Next Article in Journal
Unsupervised Mitral Valve Tracking for Disease Detection in Echocardiogram Videos
Next Article in Special Issue
Morphological Estimation of Cellularity on Neo-Adjuvant Treated Breast Cancer Histological Images
Previous Article in Journal
On the Use of Deep Active Semi-Supervised Learning for Fast Rendering in Global Illumination
Previous Article in Special Issue
Detection of HER2 from Haematoxylin-Eosin Slides Through a Cascade of Deep Learning Classifiers via Multi-Instance Learning
Article

Comparative Study of First Order Optimizers for Image Classification Using Convolutional Neural Networks on Histopathology Images

1
Nova Information Management School (NOVA IMS), Campus de Campolide, Universidade Nova de Lisboa, 1070-312 Lisboa, Portugal
2
School of Economics and Business, University of Ljubljana, Kardeljeva Ploščad 17, 1000 Ljubljana, Slovenia
*
Author to whom correspondence should be addressed.
Received: 26 August 2020 / Revised: 4 September 2020 / Accepted: 6 September 2020 / Published: 8 September 2020
(This article belongs to the Special Issue Deep Learning in Medical Image Analysis)
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. View Full-Text
Keywords: image classification; convolutional neural networks; deep learning; medical images; transfer learning; optimizers image classification; convolutional neural networks; deep learning; medical images; transfer learning; optimizers
Show Figures

Figure 1

MDPI and ACS Style

Kandel, I.; Castelli, M.; Popovič, A. Comparative Study of First Order Optimizers for Image Classification Using Convolutional Neural Networks on Histopathology Images. J. Imaging 2020, 6, 92. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging6090092

AMA Style

Kandel I, Castelli M, Popovič A. Comparative Study of First Order Optimizers for Image Classification Using Convolutional Neural Networks on Histopathology Images. Journal of Imaging. 2020; 6(9):92. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging6090092

Chicago/Turabian Style

Kandel, Ibrahem; Castelli, Mauro; Popovič, Aleš. 2020. "Comparative Study of First Order Optimizers for Image Classification Using Convolutional Neural Networks on Histopathology Images" J. Imaging 6, no. 9: 92. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging6090092

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop