Machine learning can reliably predict malignancy of breast lesions based on clinical and ultrasonographic features.

Journal: Breast cancer research and treatment
Published Date: Jul 13, 2024

Abstract

PURPOSE: To establish a reliable machine learning model to predict malignancy in breast lesions identified by ultrasound (US) and optimize the negative predictive value to minimize unnecessary biopsies.

Authors

  • I P C Buzatto
    Department of Obstetrics and Gynecology - Breast Disease Division, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, Brazil.
  • S A Recife
    Department of Gynecology & Obstetrics, Women's Health Reference Center of Ribeirão Preto (MATER), Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, Brazil.
  • L Miguel
    Department of Gynecology & Obstetrics, Women's Health Reference Center of Ribeirão Preto (MATER), Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, Brazil.
  • R M Bonini
    Department of Radiology, Hospital de Amor de Campo Grande, Campo Grande, Mato Grosso Do Sul, Brazil.
  • N Onari
    Department of Radiology, Hospital de Amor de Barretos, Barretos, Brazil.
  • A L P A Faim
    Department of Radiology, Hospital de Amor de Barretos, Barretos, Brazil.
  • L Silvestre
    Department of Obstetrics and Gynecology - Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, Brazil.
  • D P Carlotti
    Institute of Mathematics and Statistics, University of São Paulo, São Paulo, Brazil.
  • A Fröhlich
    Department of Mathematics, Federal University of Santa Catarina, Florianópolis, Brazil.
  • D G Tiezzi
    Department of Obstetrics and Gynecology - Breast Disease Division and Laboratory for Translational Data Science, Ribeirão Preto Medical School, University of São Paulo, Avenida Bandeirantes 3.900, Monte Alegre, Ribeirão Preto, Ribeirão Preto, Brazil. dtiezzi@usp.br.

Keywords

External Resources

Popular Topics
Recent Journals