Diagnosis of Endometrial Cancer Based on Back-Propagation Neural Network and Near-Infrared Spectroscopy of Tissue

Endometrial cancer is one of the most common cancers in women worldwide. Early stage and accurate diagnosis is indispensable for treatment of endometrial cancer patient. In this study, near-infrared spectra of 18 normal, 30 hyperplasia and 29 malignant pathological sections were collected. The original spectra were pretreated by using smoothing, denoising, and data compression methods, 6 principal components were extracted as the input of back propagation neural network(BPNN). The number of hidden neurons, learning rate, momentum, and learning epochs were optimized based on the RMSE of leave-one-out cross validation (LOOCV). The optimal model of BPNN built can successfully classify the samples into three groups. The results showed that BPNN coupling with NIR spectroscopy can provide an efficient method for the early diagnosis of endometrial cancer.