Spectral band selection for mitosis detection in histopathology

Humayun Irshad, Alexandre Gouaillard, Ludovic Roux, Daniel Racoceanu

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

12 Citas (Scopus)

Resumen

This study aims at evaluating the accuracy of mitosis detection on multispectral histopathological images by developing a solution specifically designed to take advantage of multi-spectral information. The proposed framework includes a selection of spectral bands and focal plane, detection of candidate mitotic regions, computation of morphological & mul-tispectral statistical features (MMSF) and study of different state-of-the-art classification methods for mitosis classification. This framework achieved 74% TPR, 76% PPV and 74% F-Measure on MITOS dataset. Our results indicate that selected multispectral bands contain discriminant information for mitotic figures, being therefore a very promising exploration area to improve the quality of the diagnosis assistance in histopathology.

Idioma originalInglés
Título de la publicación alojada2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1279-1282
Número de páginas4
ISBN (versión digital)9781467319591
DOI
EstadoPublicada - 29 jul. 2014
Publicado de forma externa
Evento2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
Duración: 29 abr. 20142 may. 2014

Serie de la publicación

Nombre2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

Conferencia

Conferencia2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
País/TerritorioChina
CiudadBeijing
Período29/04/142/05/14

Huella

Profundice en los temas de investigación de 'Spectral band selection for mitosis detection in histopathology'. En conjunto forman una huella única.

Citar esto