Spectral band selection for mitosis detection in histopathology

Autor:	Humayun Irshad, Alexandre Gouaillard, Ludovic Roux, Daniel Racoceanu
Rok vydání:	2014
Předmět:	medicine.medical_specialty business.industry Computer science Feature extraction Multispectral image Pattern recognition Spectral bands medicine.disease Breast cancer Mitotic Figure medicine Histopathology Computer vision Artificial intelligence business Mitosis Selection (genetic algorithm)
Zdroj:	ISBI Scopus-Elsevier
Popis:	This study aims at evaluating the accuracy of mitosis detection on multispectral histopathological images by developing a solution specifically designed to take advantage of multispectral information. The proposed framework includes a selection of spectral bands and focal plane, detection of candidate mitotic regions, computation of morphological & multispectral 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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2cbd9220d6076eb9e0e601d47729e647 https://doi.org/10.1109/isbi.2014.6868110 Zobrazit plný text záznamu