荧光摄影术自动胃癌风险分类的初步研究
Preliminary study of automatic gastric cancer risk classification from photofluorography.
作者信息
Togo Ren, Ishihara Kenta, Mabe Katsuhiro, Oizumi Harufumi, Ogawa Takahiro, Kato Mototsugu, Sakamoto Naoya, Nakajima Shigemi, Asaka Masahiro, Haseyama Miki
机构信息
Graduate School of Information Science and Technology, Hokkaido University, Hokkaido 060-0814, Japan.
Department of Gastroenterology, National Hospital Organization Hakodate Hospital, Hokkaido 041-8512, Japan.
出版信息
World J Gastrointest Oncol. 2018 Feb 15;10(2):62-70. doi: 10.4251/wjgo.v10.i2.62.
AIM
To perform automatic gastric cancer risk classification using photofluorography for realizing effective mass screening as a preliminary study.
METHODS
We used data for 2100 subjects including X-ray images, pepsinogen I and II levels, PGI/PGII ratio, () antibody, eradication history and interview sheets. We performed two-stage classification with our system. In the first stage, infection status classification was performed, and -infected subjects were automatically detected. In the second stage, we performed atrophic level classification to validate the effectiveness of our system.
RESULTS
Sensitivity, specificity and Youden index (YI) of infection status classification were 0.884, 0.895 and 0.779, respectively, in the first stage. In the second stage, sensitivity, specificity and YI of atrophic level classification for -infected subjects were 0.777, 0.824 and 0.601, respectively.
CONCLUSION
Although further improvements of the system are needed, experimental results indicated the effectiveness of machine learning techniques for estimation of gastric cancer risk.
目的
作为一项初步研究，使用荧光摄影术进行胃癌风险自动分类以实现有效的大规模筛查。
方法
我们使用了2100名受试者的数据，包括X线图像、胃蛋白酶原I和II水平、PGI/PGII比值、（）抗体、根除史和访谈表。我们用我们的系统进行了两阶段分类。在第一阶段，进行感染状态分类，并自动检测感染的受试者。在第二阶段，我们进行萎缩水平分类以验证我们系统的有效性。
结果
在第一阶段，感染状态分类的敏感性、特异性和尤登指数（YI）分别为0.884、0.895和0.779。在第二阶段，感染受试者萎缩水平分类的敏感性、特异性和YI分别为0.777、0.824和0.601。
结论
虽然该系统还需要进一步改进，但实验结果表明机器学习技术在评估胃癌风险方面的有效性。
Zotero 插件