Journal article
A multiple-instance learning framework for diabetic retinopathy screening
Medical Image Analysis, Vol.16(6), pp.1228-1240
08/2012
DOI: 10.1016/j.media.2012.06.003
PMID: 22850462
Abstract
[Display omitted] ► Lesion detection is supervised without manual segmentation. ► Large image datasets can be used for training. ► A large diabetic retinopathy screening dataset (>100,000 images) is presented. ► All eight types of diabetic retinopathy lesions are detected. ► Diabetic retinopathy is detected with high sensitivity/specificity. A novel multiple-instance learning framework, for automated image classification, is presented in this paper. Given reference images marked by clinicians as relevant or irrelevant, the image classifier is trained to detect patterns, of arbitrary size, that only appear in relevant images. After training, similar patterns are sought in new images in order to classify them as either relevant or irrelevant images. Therefore, no manual segmentations are required. As a consequence, large image datasets are available for training. The proposed framework was applied to diabetic retinopathy screening in 2-D retinal image datasets: Messidor (1200 images) and e-ophtha, a dataset of 25,702 examination records from the Ophdiat screening network (107,799 images). In this application, an image (or an examination record) is relevant if the patient should be referred to an ophthalmologist. Trained on one half of Messidor, the classifier achieved high performance on the other half of Messidor (Az=0.881) and on e-ophtha (Az=0.761). We observed, in a subset of 273 manually segmented images from e-ophtha, that all eight types of diabetic retinopathy lesions are detected.
Details
- Title: Subtitle
- A multiple-instance learning framework for diabetic retinopathy screening
- Creators
- Gwénolé Quellec - Inserm, UMR 1101, SFR ScInBioS, Brest F-29200, FranceMathieu Lamard - Inserm, UMR 1101, SFR ScInBioS, Brest F-29200, FranceMichael D Abràmoff - Departments of Ophthalmology and Visual Sciences, Electrical and Computer Engineering, and Biomedical Engineering, University of Iowa, Iowa City, IA 52242, USAEtienne Decencière - Centre for Mathematical Morphology, MINES ParisTech, ARMINES, Fontainebleau F-77300, FranceBruno Lay - ADCIS, Saint-Contest F-14280, FranceAli Erginay - Service d’Ophtalmologie, Hôpital Lariboisière, APHP, Paris F-75475, FranceBéatrice Cochener - Inserm, UMR 1101, SFR ScInBioS, Brest F-29200, FranceGuy Cazuguel - Inserm, UMR 1101, SFR ScInBioS, Brest F-29200, France
- Resource Type
- Journal article
- Publication Details
- Medical Image Analysis, Vol.16(6), pp.1228-1240
- DOI
- 10.1016/j.media.2012.06.003
- PMID
- 22850462
- NLM abbreviation
- Med Image Anal
- ISSN
- 1361-8415
- eISSN
- 1361-8423
- Publisher
- Elsevier B.V
- Language
- English
- Date published
- 08/2012
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Ophthalmology and Visual Sciences
- Record Identifier
- 9983806246202771
Metrics
30 Record Views