An Improved CNN-Based Pneumoconiosis Diagnosis Method on X-ray Chest Film

Pneumoconiosis is one of the most serious occupational diseases in China, which seriously endangers the health of most workers in dust environments. The diagnosis of pneumoconiosis is very complex and cumbersome, which relies mostly on doctor's medical knowledge and clinical reading experiences of X-ray chest film. Traditional image processing approach has helped doctors to reduce the misdiagnosis but with lower accuracy. An improved CNN-based pneumoconiosis diagnosis method on X-ray chest films is proposed to predict pneumoconiosis disease. The CNN structure is decomposed from 5 x 5 convolution kernel into two 3 x 3 convolution kernels to optimize the execution. Compared with GoogLeNet, the proposed GoogLeNet-CF achieves higher accuracy and gives a good result in the diagnosis of pneumoconiosis disease.