文献类型：期刊文献

英文题名：Image segmentation algorithm of lung cancer based on neural network model

作者：He, Binjun[1];Hu, Wenbin[2];Zhang, Kang[2];Yuan, Shunda[2];Han, Xiaoliang[2];Su, Chao[2];Zhao, Jiaming[2];Wang, Guzong[2];Wang, Guoxia[2];Zhang, Liuya[2]

机构：[1]Zhejiang Univ, Sch Med, Shaoxing Peoples Hosp, Dept Thoracosurg, Shaoxing, Peoples R China;[2]Shaoxing Univ, Affiliated Hosp, Shaoxing Municipal Hosp, Dept Cardiothorac Surg, Shaoxing 312000, Peoples R China

年份：2022

卷号：39

期号：3

外文期刊名：EXPERT SYSTEMS

收录：SCI-EXPANDED(收录号：WOS:000710122400001)、、EI(收录号：20214311061168)、Scopus(收录号：2-s2.0-85117581530)、WOS

语种：英文

外文关键词：fuzzy neural network; image segmentation; lung cancer; wiener filtering

外文摘要：To explore the application of neural network algorithm model in lung cancer imaging, and provide reference for the application and development of artificial neural network (ANN) algorithm model in lung cancer medical mirroring, so as to promote the development of ANN in this field. Meanwhile, it is hoped that the application of neural network algorithms in medical imaging can improve the survival rate and cure rate of lung cancer. In this study, an ANN algorithm model was selected to establish a lung cancer recognition model. After determining the lung cancer lesion area, the image segmentation algorithm was used to separately display the lung cancer lesion area, and a comparison experiment was designed to verify the accuracy of the model. ANNs were used to identify lung cancer, which can be concluded that the accuracy is 94.6%, the sensitivity is 95.7%, and the specificity is 93.5%. By combining image retrieval methods with lung cancer image segmentation algorithms, the lesion area of lung cancer can be clearly displayed. Therefore, the lung cancer image segmentation algorithm based on the neural network model has good recognition performance. This research can provide reference for the application of neural network algorithm model in the field of cancer diagnosis and treatment.