Benchmarking automated detection of the retinal external limiting membrane in 3D spectral domain optical coherence tomography image dataset of full thickness macular holes

Purpose. To study the features of regenerative processes occurring in the microstructures of the foveolar region after successful surgery of the primary full-thickness macular holes (FTMH) by the method of «temporal inverted ILM flap». Material and methods. Using spectral optical coherence tomography (SOCT), the features of regenerative processes in the microstructures of the foveolar region were studied in 31 patients (32 eyes) with stage II-IV FTMH according to J. Gass (1995), who were successfully operated on for this reason. Results. Regenerative processes of gradual restoration of microstructures of the foveolar region began from the first days after surgery and continued for 1 year. As a result, the U-shaped foveolar contour was restored, the central retinal thickness changed (from 399±61.4 to 195±61 microns, p<0.05); the external limiting membrane (ELM) and the ellipsoid zone (EZ) were completely restored in 27/32 (84.4%) and 23/32 (71.8%) eyes, respectively. Conclusion. Regenerative processes in the microstructures of the foveolar zone are of a step-by-step nature and are traced for one year after the surgery of the primary FTMH by the method of «temporal inverted ILM flap». The essence of the processes: overlapping FTMH with flaps of ILM, filling its lumen with a «glial plug», restoring the ELM, EZ and interdigitative zones. Key words: foveal microstructure, primary full-thickness macular holes, temporal inverted ILM flap, optical coherence tomography.

Download Full-text

Differences in the presentation of stage 1 macular holes illustration by optical coherence tomography

European Journal of Ophthalmology ◽

10.1177/1120672120904661 ◽

2020 ◽

pp. 112067212090466

Author(s):

Zaïnab Bentaleb Machkour ◽

Justus G Garweg ◽

Francesco Bandello ◽

Philippe Denis ◽

Laurent Kodjikian

Keyword(s):

Optical Coherence Tomography ◽

Spectral Domain ◽

Optical Coherence ◽

Full Thickness ◽

Vitreoretinal Interface ◽

Inner Limiting Membrane ◽

Macular Holes ◽

Tangential Traction ◽

Stage 1

Objective: To present two different phases of progression of Gass stage 1 foveolar detachment to lamellar or full-thickness macular holes revealed with spectral domain optical coherence tomography. Design: This is an observational study. Participants: The medical records of four patients (four eyes) with foveolar detachment that had evolved into stage 1 macular holes were compared. The patients manifested neither co-existing myopia nor any other ocular pathology. Methods: At each consultation, best-corrected visual acuity, dilated fundus examination, and spectral domain optical coherence tomography were performed to ascertain whether the foveolar detachment was associated with posterior vitreal detachment. Results: In two of the eyes, and at an early phase of the disease, an incomplete posterior vitreal detachment and vitreal adhesion at the head of the optic nerve were observed. In the other two cases, the traction was not antero-posterior but tangential and had been effected by thickening of the inner limiting membrane or by the presence of a discrete epiretinal membrane in the papillomacular area; the posterior vitreal detachment was complete. In the former two cases and in one of the latter, the foveolar detachments had progressed to full-thickness macular holes. The visual acuities were better in the latter than in the former two eyes. Conclusion: Two different pathological mechanisms appear to underlie the formation of macular holes: The optical coherence tomography–guided classification of Gass stage 1 macular hole as an antero-posterior traction with a triangular foveolar detachment has to be distinguished from a tangential traction and a complete posterior vitreal detachment. Tangential traction is typically associated with a more dome-shaped or irregular foveolar detachment and a hyper-reflective band at the vitreoretinal interface.

Download Full-text

Influence of Pseudophakic Lens Capsule Opacification on Spectral Domain and Time Domain Optical Coherence Tomography Image Quality

Current Eye Research ◽

10.3109/02713683.2014.941069 ◽

2014 ◽

Vol 40 (6) ◽

pp. 579-584 ◽

Cited By ~ 2

Author(s):

Carlo Cagini ◽

Francesca Pietrolucci ◽

Marco Lupidi ◽

Marco Messina ◽

Francesco Piccinelli ◽

...

Keyword(s):

Optical Coherence Tomography ◽

Image Quality ◽

Time Domain ◽

Lens Capsule ◽

Spectral Domain ◽

Optical Coherence Tomography Image ◽

Optical Coherence ◽

Tomography Image

Download Full-text

Effect of Spectral Domain Optical Coherence Tomography Image Quality on Macular Thickness Measurements and Error Rate

Current Eye Research ◽

10.1080/02713683.2016.1179332 ◽

2016 ◽

Vol 42 (2) ◽

pp. 282-286 ◽

Cited By ~ 3

Author(s):

Khalil Ghasemi Falavarjani ◽

Amirabbas Mehrpuya ◽

Foad Amirkourjani

Keyword(s):

Optical Coherence Tomography ◽

Image Quality ◽

Error Rate ◽

Macular Thickness ◽

Spectral Domain ◽

Optical Coherence Tomography Image ◽

Optical Coherence ◽

Tomography Image ◽

Thickness Measurements

Download Full-text

A Regularization Method for Deconvolution of Optical Coherence Tomography Image

2020 39th Chinese Control Conference (CCC) ◽

10.23919/ccc50068.2020.9188754 ◽

2020 ◽

Author(s):

Yina Du ◽

Shangjie Ren ◽

Jingjiang Xu ◽

Feng Dong

Keyword(s):

Optical Coherence Tomography ◽

Regularization Method ◽

Optical Coherence Tomography Image ◽

Optical Coherence ◽

Tomography Image

Download Full-text

Unraveling the deep learning gearbox in optical coherence tomography image segmentation towards explainable artificial intelligence

Communications Biology ◽

10.1038/s42003-021-01697-y ◽

2021 ◽

Vol 4 (1) ◽

Author(s):

Peter M. Maloca ◽

Philipp L. Müller ◽

Aaron Y. Lee ◽

Adnan Tufail ◽

Konstantinos Balaskas ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Optical Coherence Tomography ◽

Image Segmentation ◽

Convolutional Neural Network ◽

Learning Algorithm ◽

Ground Truth ◽

Optical Coherence Tomography Image ◽

Optical Coherence ◽

Tomography Image

AbstractMachine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization (‘neural recording’). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications.

Download Full-text