BreasTomo-Synth: An in silico-generated Digital Breast Tomosynthesis dataset for AI-based tumor segmentation

Cristina Alfaro Vergara; Domingo Mery; Claudia Prieto; Nicolás Araya Caro

doi:10.5281/ZENODO.14270328

BreasTomo-Synth: An in silico-generated Digital Breast Tomosynthesis dataset for AI-based tumor segmentation

Título traducido de la contribución: BreasTomo-Synth: Un conjunto de datos de tomosíntesis mamaria digital generado in silico para la segmentación de tumores basada en IA

Cristina Alfaro Vergara
, Domingo Mery
, Claudia Prieto
, Nicolás Araya Caro

Departamento de Tecnología Médica

Pontificia Universidad Católica de Chile

Producción científica: Otra contribución › revisión exhaustiva

Resumen

BreastTomoSynth es un conjunto de datos de Tomosíntesis Digital de Mama (DBT) generado in silico que contiene regiones de interés (ROI) de tumores espiculados y tejido mamario sano. Los archivos en formato TIFF incluyen imágenes de tumores mamarios generadas in silico y sus respectivas máscaras de segmentación. Cada ROI tiene un tamaño de 109x109 píxeles. El conjunto de datos se creó con VICTRE, un software de Badano et al., aprobado por la FDA [1].

Las futuras versiones del conjunto de datos incluirán las imágenes DBT completas y los archivos con las coordenadas de inserción de cada tumor simulado.

Título traducido de la contribución	BreasTomo-Synth: Un conjunto de datos de tomosíntesis mamaria digital generado in silico para la segmentación de tumores basada en IA
Idioma original	Inglés
Tipo	Conjunto de datos
DOI	https://doi.org/10.5281/ZENODO.14270328
Estado	Publicada - 3 dic. 2024

Palabras clave

Segmentación
Tomosíntesis Digital de Mama

Acceder al documento

10.5281/ZENODO.14270328Licencia: CC BY

Citar esto

@misc{e33310f500074ef68cf714511c292cb1,

title = "BreasTomo-Synth: An in silico-generated Digital Breast Tomosynthesis dataset for AI-based tumor segmentation",

abstract = "BreastTomoSynth is an in silico-generated Digital Breast Tomosynthesis (DBT) dataset containing regions of interest (ROI) of spiculated tumours and healthy breast tissue. The tiff format files include in-silico-generated breast tumor images and their respective segmentation masks. Each ROI is of size 109x109 pixels. The dataset was created with VICTRE, an FDA-cleared software from Badano et al. [1] Future dataset versions will include the complete DBT images and files with the insertion coordinates of each simulated tumor.",

keywords = "Segmentaci{\'o}n, Tomos{\'i}ntesis Digital de Mama, Segmentation, Digital Breast Tomosynthesis",

author = "Vergara, \{Cristina Alfaro\} and Domingo Mery and Claudia Prieto and \{Araya Caro\}, Nicol{\'a}s",

year = "2024",

month = dec,

day = "3",

doi = "10.5281/ZENODO.14270328",

language = "English",

type = "Other",

}

TY - GEN

T1 - BreasTomo-Synth

T2 - An in silico-generated Digital Breast Tomosynthesis dataset for AI-based tumor segmentation

AU - Vergara, Cristina Alfaro

AU - Mery, Domingo

AU - Prieto, Claudia

AU - Araya Caro, Nicolás

PY - 2024/12/3

Y1 - 2024/12/3

N2 - BreastTomoSynth is an in silico-generated Digital Breast Tomosynthesis (DBT) dataset containing regions of interest (ROI) of spiculated tumours and healthy breast tissue. The tiff format files include in-silico-generated breast tumor images and their respective segmentation masks. Each ROI is of size 109x109 pixels. The dataset was created with VICTRE, an FDA-cleared software from Badano et al. [1] Future dataset versions will include the complete DBT images and files with the insertion coordinates of each simulated tumor.

AB - BreastTomoSynth is an in silico-generated Digital Breast Tomosynthesis (DBT) dataset containing regions of interest (ROI) of spiculated tumours and healthy breast tissue. The tiff format files include in-silico-generated breast tumor images and their respective segmentation masks. Each ROI is of size 109x109 pixels. The dataset was created with VICTRE, an FDA-cleared software from Badano et al. [1] Future dataset versions will include the complete DBT images and files with the insertion coordinates of each simulated tumor.

KW - Segmentación

KW - Tomosíntesis Digital de Mama

KW - Segmentation

KW - Digital Breast Tomosynthesis

U2 - 10.5281/ZENODO.14270328

DO - 10.5281/ZENODO.14270328

M3 - Other contribution

ER -

BreasTomo-Synth: An in silico-generated Digital Breast Tomosynthesis dataset for AI-based tumor segmentation

Resumen

Palabras clave

Acceder al documento

Huella

Citar esto