Autor según el artículo: Singh VK; Romani S; Rashwan HA; Akram F; Pandey N; Sarker MMK; Abdulwahab S; Torrents-Barrena J; Saleh A; Arquez M; Arenas M; Puig D
Departamento: Ciències Mèdiques Bàsiques Enginyeria Informàtica i Matemàtiques
Autor/es de la URV: AKRAM, FARHAN / Arenas Prat, Meritxell / Puig Valls, Domènec Savi / Romaní Also, Santiago
Palabras clave: Cancer molecular subtypes Cgan Cnn Mammography Mass segmentation Mass shape classification
Resumen: © Springer Nature Switzerland AG 2018. This paper proposes a novel approach based on conditional Generative Adversarial Networks (cGAN) for breast mass segmentation in mammography. We hypothesized that the cGAN structure is well-suited to accurately outline the mass area, especially when the training data is limited. The generative network learns intrinsic features of tumors while the adversarial network enforces segmentations to be similar to the ground truth. Experiments performed on dozens of malignant tumors extracted from the public DDSM dataset and from our in-house private dataset confirm our hypothesis with very high Dice coefficient and Jaccard index (>94% and >89%, respectively) outperforming the scores obtained by other state-of-the-art approaches. Furthermore, in order to detect portray significant morphological features of the segmented tumor, a specific Convolutional Neural Network (CNN) have also been designed for classifying the segmented tumor areas into four types (irregular, lobular, oval and round), which provides an overall accuracy about 72% with the DDSM dataset.
Áreas temáticas: Administração pública e de empresas, ciências contábeis e turismo Arquitetura, urbanismo e design Ciência da computação Ciências ambientais Educação Engenharias iv Geociências Interdisciplinar Linguística e literatura
Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
Direcció de correo del autor: meritxell.arenas@urv.cat santiago.romani@urv.cat domenec.puig@urv.cat
ISSN: 16113349
Identificador del autor: 0000-0003-0815-2570 0000-0001-6673-9615 0000-0002-0562-4205
Fecha de alta del registro: 2023-02-22
Versión del articulo depositado: info:eu-repo/semantics/submittedVersion
Enlace a la fuente original: https://link.springer.com/chapter/10.1007/978-3-030-00934-2_92#citeas
Referencia al articulo segun fuente origial: 14th Conference On Artificial Intelligence In Medicine, Aime 2013. 11071 LNCS 833-840
Referencia de l'ítem segons les normes APA: Singh VK; Romani S; Rashwan HA; Akram F; Pandey N; Sarker MMK; Abdulwahab S; Torrents-Barrena J; Saleh A; Arquez M; Arenas M; Puig D (2018). Conditional generative adversarial and convolutional networks for X-ray breast mass segmentation and shape classification.
URL Documento de licencia: http://repositori.urv.cat/ca/proteccio-de-dades/
DOI del artículo: 10.1007/978-3-030-00934-2_92
Entidad: Universitat Rovira i Virgili
Año de publicación de la revista: 2018
Tipo de publicación: Proceedings Paper