无线电技术
肺癌
人工智能
计算机断层摄影术
计算机科学
融合
放射基因组学
放射科
医学
肿瘤科
语言学
哲学
作者
Panyanat Aonpong,Yutaro Iwamoto,Xian-Hua Han,Lanfen Lin,Yen‐Wei Chen
标识
DOI:10.1109/embc46164.2021.9630703
摘要
Non-small cell lung cancer (NSCLC) is a type of lung cancer that has a high recurrence rate after surgery. Precise prediction of preoperative prognosis for NSCLC recurrence tends to contribute to the suitable preparation for treatment. Currently, many studied have been conducted to predict the recurrence of NSCLC based on Computed Tomography-images (CT images) or genetic data. The CT image is not expensive but inaccurate. The gene data is more expensive but has high accuracy. In this study, we proposed a genotype-guided radiomics method called GGR and GGR_Fusion to make a higher accuracy prediction model with requires only CT images. The GGR is a two-step method which is consists of two models: the gene estimation model using deep learning and the recurrence prediction model using estimated genes. We further propose an improved performance model based on the GGR model called GGR_Fusion to improve the accuracy. The GGR_Fusion uses the extracted features from the gene estimation model to enhance the recurrence prediction model. The experiments showed that the prediction performance can be improved significantly from 78.61% accuracy, AUC=0.66 (existing radiomics method), 79.09% accuracy, AUC=0.68 (deep learning method) to 83.28% accuracy, AUC=0.77 by the proposed GGR and 84.39% accuracy, AUC=0.79 by the proposed GGR_Fusion.Clinical Relevance—This study improved the preoperative recurrence of NSCLC prediction accuracy from 78.61% by the conventional method to 84.39% by our proposed method using only the CT image.
科研通智能强力驱动
Strongly Powered by AbleSci AI