深度学习评估双参数前列腺MRI图像质量的可行性研究
本研究利用PI-CAI数据集的双参数前列腺MRI,由三位专家建立图像质量三分类标签,训练3D深度学习模型并与四位经验较少读者比较。模型与专家共识在T2W和ADC图的kappa分别为0.42和0.61,与经验较少读者相当,提示DL可作为自动化质量评估工具。
要点
- DL模型与专家共识的kappa在T2W为0.42、ADC为0.61,分别达中等和良好一致性。
- 经验较少读者与专家共识的kappa在T2W为0.39–0.56、ADC为0.39–0.62。
- DL模型评估双参数前列腺MRI图像质量的性能与经验较少读者相当。
核心结论
- 深度学习在双参数前列腺MRI图像质量评估中可达到与经验较少读者相当的性能,是自动化质量评估工具的可行选择。
- 作者建议,用更具代表性数据集、由更大规模专家组标注训练的DL模型,可能提供可靠的图像质量评估,并有望替代或辅助人工视觉评估。
研究设计与样本
- 可行性研究,使用PI-CAI数据集的双参数前列腺MRI扫描。
- 图像质量采用3点Likert量表(差、中等、优秀)评估,由三位专家读者建立开发集(500例)和测试集(100例)的参考标准标签。
- 在开发集上训练3D深度学习模型,使用概率性前列腺掩膜和序数损失函数;四位经验较少读者对测试集评分以进行性能比较。
诊断标准与关键数值
- 图像质量评估采用3点Likert量表:差、中等、优秀。
- DL模型与专家共识的kappa:T2W图像0.42(中等一致性),ADC图0.61(良好一致性)。
- 经验较少读者与专家共识的kappa:T2W图像0.39–0.56(一般至中等一致性),ADC图0.39–0.62(一般至良好一致性)。
临床应用与阅片要点
- DL模型可作为双参数前列腺MRI图像质量的自动化评估工具,性能与经验较少读者相当。
- 作者建议,用更具代表性数据集、由更大规模专家组标注训练的DL模型,可能提供可靠的图像质量评估,并有望替代或辅助人工视觉评估。
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
BACKGROUND: Although systems such as Prostate Imaging Quality (PI-QUAL) have been proposed for quality assessment, visual evaluations by human readers remain somewhat inconsistent, particularly among less-experienced readers.
OBJECTIVES: To assess the feasibility of deep learning (DL) for the automated assessment of image quality in bi-parametric MRI scans and compare its performance to that of less-experienced readers.
METHODS: We used bi-parametric prostate MRI scans from the PI-CAI dataset in this study. A 3-point Likert scale, consisting of poor, moderate, and excellent, was utilized for assessing image quality. Three expert readers established the ground-truth labels for the development (500) and testing sets (100). We trained a 3D DL model on the development set using probabilistic prostate masks and an ordinal loss function. Four less-experienced readers scored the testing set for performance comparison.
RESULTS: The kappa scores between the DL model and the expert consensus for T2W images and ADC maps were 0.42 and 0.61, representing moderate and good levels of agreement. The kappa scores between the less-experienced readers and the expert consensus for T2W images and ADC maps ranged from 0.39 to 0.56 (fair to moderate) and from 0.39 to 0.62 (fair to good).
CONCLUSIONS: Deep learning (DL) can offer performance comparable to that of less-experienced readers when assessing image quality in bi-parametric prostate MRI, making it a viable option for an automated quality assessment tool. We suggest that DL models trained on more representative datasets, annotated by a larger group of experts, could yield reliable image quality assessment and potentially substitute or assist visual evaluations by human readers.
引用
- Alis, Kartal, Seker, et al. Deep learning for assessing image quality in bi-parametric prostate MRI: A feasibility study. Eur J Radiol. 2023. PMID: 37354768. doi:10.1016/j.ejrad.2023.110924
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。