Department of Medical Ultrasonics, The First People's Hospital of Foshan, No. 81, Lingnan Avenue North, Foshan, 528000, China.
Department of Radiology, Nanfang Hospital, Southern Medical University, 1838 Guangzhou Avenue North, Guangzhou, 510515, China.
Eur Radiol. 2024 Oct;34(10):6862-6876. doi: 10.1007/s00330-024-10719-2. Epub 2024 Apr 3.
The preoperative classification of pleomorphic adenomas (PMA) and Warthin tumors (WT) in the parotid gland plays an essential role in determining therapeutic strategies. This study aims to develop and validate an ultrasound-based ensemble machine learning (USEML) model, employing nonradiative and noninvasive features to differentiate PMA from WT.
A total of 203 patients with histologically confirmed PMA or WT who underwent parotidectomy from two centers were enrolled. Clinical factors, ultrasound (US) features, and radiomic features were extracted to develop three types of machine learning model: clinical models, US models, and USEML models. The diagnostic performance of the USEML model, as well as that of physicians based on experience, was evaluated and validated using receiver operating characteristic (ROC) curves in internal and external validation cohorts. DeLong's test was used for comparisons of AUCs. SHAP values were also utilized to explain the classification model.
The USEML model achieved the highest AUC of 0.891 (95% CI, 0.774-0.961), surpassing the AUCs of both the US (0.847; 95% CI, 0.720-0.932) and clinical (0.814; 95% CI, 0.682-0.908) models. The USEML model also outperformed physicians in both internal and external validation datasets (both p < 0.05). The sensitivity, specificity, negative predictive value, and positive predictive value of the USEML model and physician experience were 89.3%/75.0%, 87.5%/54.2%, 87.5%/65.6%, and 89.3%/65.0%, respectively.
The USEML model, incorporating clinical factors, ultrasound factors, and radiomic features, demonstrated efficient performance in distinguishing PMA from WT in the parotid gland.
This study developed a machine learning model for preoperative diagnosis of pleomorphic adenoma and Warthin tumor in the parotid gland based on clinical, ultrasound, and radiomic features. Furthermore, it outperformed physicians in an external validation dataset, indicating its potential for clinical application.
• Differentiating pleomorphic adenoma (PMA) and Warthin tumor (WT) affects management decisions and is currently done by invasive biopsy. • Integration of US-radiomic, clinical, and ultrasound findings in a machine learning model results in improved diagnostic accuracy. • The ultrasound-based ensemble machine learning (USEML) model consistently outperforms physicians, suggesting its potential applicability in clinical settings.
腮腺多形性腺瘤（PMA）和沃辛瘤（WT）的术前分类在确定治疗策略方面起着至关重要的作用。本研究旨在开发和验证一种基于超声的集成机器学习（USEML）模型，该模型利用非放射性和非侵入性特征来区分 PMA 和 WT。
本研究共纳入了 203 名经组织学证实的腮腺 PMA 或 WT 患者，这些患者分别来自两个中心，接受了腮腺切除术。提取临床因素、超声（US）特征和放射组学特征，以开发三种类型的机器学习模型：临床模型、US 模型和 USEML 模型。使用内部和外部验证队列中的接收者操作特征（ROC）曲线评估和验证 USEML 模型以及医生基于经验的诊断性能。使用 DeLong 检验比较 AUC。还利用 SHAP 值来解释分类模型。
USEML 模型的 AUC 最高，为 0.891（95%CI，0.774-0.961），优于 US（0.847；95%CI，0.720-0.932）和临床（0.814；95%CI，0.682-0.908）模型的 AUC。USEML 模型在内部和外部验证数据集中的表现也优于医生（均 p<0.05）。USEML 模型和医生经验的灵敏度、特异性、阴性预测值和阳性预测值分别为 89.3%/75.0%、87.5%/54.2%、87.5%/65.6%和 89.3%/65.0%。
USEML 模型结合了临床因素、超声因素和放射组学特征，在区分腮腺中的 PMA 和 WT 方面表现出高效能。
本研究基于临床、超声和放射组学特征开发了一种用于术前诊断腮腺多形性腺瘤和沃辛瘤的机器学习模型。此外，在外部验证数据集中，它的表现优于医生，表明其在临床应用中的潜力。
区分多形性腺瘤（PMA）和沃辛瘤（WT）会影响管理决策，目前通过有创活检来完成。
将 US-放射组学、临床和超声发现整合到机器学习模型中可提高诊断准确性。
基于超声的集成机器学习（USEML）模型始终优于医生，这表明其在临床环境中的潜在适用性。
