School of information science and engineering, Central South University, Changsha 410083, China; "Mobile Health" Ministry of Education-China Mobile Joint Laboratory, Changsha 410083, China; School of Software, Central South University, Changsha 410083, China.
PET-CT Center, The Second Xiangya Hospital of Central South University, Changsha 410083, China .
Comput Methods Programs Biomed. 2018 Jun;159:87-101. doi: 10.1016/j.cmpb.2018.03.004. Epub 2018 Mar 11.
Non-small cell lung cancer (NSCLC) is a high risk cancer and is usually scanned by PET-CT for testing, predicting and then give the treatment methods. However, in the actual hospital system, at least 640 images must be generated for each patient through PET-CT scanning. Especially in developing countries, a huge number of patients in NSCLC are attended by doctors. Artificial system can predict and make decision rapidly. According to explore and research artificial medical system, the selection of artificial observations also can result in low work efficiency for doctors. In this study, data information of 2,789,675 patients in three hospitals in China are collected, compiled, and used as the research basis; these data are obtained through image acquisition and diagnostic parameter machine decision-making method on the basis of the machine diagnosis and medical system design model of adjuvant therapy. By combining image and diagnostic parameters, the machine decision diagnosis auxiliary algorithm is established. Experimental result shows that the accuracy has reached 77% in NSCLC.
非小细胞肺癌（NSCLC）是一种高危癌症，通常通过 PET-CT 进行检测、预测，然后给出治疗方法。然而，在实际的医院系统中，每个患者至少需要通过 PET-CT 扫描生成 640 张图像。特别是在发展中国家，大量的 NSCLC 患者由医生治疗。人工系统可以快速预测和做出决策。根据对人工医学系统的探索和研究，人工观察的选择也会导致医生的工作效率低下。在这项研究中，收集、整理了中国三家医院的 2789675 名患者的数据信息，并将其作为研究基础；这些数据是通过机器诊断和辅助治疗的医学系统设计模型的图像采集和诊断参数机器决策方法获得的。通过结合图像和诊断参数，建立了机器决策诊断辅助算法。实验结果表明，NSCLC 的准确率达到了 77%。
