Department of Radiology, Peking University First Hospital, Beijing, China.
Beijing Smart Tree Medical Technology Co. Ltd, Beijing, China.
J Magn Reson Imaging. 2023 Oct;58(4):1067-1081. doi: 10.1002/jmri.28608. Epub 2023 Feb 24.
Deep learning for diagnosing clinically significant prostate cancer (csPCa) is feasible but needs further evaluation in patients with prostate-specific antigen (PSA) levels of 4-10 ng/mL.
To explore diffusion-weighted imaging (DWI), alone and in combination with T2-weighted imaging (T2WI), for deep-learning-based models to detect and localize visible csPCa.
Retrospective.
One thousand six hundred twenty-eight patients with systematic and cognitive-targeted biopsy-confirmation (1007 csPCa, 621 non-csPCa) were divided into model development (N = 1428) and hold-out test (N = 200) datasets.
FIELD STRENGTH/SEQUENCE: DWI with diffusion-weighted single-shot gradient echo planar imaging sequence and T2WI with T2-weighted fast spin echo sequence at 3.0-T and 1.5-T.
The ground truth of csPCa was annotated by two radiologists in consensus. A diffusion model, DWI and apparent diffusion coefficient (ADC) as input, and a biparametric model (DWI, ADC, and T2WI as input) were trained based on U-Net. Three radiologists provided the PI-RADS (version 2.1) assessment. The performances were determined at the lesion, location, and the patient level.
The performance was evaluated using the areas under the ROC curves (AUCs), sensitivity, specificity, and accuracy. A P value <0.05 was considered statistically significant.
The lesion-level sensitivities of the diffusion model, the biparametric model, and the PI-RADS assessment were 89.0%, 85.3%, and 90.8% (P = 0.289-0.754). At the patient level, the diffusion model had significantly higher sensitivity than the biparametric model (96.0% vs. 90.0%), while there was no significant difference in specificity (77.0%. vs. 85.0%, P = 0.096). For location analysis, there were no significant differences in AUCs between the models (sextant-level, 0.895 vs. 0.893, P = 0.777; zone-level, 0.931 vs. 0.917, P = 0.282), and both models had significantly higher AUCs than the PI-RADS assessment (sextant-level, 0.734; zone-level, 0.863).
The diffusion model achieved the best performance in detecting and localizing csPCa in patients with PSA levels of 4-10 ng/mL.
3 TECHNICAL EFFICACY: Stage 2.
深度学习诊断临床上有意义的前列腺癌（csPCa）是可行的，但需要在前列腺特异性抗原（PSA）水平为 4-10ng/mL 的患者中进一步评估。
探索扩散加权成像（DWI）单独或与 T2 加权成像（T2WI）联合用于基于深度学习的模型，以检测和定位可见的 csPCa。
回顾性。
1628 例接受系统和认知靶向活检证实的患者（1007 例 csPCa，621 例非 csPCa）分为模型开发（N=1428）和保留测试（N=200）数据集。
场强/序列：在 3.0-T 和 1.5-T 上使用扩散加权单次激发梯度回波平面成像序列进行 DWI 和 T2 加权快速自旋回波序列进行 T2WI。
由两位放射科医生对 csPCa 的真实情况进行共识注释。基于 U-Net 训练了一个扩散模型，以 DWI 和表观扩散系数（ADC）作为输入，以及一个双参数模型（DWI、ADC 和 T2WI 作为输入）。三位放射科医生提供了 PI-RADS（版本 2.1）评估。在病变、位置和患者水平上确定了性能。
使用 ROC 曲线下的面积（AUCs）、敏感性、特异性和准确性来评估性能。P 值<0.05 被认为具有统计学意义。
在病变水平，扩散模型、双参数模型和 PI-RADS 评估的敏感性分别为 89.0%、85.3%和 90.8%（P=0.289-0.754）。在患者水平上，扩散模型的敏感性明显高于双参数模型（96.0% vs. 90.0%），而特异性无显著差异（77.0% vs. 85.0%，P=0.096）。对于位置分析，模型之间的 AUC 无显著差异（六分位水平，0.895 vs. 0.893，P=0.777；区域水平，0.931 vs. 0.917，P=0.282），且两个模型的 AUC 均明显高于 PI-RADS 评估（六分位水平，0.734；区域水平，0.863）。
在 PSA 水平为 4-10ng/mL 的患者中，扩散模型在检测和定位 csPCa 方面表现最佳。
3 级 技术功效：2 级
