Articles producció científica> Enginyeria Informàtica i Matemàtiques

Conditional generative adversarial and convolutional networks for X-ray breast mass segmentation and shape classification

  • Identification data

    Identifier: imarina:4089619
    Authors:
    Singh, Vivek KumarRomani, SantiagoRashwan, Hatem AAkram, FarhanPandey, NidhiKamal Sarker, Md MostafaAbdulwahab, SaddamTorrents-Barrena, JordinaSaleh, AdelArquez, MiguelArenas, MeritxellPuig, Domenec
    Abstract:
    © 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.
  • Others:

    Author, as appears in the article.: Singh, Vivek Kumar; Romani, Santiago; Rashwan, Hatem A; Akram, Farhan; Pandey, Nidhi; Kamal Sarker, Md Mostafa; Abdulwahab, Saddam; Torrents-Barrena, Jordina; Saleh, Adel; Arquez, Miguel; Arenas, Meritxell; Puig, Domenec
    Department: Ciències Mèdiques Bàsiques Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / Abdulwahab, Saddam Abdulrhman Hamed / AKRAM, FARHAN / Arenas Prat, Meritxell / Puig Valls, Domènec Savi / Romaní Also, Santiago
    Keywords: Mass shape classification Mass segmentation Mammography Cnn Cgan Cancer molecular subtypes
    Abstract: © 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.
    Thematic Areas: Linguística e literatura Interdisciplinar Geociências Engenharias iv Educação Ciências ambientais Ciência da computação Arquitetura, urbanismo e design Administração pública e de empresas, ciências contábeis e turismo
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    ISSN: 16113349
    Author's mail: saddam.abdulwahab@urv.cat hatem.abdellatif@urv.cat saddam.abdulwahab@urv.cat meritxell.arenas@urv.cat santiago.romani@urv.cat domenec.puig@urv.cat
    Author identifier: 0000-0001-5421-1637 0000-0003-0815-2570 0000-0001-6673-9615 0000-0002-0562-4205
    Record's date: 2024-10-12
    Papper version: info:eu-repo/semantics/submittedVersion
    Link to the original source: https://link.springer.com/chapter/10.1007/978-3-030-00934-2_92#citeas
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Automatic Evaluation Of Disclosure Risks Of Text Anonymization Methods. 11071 LNCS 833-840
    APA: Singh, Vivek Kumar; Romani, Santiago; Rashwan, Hatem A; Akram, Farhan; Pandey, Nidhi; Kamal Sarker, Md Mostafa; Abdulwahab, Saddam; Torrents-Barrena, (2018). Conditional generative adversarial and convolutional networks for X-ray breast mass segmentation and shape classification. Heidelberg: Springer Berlin Heidelberg
    Article's DOI: 10.1007/978-3-030-00934-2_92
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2018
    Publication Type: Proceedings Paper
  • Keywords:

    Mass shape classification
    Mass segmentation
    Mammography
    Cnn
    Cgan
    Cancer molecular subtypes
    Linguística e literatura
    Interdisciplinar
    Geociências
    Engenharias iv
    Educação
    Ciências ambientais
    Ciência da computação
    Arquitetura, urbanismo e design
    Administração pública e de empresas, ciências contábeis e turismo
  • Documents:

  • Cerca a google

    Search to google scholar