基于深度学习重建的前列腺T_(2)WI的图像质量和对移行带前列腺癌的诊断效能  

Evaluation of image quality of deep learning-based reconstruction of prostate T_(2)WI and diagnostic performance for prostate cancer in transition zone

作　　者：杨博文 程昊 刘明[2] 侯惠民[2] 王淼 张晨[1] 李春媚[1] 陈敏[1] Yang Bowen;Cheng Hao;Liu Ming;Hou Huimin;Wang Miao;Zhang Chen;Li Chunmei;Chen Min(Department of Radiology,Beijing Hospital,National Center of Gerontology,Institute of Geriatric Medicine,Chinese Academy of Medical Sciences,Beijing 100730,China;Department of Urology,Beijing Hospital,National Center of Gerontology,Institute of Geriatric Medicine,Chinese Academy of Medical Sciences,Beijing 100730,China)

机构地区：[1]北京医院放射科、国家老年医学中心、中国医学科学院老年医学研究院,北京100730 [2]北京医院泌尿外科、国家老年医学中心、中国医学科学院老年医学研究院,北京100730

出　　处：《中华放射学杂志》2023年第11期1208-1214,共7页Chinese Journal of Radiology

基　　金：中央高水平医院临床科研业务费专项(BJ-2022-115)。

摘　　要：目的评估基于深度学习方法重建的前列腺T_(2)WI(简称深度学习T_(2)WI)的图像质量及对移行带前列腺癌(PCa)的诊断效能。方法前瞻性连续收集2020年12月至2022年9月北京医院因前列腺特异性抗原水平升高而行前列腺MRI的79例患者。扫描序列包括横断面常规T_(2)WI、深度学习T_(2)WI和扩散加权成像,记录扫描时间。对图像质量进行主观评分,评价项目包括图像质量、诊断置信度、噪声、伪影、图像清晰度及病变可检测性。对图像质量进行客观评价,计算信噪比(SNR)及对比信噪比(CNR)。对移行带病变分别采用深度学习T_(2)WI和常规T_(2)WI进行双参数MRI前列腺影像报告和数据系统2.1版(PI-RADS v2.1)评分。对深度学习T_(2)WI和常规T_(2)WI的图像质量主、客观评价指标采用Wilcoxon符号秩和检验进行比较。对于移行带病变,以病理结果为金标准,基于病灶水平(移行带全部病变)和患者水平(移行带最高分病变),分别绘制受试者操作特征曲线,评估深度学习T_(2)WI和常规T_(2)WI的PI-RADS评分对移行带PCa的诊断效能,采用DeLong检验比较曲线下面积(AUC)。结果深度学习T_(2)WI的扫描时间为1 min 38 s,常规T_(2)WI为4 min 37 s,缩短了64.6%。深度学习T_(2)WI与常规T_(2)WI图像质量各主观评价指标的评分均为5(4,5)分,2组图像间图像质量和病变可检测性评分差异有统计学意义(Z=-2.32、-2.36,P=0.020、0.018),其他评价指标评分差异均无统计学意义(P>0.05)。深度学习T_(2)WI和常规T_(2)WI的SNR分别为17.11(14.09,21.92)、9.15(7.16,11.17),差异有统计学意义(Z=-7.72,P<0.001)。深度学习T_(2)WI和常规T_(2)WI的CNR分别为20.78(13.42,31.42)、11.05(7.82,16.25),差异有统计学意义(Z=-7.54,P<0.001)。基于病灶水平(40个PCa和48个良性病灶),深度学习T_(2)WI和常规T_(2)WI的双参数PI-RADS评分诊断移行带PCa的AUC分别为0.915(95%CI 0.856~0.975)、0.916(95%CI 0.857~0.976),差异无统计学意义(Z=Objective To evaluate the image quality of prostate T_(2)WI reconstructed based on deep learning(deep learning T_(2)WI)and the diagnostic performance for prostate cancer(PCa)in the transition zone.Methods Totally 79 patients who underwent prostate MRI for elevated prostate specific antigen from December 2020 to September 2022 were prospectively consecutively collected from Beijing Hospital.Scan sequences included axial standard T_(2)WI,deep learning T_(2)WI,and diffusion-weighted imaging.The scan time was recorded.The image quality was scored subjectively including image quality,diagnostic confidence,noise level,artifacts,clarity and lesion detectability.For objective evaluation of image quality,signal-to-noise ratio(SNR)and contrast signal-to-noise ratio(CNR)were calculated.Two-parameter MRI prostate imaging reporting and data system version 2.1(PI-RADS v2.1)scoring was performed for transition zone lesions using deep learning T_(2)WI and standard T_(2)WI,respectively.The subjective and objective image quality evaluation metrics for deep learning T_(2)WI and standard T_(2)WI were compared using the Wilcoxon signed-rank test.For transition zone lesions,the diagnostic performance of PI-RADS scores with deep learning T_(2)WI and standard T_(2)WI for PCa was evaluated by the receiver operating characteristic curve based on the lesion(all lesions in the transition zone)and the patient(the most malignant lesions in the transition zone),respectively,using the pathologic results as the gold standard.The area under the curve(AUC)was compared using the DeLong test.Results Deep learning T_(2)WI significantly reduced the examination time by 64.6.%,from 4 min 37 s to 1 min 38 s.The scores of subjective image quality of deep learning T_(2)WI and standard T_(2)WI all were 5(4,5).The differences in image quality and lesion detectability were statistically significant(Z=-2.32,-2.36,P=0.020,0.018),and the differences of all other image quality evaluation metrics were not statistically significant(P>0.05).The SNR of deep learning

关 键 词：前列腺 磁共振成像 图像质量 深度学习 

分 类 号：R445.2[医药卫生—影像医学与核医学] R737.25[医药卫生—诊断学]