基于深度学习的 MRI 可见前列腺癌自动评估系统：高级放大扩散加权成像与常规技术的比较。
Automated deep-learning system in the assessment of MRI-visible prostate cancer: comparison of advanced zoomed diffusion-weighted imaging and conventional technique.
机构信息
Department of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, No. 600, Yi Shan Road, Shanghai, 200233, China.
MR Application Development, Siemens Shenzhen magnetic Resonance Ltd., Shenzhen, China.
出版信息
Cancer Imaging. 2023 Jan 17;23(1):6. doi: 10.1186/s40644-023-00527-0.
BACKGROUND
Deep-learning-based computer-aided diagnosis (DL-CAD) systems using MRI for prostate cancer (PCa) detection have demonstrated good performance. Nevertheless, DL-CAD systems are vulnerable to high heterogeneities in DWI, which can interfere with DL-CAD assessments and impair performance. This study aims to compare PCa detection of DL-CAD between zoomed-field-of-view echo-planar DWI (z-DWI) and full-field-of-view DWI (f-DWI) and find the risk factors affecting DL-CAD diagnostic efficiency.
METHODS
This retrospective study enrolled 354 consecutive participants who underwent MRI including T2WI, f-DWI, and z-DWI because of clinically suspected PCa. A DL-CAD was used to compare the performance of f-DWI and z-DWI both on a patient level and lesion level. We used the area under the curve (AUC) of receiver operating characteristics analysis and alternative free-response receiver operating characteristics analysis to compare the performances of DL-CAD using f- DWI and z-DWI. The risk factors affecting the DL-CAD were analyzed using logistic regression analyses. P values less than 0.05 were considered statistically significant.
RESULTS
DL-CAD with z-DWI had a significantly better overall accuracy than that with f-DWI both on patient level and lesion level (AUC: 0.89 vs. 0.86; AUC: 0.86 vs. 0.76; P < .001). The contrast-to-noise ratio (CNR) of lesions in DWI was an independent risk factor of false positives (odds ratio [OR] = 1.12; P < .001). Rectal susceptibility artifacts, lesion diameter, and apparent diffusion coefficients (ADC) were independent risk factors of both false positives (OR = 5.46; OR = 1.12; OR = 0.998; all P < .001) and false negatives (OR = 3.31; OR = 0.82; OR = 1.007; all P ≤ .03) of DL-CAD.
CONCLUSIONS
Z-DWI has potential to improve the detection performance of a prostate MRI based DL-CAD.
TRIAL REGISTRATION
ChiCTR, NO. ChiCTR2100041834 . Registered 7 January 2021.
背景
基于深度学习的计算机辅助诊断（DL-CAD）系统利用 MRI 检测前列腺癌（PCa）的性能已经得到了很好的验证。然而，DL-CAD 系统易受到 DWI 中高度异质性的影响，这可能会干扰 DL-CAD 评估并降低其性能。本研究旨在比较前列腺癌的磁共振弥散加权成像（MRI-DWI）中不同视野下的深度学习辅助诊断（DL-CAD）检测性能，发现影响 DL-CAD 诊断效率的相关因素。
方法
本回顾性研究纳入了 354 名因临床疑似前列腺癌而行 MRI（包括 T2WI、f-DWI 和 z-DWI）检查的连续患者。利用 DL-CAD 比较 f-DWI 和 z-DWI 在患者和病灶水平上的表现。我们使用受试者工作特征曲线下面积（AUC）和替代自由反应接收器操作特性分析来比较 f-DWI 和 z-DWI 中 DL-CAD 的性能。使用逻辑回归分析来分析影响 DL-CAD 的相关因素。P 值小于 0.05 被认为具有统计学意义。
结果
在患者和病灶水平上，基于 z-DWI 的 DL-CAD 的整体准确性均显著高于基于 f-DWI 的 DL-CAD（AUC：0.89 对 0.86；AUC：0.86 对 0.76；P < 0.001）。DWI 中病灶的对比噪声比（CNR）是假阳性的独立危险因素（比值比[OR] = 1.12；P < 0.001）。直肠磁化率伪影、病灶直径和表观扩散系数（ADC）是 DL-CAD 假阳性（OR = 5.46；OR = 1.12；OR = 0.998；均 P < 0.001）和假阴性（OR = 3.31；OR = 0.82；OR = 1.007；均 P ≤ 0.03）的独立危险因素。
结论
z-DWI 有潜力提高基于前列腺 MRI 的 DL-CAD 的检测性能。
临床试验注册
ChiCTR，编号 ChiCTR2100041834。注册于 2021 年 1 月 7 日。
Zotero 插件