Abstract：
OBJECTIVE: The aim of this study was to develop a model for predicting the Gleason score of patients with prostate cancer based on ultrasound images.
METHODS: Transrectal ultrasound images of 838 prostate cancer patients from The Cancer Imaging Archive database were included in this cross-section study. Data were randomly divided into the training set and testing set (ratio 7:3). A total of 103 radiomic features were extracted from the ultrasound image. Lasso regression was used to select radiomic features. Random forest and broad learning system (BLS) methods were utilized to develop the model. The area under the curve (AUC) was calculated to evaluate the model performance.
RESULTS: After the screening, 10 radiomic features were selected. The AUC and accuracy of the radiomic feature variables random forest model in the testing set were 0.727 (95% CI, 0.694-0.760) and 0.646 (95% CI, 0.620-0.673), respectively. When PSA and radiomic feature variables were included in the random forest model, the AUC and accuracy of the model were 0.770 (95% CI, 0.740-0.800) and 0.713 (95% CI, 0.688-0.738), respectively. While the BLS method was utilized to construct the model, the AUC and accuracy of the model were 0.726 (95% CI, 0.693-0.759) and 0.698 (95% CI, 0.673-0.723), respectively. In predictions for different Gleason grades, the highest AUC of 0.847 (95% CI, 0.749-0.945) was found to predict Gleason grade 5 (Gleason score ≥9).
CONCLUSIONS: A model based on transrectal ultrasound image features showed a good ability to predict Gleason scores in prostate cancer patients.
CONCLUSIONS: This study used ultrasound-based radiomics to predict the Gleason score of patients with prostate cancer.
METHODS: Transrectal ultrasound images of 838 prostate cancer patients from The Cancer Imaging Archive database were included in this cross-section study. Data were randomly divided into the training set and testing set (ratio 7:3). A total of 103 radiomic features were extracted from the ultrasound image. Lasso regression was used to select radiomic features. Random forest and broad learning system (BLS) methods were utilized to develop the model. The area under the curve (AUC) was calculated to evaluate the model performance.
RESULTS: After the screening, 10 radiomic features were selected. The AUC and accuracy of the radiomic feature variables random forest model in the testing set were 0.727 (95% CI, 0.694-0.760) and 0.646 (95% CI, 0.620-0.673), respectively. When PSA and radiomic feature variables were included in the random forest model, the AUC and accuracy of the model were 0.770 (95% CI, 0.740-0.800) and 0.713 (95% CI, 0.688-0.738), respectively. While the BLS method was utilized to construct the model, the AUC and accuracy of the model were 0.726 (95% CI, 0.693-0.759) and 0.698 (95% CI, 0.673-0.723), respectively. In predictions for different Gleason grades, the highest AUC of 0.847 (95% CI, 0.749-0.945) was found to predict Gleason grade 5 (Gleason score ≥9).
CONCLUSIONS: A model based on transrectal ultrasound image features showed a good ability to predict Gleason scores in prostate cancer patients.
CONCLUSIONS: This study used ultrasound-based radiomics to predict the Gleason score of patients with prostate cancer.
摘要：
目的：本研究的目的是开发一种基于超声图像预测前列腺癌患者Gleason评分的模型。
方法：本横断面研究包括来自癌症影像档案数据库的838名前列腺癌患者的经直肠超声图像。将数据随机分为训练集和测试集(比率7:3)。从超声图像中总共提取了103个放射学特征。套索回归用于选择放射学特征。随机森林和广泛学习系统（BLS）方法被用来开发模型。计算曲线下面积(AUC)以评估模型性能。
结果：筛选后，选择了10个放射学特征。检验集中影像组学特征变量随机森林模型的AUC和准确率分别为0.727(95%CI,0.694-0.760)和0.646(95%CI,0.620-0.673),分别。当PSA和放射学特征变量包括在随机森林模型中时，模型的AUC和准确性分别为0.770（95％CI，0.740-0.800）和0.713（95％CI，0.688-0.738），分别。虽然BLS方法被用来构建模型，模型的AUC和准确性分别为0.726（95％CI，0.693-0.759）和0.698（95％CI，0.673-0.723），分别。在对不同格里森等级的预测中，发现最高AUC-0.847(95%CI,0.749-0.945)可预测Gleason5级(Gleason评分≥9).
结论：基于经直肠超声图像特征的模型显示出预测前列腺癌患者Gleason评分的良好能力。
结论：本研究使用基于超声的影像组学来预测前列腺癌患者的Gleason评分。
方法：本横断面研究包括来自癌症影像档案数据库的838名前列腺癌患者的经直肠超声图像。将数据随机分为训练集和测试集(比率7:3)。从超声图像中总共提取了103个放射学特征。套索回归用于选择放射学特征。随机森林和广泛学习系统（BLS）方法被用来开发模型。计算曲线下面积(AUC)以评估模型性能。
结果：筛选后，选择了10个放射学特征。检验集中影像组学特征变量随机森林模型的AUC和准确率分别为0.727(95%CI,0.694-0.760)和0.646(95%CI,0.620-0.673),分别。当PSA和放射学特征变量包括在随机森林模型中时，模型的AUC和准确性分别为0.770（95％CI，0.740-0.800）和0.713（95％CI，0.688-0.738），分别。虽然BLS方法被用来构建模型，模型的AUC和准确性分别为0.726（95％CI，0.693-0.759）和0.698（95％CI，0.673-0.723），分别。在对不同格里森等级的预测中，发现最高AUC-0.847(95%CI,0.749-0.945)可预测Gleason5级(Gleason评分≥9).
结论：基于经直肠超声图像特征的模型显示出预测前列腺癌患者Gleason评分的良好能力。
结论：本研究使用基于超声的影像组学来预测前列腺癌患者的Gleason评分。
