Triagem virtual de imagens de imuno-histoqu\'imica usando redes neurais artificiais e espectro de padr\~oes

TL;DR

This paper presents a neural network-based image classifier utilizing pattern spectra and PCA for content-based retrieval of immunohistochemical images, aiding pathologists in faster analysis.

Contribution

It introduces a novel combination of pattern spectra, PCA, and neural networks for classifying immunohistochemical images in a CBIR system.

Findings

Achieved reasonable classification performance

Effective feature selection with pattern spectra and PCA

Integrated neural networks for content-based image retrieval

Abstract

The importance of organizing medical images according to their nature, application and relevance is increasing. Furhermore, a previous selection of medical images can be useful to accelerate the task of analysis by pathologists. Herein this work we propose an image classifier to integrate a CBIR (Content-Based Image Retrieval) selection system. This classifier is based on pattern spectra and neural networks. Feature selection is performed using pattern spectra and principal component analysis, whilst image classification is based on multilayer perceptrons and a composition of self-organizing maps and learning vector quantization. These methods were applied for content selection of immunohistochemical images of placenta and newdeads lungs. Results demonstrated that this approach can reach reasonable classification performance.