Introducing lifelong machine learning in the active tuberculosis classification through chest radiographs

Título: Introducing lifelong machine learning in the active tuberculosis classification through chest radiographs

Autores: Regina Alves, Frederico Tavares, José Seixas and Anete Trajman

Resumo:
Tuberculosis (TB) is a contagious disease which is among the top 10 causes of death in the world. In order to eliminate the disease by 2050, the treatment of TB infection (TBI) is essential, which requires radiological reports to exclude active tuberculosis. The automatic X-ray classifiers used today are based on models that do not guarantee the retention of knowledge if they need to learn new tasks over time. This work proposes the introduction of the lifelong machine learning (LML) paradigm in automatic X-ray classifiers aimed at helping to diagnose active TB (ATB). Two LML algorithms, Efficient Lifelong Learning Algorithm (ELLA) and Learning without Forgetting (LwF), are applied to the TB and pneumonia classification tasks. The results show that it is possible to keep the performance in both tasks with the LML paradigm.

Palavras-chave:
lifelong learning, machine learning, tuberculosis, tuberculosis infection, latent tuberculosis, x-ray classification.

Páginas: 8

Código DOI: 10.21528/CBIC2021-119

Artigo em pdf: CBIC_2021_paper_119.pdf

Arquivo BibTeX: CBIC_2021_119.bib