Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Ronald Reagan-UCLA Medical Center, 924 Westwood Boulevard, Suite 650, Los Angeles, CA, 90024, USA.
Department of Biostatistics, UCLA School of Public Heath, Room 51-253A, Los Angeles, CA, 90095, USA.
Abdom Radiol (NY). 2017 Jul;42(7):1919-1928. doi: 10.1007/s00261-017-1095-6.
To evaluate the performance of a novel, quantitative computer-aided diagnostic (CAD) algorithm on four-phase multidetector computed tomography (MDCT) to detect peak lesion attenuation to enable differentiation of clear cell renal cell carcinoma (ccRCC) from chromophobe RCC (chRCC), papillary RCC (pRCC), oncocytoma, and fat-poor angiomyolipoma (fp-AML).
We queried our clinical databases to obtain a cohort of histologically proven renal masses with preoperative MDCT with four phases [unenhanced (U), corticomedullary (CM), nephrographic (NP), and excretory (E)]. A whole lesion 3D contour was obtained in all four phases. The CAD algorithm determined a region of interest (ROI) of peak lesion attenuation within the 3D lesion contour. For comparison, a manual ROI was separately placed in the most enhancing portion of the lesion by visual inspection for a reference standard, and in uninvolved renal cortex. Relative lesion attenuation for both CAD and manual methods was obtained by normalizing the CAD peak lesion attenuation ROI (and the reference standard manually placed ROI) to uninvolved renal cortex with the formula [(peak lesion attenuation ROI - cortex ROI)/cortex ROI] × 100%. ROC analysis and area under the curve (AUC) were used to assess diagnostic performance. Bland-Altman analysis was used to compare peak ROI between CAD and manual method.
The study cohort comprised 200 patients with 200 unique renal masses: 106 (53%) ccRCC, 32 (16%) oncocytomas, 18 (9%) chRCCs, 34 (17%) pRCCs, and 10 (5%) fp-AMLs. In the CM phase, CAD-derived ROI enabled characterization of ccRCC from chRCC, pRCC, oncocytoma, and fp-AML with AUCs of 0.850 (95% CI 0.732-0.968), 0.959 (95% CI 0.930-0.989), 0.792 (95% CI 0.716-0.869), and 0.825 (95% CI 0.703-0.948), respectively. On Bland-Altman analysis, there was excellent agreement of CAD and manual methods with mean differences between 14 and 26 HU in each phase.
A novel, quantitative CAD algorithm enabled robust peak HU lesion detection and discrimination of ccRCC from other renal lesions with similar performance compared to the manual method.
评估一种新型定量计算机辅助诊断（CAD）算法在四期多层螺旋 CT（MDCT）检测峰值病变衰减中的性能，以区分透明细胞肾细胞癌（ccRCC）与嫌色细胞 RCC（chRCC）、乳头状 RCC（pRCC）、嗜酸细胞瘤和乏脂性血管平滑肌脂肪瘤（fp-AML）。
我们在临床数据库中查询了术前 MDCT 具有四个阶段（未增强（U）、皮质髓质（CM）、肾图（NP）和排泄期（E））的经组织学证实的肾肿块队列。在所有四个阶段都获得了整个病变的 3D 轮廓。CAD 算法在 3D 病变轮廓内确定了峰值病变衰减的感兴趣区域（ROI）。为了进行比较，通过视觉检查分别在病变最增强部分手动放置 ROI 作为参考标准，并在未受累的肾皮质中放置 ROI。通过将 CAD 峰值病变衰减 ROI（和手动放置的 ROI）与未受累的肾皮质归一化为公式[(峰值病变衰减 ROI-皮质 ROI)/皮质 ROI]×100%来获得 CAD 和手动方法的相对病变衰减。ROC 分析和曲线下面积（AUC）用于评估诊断性能。Bland-Altman 分析用于比较 CAD 和手动方法之间的峰值 ROI。
研究队列包括 200 名患有 200 个独特肾肿块的患者：106 名（53%）ccRCC、32 名（16%）嗜酸细胞瘤、18 名（9%）chRCC、34 名（17%）pRCC 和 10 名（5%）fp-AML。在 CM 期，CAD 衍生的 ROI 能够以 AUC 为 0.850（95%CI 0.732-0.968）、0.959（95%CI 0.930-0.989）、0.792（95%CI 0.716-0.869）和 0.825（95%CI 0.703-0.948），分别对 ccRCC 与 chRCC、pRCC、嗜酸细胞瘤和 fp-AML 进行特征描述。在 Bland-Altman 分析中，CAD 和手动方法之间具有极好的一致性，各阶段的平均差异在 14-26 HU 之间。
一种新型定量 CAD 算法能够可靠地检测峰值 HU 病变，并与手动方法相比，能够准确地区分 ccRCC 与其他具有相似表现的肾病变。
