Computer-aided classification system for early endometrial cancer of co-registered photoacoustic and ultrasonic signals

Abstract

Stage IA endometrial cancer is the only candidate for conservative management. Therefore, early diagnosis of endometrial cancer is very important. Co-registered photoacoustic (PA) and ultrasonic (US) imaging system is available to detect early endometrial cancer (EEC) based on a cylindrical diffuser. To correctly detect and diagnose EEC from FIGO stage IA and stage IB by co-registered PA and US imaging system, a convolutional neural network (CNN) classifier of EEC for co-registered PA and US images was proposed. Activation function ReLU and the dropout technique were used in the CNN classifier. The experiment results show the area under the receiver operating characteristic curve of the proposed algorithm is 0.9998 with a sensitivity of 98.75% and specificity of 98.75%. The CNN classifier could be used in the computer-aided diagnosis for early endometrial cancer of the co-registered PA and US imaging system.