Using multi-layer perceptron with Laplacian edge detector for bladder cancer diagnosis

TLDR

The study investigates whether a simpler Multi‑Layer Perceptron can be used for urinary bladder cancer detection alongside conventional deep learning methods. The authors train and test a Multi‑Layer Perceptron on 1997 bladder cancer and 986 non‑cancer images pre‑processed with a Laplacian edge detector. The approach achieved an AUC of up to 0.99, with optimal performance using 50×50 and 100×100 image sizes.

Abstract

In this paper, the urinary bladder cancer diagnostic method which is based on Multi-Layer Perceptron and Laplacian edge detector is presented. The aim of this paper is to investigate the implementation possibility of a simpler method (Multi-Layer Perceptron) alongside commonly used methods, such as Deep Learning Convolutional Neural Networks, for the urinary bladder cancer detection. The dataset used for this research consisted of 1997 images of bladder cancer and 986 images of non-cancer tissue. The results of the conducted research showed that using Multi-Layer Perceptron trained and tested with images pre-processed with Laplacian edge detector are achieving AUC value up to 0.99. When different image sizes are compared it can be seen that the best results are achieved if 50×50 and 100×100 images were used.