EyeQual: Accurate, explainable, retinal image quality assessment

Authors: Costa, P., Campilho, A., Hooi, B., Smailagic, A., Kitani, K., Liu, S., Faloutsos, C. and Galdran, A.

Journal: Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017

Volume: 2017-December

Pages: 323-330

ISBN: 9781538614174

DOI: 10.1109/ICMLA.2017.0-140

Abstract:

Given a retinal image, can we automatically determine whether it is of high quality (suitable for medical diagnosis)? Can we also explain our decision, pinpointing the region or regions that led to our decision? Images from human retinas are vital for the diagnosis of multiple health issues, like hypertension, diabetes, and Alzheimer's; low quality images may force the patient to come back again for a second scanning, wasting time and possibly delaying treatment. However, existing retinal image quality assessment methods are either black boxes without explanations of the results or depend heavily on feature engineering or on complex and error-prone anatomical structures' segmentation. Therefore, we propose EyeQual, that solves exactly this problem. EyeQual is novel, fast for inference, accurate and explainable, pinpointing low-quality regions on the image. We evaluated EyeQual on two real datasets where it achieved 100% accuracy taking just 36 milliseconds for each image.

Source: Scopus

EyeQual: Accurate, Explainable, Retinal Image Quality Assessment

Authors: Costa, P., Campilho, A., Hooi, B., Smailagic, A., Kitani, K., Liu, S., Faloutsos, C. and Galdran, A.

Journal: 2017 16TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA)

Pages: 323-330

DOI: 10.1109/ICMLA.2017.0-140

Source: Web of Science (Lite)

EyeQual: Accurate, Explainable, Retinal Image Quality Assessment.

Authors: Costa, P., Campilho, A.J.C., Hooi, B., Smailagic, A., Kitani, K., Liu, S., Faloutsos, C. and Galdran, A.

Editors: Chen, X., Luo, B., Luo, F., Palade, V. and Wani, M.A.

Journal: ICMLA

Pages: 323-330

Publisher: IEEE

ISBN: 978-1-5386-1418-1

https://ieeexplore.ieee.org/xpl/conhome/8258911/proceeding

Source: DBLP