TY - JOUR
T1 - FundusQ-Net: a Regression Quality Assessment Deep Learning Algorithm for Fundus Images Quality Grading
T2 - A regression quality assessment deep learning algorithm for fundus images quality grading: FundusQ-Net for DFI quality grading
AU - Abramovich, Or
AU - Pizem, Hadas
AU - Van Eijgen, Jan
AU - Oren, Ilan
AU - Melamed, Joshua
AU - Stalmans, Ingeborg
AU - Blumenthal, Eytan Z.
AU - Behar, Joachim A.
N1 - Publisher Copyright:
© 2023
PY - 2023/9
Y1 - 2023/9
N2 - Objective: Ophthalmological pathologies such as glaucoma, diabetic retinopathy and age-related macular degeneration are major causes of blindness and vision impairment. There is a need for novel decision support tools that can simplify and speed up the diagnosis of these pathologies. A key step in this process is to automatically estimate the quality of the fundus images to make sure these are interpretable by a human operator or a machine learning model. We present a novel fundus image quality scale and deep learning (DL) model that can estimate fundus image quality relative to this new scale. Methods: A total of 1245 images were graded for quality by two ophthalmologists within the range 1–10, with a resolution of 0.5. A DL regression model was trained for fundus image quality assessment. The architecture used was Inception-V3. The model was developed using a total of 89,947 images from 6 databases, of which 1245 were labeled by the specialists and the remaining 88,702 images were used for pre-training and semi-supervised learning. The final DL model was evaluated on an internal test set (n=209) as well as an external test set (n=194). Results: The final DL model, denoted FundusQ-Net, achieved a mean absolute error of 0.61 (0.54–0.68) on the internal test set. When evaluated as a binary classification model on the public DRIMDB database as an external test set the model obtained an accuracy of 99%. Significance: the proposed algorithm provides a new robust tool for automated quality grading of fundus images.
AB - Objective: Ophthalmological pathologies such as glaucoma, diabetic retinopathy and age-related macular degeneration are major causes of blindness and vision impairment. There is a need for novel decision support tools that can simplify and speed up the diagnosis of these pathologies. A key step in this process is to automatically estimate the quality of the fundus images to make sure these are interpretable by a human operator or a machine learning model. We present a novel fundus image quality scale and deep learning (DL) model that can estimate fundus image quality relative to this new scale. Methods: A total of 1245 images were graded for quality by two ophthalmologists within the range 1–10, with a resolution of 0.5. A DL regression model was trained for fundus image quality assessment. The architecture used was Inception-V3. The model was developed using a total of 89,947 images from 6 databases, of which 1245 were labeled by the specialists and the remaining 88,702 images were used for pre-training and semi-supervised learning. The final DL model was evaluated on an internal test set (n=209) as well as an external test set (n=194). Results: The final DL model, denoted FundusQ-Net, achieved a mean absolute error of 0.61 (0.54–0.68) on the internal test set. When evaluated as a binary classification model on the public DRIMDB database as an external test set the model obtained an accuracy of 99%. Significance: the proposed algorithm provides a new robust tool for automated quality grading of fundus images.
KW - Deep learning
KW - Fundus image
KW - Quality assessment
KW - Semi supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85161342782&partnerID=8YFLogxK
U2 - 10.1016/j.cmpb.2023.107522
DO - 10.1016/j.cmpb.2023.107522
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85161342782
SN - 0169-2607
VL - 239
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
M1 - 107522
ER -