Onozato Yuki, Suzuki Hidemi, Matsumoto Hiroki, Ito Takamasa, Yamamoto Takayoshi, Tanaka Kazuhisa, Sakairi Yuichi, Matsui Yukiko, Iwata Takekazu, Iida Tomohiko, Iizasa Toshihiko, Yoshino Ichiro
Department of General Thoracic Surgery, Chiba University Graduate School of Medicine, Inohana, Chuo-ku, Chiba-shi, Chiba, Japan.
Department of Thoracic Surgery, Kimitsu Chuo Hospital, Sakurai, Kisarazu-shi, Chiba, Japan.
J Thorac Dis. 2024 Aug 31;16(8):4935-4946. doi: 10.21037/jtd-23-1840. Epub 2024 Aug 15.
Minimally invasive approaches have been a standard choice of surgery for noninvasive thymic epithelial tumors (TETs), but we sometimes experience cases requiring combined resection of adjacent structures. We develop and validate machine learning models to predict combined resection based on preoperative contrast-enhanced computed tomography (CT).
This study included 212 patients with TETs (140 in the training cohort and 72 in the validation cohort) who underwent radical surgery. Radiomics features were extracted from contrast-enhanced CT and predicted with five feature selection methods and seven machine learning models in nested cross validation. The clinical utility of the models was analyzed by a decision curve analysis (DCA).
Fifty-five patients in the training cohort and 28 in the validation cohort required combined resection. The classifiers random forest (RF), gradient boosting (GB), and eXtreme Gradient Boosting (XGB) indicated high predictive performance, with the XGB classifier based on features selected by GB performing the best, with an area under the curve (AUC) of 0.797. In the validation cohort, the classifier had an AUC of 0.817. The DCA showed the validity of the model with a threshold range of 15-72%. When restricted to combined pulmonary and pericardial resection, the respective AUCs were 0.736 and 0.674 for the training cohort and 0.806 and 0.924 for the validation cohort.
The machine learning model based on preoperative CT images was able to diagnose TETs requiring combined resection with high accuracy. The DCA demonstrated a wide range of model validity and may aid in surgical approach selection.
微创方法一直是无创性胸腺上皮肿瘤（TETs）手术的标准选择，但我们有时会遇到需要联合切除相邻结构的病例。我们开发并验证了基于术前增强计算机断层扫描（CT）预测联合切除的机器学习模型。
本研究纳入了212例行根治性手术的TETs患者（训练队列140例，验证队列72例）。从增强CT中提取影像组学特征，并在嵌套交叉验证中用五种特征选择方法和七种机器学习模型进行预测。通过决策曲线分析（DCA）分析模型的临床实用性。
训练队列中有55例患者、验证队列中有28例患者需要联合切除。分类器随机森林（RF）、梯度提升（GB）和极端梯度提升（XGB）显示出较高的预测性能，基于GB选择的特征的XGB分类器表现最佳，曲线下面积（AUC）为0.797。在验证队列中，该分类器的AUC为0.817。DCA显示模型在15%-72%的阈值范围内有效。当仅限于联合肺和心包切除时，训练队列的AUC分别为0.736和0.674，验证队列的AUC分别为0.806和0.924。
基于术前CT图像的机器学习模型能够高精度诊断需要联合切除的TETs。DCA证明了模型在广泛范围内的有效性，可能有助于手术方式的选择。
