前列腺MRI中T2加权成像的深度学习图像质量评估存在偏倚
这项三中心回顾性研究由五名腹部放射科医生对2105组轴位T2WI序列进行图像质量分级,并开发深度学习分类模型,模型与医生的一致性为二次加权kappa 0.53。在11723例未记录前列腺癌的检查中,轻度和中度图像质量退化组的临床显著前列腺癌比例均显著高于匹配的最优质量对照组,提示深度学习图像质量评估可能受临床显著前列腺癌存在的影响。
要点
- 深度学习T2WI图像质量模型与放射科医生的一致性为中等(二次加权kappa 0.53)。
- 中度退化组临床显著前列腺癌比例为26.3%,高于最优对照组的22.7%,差异3.6%(95%CI 0.4%–6.8%,p=0.03)。
- 轻度退化组临床显著前列腺癌比例为22.9%,高于最优对照组的20.2%,差异2.7%(95%CI 0.7%–4.7%,p=0.008)。
核心结论
- 深度学习图像质量评估在临床显著前列腺癌患者中倾向于更差,这引发了对其临床应用的担忧。
研究设计与样本
- 三中心回顾性研究,五名腹部放射科医生将2105组轴位T2WI序列分为最优、轻度、中度、重度退化,用1719组开发深度学习图像质量分类模型。
诊断标准与关键数值
- 模型与放射科医生的一致性用二次加权kappa评估,结果为0.53。
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
OBJECTIVES: To determine whether deep learning (DL)-based image quality (IQ) assessment of T2-weighted images (T2WI) could be biased by the presence of clinically significant prostate cancer (csPCa).
METHODS: In this three-center retrospective study, five abdominal radiologists categorized IQ of 2,105 transverse T2WI series into optimal, mild, moderate, and severe degradation. An IQ classification model was developed using 1,719 series (development set). The agreement between the model and radiologists was assessed using the remaining 386 series with a quadratic weighted kappa. The model was applied to 11,723 examinations that were not included in the development set and without documented prostate cancer at the time of MRI (patient age, 65.5 ± 8.3 years [mean ± standard deviation]). Examinations categorized as mild to severe degradation were used as target groups, whereas those as optimal were used to construct matched control groups. Case-control matching was performed to mitigate the effects of pre-MRI confounding factors, such as age and prostate-specific antigen value. The proportion of patients with csPCa was compared between the target and matched control groups using the chi-squared test.
RESULTS: The agreement between the model and radiologists was moderate with a quadratic weighted kappa of 0.53. The mild-moderate IQ-degraded groups had significantly higher csPCa proportions than the matched control groups with optimal IQ: moderate (N = 126) vs. optimal (N = 504), 26.3% vs. 22.7%, respectively, difference = 3.6% [95% confidence interval: 0.4%, 6.8%], p = 0.03; mild (N = 1,399) vs. optimal (N = 1,399), 22.9% vs. 20.2%, respectively, difference = 2.7% [0.7%, 4.7%], p = 0.008.
CONCLUSION: The DL-based IQ tended to be worse in patients with csPCa, raising concerns about its clinical application.
引用
- Nakai H, Froemming AT, Kawashima A, et al. Bias in deep learning-based image quality assessments of T2-weighted imaging in prostate MRI. Abdom Radiol (NY). 2025. PMID: 40853469. doi:10.1007/s00261-025-05163-9
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。