Classification of H&E Images via CNN Models with XAI Approaches, DeepDream Representations and Multiple Classifiers

Leandro Neves, João Martinez, Leonardo Longo, Guilherme Freire Roberto, Thaína Tosta, Paulo de Faria, Adriano Loyola, Sérgio Cardoso, Adriano Silva, Marcelo Zanchetta do Nascimento, Guilherme Rozendo

2023

Abstract

The study of diseases via histological images with machine learning techniques has provided important advances for diagnostic support systems. In this project, a study was developed to classify patterns in histological images, based on the association of convolutional neural networks, explainable artificial intelligence techniques, DeepDream representations and multiple classifiers. The images under investigation were representatives of breast cancer, colorectal cancer, liver tissue, and oral dysplasia. The most relevant features were associated by applying the Relief algorithm. The classifiers used were Rotation Forest, Multilayer Perceptron, Logistic, Random Forest, Decorate, IBk, K*, and SVM. The main results were areas under the ROC curve ranging from 0.994 to 1, achieved with a maximum of 100 features. The collected information allows for expanding the use of consolidated techniques in the area of classification and pattern recognition, in addition to supporting future applications in computer-aided diagnosis.

Paper Citation

in Harvard Style

Neves L., Martinez J., Longo L., Freire Roberto G., Tosta T., de Faria P., Loyola A., Cardoso S., Silva A., Zanchetta do Nascimento M. and Rozendo G. (2023). Classification of H&E Images via CNN Models with XAI Approaches, DeepDream Representations and Multiple Classifiers. In Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-648-4, SciTePress, pages 354-364. DOI: 10.5220/0011839400003467

in Bibtex Style

@conference{iceis23,
author={Leandro Neves and João Martinez and Leonardo Longo and Guilherme Freire Roberto and Thaína Tosta and Paulo de Faria and Adriano Loyola and Sérgio Cardoso and Adriano Silva and Marcelo Zanchetta do Nascimento and Guilherme Rozendo},
title={Classification of H&E Images via CNN Models with XAI Approaches, DeepDream Representations and Multiple Classifiers},
booktitle={Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2023},
pages={354-364},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011839400003467},
isbn={978-989-758-648-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Classification of H&E Images via CNN Models with XAI Approaches, DeepDream Representations and Multiple Classifiers
SN - 978-989-758-648-4
AU - Neves L.
AU - Martinez J.
AU - Longo L.
AU - Freire Roberto G.
AU - Tosta T.
AU - de Faria P.
AU - Loyola A.
AU - Cardoso S.
AU - Silva A.
AU - Zanchetta do Nascimento M.
AU - Rozendo G.
PY - 2023
SP - 354
EP - 364
DO - 10.5220/0011839400003467
PB - SciTePress