2026-06-02T07:26:13Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/156592026-02-03T12:05:03Zcom_10630_2254col_10630_37959

Non-negative matrix factorization for medical imaging Stoean, Ruxandra Atencia-Ruiz, Miguel Alejandro Matemáticas aplicadas - Congresos A non-negative matrix factorization approach to dimensionality reduction is proposed to aid classification of images. The original images can be stored as lower-dimensional columns of a matrix that hold degrees of belonging to feature components, so they can be used in the training phase of the classification at lower runtime and without loss in accuracy. The extracted features can be visually examined and images reconstructed with limited error. The proof of concept is performed on a benchmark of handwritten digits, followed by the application to histopathological colorectal cancer slides. Results are encouraging, though dealing with real-world medical data raises a number of issues. 2018-05-02T12:57:58Z 2018-05-02T12:57:58Z 2018-05-02T12:57:58Z 2018 conference output Atencia, Miguel, and Ruxandra Stoean. 2018. “Non-Negative Matrix Factorization for Medical Imaging.” In European Symposium on Artificial Neural Networks, edited by M. Verleysen, 379–384. https://hdl.handle.net/10630/15659 eng European Symposium on Artificial Neural Networks (ESANN) Brujas (Bélgica) 25 Abril 2018 open access Atribución-NoComercial-CompartirIgual 4.0 Internacional i6doc.com