A transfer-learning approach for lesion detection in endoscopic images from the urinary tract

Ureteroscopy and cystoscopy are the gold standard methods to identify and treat tumors along the urinary tract. It has been reported that during a normal procedure a rate of 10-20 % of the lesions could be missed. In this work we study the implementation of 3 different Convolutional Neural Networks (CNNs), using a 2-steps training strategy, to classify images from the urinary tract with and without lesions. A total of 6,101 images from ureteroscopy and cystoscopy procedures were collected. The CNNs were trained and tested using transfer learning in a two-steps fashion on 3 datasets. The datasets used were: 1) only ureteroscopy images, 2) only cystoscopy images and 3) the combination of both of them. For cystoscopy data, VGG performed better obtaining an Area Under the ROC Curve (AUC) value of 0.846. In the cases of ureteroscopy and the combination of both datasets, ResNet50 achieved the better results with AUC values of 0.987 and 0.940. The use of a training dataset which comprehends both domains results in general better performances, but performing a second stage of transfer learning achieves comparable ones. There is no single model which performs better in all scenarios, but ResNet50 is the network that achieves the better performances in most of them. The obtained results open the opportunity for further investigation with a view for improving lesion detection in endoscopic images of the urinary system. Clinical relevance — A computer-assisted method based on CNNs could lead to a better early and adequate detection of tumor-like lesions in the urinary tract. This could support surgeons to perform better follow-ups and reduce the high recurrence rates present on this disease.