We developed machine and deep learning models to predict chemoradiotherapy in rectal cancer using18F-FDG PET images and harmonized image features extracted from18F-FDG PET/CT images. Patients diagnosed with pathologic T-stage III rectal cancer with a tumor size > 2 cm were treated with neoadjuvant chemoradiotherapy. Patients with rectal cancer were divided into an internal dataset (n = 116) and an external dataset obtained from a separate institution (n = 40), which were used in the model. AUC was calculated to select image features associated with radiochemotherapy response. In the external test, the machine-learning signature extracted from18F-FDG PET image features achieved the highest accuracy and AUC value of 0.875 and 0.896. The harmonized first-order radiomics model had a higher efficiency with accuracy and an AUC of 0.771 than the second-order model in the external test. The deep learning model using the balanced dataset showed an accuracy of 0.867 in the internal test but an accuracy of 0.557 in the external test. Deep-learning models using18F-FDG PET images must be harmonized to demonstrate reproducibility with external data. Harmonized18F-FDG PET image features as an element of machine learning could help predict chemoradiotherapy responses in external tests with reproducibility.
我们开发了机器学习和深度学习模型，利用¹⁸F-FDG PET图像及从¹⁸F-FDG PET/CT图像中提取的标准化影像特征，预测直肠癌患者的放化疗反应。研究对象为经病理确诊为T分期III期、肿瘤尺寸大于2厘米并接受新辅助放化疗的直肠癌患者。患者数据分为内部数据集（n = 116）和来自独立机构的外部数据集（n = 40），均用于模型构建。通过计算受试者工作特征曲线下面积筛选与放化疗反应相关的影像特征。在外部测试中，基于¹⁸F-FDG PET影像特征构建的机器学习模型取得了最佳性能，其准确率达0.875，AUC值为0.896。标准化一阶影像组学模型在外部测试中表现出比二阶模型更高的效能，准确率为0.771，AUC值为0.771。使用平衡数据集构建的深度学习模型在内部测试中准确率达0.867，但在外部测试中准确率仅为0.557。基于¹⁸F-FDG PET图像的深度学习模型需进行标准化处理，才能在外部分数据中展现可重复性。作为机器学习要素的标准化¹⁸F-FDG PET影像特征，有助于在外部测试中实现具有可重复性的放化疗反应预测。
肿瘤(癌症)患者之家