Establishment of a new non-invasive imaging prediction model for liver metastasis in colon cancer.
Establishment of a new non-invasive imaging prediction model for liver metastasis in colon cancer.
复制标题
DOI：
--
复制
发表时间：
2019
影响因子：
5.3
通讯作者：
Yu Li;A. Eresen;J. Shangguan;Jia Yang;Yun Lu;Dong Chen;Jian Wang;Yury Velichko;V. Yaghmai;Zhuoli Zhang
中科院分区：
文献类型：
--
作者：
Yu Li;A. Eresen;J. Shangguan;Jia Yang;Yun Lu;Dong Chen;Jian Wang;Yury Velichko;V. Yaghmai;Zhuoli Zhang
本研究的目的是开发和验证一种新的基于术前计算机断层扫描（CT）数据的无创人工智能（AI）模型，以预测结肠癌（CC）中肝转移（LM）的存在。共有48例符合条件的CC患者入组，包括24例LM患者和24例无LM患者。利用从CT数据中提取的6个临床因素和152个肿瘤图像特征，利用5倍交叉验证的支持向量机建立了临床、放射组学和混合（临床和放射组学特征的组合）3个模型。根据准确性、特异性、敏感性和曲线下面积（AUC）对每个模型的性能进行评估。对于放射组学模型，总共使用了四个图像特征来构建模型，训练准确率为83.87%，验证准确率为79.50%。采用所选临床变量的临床模型的训练和验证准确率分别为69.82%和69.50%。结合相关图像特征和临床变量的混合模型提高了训练集（90.63%）和验证集（85.50%）的准确率。AUC方面，杂种模型（0.96;0.87）和放射组学模型（0.91;0.85）较临床模型（0.71;0.69）有显著改善，杂种模型预测效果最好。综上所述，利用术前常规CT数据开发的AI模型可以准确预测CC患者的LM，无需额外的手术。此外，将图像特征与临床特征相结合，大大提高了模型的预测性能。因此，我们产生了一个很有前途的工具，可以指导和个体化监测肝癌高风险的CC患者。
The aim of this study was to develop and validate a new non-invasive artificial intelligence (AI) model based on preoperative computed tomography (CT) data to predict the presence of liver metastasis (LM) in colon cancer (CC). A total of forty-eight eligible CC patients were enrolled, including twenty-four patients with LM and twenty-four patients without LM. Six clinical factors and one hundred and fifty-two tumor image features extracted from CT data were utilized to develop three models: clinical, radiomics, and hybrid (a combination of clinical and radiomics features) using support vector machines with 5-fold cross-validation. The performance of each model was evaluated in terms of accuracy, specificity, sensitivity, and area under the curve (AUC). For the radiomics model, a total of four image features utilized to construct the model resulting in an accuracy of 83.87% for training and 79.50% for validation. The clinical model that employed two selected clinical variables had an accuracy of 69.82% and 69.50% for training and validation, respectively. The hybrid model that combined relevant image features and clinical variables improved accuracy of both training (90.63%) and validation (85.50%) sets. In terms of AUC, hybrid (0.96; 0.87) and radiomics models (0.91; 0.85) demonstrated a significant improvement compared with the clinical model (0.71; 0.69), and the hybrid model had the best prediction performance. In conclusion, the AI model developed using preoperative conventional CT data can accurately predict LM in CC patients without additional procedures. Furthermore, combining image features with clinical characteristics greatly improved the model's prediction performance. We have thus generated a promising tool that allows guidance and individualized surveillance of CC patients with high risks of LM.