Detection of oedema on optical coherence tomography images using deep learning model trained on noisy clinical data
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Detection of oedema on optical coherence tomography images using deep learning model trained on noisy clinical data. / Potapenko, Ivan; Kristensen, Mads; Thiesson, Bo; Ilginis, Tomas; Lykke Sørensen, Torben; Nouri Hajari, Javad; Fuchs, Josefine; Hamann, Steffen; la Cour, Morten.
In: Acta Ophthalmologica, Vol. 100, No. 1, 2022, p. 103-110.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Detection of oedema on optical coherence tomography images using deep learning model trained on noisy clinical data
AU - Potapenko, Ivan
AU - Kristensen, Mads
AU - Thiesson, Bo
AU - Ilginis, Tomas
AU - Lykke Sørensen, Torben
AU - Nouri Hajari, Javad
AU - Fuchs, Josefine
AU - Hamann, Steffen
AU - la Cour, Morten
N1 - © 2021 Acta Ophthalmologica Scandinavica Foundation. Published by John Wiley & Sons Ltd.
PY - 2022
Y1 - 2022
N2 - PURPOSE: To meet the demands imposed by the continuing growth of the Age-related macular degeneration (AMD) patient population, automation of follow-ups by detecting retinal oedema using deep learning might be a viable approach. However, preparing and labelling data for training is time consuming. In this study, we investigate the feasibility of training a convolutional neural network (CNN) to accurately detect retinal oedema on optical coherence tomography (OCT) images of AMD patients with labels derived directly from clinical treatment decisions, without extensive preprocessing or relabelling.METHODS: A total of 50 439 OCT images with associated treatment information were retrieved from databases at the Department of Ophthalmology, Rigshospitalet, Copenhagen, Denmark between 01.06.2007 and 01.06.2018. A CNN was trained on the retrieved data with the recorded treatment decisions as labels and validated on a subset of the data relabelled by three ophthalmologists to denote presence of oedema.RESULTS: Moderate inter-grader agreement on presence of oedema in the relabelled data was found (76.4%). Despite different training and validation labels, the CNN performed on par with inter-grader agreement in detecting oedema on OCT images (AUC 0.97, accuracy 90.9%) and previously published models based on relabelled datasets.CONCLUSION: The level of performance shown by the current model might make it valuable in detecting disease activity in automated AMD patient follow-up systems. Our approach demonstrates that high accuracy is not necessarily constrained by incongruent training and validation labels. These results might encourage the use of existing clinical databases for development of deep learning based algorithms without labour-intensive preprocessing in the future.
AB - PURPOSE: To meet the demands imposed by the continuing growth of the Age-related macular degeneration (AMD) patient population, automation of follow-ups by detecting retinal oedema using deep learning might be a viable approach. However, preparing and labelling data for training is time consuming. In this study, we investigate the feasibility of training a convolutional neural network (CNN) to accurately detect retinal oedema on optical coherence tomography (OCT) images of AMD patients with labels derived directly from clinical treatment decisions, without extensive preprocessing or relabelling.METHODS: A total of 50 439 OCT images with associated treatment information were retrieved from databases at the Department of Ophthalmology, Rigshospitalet, Copenhagen, Denmark between 01.06.2007 and 01.06.2018. A CNN was trained on the retrieved data with the recorded treatment decisions as labels and validated on a subset of the data relabelled by three ophthalmologists to denote presence of oedema.RESULTS: Moderate inter-grader agreement on presence of oedema in the relabelled data was found (76.4%). Despite different training and validation labels, the CNN performed on par with inter-grader agreement in detecting oedema on OCT images (AUC 0.97, accuracy 90.9%) and previously published models based on relabelled datasets.CONCLUSION: The level of performance shown by the current model might make it valuable in detecting disease activity in automated AMD patient follow-up systems. Our approach demonstrates that high accuracy is not necessarily constrained by incongruent training and validation labels. These results might encourage the use of existing clinical databases for development of deep learning based algorithms without labour-intensive preprocessing in the future.
KW - Algorithms
KW - Deep Learning
KW - Education, Medical, Graduate/methods
KW - Female
KW - Follow-Up Studies
KW - Humans
KW - Macula Lutea/diagnostic imaging
KW - Macular Degeneration/complications
KW - Macular Edema/diagnosis
KW - Male
KW - Middle Aged
KW - Ophthalmologists/education
KW - ROC Curve
KW - Retrospective Studies
KW - Tomography, Optical Coherence/methods
U2 - 10.1111/aos.14895
DO - 10.1111/aos.14895
M3 - Journal article
C2 - 33991170
VL - 100
SP - 103
EP - 110
JO - Acta Ophthalmologica
JF - Acta Ophthalmologica
SN - 1755-375X
IS - 1
ER -
ID: 298764622