Department of Biomedical Imaging and Image-guided Therapy, Vienna General Hospital, Medical University of Vienna, Waehringer Guertel 18-20, Vienna, Austria.
Radiology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.
Eur Radiol. 2018 Jan;28(1):235-242. doi: 10.1007/s00330-017-4937-2. Epub 2017 Jul 14.
To assess the performance of the "Computer-Aided Nodule Assessment and Risk Yield" (CANARY) software in the differentiation and risk assessment of histological subtypes of lung adenocarcinomas manifesting as pure ground glass nodules on computed tomography (CT).
64 surgically resected and histologically proven adenocarcinomas manifesting as pure ground-glass nodules on CT were assessed using CANARY software, which classifies voxel-densities into three risk components (low, intermediate, and high risk). Differences in risk components between histological adenocarcinoma subtypes were analysed. To determine the optimal threshold reflecting the presence of an invasive focus, sensitivity, specificity, negative predictive value, and positive predictive value were calculated.
28/64 (44%) were adenocarcinomas in situ (AIS); 26/64 (41%) were minimally invasive adenocarcinomas (MIA); and 10/64 (16%) were invasive ACs (IAC). The software showed significant differences in risk components between histological subtypes (P<0.001-0.003). A relative volume of 45% or less of low-risk components was associated with histological invasiveness (specificity 100%, positive predictive value 100%).
CANARY-based risk assessment of ACs manifesting as pure ground glass nodules on CT allows the differentiation of their histological subtypes. A threshold of 45% of low-risk components reflects invasiveness in these groups.
• CANARY-based risk assessment allows the differentiation of their histological subtypes. • 45% or less of low-risk component reflects histological invasiveness. • CANARY has potential role in suspected adenocarcinomas manifesting as pure ground-glass nodules.
评估“计算机辅助结节评估和风险获益”（CANARY）软件在 CT 表现为纯磨玻璃结节的肺腺癌组织学亚型鉴别和风险评估中的性能。
对 64 例经手术切除和组织学证实的 CT 表现为纯磨玻璃结节的腺癌患者使用 CANARY 软件进行评估，该软件将体素密度分为三个风险成分（低、中、高风险）。分析组织学腺癌亚型之间风险成分的差异。为确定反映侵袭灶存在的最佳阈值，计算了敏感性、特异性、阴性预测值和阳性预测值。
64 例中有 28 例（44%）为原位腺癌（AIS）；26 例（41%）为微浸润腺癌（MIA）；10 例（16%）为浸润性腺癌（IAC）。软件在组织学亚型之间显示出风险成分的显著差异（P<0.001-0.003）。低风险成分的相对体积为 45%或更小与组织学侵袭性相关（特异性 100%，阳性预测值 100%）。
基于 CANARY 的 CT 表现为纯磨玻璃结节的腺癌风险评估可区分其组织学亚型。低风险成分的阈值为 45%反映了这些组的侵袭性。
•CANARY 基于风险评估可区分其组织学亚型。•低风险成分的 45%或更小反映了组织学侵袭性。•CANARY 在疑似表现为纯磨玻璃结节的腺癌中有潜在作用。
Zotero 插件