Guo Erjia, Chen Li, Xu Lili, Zhang Daming, Zhang Jiahui, Zhang Xiaoxiao, Bai Xin, Peng Qianyu, Zhu Jinxia, Nickel Marcel Dominik, Jin Zhengyu, Zhang Gumuyang, Sun Hao
Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China.
Department of Radiology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, No. 1, East Banshan Road, Gongshu District, Hangzhou, Zhejiang, 310022, China.
Abdom Radiol (NY). 2025 Apr 1. doi: 10.1007/s00261-025-04895-y.
To investigate the value of deep learning (DL) in T2-weighted imaging (T2) of the bladder regarding acquisition time (TA), image quality, and diagnostic confidence compared to standard T2-weighted turbo-spin-echo (TSE) imaging (T2).
We prospectively enrolled a total of 28 consecutive patients for the evaluation of bladder cancer. T2 and T2 sequences in three planes were performed for each participant, and acquisition time was compared between the two acquisition protocols. The image evaluation was conducted independently by two radiologists using a 5-point Likert scale for artifacts, noise, overall image quality, and diagnostic confidence, with 5 indicating the best quality. Additionally, T2 scoring based on Vesical Imaging-Reporting and Data System (VI-RADS) was performed by two readers.
Compared to T2, the acquisition time of T2 was reduced by 49.4% in the axial and by 43.8% in the coronal and sagittal orientations. The severity and impact of artifacts and noise levels were superior in T2 versus T2 (both p < 0.05). The overall image quality in T2 was demonstrated to be higher compared to that in T2 in axial and sagittal imaging (both p < 0.05). The diagnostic confidence and T2 scoring of both sequences in all planes did not differ (p > 0.05).
Our study preliminarily demonstrated the feasibility of T2-weighted imaging with DL reconstruction of bladder MR in clinical practice. T2 achieved a reduction in acquisition time, superior lesion detectability, and overall image quality with similar diagnostic confidence and T2 score compared to the standard T2 TSE sequence.
与标准的T2加权快速自旋回波（TSE）成像（T2）相比，研究深度学习（DL）在膀胱T2加权成像（T2WI）中的采集时间（TA）、图像质量和诊断置信度方面的价值。
我们前瞻性地连续纳入了28例患者以评估膀胱癌。对每位参与者在三个平面上进行T2WI和T2序列检查，并比较两种采集方案之间的采集时间。由两名放射科医生独立使用5分李克特量表对伪影、噪声、整体图像质量和诊断置信度进行图像评估，5分表示质量最佳。此外，由两名阅片者根据膀胱影像报告和数据系统（VI-RADS）进行T2WI评分。
与T2相比，T2WI在轴向的采集时间减少了49.4%，在冠状面和矢状面方向减少了43.8%。T2WI中伪影和噪声水平的严重程度及影响优于T2（均p<0.05）。在轴向和矢状面成像中，T2WI的整体图像质量被证明高于T2（均p<0.05）。两个序列在所有平面上的诊断置信度和T2WI评分均无差异（p>0.05）。
我们的研究初步证明了在临床实践中使用DL重建的膀胱磁共振T2加权成像的可行性。与标准的T2 TSE序列相比，T2WI在采集时间上有所减少，病变可检测性更佳，整体图像质量更高，且诊断置信度和T2WI评分相似。
