Analysis of Potential Biases on Mammography Datasets for Deep Learning Model Development

Autores: Blanca Zufiria Gerbolés Karen López-Linares Román María Jesús García González Kristin May Rebescher Iván Lalaguna Esther Albertín Marcía B. Cimadevila Javier García María J. Ledesma Iván Macía Oliver

Fecha: 18.09.2022


Abstract

The development of democratized, generalizable deep learning applications for health care systems is challenging as potential biases could easily emerge. This paper provides an overview of the potential biases that appear in image analysis datasets that affect the development and performance of artificial intelligence algorithms. Especially, an exhaustive analysis of mammography data has been carried out at the patient, image and source of origin levels. Furthermore, we summarize some techniques to alleviate these biases for the development of fair deep learning models. We present a learning task to classify negative and positive screening mammographies and analyze the influence of biases in the performance of the algorithm.

BIB_text

@Article {
title = {Analysis of Potential Biases on Mammography Datasets for Deep Learning Model Development},
pages = {59-67},
keywds = {
bias, deep learning, mammography, breast cancer
}
abstract = {

The development of democratized, generalizable deep learning applications for health care systems is challenging as potential biases could easily emerge. This paper provides an overview of the potential biases that appear in image analysis datasets that affect the development and performance of artificial intelligence algorithms. Especially, an exhaustive analysis of mammography data has been carried out at the patient, image and source of origin levels. Furthermore, we summarize some techniques to alleviate these biases for the development of fair deep learning models. We present a learning task to classify negative and positive screening mammographies and analyze the influence of biases in the performance of the algorithm.


}
isbn = {978-303117720-0},
date = {2022-09-18},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (España)

+(34) 943 309 230

Zorrotzaurreko Erribera 2, Deusto,
48014 Bilbao (España)

close overlay

Las cookies de publicidad comportamental son necesarias para cargar el contenido

Aceptar cookies de publicidad comportamental