Dataset Information

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

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.

SUBMITTER: Bar-David D

PROVIDER: S-EPMC10561735 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Bar-David Daniel D Bar-David Laura L Shapira Yinon Y Leibu Rina R Dori Dalia D Gebara Aseel A Schneor Ronit R Fischer Anath A Soudry Shiri S

IEEE journal of translational engineering in health and medicine 20230724

- 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).<h4>Methods</h4>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 a ...[more]

PMID: 37817823

Similar Datasets

Project description:ObjectiveTo evaluate agreement between fluorescein angiography (FA) and optical coherence tomography (OCT) results for diagnosis of macular edema in patients with uveitis.DesignMulticenter cross-sectional study.ParticipantsFour hundred seventy-nine eyes with uveitis from 255 patients.MethodsThe macular status of dilated eyes with intermediate uveitis, posterior uveitis, or panuveitis was assessed via Stratus-3 OCT and FA. To evaluate agreement between the diagnostic approaches, ? statistics were used.Main outcome measuresMacular thickening (MT; center point thickness, ? 240 ?m per reading center grading of OCT images) and macular leakage (ML; central subfield fluorescein leakage, ? 0.44 disc areas per reading center grading of FA images), and agreement between these outcomes in diagnosing macular edema.ResultsOptical coherence tomography (90.4%) more frequently returned usable information regarding macular edema than FA (77%) or biomicroscopy (76%). Agreement in diagnosis of MT and ML (? = 0.44) was moderate. Macular leakage was present in 40% of cases free of MT, whereas MT was present in 34% of cases without ML. Biomicroscopic evaluation for macular edema failed to detect 40% and 45% of cases of MT and ML, respectively, and diagnosed 17% and 17% of cases with macular edema that did not have MT or ML, respectively; these results may underestimate biomicroscopic errors (ophthalmologists were not explicitly masked to OCT and FA results). Among eyes free of ML, phakic eyes without cataract rarely (4%) had MT. No factors were found that effectively ruled out ML when MT was absent.ConclusionsOptical coherence tomography and FA offered only moderate agreement regarding macular edema status in uveitis cases, probably because what they measure (MT and ML) are related but nonidentical macular pathologic characteristics. Given its lower cost, greater safety, and greater likelihood of obtaining usable information, OCT may be the best initial test for evaluation of suspected macular edema. However, given that ML cannot be ruled out if MT is absent and vice versa, obtaining the second test after negative results on the first seems justified when detection of ML or MT would alter management. Given that biomicroscopic evaluation for macular edema erred frequently, ancillary testing for macular edema seems indicated when knowledge of ML or MT status would affect management.Financial disclosure(s)Proprietary or commercial disclosure may be found after the references.

Project description:Given the capacity of Optical Coherence Tomography (OCT) imaging to display structural changes in a wide variety of eye diseases and neurological disorders, the need for OCT image segmentation and the corresponding data interpretation is latterly felt more than ever before. In this paper, we wish to address this need by designing a semi-automatic software program for applying reliable segmentation of 8 different macular layers as well as outlining retinal pathologies such as diabetic macular edema. The software accommodates a novel graph-based semi-automatic method, called "Livelayer" which is designed for straightforward segmentation of retinal layers and fluids. This method is chiefly based on Dijkstra's Shortest Path First (SPF) algorithm and the Live-wire function together with some preprocessing operations on the to-be-segmented images. The software is indeed suitable for obtaining detailed segmentation of layers, exact localization of clear or unclear fluid objects and the ground truth, demanding far less endeavor in comparison to a common manual segmentation method. It is also valuable as a tool for calculating the irregularity index in deformed OCT images. The amount of time (seconds) that Livelayer required for segmentation of Inner Limiting Membrane, Inner Plexiform Layer-Inner Nuclear Layer, Outer Plexiform Layer-Outer Nuclear Layer was much less than that for the manual segmentation, 5 s for the ILM (minimum) and 15.57 s for the OPL-ONL (maximum). The unsigned errors (pixels) between the semi-automatically labeled and gold standard data was on average 2.7, 1.9, 2.1 for ILM, IPL-INL, OPL-ONL, respectively. The Bland-Altman plots indicated perfect concordance between the Livelayer and the manual algorithm and that they could be used interchangeably. The repeatability error was around one pixel for the OPL-ONL and < 1 for the other two. The unsigned errors between the Livelayer and the manual algorithm was 1.33 for ILM and 1.53 for Nerve Fiber Layer-Ganglion Cell Layer in peripapillary B-Scans. The Dice scores for comparing the two algorithms and for obtaining the repeatability on segmentation of fluid objects were at acceptable levels.

Dataset Information

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

Methods

Results

Conclusions

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets