Jha Ashish Kumar, Mithun Sneha, Sherkhane Umeshkumar B, Jaiswar Vinay, Shah Sneha, Purandare Nilendu, Prabhash Kumar, Maheshwari Amita, Gupta Sudeep, Wee Leonard, Rangarajan V, Dekker Andre
Department of Radiation Oncology (Maastro), GROW - School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, Netherlands.
Department of Nuclear Medicine, Tata Memorial Hospital, Mumbai, India.
Front Nucl Med. 2023 May 17;3:1138552. doi: 10.3389/fnume.2023.1138552. eCollection 2023.
The role of artificial intelligence and radiomics in prediction model development in cancer has been increasing every passing day. Cervical cancer is the 4th most common cancer in women worldwide, contributing to 6.5% of all cancer types. The treatment outcome of cervical cancer patients varies and individualized prediction of disease outcome is of paramount importance.
The purpose of this study is to develop and validate the digital signature for 5-year overall survival prediction in cervical cancer using robust CT radiomic and clinical features.
Pretreatment clinical features and CT radiomic features of 68 patients, who were treated with chemoradiation therapy in our hospital, were used in this study. Radiomic features were extracted using an in-house developed python script and pyradiomic package. Clinical features were selected by the recursive feature elimination technique. Whereas radiomic feature selection was performed using a multi-step process i.e., step-1: only robust radiomic features were selected based on our previous study, step-2: a hierarchical clustering was performed to eliminate feature redundancy, and step-3: recursive feature elimination was performed to select the best features for prediction model development. Four machine algorithms i.e., Logistic regression (LR), Random Forest (RF), Support vector classifier (SVC), and Gradient boosting classifier (GBC), were used to develop 24 models (six models using each algorithm) using clinical, radiomic and combined features. Models were compared based on the prediction score in the internal validation.
The average prediction accuracy was found to be 0.65 (95% CI: 0.60-0.70), 0.72 (95% CI: 0.63-0.81), and 0.77 (95% CI: 0.72-0.82) for clinical, radiomic, and combined models developed using four prediction algorithms respectively. The average prediction accuracy was found to be 0.69 (95% CI: 0.62-0.76), 0.79 (95% CI: 0.72-0.86), 0.71 (95% CI: 0.62-0.80), and 0.72 (95% CI: 0.66-0.78) for LR, RF, SVC and GBC models developed on three datasets respectively.
Our study shows the promising predictive performance of a robust radiomic signature to predict 5-year overall survival in cervical cancer patients.
人工智能和放射组学在癌症预测模型开发中的作用与日俱增。宫颈癌是全球女性中第四大常见癌症，占所有癌症类型的6.5%。宫颈癌患者的治疗结果各不相同，对疾病结果进行个体化预测至关重要。
本研究旨在利用稳健的CT放射组学和临床特征，开发并验证用于预测宫颈癌5年总生存率的数字签名。
本研究使用了我院68例接受放化疗治疗患者的治疗前临床特征和CT放射组学特征。放射组学特征使用内部开发的Python脚本和pyradiomic软件包提取。临床特征通过递归特征消除技术进行选择。而放射组学特征选择则采用多步骤过程，即步骤1：根据我们之前的研究仅选择稳健的放射组学特征；步骤2：进行层次聚类以消除特征冗余；步骤3：进行递归特征消除以选择用于预测模型开发的最佳特征。使用四种机器学习算法，即逻辑回归（LR）、随机森林（RF）、支持向量分类器（SVC）和梯度提升分类器（GBC），利用临床、放射组学和联合特征开发24个模型（每种算法六个模型）。根据内部验证中的预测分数对模型进行比较。
分别使用四种预测算法开发的临床、放射组学和联合模型的平均预测准确率分别为0.65（95%CI：0.60 - 0.70）、0.72（95%CI：0.63 - 0.81）和0.77（95%CI：0.72 - 0.82）。分别在三个数据集上开发的LR、RF、SVC和GBC模型的平均预测准确率分别为0.69（95%CI：0.62 - 0.76）、0.79（95%CI：0.72 - 0.86）、0.71（95%CI：0.62 - 0.80）和0.72（95%CI：0.66 - 0.78）。
我们的研究表明，稳健的放射组学特征在预测宫颈癌患者5年总生存率方面具有良好的预测性能。
