Method for establishing eosinophilic granulocyte proportion model by utilizing nasal polyp pathological picture

• Main Authors: WANG WEIHAO, CHEN JIANNING, REN YONG, HUANG GUIFANG, QIU HUIJUN, YUAN TIAN, WU QINGWU, YUAN LIANXIONG, LI QUAN, ZHENG RUI, HONG HAIYU, SUN YUEQI, HAN LANQING, WANG LUNJI, YANG QINTAI, KONG WEIFENG, HUANG XUEKUN, YE JUNJIE, DENG HUIYI
• Format: Patent
• Language: Chinese; English
• Published: 31.01.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention discloses a method for establishing an eosinophilic granulocyte proportion model by utilizing a nasal polyp pathological picture, and the method comprises the following steps: preparingdata, manufacturing nasal polyp into a slide, scanning by using a digital pathological instrument to obtain a WSI picture, and cutting the WSI picture to obtain small pathological pictures; dividing all the small pathological pictures into training set data and test set data according to a set proportion; establishing the eosinophilic granulocyte proportion model; performing training on an ImageNet data set by adopting an Inception V3 model to obtain model parameters, removing the last full connection layer FC of the model, adding a full connection layer FC, wherein only one neuron is arranged in the full connection layer FC, and no activation function is adopted; setting a loss function to employ a mean square error MSE, and setting a learning rate lr. The method is applied to a chronicnasosinusitis nasal polyp p