Cystoscopic Image Classification by an Ensemble of VGG-Nets

Over the last three decades, artificial intelligence has attracted lots of attentions in medical diagnosis tasks. However, few studies have been presented to assist urologists to diagnose bladder cancer in spite of its high prevalence worldwide. In this paper, a new computer aided diagnosis system is proposed to classify four types of cystoscopic images including malignant masses, benign masses, blood in urine, and normal. The proposed classifier is an ensemble of a well-known type of convolutional neural networks (CNNs) called VGG-Net. To combine the VGG-Nets, bootstrap aggregating approach is used. The proposed ensemble classifier was evaluated on a dataset of 720 images. Based on the experiments, the presented method achieved an accuracy of 63% which outperforms base VGG-Nets and other competing methods.

Automated summary

Over the last three decades, artificial intelligence in medical diagnosis tasks has attracted much attention. This paper proposes a new computer aided diagnosis system to classify four types of cystoscopic images, achieving an accuracy of 63% which outperforms base VGG-Nets and other competing methods.