文献速递泌尿生殖腹部MR

基于级联深度学习与随机森林分类的MRI前列腺癌前列腺外侵犯自动检测与分级

Automated Detection and Grading of Extraprostatic Extension of Prostate Cancer at MRI via Cascaded Deep Learning and Random Forest Classification.
PubMed 文献 · Acad Radiol · 2024-04-25

研究纳入634例前列腺癌患者,利用深度学习自动分割前列腺与病灶并提取面积与距离特征,经随机森林分类模型对T2W、ADC图及高b值DWI进行前列腺外侵犯自动分级。模型在独立测试集(127例)中EPE≥1阈值下敏感度0.67、特异度0.73、准确率0.72,放射科医生分别为0.81、0.62、0.66,作者认为该自动化流程的预测准确率接近医师水平。

要点

  • AI流程基于T2W、ADC图及高b值DWI自动提取病灶面积与距离特征完成EPE分级。
  • EPE≥1为阳性阈值时AI敏感度0.67、特异度0.73、准确率0.72,医师为0.81、0.62、0.66。
  • AI所赋EPE 0-3级对应的ROC AUC分别为0.70、0.65、0.68、0.55。

核心结论

  • 该AI流程对影像学EPE分级的准确率接近医师预测组织学EPE的水平,作者认为其一致性与自动化特点可能有助于医师评估前列腺癌患者的EPE风险。

研究设计与样本

  • 由专家级泌尿生殖放射科医师对634例患者的MRI扫描进行前瞻性临床评估并按分级技术赋EPE风险,训练集507例、独立测试集127例,利用现有前列腺器官与病灶分割深度学习模型提取面积与距离特征供随机森林分类模型使用,以组织病理学EPE为参考标准。

关键影像表现/征象

  • 基于前列腺T2W MRI、ADC图及高b值DWI提取病灶面积与距离特征用于EPE分级。
  • EPE 0-3级的ROC AUC分别为0.70、0.65、0.68、0.55。
  • 采用病灶检测概率阈值0.45与距离特征时平衡准确率为0.390±0.078。

诊断标准与关键数值

  • 以EPE≥1为阳性阈值时,模型敏感度0.67、特异度0.73、准确率0.72,医师敏感度0.81、特异度0.62、准确率0.66,均以组织病理学为金标准。

临床应用与阅片要点

  • 作者认为该自动化流程因一致性与自动化特点,可能有助于医师评估接受前列腺癌治疗患者的EPE风险。

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

RATIONALE AND OBJECTIVES: Extraprostatic extension (EPE) is well established as a significant predictor of prostate cancer aggression and recurrence. Accurate EPE assessment prior to radical prostatectomy can impact surgical approach. We aimed to utilize a deep learning-based AI workflow for automated EPE grading from prostate T2W MRI, ADC map, and High B DWI.

MATERIAL AND METHODS: An expert genitourinary radiologist conducted prospective clinical assessments of MRI scans for 634 patients and assigned risk for EPE using a grading technique. The training set and held-out independent test set consisted of 507 patients and 127 patients, respectively. Existing deep-learning AI models for prostate organ and lesion segmentation were leveraged to extract area and distance features for random forest classification models. Model performance was evaluated using balanced accuracy, ROC AUCs for each EPE grade, as well as sensitivity, specificity, and accuracy compared to EPE on histopathology.

RESULTS: A balanced accuracy score of .390 ± 0.078 was achieved using a lesion detection probability threshold of 0.45 and distance features. Using the test set, ROC AUCs for AI-assigned EPE grades 0-3 were 0.70, 0.65, 0.68, and 0.55 respectively. When using EPE≥ 1 as the threshold for positive EPE, the model achieved a sensitivity of 0.67, specificity of 0.73, and accuracy of 0.72 compared to radiologist sensitivity of 0.81, specificity of 0.62, and accuracy of 0.66 using histopathology as the ground truth.

CONCLUSION: Our AI workflow for assigning imaging-based EPE grades achieves an accuracy for predicting histologic EPE approaching that of physicians. This automated workflow has the potential to enhance physician decision-making for assessing the risk of EPE in patients undergoing treatment for prostate cancer due to its consistency and automation.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Simon BD, Merriman KM, Harmon SA, et al. Automated Detection and Grading of Extraprostatic Extension of Prostate Cancer at MRI via Cascaded Deep Learning and Random Forest Classification. Acad Radiol. 2024. PMID: 38670874. doi:10.1016/j.acra.2024.04.011

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。