Articles producció científica> Enginyeria Informàtica i Matemàtiques

Transformer-Based Radiomics for Predicting Breast Tumor Malignancy Score in Ultrasonography

  • Dades identificatives

    Identificador: imarina:9385562
    Handle: https://hdl.handle.net/20.500.11797/imarina9385562
    Autors:
    Hassanien, Mohamed ASingh, Vivek KumarPuig, DomenecAbdel-Nasser, Mohamed
    Resum:
    Breast cancer must be detected early to reduce the mortality rate. Ultrasound images can make it easier for the clinician to diagnose cases of dense breasts. This study presents a deep vision transformer-based approach for predicting breast cancer malignancy scores from ultrasound images. In particular, various state-of-the-art deep vision transformers such as BEiT, CaiT, Swin, XCiT, and VisFormer are adapted and trained to extract robust radiomics to classify breast tumors in ultrasound images as benign or malignant. The best-performing model is used to predict the malignancy score of each input ultrasound image. Experimental results revealed that the proposed approach achieves promising results for the detection of malignant tumors of the breast on ultrasound images.

  • Altres:

    Autor segons l'article: Hassanien, Mohamed A; Singh, Vivek Kumar; Puig, Domenec; Abdel-Nasser, Mohamed
    Departament: Enginyeria Informàtica i Matemàtiques
    Autor/s de la URV: Abdelnasser Mohamed Mahmoud, Mohamed / Puig Valls, Domènec Savi
    Paraules clau: Breast cancer Cad systems Radiomics Ultrasound imaging Vision transformer Vision transformers
    Resum: Breast cancer must be detected early to reduce the mortality rate. Ultrasound images can make it easier for the clinician to diagnose cases of dense breasts. This study presents a deep vision transformer-based approach for predicting breast cancer malignancy scores from ultrasound images. In particular, various state-of-the-art deep vision transformers such as BEiT, CaiT, Swin, XCiT, and VisFormer are adapted and trained to extract robust radiomics to classify breast tumors in ultrasound images as benign or malignant. The best-performing model is used to predict the malignancy score of each input ultrasound image. Experimental results revealed that the proposed approach achieves promising results for the detection of malignant tumors of the breast on ultrasound images.
    Àrees temàtiques: Artificial intelligence Ciências agrárias i Comunicació i informació Engenharias iii Engenharias iv General o multidisciplinar Información y documentación Interdisciplinar Medicina ii
    Accès a la llicència d'ús: https://creativecommons.org/licenses/by/3.0/es/
    Adreça de correu electrònic de l'autor: domenec.puig@urv.cat mohamed.abdelnasser@urv.cat
    Identificador de l'autor: 0000-0002-0562-4205 0000-0002-1074-2441
    Data d'alta del registre: 2024-10-12
    Versió de l'article dipositat: info:eu-repo/semantics/publishedVersion
    Enllaç font original: https://ebooks.iospress.nl/doi/10.3233/FAIA220351
    Referència a l'article segons font original: Frontiers In Artificial Intelligence And Applications. 356 298-307
    Referència de l'ítem segons les normes APA: Hassanien, Mohamed A; Singh, Vivek Kumar; Puig, Domenec; Abdel-Nasser, Mohamed (2022). Transformer-Based Radiomics for Predicting Breast Tumor Malignancy Score in Ultrasonography. Amsterdam: IOS Press
    URL Document de llicència: https://repositori.urv.cat/ca/proteccio-de-dades/
    DOI de l'article: 10.3233/FAIA220351
    Entitat: Universitat Rovira i Virgili
    Any de publicació de la revista: 2022
    Tipus de publicació: Proceedings Paper

  • Paraules clau:

    Artificial Intelligence
    Breast cancer
    Cad systems
    Radiomics
    Ultrasound imaging
    Vision transformer
    Vision transformers
    Artificial intelligence
    Ciências agrárias i
    Comunicació i informació
    Engenharias iii
    Engenharias iv
    General o multidisciplinar
    Información y documentación
    Interdisciplinar
    Medicina ii

  • Documents:

    DocumentPrincipal

  • Cerca a google

    Search to google scholar