Role Of Artificial Intelligence On How Macular Hole Is Measured By Swept-Source OCT

Role Of Artificial Intelligence On How Macular Hole Is Measured By Swept-Source OCT

September 20, 2021

Swept-source (SS) OCT is a variation of OCT that offers improvements in visualizing the vitreous, retina, and choroid at one image. Δ

The increased scan speeds, decreased signal attenuation, more comprehensive imaging, and deeper tissue penetration make SS-OCT ideal for capturing a wide range of views and studying structures below the retinal pigmented epithelium (RPE), especially the choroid. Δ

OCT can show progressive degeneration of the photoreceptor layers through the change in the integrity of the outer retinal hyperreflective bands. Δ

OCT also enables the detection of macular abnormalities like CME, epiretinal membrane (ERM), vitreomacular traction interface abnormalities, or macular holes.

However, few studies have been conducted to evaluate the association between visual acuity (VA) and OCT changes. Δ

Previous studies have shown that the ellipsoid zone (EZ) was associated with better VA and thicker fovea in RP patients. At the same time, the absence of EZ may reflect foveal dysfunction in patients with RP.

The development of a deep learning model to help conduct segmentation of swept-source optical coherence tomography (OCT) images to measure the volume of macular holes was the focus of a presentation in the Lions’ Lair competition, a retina research proposals competition held during the 2021 Canadian Ophthalmological Society Annual Meeting and Exhibition. Δ Δ

The premise of this is to possibly augment the International Vitreomacular Traction Study [IVTS] group’s classification of macular holes from 2013.  

The IVTS upgraded the initial classification macular holes by taking an OCT-dependent and anatomical classification of macular holes. Macular hole classification through IVTS is crucial for surgical planning and prognostic considerations for patients. Δ

The IVTS group took anatomical classification as the main etiology for macular holes. The small macular holes measure less than 250 µm, medium-sized macular holes measure between 251 µm and 400 µm, and large macular holes measure more than 400 µm.

However, vitreomacular traction can occur in areas other than the macula. Moreover, the retina is 3-dimensional tissue. Δ

Looking at the retina in a 2-dimensional manner is doing a disservice not only to surgeons but to  patients. Δ

Indeed, using a measure like minimum linear diameter is 1-dimensional, yet the retina is a 3-dimensional structure. Δ

With 3-dimensional viewing, vitreomacular traction was easier to identify. The high density radial scanning is superior to standard raster volume scanning in detecting small full-thickness macular holes.

Moreover, research has shown high inter- and intrauser variability within same eye measurements for minimum linear diameter macular holes.

This changes the prognostic considerations and surgical planning, bringing a patient at times from a small macular hole classification to a large deficit, and vice versa.

With minimum linear diameter, there is a tremendous amount of OCT segmentation dependence. With [minimum linear diameter] being the main biomarker for surgical planning for macular hole surgery, our biomarkers need to be as accurate, precise, and reproducible as possible for our patients. Δ Δ Δ

Researchers employed a deep learning model to obtain automated measurements of macular hole volume, which he described as a robust, 3-dimensional biomarker for macular hole size that can assist in surgical planning and prognostic counseling for patients with full-thickness macular holes.

The pilot study involved 25 patients from the Vitreous Retina Macula Specialists of Toronto (VRMTO) practice, who had full-thickness macular holes, where 3-dimensional OCT images of the holes were obtained preoperatively, 1 month after surgery, and 1 year after surgery. Δ

A single vitreoretinal surgeon, Choudhry, medical director at VRMTO, manually assessed the minimum linear diameter and macular hole volume. A convolutional neural network was developed to assess volume in an automated fashion.

Investigators also looked to see if there were correlations between volume and change in vision in comparison with minimum linear diameter.

The correlation between automated macular hole volume, as determined by our deep learning model, and the manual macular hole volume, as determined by our vitreoretinal surgery, was 0.94.

The deep learning model needs to be validated before being implemented in daily surgical practice. This would give vitreoretinal surgeons another biomarker in their arsenal to help plan surgery and to improve prognostic outcomes for patients. Δ Δ

Increasing the amount of OCT scans in the training set will help reveal what the macular hole volume truly is.

Future directions may see AI provide information, such as how much peeling of the internal limiting membrane is needed, and employ data from known past surgeries. Δ