Department of Ultrasound, Jiangsu Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing, China.
Department of Ultrasound, Affiliated People's Hospital of Jiangsu University, Zhenjiang, China.
Front Endocrinol (Lausanne). 2022 Apr 22;13:872153. doi: 10.3389/fendo.2022.872153. eCollection 2022.
BRAF is the most common mutated gene in thyroid cancer and is most closely related to papillary thyroid carcinoma(PTC). We investigated the value of elasticity and grayscale ultrasonography for predicting BRAF mutations in PTC.
138 patients with PTC who underwent preoperative ultrasound between January 2014 and 2021 were retrospectively examined. Patients were divided into BRAF mutation-free group (n=75) and BRAF mutation group (n=63). Patients were randomly divided into training (n=96) and test (n=42) groups. A total of 479 radiomic features were extracted from the grayscale and elasticity ultra-sonograms. Regression analysis was done to select the features that provided the most information. Then, 10-fold cross-validation was used to compare the performance of different classification algorithms. Logistic regression was used to predict BRAF mutations.
Eight radiomics features were extracted from the grayscale ultrasonogram, and five radiomics features were extracted from the elasticity ultrasonogram. Three models were developed using these radiomic features. The models were derived from elasticity ultrasound, grayscale ultrasound, and a combination of grayscale and elasticity ultrasound, with areas under the curve (AUC) 0.952 [95% confidence interval (CI), 0.914-0.990], AUC 0.792 [95% CI, 0.703-0.882], and AUC 0.985 [95% CI, 0.965-1.000] in the training dataset, AUC 0.931 [95% CI, 0.841-1.000], AUC 0. 725 [95% CI, 0.569-0.880], and AUC 0.938 [95% CI, 0.851-1.000] in the test dataset, respectively.
The radiomic model based on grayscale and elasticity ultrasound had a good predictive value for BRAF gene mutations in patients with PTC.
探讨超声弹性成像及灰阶超声特征在预测甲状腺乳头状癌（PTC）患者 BRAF 基因突变中的价值。
回顾性分析 2014 年 1 月至 2021 年期间在我院行术前超声检查的 138 例 PTC 患者的临床资料。根据是否存在 BRAF 基因突变，将患者分为 BRAF 基因突变阴性组（75 例）和 BRAF 基因突变阳性组（63 例）。将患者随机分为训练组（96 例）和测试组（42 例）。对灰阶及弹性超声图像提取共 479 个放射组学特征，采用回归分析筛选出信息量最大的特征，然后采用 10 折交叉验证比较不同分类算法的性能，建立基于放射组学特征的 LOGISTIC 回归预测模型，预测 BRAF 基因突变。
从灰阶超声图像中提取了 8 个放射组学特征，从弹性超声图像中提取了 5 个放射组学特征，基于这些放射组学特征建立了 3 个模型，即弹性超声模型、灰阶超声模型和灰阶及弹性超声联合模型。在训练集和测试集中，各模型的 AUC 分别为 0.952（95%CI：0.914～0.990）、0.792（95%CI：0.703～0.882）和 0.985（95%CI：0.965～1.000）、0.931（95%CI：0.841～1.000）、0.725（95%CI：0.569～0.880）和 0.938（95%CI：0.851～1.000）。
基于灰阶及弹性超声的放射组学模型对 PTC 患者 BRAF 基因突变具有良好的预测价值。
