腹部MR

挑战性临床病例中的前列腺自动分割:三种人工智能方法的比较

Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods.
PubMed 文献 · Abdom Radiol (NY) · 2024-03-21

本研究在单中心回顾性数据库中筛选683例扫描(651例患者),纳入既往接受过前列腺肿瘤治疗、经尿道前列腺电切术、腹会阴切除术、髋关节假体、前列腺体积过大或过小、全腺体肿瘤负荷、不同磁体强度、图像质量差及不同扫描仪等挑战性病例。比较三种前列腺分割AI算法与专家分割的Dice相似系数(DSC),基于深度学习的模型DSC显著高于基于形状的商业模型(p<0.01)。前列腺体积和信号质量差对所有模型性能均有负面影响(p<0.01)。

要点

  • 基于深度学习的模型1总体DSC为0.916,显著高于模型2的0.873和模型3的0.894(p<0.01)。
  • 前列腺体积大或小以及信号质量差会降低所有分割模型的性能(p<0.01)。
  • 基于形状的因素影响深度学习模型(p<0.001),信号因素影响所有模型(p<0.001)。

核心结论

  • 影响前列腺解剖和信号条件的因素可对深度学习和非深度学习分割模型均产生不利影响。

研究设计与样本

  • 单中心回顾性数据库研究,纳入683例扫描(651例患者),平均前列腺体积60.1 cc(范围9.05-329 cc),要求有轴位T2加权序列及专家放射科医师对应的前列腺器官分割;评估三种算法:基于深度学习的模型、商业可用的基于形状的模型、基于联邦深度学习的模型。

关键影像表现/征象

  • 基于深度学习的模型1总体DSC为0.916(范围0.707-0.971),模型2为0.873(范围0-0.997),模型3为0.894(范围0.025-0.961)。

诊断标准与关键数值

  • 以专家放射科医师的分割为参考,计算Dice相似系数(DSC)评估各模型性能。
  • 模型1总体DSC 0.916,模型2 0.873,模型3 0.894,深度学习模型显著更高(p<0.01)。
  • 亚组分析中模型1优于模型2(所有p<0.05)和模型3(所有p<0.001)。
  • 前列腺体积和信号质量差对所有模型性能有负面影响(p<0.01)。

临床应用与阅片要点

  • 原文结论指出影响前列腺解剖和信号条件的因素可对深度学习和非深度学习分割模型均产生不利影响。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVE: Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters.

MATERIALS AND METHODS: A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model.

RESULTS: 683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05-329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001).

CONCLUSION: Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Johnson LA, Harmon SA, Yilmaz EC, et al. Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods. Abdom Radiol (NY). 2024. PMID: 38512516. doi:10.1007/s00261-024-04242-7

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。