文献速递泌尿生殖腹部MR

基于深度学习的人工智能用于双参数MRI前列腺癌检测

Deep learning-based artificial intelligence for prostate cancer detection at biparametric MRI.
PubMed 文献 · Abdom Radiol (NY) · 2022-01-31

本研究利用两家机构的MRI扫描数据训练和测试全自动深度学习前列腺癌检测系统,共纳入525例患者,算法可检测任何前列腺癌≥ISUP1级病变。在验证集中AHNet模型检测敏感度74.4%、PPV 47.8%、平均假阳性病灶数0.87个/患者;测试集中UNet敏感度72.8%、AHNet敏感度63.0%。作者认为该系统可作为放射科医生的辅助工具。

要点

  • 算法在双参数MRI上检测任何前列腺癌≥ISUP1级病变,验证集AHNet敏感度74.4%、PPV 47.8%。
  • 假阳性病灶仍是AI辅助检测算法的挑战,验证集AHNet平均假阳性病灶0.87个/患者。
  • 作者认为该系统可作为放射科医生的辅助工具。

核心结论

  • 作者开发了基于深度学习的AI方法,可在双参数MRI上预测前列腺癌病灶,性能指标合理;假阳性病灶仍是AI辅助检测算法的挑战,该系统可作为放射科医生的辅助工具。

研究设计与样本

  • 研究使用两家机构的MRI扫描进行算法训练、验证和测试;MRI可见病灶由经验丰富的放射科医生勾画,所有病灶均经MRI-TRUS引导活检;病灶掩码和组织病理学结果作为真实标签训练UNet和AH-Net架构用于前列腺癌病灶检测和分割;算法训练用于检测任何前列腺癌≥ISUP1级。

诊断标准与关键数值

  • 训练集AHNet模型Dice系数为0.403,UNet模型为0.372。
  • 验证集AHNet模型Dice系数为0.307,UNet模型为0.287。
  • 验证集UNet模型检测敏感度70.9%、PPV 35.5%、平均假阳性病灶1.41个/患者(范围0-6)。
  • 验证集AHNet模型检测敏感度74.4%、PPV 47.8%、平均假阳性病灶0.87个/患者(范围0-5)。
  • 测试集UNet模型检测敏感度72.8%、平均假阳性病灶1.90个/患者(范围0-7);AHNet模型检测敏感度63.0%、平均假阳性病灶1.40个/患者(范围0-6)。

临床应用与阅片要点

  • 作者认为该系统可作为放射科医生的辅助工具。
  • 假阳性病灶仍是AI辅助检测算法的挑战。

局限性

  • 假阳性病灶仍是AI辅助检测算法的挑战。

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

PURPOSE: To present fully automated DL-based prostate cancer detection system for prostate MRI.

METHODS: MRI scans from two institutions, were used for algorithm training, validation, testing. MRI-visible lesions were contoured by an experienced radiologist. All lesions were biopsied using MRI-TRUS-guidance. Lesions masks, histopathological results were used as ground truth labels to train UNet, AH-Net architectures for prostate cancer lesion detection, segmentation. Algorithm was trained to detect any prostate cancer ≥ ISUP1. Detection sensitivity, positive predictive values, mean number of false positive lesions per patient were used as performance metrics.

RESULTS: 525 patients were included for training, validation, testing of the algorithm. Dataset was split into training (n = 368, 70%), validation (n = 79, 15%), test (n = 78, 15%) cohorts. Dice coefficients in training, validation sets were 0.403, 0.307, respectively, for AHNet model compared to 0.372, 0.287, respectively, for UNet model. In validation set, detection sensitivity was 70.9%, PPV was 35.5%, mean number of false positive lesions/patient was 1.41 (range 0-6) for UNet model compared to 74.4% detection sensitivity, 47.8% PPV, mean number of false positive lesions/patient was 0.87 (range 0-5) for AHNet model. In test set, detection sensitivity for UNet was 72.8% compared to 63.0% for AHNet, mean number of false positive lesions/patient was 1.90 (range 0-7), 1.40 (range 0-6) in UNet, AHNet models, respectively.

CONCLUSION: We developed a DL-based AI approach which predicts prostate cancer lesions at biparametric MRI with reasonable performance metrics. While false positive lesion calls remain as a challenge of AI-assisted detection algorithms, this system can be utilized as an adjunct tool by radiologists.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Mehralivand, Yang, Harmon, et al. Deep learning-based artificial intelligence for prostate cancer detection at biparametric MRI. Abdom Radiol (NY). 2022. PMID: 35099572. doi:10.1007/s00261-022-03419-2

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。