Multiple instance learning for lung pathophysiological findings detection using CT scans

• Tipo: Artigo em Revista Científica Internacional
• Data: 2022

Autores

Frade, J (Autor) Outra; Pereira, T (Autor) Outra; Morgado, J (Autor) Outra; Silva, F (Autor) Outra; Freitas, C (Autor) Outra; Mendes, J (Autor) Outra; Negrao, E (Autor) Outra; de Lima, BF (Autor) Outra; da Silva, MC (Autor) Outra; António Madureira (Autor) FMUP; Ramos, I (Autor) Outra; Costa, JL (Autor) Outra; Hespanhol V (Autor) FMUP; Cunha, A (Autor) Outra; Oliveira, HP (Autor) FCUP

Revista

Título: Medical and Biological Engineering and Computing

Vol. 60

Páginas: 1569-1584

ISSN: 0140-0118

Editora: Springer Nature

Indexação

ISI Web of Knowledge - 4 Citações

Scopus - 8 Citações

Outras Informações

ID Authenticus: P-00W-C33

DOI: 10.1007/s11517-022-02526-y

Abstract (EN): Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 16