Automatic breast density classification using a convolutional neural network architecture search procedure

Pablo Fonseca; Julio Mendoza; Jacques Wainer; Jose Ferrer; Joseph Pinto; Jorge Guerrero; Benjamin Castaneda

doi:10.1117/12.2081576

Automatic breast density classification using a convolutional neural network architecture search procedure

Pablo Fonseca, Julio Mendoza, Jacques Wainer, Jose Ferrer, Joseph Pinto, Jorge Guerrero, Benjamin Castaneda

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

54 Citas (Scopus)

Resumen

Breast parenchymal density is considered a strong indicator of breast cancer risk and therefore useful for preventive tasks. Measurement of breast density is often qualitative and requires the subjective judgment of radiologists. Here we explore an automatic breast composition classification workflow based on convolutional neural networks for feature extraction in combination with a support vector machines classifier. This is compared to the assessments of seven experienced radiologists. The experiments yielded an average kappa value of 0.58 when using the mode of the radiologists' classifications as ground truth. Individual radiologist performance against this ground truth yielded kappa values between 0.56 and 0.79.

Idioma original	Inglés
Título de la publicación alojada	Medical Imaging 2015
Subtítulo de la publicación alojada	Computer-Aided Diagnosis
Editores	Lubomir M. Hadjiiski, Lubomir M. Hadjiiski, Georgia D. Tourassi, Georgia D. Tourassi
Editorial	SPIE
ISBN (versión digital)	9781628415049, 9781628415049
DOI	https://doi.org/10.1117/12.2081576
Estado	Publicada - 2015
Evento	SPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis - Orlando, Estados Unidos Duración: 22 feb. 2015 → 25 feb. 2015

Serie de la publicación

Nombre	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volumen	9414
ISSN (versión impresa)	1605-7422

Conferencia

Conferencia	SPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis
País/Territorio	Estados Unidos
Ciudad	Orlando
Período	22/02/15 → 25/02/15

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

Acceder al documento

10.1117/12.2081576

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Fonseca, P., Mendoza, J., Wainer, J., Ferrer, J., Pinto, J., Guerrero, J., & Castaneda, B. (2015). Automatic breast density classification using a convolutional neural network architecture search procedure. En L. M. Hadjiiski, L. M. Hadjiiski, G. D. Tourassi, & G. D. Tourassi (Eds.), Medical Imaging 2015: Computer-Aided Diagnosis Artículo 941428 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9414). SPIE. https://doi.org/10.1117/12.2081576

Fonseca, Pablo ; Mendoza, Julio ; Wainer, Jacques et al. / Automatic breast density classification using a convolutional neural network architecture search procedure. Medical Imaging 2015: Computer-Aided Diagnosis. editor / Lubomir M. Hadjiiski ; Lubomir M. Hadjiiski ; Georgia D. Tourassi ; Georgia D. Tourassi. SPIE, 2015. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).

@inproceedings{c0ae52ec26774bc1ba55af0b893e710f,

title = "Automatic breast density classification using a convolutional neural network architecture search procedure",

abstract = "Breast parenchymal density is considered a strong indicator of breast cancer risk and therefore useful for preventive tasks. Measurement of breast density is often qualitative and requires the subjective judgment of radiologists. Here we explore an automatic breast composition classification workflow based on convolutional neural networks for feature extraction in combination with a support vector machines classifier. This is compared to the assessments of seven experienced radiologists. The experiments yielded an average kappa value of 0.58 when using the mode of the radiologists' classifications as ground truth. Individual radiologist performance against this ground truth yielded kappa values between 0.56 and 0.79.",

keywords = "Mammograms, automatic assessment, breast density, convolutional neural networks, feature learning",

author = "Pablo Fonseca and Julio Mendoza and Jacques Wainer and Jose Ferrer and Joseph Pinto and Jorge Guerrero and Benjamin Castaneda",

note = "Publisher Copyright: {\textcopyright} 2015 SPIE.; SPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis ; Conference date: 22-02-2015 Through 25-02-2015",

year = "2015",

doi = "10.1117/12.2081576",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Hadjiiski, {Lubomir M.} and Hadjiiski, {Lubomir M.} and Tourassi, {Georgia D.} and Tourassi, {Georgia D.}",

booktitle = "Medical Imaging 2015",

}

Fonseca, P, Mendoza, J, Wainer, J, Ferrer, J, Pinto, J, Guerrero, J & Castaneda, B 2015, Automatic breast density classification using a convolutional neural network architecture search procedure. En LM Hadjiiski, LM Hadjiiski, GD Tourassi & GD Tourassi (eds.), Medical Imaging 2015: Computer-Aided Diagnosis., 941428, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9414, SPIE, SPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis, Orlando, Estados Unidos, 22/02/15. https://doi.org/10.1117/12.2081576

Automatic breast density classification using a convolutional neural network architecture search procedure. / Fonseca, Pablo; Mendoza, Julio; Wainer, Jacques et al.
Medical Imaging 2015: Computer-Aided Diagnosis. ed. / Lubomir M. Hadjiiski; Lubomir M. Hadjiiski; Georgia D. Tourassi; Georgia D. Tourassi. SPIE, 2015. 941428 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9414).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Automatic breast density classification using a convolutional neural network architecture search procedure

AU - Fonseca, Pablo

AU - Mendoza, Julio

AU - Wainer, Jacques

AU - Ferrer, Jose

AU - Pinto, Joseph

AU - Guerrero, Jorge

AU - Castaneda, Benjamin

PY - 2015

Y1 - 2015

N2 - Breast parenchymal density is considered a strong indicator of breast cancer risk and therefore useful for preventive tasks. Measurement of breast density is often qualitative and requires the subjective judgment of radiologists. Here we explore an automatic breast composition classification workflow based on convolutional neural networks for feature extraction in combination with a support vector machines classifier. This is compared to the assessments of seven experienced radiologists. The experiments yielded an average kappa value of 0.58 when using the mode of the radiologists' classifications as ground truth. Individual radiologist performance against this ground truth yielded kappa values between 0.56 and 0.79.

AB - Breast parenchymal density is considered a strong indicator of breast cancer risk and therefore useful for preventive tasks. Measurement of breast density is often qualitative and requires the subjective judgment of radiologists. Here we explore an automatic breast composition classification workflow based on convolutional neural networks for feature extraction in combination with a support vector machines classifier. This is compared to the assessments of seven experienced radiologists. The experiments yielded an average kappa value of 0.58 when using the mode of the radiologists' classifications as ground truth. Individual radiologist performance against this ground truth yielded kappa values between 0.56 and 0.79.

KW - Mammograms

KW - automatic assessment

KW - breast density

KW - convolutional neural networks

KW - feature learning

UR - http://www.scopus.com/inward/record.url?scp=84948844104&partnerID=8YFLogxK

U2 - 10.1117/12.2081576

DO - 10.1117/12.2081576

M3 - Conference contribution

AN - SCOPUS:84948844104

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2015

A2 - Hadjiiski, Lubomir M.

A2 - Tourassi, Georgia D.

PB - SPIE

T2 - SPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis

Y2 - 22 February 2015 through 25 February 2015

ER -

Fonseca P, Mendoza J, Wainer J, Ferrer J, Pinto J, Guerrero J et al. Automatic breast density classification using a convolutional neural network architecture search procedure. En Hadjiiski LM, Hadjiiski LM, Tourassi GD, Tourassi GD, editores, Medical Imaging 2015: Computer-Aided Diagnosis. SPIE. 2015. 941428. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2081576

Automatic breast density classification using a convolutional neural network architecture search procedure

Resumen

Serie de la publicación

Conferencia

ODS de las Naciones Unidas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto