Author(s):
Kandel, Ibrahem ; Castelli, Mauro ; Popovič, Aleš
Date: 2020
Persistent ID: http://hdl.handle.net/10362/105501
Origin: Repositório Institucional da UNL
Project/scholarship:
info:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FDS%2F0113%2F2019/PT;
info:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FDS%2F0022%2F2018/PT;
Subject(s): Convolutional neural networks; Deep learning; Image classification; Medical images; Optimizers; Transfer learning; Radiology Nuclear Medicine and imaging; Computer Vision and Pattern Recognition; Computer Graphics and Computer-Aided Design; Electrical and Electronic Engineering; SDG 3 - Good Health and Well-being
Description
Kandel, I., Castelli, M., & Popovič, A. (2020). Comparative Study of First Order Optimizers for Image Classification Using Convolutional Neural Networks on Histopathology Images. Journal of Imaging, 6(9), 1-17. [0092]. https://doi.org/10.3390/JIMAGING6090092
The classification of histopathology images requires an experienced physician with years of experience to classify the histopathology images accurately. In this study, an algorithm was developed to assist physicians in classifying histopathology images; the algorithm receives the histopathology image as an input and produces the percentage of cancer presence. The primary classifier used in this algorithm is the convolutional neural network, which is a state-of-the-art classifier used in image classification as it can classify images without relying on the manual selection of features from each image. The main aim of this research is to improve the robustness of the classifier used by comparing six different first-order stochastic gradient-based optimizers to select the best for this particular dataset. The dataset used to train the classifier is the PatchCamelyon public dataset, which consists of 220,025 images to train the classifier; the dataset is composed of 60% positive images and 40% negative images, and 57,458 images to test its performance. The classifier was trained on 80% of the images and validated on the rest of 20% of the images; then, it was tested on the test set. The optimizers were evaluated based on their AUC of the ROC curve. The results show that the adaptative based optimizers achieved the highest results except for AdaGrad that achieved the lowest results.
