PadChest: A large chest x-ray image dataset with multi-label annotated reports
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/108722
Título: | PadChest: A large chest x-ray image dataset with multi-label annotated reports |
---|---|
Autor/es: | Bustos, Aurelia | Pertusa, Antonio | Salinas, Jose-Maria | Iglesia-Vayá, Maria de la |
Grupo/s de investigación o GITE: | Reconocimiento de Formas e Inteligencia Artificial |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos | Universidad de Alicante. Instituto Universitario de Investigación Informática |
Palabras clave: | X-Ray image dataset | Deep neural networks | Radiographic findings | Differential diagnoses | Anatomical locations |
Área/s de conocimiento: | Lenguajes y Sistemas Informáticos |
Fecha de publicación: | dic-2020 |
Editor: | Elsevier |
Cita bibliográfica: | Medical Image Analysis. 2020, 66: 101797. https://doi.org/10.1016/j.media.2020.101797 |
Resumen: | We present a labeled large-scale, high resolution chest x-ray dataset for the automated exploration of medical images along with their associated reports. This dataset includes more than 160,000 images obtained from 67,000 patients that were interpreted and reported by radiologists at San Juan Hospital (Spain) from 2009 to 2017, covering six different position views and additional information on image acquisition and patient demography. The reports were labeled with 174 different radiographic findings, 19 differential diagnoses and 104 anatomic locations organized as a hierarchical taxonomy and mapped onto standard Unified Medical Language System (UMLS) terminology. Of these reports, 27% were manually annotated by trained physicians and the remaining set was labeled using a supervised method based on a recurrent neural network with attention mechanisms. The labels generated were then validated in an independent test set achieving a 0.93 Micro-F1 score. To the best of our knowledge, this is one of the largest public chest x-ray databases suitable for training supervised models concerning radiographs, and the first to contain radiographic reports in Spanish. The PadChest dataset can be downloaded from http://bimcv.cipf.es/bimcv-projects/padchest/. |
Patrocinador/es: | This work was supported by Medbravo, the Pattern Recognition and Artificial Intelligence Group (GRFIA) and the University Institute for Computing Research (IUII) at the University of Alicante. The Medical Image Bank of the Valencian Community as well as de-identification and anonymization services, were partially funded by the European Union through the Operational Program of the European Fund of Regional Development (FEDER) for the Valencian Community 2014–2020 and the Horizon 2020 Framework Programme under grant agreement 688945 (Euro-BioImaging PrepPhase II). |
URI: | http://hdl.handle.net/10045/108722 |
ISSN: | 1361-8415 (Print) | 1361-8423 (Online) |
DOI: | 10.1016/j.media.2020.101797 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2020 Elsevier B.V. |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.1016/j.media.2020.101797 |
Aparece en las colecciones: | INV - GRFIA - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Bustos_etal_2020_MedicalImageAnal_final.pdf | Versión final (acceso restringido) | 6,85 MB | Adobe PDF | Abrir Solicitar una copia |
Bustos_etal_2020_MedicalImageAnal_preprint.pdf | Preprint (acceso abierto) | 4,15 MB | Adobe PDF | Abrir Vista previa |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.