Department of Ultrasound, The Second Clinical Medical College, Jinan University (Shenzhen People's Hospital), Shenzhen, Guangdong, China.
Department of Research & Development, Yizhun Medical AI Co. Ltd., Beijing, China.
Clin Breast Cancer. 2024 Jul;24(5):e379-e388.e1. doi: 10.1016/j.clbc.2024.02.017. Epub 2024 Feb 29.
To develop a nomogram based on photoacoustic imaging (PAI) radiomics and BI-RADs to identify breast cancer (BC) in BI-RADS 4 or 5 lesions detected by ultrasound (US).
In this retrospective study, 119 females with 119 breast lesions at US and PAI examination were included (January 2022 to December 2022). Patients were divided into the training set (n = 83) or testing set (n = 36) to develop a nomogram to identify BC in BI-RADS 4 or 5 lesions. Relevant factors at clinic, BI-RADS category, and PAI were reviewed. Univariate and multivariate regression was used to evaluate factors for associations with BC. To evaluate the diagnostic performance of nomogram, the area under the curve (AUC) of receiver operating characteristic curve, accuracy, specificity and sensitivity was employed.
The nomogram that included BI-RADS category and PAI radiomics score demonstrated a high AUC of 0.925 (95%CI: 0.8467-0.9712) in the training set and 0.926 (95%CI: 0.846-1.000) in the test set. The nomogram also showed significantly better discrimination than the radiomics score (P = .048) or BI-RADS category (P = .009) in the training set. These significant differences were demonstrated in the testing set, outperform the radiomics score (P = .038) and BI-RADS category (P = .013).
The nomogram developed with BI-RADS and PAI radiomics score can effectively identify BC in BI-RADS 4 or 5 lesions. This technique has the potential to further improve early diagnostic accuracy for BC.
基于光声成像（PAI）放射组学和 BI-RADS 建立列线图，以识别超声（US）检测到的 BI-RADS 4 或 5 级病变中的乳腺癌（BC）。
本回顾性研究纳入了 119 名女性的 119 个乳腺病变，这些病变在 US 和 PAI 检查中均被发现（2022 年 1 月至 2022 年 12 月）。患者被分为训练集（n=83）或测试集（n=36），以开发一种列线图来识别 BI-RADS 4 或 5 级病变中的 BC。回顾了临床、BI-RADS 类别和 PAI 相关因素。采用单因素和多因素回归分析评估与 BC 相关的因素。为了评估列线图的诊断性能，采用受试者工作特征曲线下面积（AUC）、准确性、特异性和敏感性来评估。
包括 BI-RADS 类别和 PAI 放射组学评分的列线图在训练集的 AUC 为 0.925（95%CI：0.8467-0.9712），在测试集的 AUC 为 0.926（95%CI：0.846-1.000）。与训练集中的放射组学评分（P=0.048）或 BI-RADS 类别（P=0.009）相比，该列线图具有更高的鉴别能力。在测试集中也表现出显著差异，优于放射组学评分（P=0.038）和 BI-RADS 类别（P=0.013）。
基于 BI-RADS 和 PAI 放射组学评分建立的列线图可以有效识别 BI-RADS 4 或 5 级病变中的 BC。该技术有可能进一步提高 BC 的早期诊断准确性。
