Modelo combinado e interpretável para a classificação de células leucêmicas

• Ano de defesa: 2022
• Autor(a) principal: Sant’Anna, Yúri Faro Dantas de
• Orientador(a): Dantas, Daniel Oliveira
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Programa de Pós-Graduação: Pós-Graduação em Ciência da Computação
• Palavras-chave em Português: Classificação de leucemia; Aprendizagem combinada; Aprendizagem de máquina; Análise de características
• Palavras-chave em Inglês: Leukemia classification; Ensemble learning; Machine learning; Feature analysis
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://ri.ufs.br/jspui/handle/riufs/19527

The lymphocyte classification problem is usually solved by deep learning approaches based on convolutional neural networks with multiple layers. However, these techniques require specific hardware and long training times. This work proposes a lightweight image classification system capable of discriminating between healthy and cancerous lymphocytes of leukemia patients using image processing and feature-based machine learning techniques that require less training time and can run on a standard CPU. The features are composed of statistical, morphological, textural, frequency, and contour features extracted from each image and used to train a set of lightweight algorithms that classify the lymphocytes into malignant or healthy. After the training, these classifiers were combined into an ensemble classifier to improve the results. The proposed method has a lower computational cost than most deep learning approaches in learning time and neural network size. Our results contribute to the leukemia classification system showing that high performance can be achieved by classifiers trained with a rich set of features. With principal component analysis, it is possible to reduce the number of features used while maintaining a high accuracy.