Liu Lu, Cai Wenjun, Zheng Feibo, Tian Hongyan, Li Yanping, Wang Ting, Chen Xiaonan, Zhu Wenjing
Department of Ultrasound Medicine, South China Hospital, Medical School, Shenzhen University, Shenzhen, P. R. China.
Department of Ultrasound, Shenzhen University General Hospital, Medical School, Shenzhen University, Shenzhen, P. R. China.
Insights Imaging. 2025 Jan 13;16(1):14. doi: 10.1186/s13244-024-01874-7.
To develop an automatic segmentation model to delineate the adnexal masses and construct a machine learning model to differentiate between low malignant risk and intermediate-high malignant risk of adnexal masses based on ovarian-adnexal reporting and data system (O-RADS).
A total of 663 ultrasound images of adnexal mass were collected and divided into two sets according to experienced radiologists: a low malignant risk set (n = 446) and an intermediate-high malignant risk set (n = 217). Deep learning segmentation models were trained and selected to automatically segment adnexal masses. Radiomics features were extracted utilizing a feature analysis system in Pyradiomics. Feature selection was conducted using the Spearman correlation analysis, Mann-Whitney U-test, and least absolute shrinkage and selection operator (LASSO) regression. A nomogram integrating radiomic and clinical features using a machine learning model was established and evaluated. The SHapley Additive exPlanations were used for model interpretability and visualization.
The FCN ResNet101 demonstrated the highest segmentation performance for adnexal masses (Dice similarity coefficient: 89.1%). Support vector machine achieved the best AUC (0.961, 95% CI: 0.925-0.996). The nomogram using the LightGBM algorithm reached the best AUC (0.966, 95% CI: 0.927-1.000). The diagnostic performance of the nomogram was comparable to that of experienced radiologists (p > 0.05) and outperformed that of less-experienced radiologists (p < 0.05). The model significantly improved the diagnostic accuracy of less-experienced radiologists.
The segmentation model serves as a valuable tool for the automated delineation of adnexal lesions. The machine learning model exhibited commendable classification capability and outperformed the diagnostic performance of less-experienced radiologists.
The ultrasound radiomics-based machine learning model holds the potential to elevate the professional ability of less-experienced radiologists and can be used to assist in the clinical screening of ovarian cancer.
We developed an image segmentation model to automatically delineate adnexal masses. We developed a model to classify adnexal masses based on O-RADS. The machine learning model has achieved commendable classification performance. The machine learning model possesses the capability to enhance the proficiency of less-experienced radiologists. We used SHapley Additive exPlanations to interpret and visualize the model.
开发一种自动分割模型以勾勒附件包块，并构建一种机器学习模型，基于卵巢附件报告和数据系统（O-RADS）区分附件包块的低恶性风险和中高恶性风险。
收集了663张附件包块的超声图像，并根据经验丰富的放射科医生将其分为两组：低恶性风险组（n = 446）和中高恶性风险组（n = 217）。训练并选择深度学习分割模型以自动分割附件包块。利用Pyradiomics中的特征分析系统提取影像组学特征。使用Spearman相关分析、Mann-Whitney U检验和最小绝对收缩和选择算子（LASSO）回归进行特征选择。建立并评估使用机器学习模型整合影像组学和临床特征的列线图。使用SHapley加性解释进行模型解释和可视化。
FCN ResNet101在附件包块分割性能方面表现最佳（骰子相似系数：89.1%）。支持向量机获得了最佳的AUC（0.961，95% CI：0.925 - 0.996）。使用LightGBM算法的列线图达到了最佳的AUC（0.966，95% CI：0.927 - 1.000）。列线图的诊断性能与经验丰富的放射科医生相当（p > 0.05），且优于经验不足的放射科医生（p < 0.05）。该模型显著提高了经验不足的放射科医生的诊断准确性。
分割模型是自动勾勒附件病变的有价值工具。机器学习模型表现出值得称赞的分类能力，且优于经验不足的放射科医生的诊断性能。
基于超声影像组学的机器学习模型有潜力提升经验不足的放射科医生的专业能力，并可用于辅助卵巢癌的临床筛查。
我们开发了一种图像分割模型以自动勾勒附件包块。我们开发了一种基于O-RADS对附件包块进行分类的模型。机器学习模型取得了值得称赞的分类性能。机器学习模型具备提高经验不足的放射科医生熟练程度的能力。我们使用SHapley加性解释来解释和可视化模型。
