Deep image mining for diabetic retinopathy screening

•A ConvNet is trained to detect images with referable diabetic retinopathy (DR).•Training is supervised with image-level annotations only (referable DR or not).•Thanks to a modified training procedure, pathological pixels can also be detected.•This solution outperforms DR screening systems in a publ...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Medical image analysis 2017-07, Vol.39, p.178-193
Hauptverfasser:	Quellec, Gwenolé, Charrière, Katia, Boudi, Yassine, Cochener, Béatrice, Lamard, Mathieu
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Back propagation Biomarkers Boxes Competition Data mining Data Mining - methods Decision analysis Decision making Deep learning Detectors Diabetes Diabetes mellitus Diabetic retinopathy Diabetic Retinopathy - diagnostic imaging Diabetic retinopathy screening Exudates Exudation Eye Eyes & eyesight Hemorrhage Humans Image analysis Image classification Image detection Image Interpretation, Computer-Assisted - methods Image mining Image processing Image segmentation Learning algorithms Lesion detection Lesions Machine Learning Medical diagnosis Medical imaging Medical screening Pathology Pixels Retina - diagnostic imaging Retinopathy Spots
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!