Elastic Deformation of Optical Coherence Tomography Images of Diabetic Macular Edema for Deep-Learning Models Training: How Far to Go?

Daniel Bar-David; Laura Bar-David; Yinon Shapira; Rina Leibu; Dalia Dori; Aseel Gebara; Ronit Schneor; Anath Fischer; Shiri Soudry

doi:10.1109/JTEHM.2023.3294904

Elastic Deformation of Optical Coherence Tomography Images of Diabetic Macular Edema for Deep-Learning Models Training: How Far to Go?

IEEE J Transl Eng Health Med. 2023 Jul 24:11:487-494. doi: 10.1109/JTEHM.2023.3294904. eCollection 2023.

Authors

Affiliations

¹ Faculty of Mechanical EngineeringTechnion Israel Institute of Technology Haifa 3200003 Israel.
² Department of OphthalmologyRambam Health Care Campus Haifa 3109601 Israel.
³ Department of OphthalmologyCarmel Medical Center Haifa 3436212 Israel.
⁴ Clinical Research Institute at RambamRambam Health Care Campus Haifa 3109601 Israel.
⁵ The Ruth and Bruce Rappaport Faculty of MedicineTechnion Israel Institute of Technology Haifa 3525433 Israel.

Abstract

- Objective: To explore the clinical validity of elastic deformation of optical coherence tomography (OCT) images for data augmentation in the development of deep-learning model for detection of diabetic macular edema (DME).

Methods: Prospective evaluation of OCT images of DME (n = 320) subject to elastic transformation, with the deformation intensity represented by ([Formula: see text]). Three sets of images, each comprising 100 pairs of scans (100 original & 100 modified), were grouped according to the range of ([Formula: see text]), including low-, medium- and high-degree of augmentation; ([Formula: see text] = 1-6), ([Formula: see text] = 7-12), and ([Formula: see text] = 13-18), respectively. Three retina specialists evaluated all datasets in a blinded manner and designated each image as 'original' versus 'modified'. The rate of assignment of 'original' value to modified images (false-negative) was determined for each grader in each dataset.

Results: The false-negative rates ranged between 71-77% for the low-, 63-76% for the medium-, and 50-75% for the high-augmentation categories. The corresponding rates of correct identification of original images ranged between 75-85% ([Formula: see text]0.05) in the low-, 73-85% ([Formula: see text]0.05 for graders 1 & 2, p = 0.01 for grader 3) in the medium-, and 81-91% ([Formula: see text]) in the high-augmentation categories. In the subcategory ([Formula: see text] = 7-9) the false-negative rates were 93-83%, whereas the rates of correctly identifying original images ranged between 89-99% ([Formula: see text]0.05 for all graders).

Conclusions: Deformation of low-medium intensity ([Formula: see text] = 1-9) may be applied without compromising OCT image representativeness in DME. Clinical and Translational Impact Statement-Elastic deformation may efficiently augment the size, robustness, and diversity of training datasets without altering their clinical value, enhancing the development of high-accuracy algorithms for automated interpretation of OCT images.

Keywords: DME; Data augmentation; OCT; deep learning; elastic deformation.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Deep Learning*
Diabetes Mellitus*
Diabetic Retinopathy* / diagnosis
Humans
Macular Edema* / diagnostic imaging
Retina
Tomography, Optical Coherence / methods

Grants and funding

This work was supported by the Israeli Ministry of Health, Kopel, under Grant 2028211.