Predictors of Visual Acuity Outcomes Following Vitrectomy for Idiopathic Macular Hole

Accuracy of generative deep learning model for macular anatomy prediction from optical coherence tomography images in macular hole surgery

This study aims to propose a generative deep learning model (GDLM) based on a variational autoencoder that predicts macular optical coherence tomography (OCT) images following full-thickness macular hole (FTMH) surgery and evaluate its clinical accuracy. Preoperative and 6-month postoperative swept-source OCT data were collected from 150 patients with successfully closed FTMH using 6 × 6 mm2 macular volume scan datasets. Randomly selected and augmented 120,000 training and 5000 validation pairs of OCT images were used to train the GDLM. We assessed the accuracy and F1 score of concordance for neurosensory retinal areas, performed Bland-Altman analysis of foveolar height (FH) and mean foveal thickness (MFT), and predicted postoperative external limiting membrane (ELM) and ellipsoid zone (EZ) restoration accuracy between artificial intelligence (AI)-OCT and ground truth (GT)-OCT images. Accuracy and F1 scores were 94.7% and 0.891, respectively. Average FH (228.2 vs. 233.4 μm, P = 0.587) and MFT (271.4 vs. 273.3 μm, P = 0.819) were similar between AI- and GT-OCT images, within 30.0% differences of 95% limits of agreement. ELM and EZ recovery prediction accuracy was 88.0% and 92.0%, respectively. The proposed GDLM accurately predicted macular OCT images following FTMH surgery, aiding patient and surgeon understanding of postoperative macular features.

Prediction of postoperative visual acuity after vitrectomy for macular hole using deep learning-based artificial intelligence

PURPOSE

To create a model for prediction of postoperative visual acuity (VA) after vitrectomy for macular hole (MH) treatment using preoperative optical coherence tomography (OCT) images, using deep learning (DL)-based artificial intelligence.

METHODS

This was a retrospective single-center study. We evaluated 259 eyes that underwent vitrectomy for MHs. We divided the eyes into four groups, based on their 6-month postoperative Snellen VA values: (A) ≥ 20/20; (B) 20/25-20/32; (C) 20/32-20/63; and (D) ≤ 20/100. Training data were randomly selected, comprising 20 eyes in each group. Test data were also randomly selected, comprising 52 total eyes in the same proportions as those of each group in the total database. Preoperative OCT images with corresponding postoperative VA values were used to train the original DL network. The final prediction of postoperative VA was subjected to regression analysis based on inferences made with DL network output. We created a model for predicting postoperative VA from preoperative VA, MH size, and age using multivariate linear regression. Precision values were determined, and correlation coefficients between predicted and actual postoperative VA values were calculated in two models.

RESULTS

The DL and multivariate models had precision values of 46% and 40%, respectively. The predicted postoperative VA values on the basis of DL and on preoperative VA and MH size were correlated with actual postoperative VA at 6 months postoperatively (P < .0001 and P < .0001, r = .62 and r = .55, respectively).

CONCLUSION

Postoperative VA after MH treatment could be predicted via DL using preoperative OCT images with greater accuracy than multivariate linear regression using preoperative VA, MH size, and age.

Vertical and Horizontal M-Charts and Microperimetry for Assessment of the Visual Function in Patients after Vitrectomy with ILM Peeling due to Stage 4 Macular Hole

Purpose

To examine the relationship between the morphological and functional results in eyes after pars plana vitrectomy (PPV) with internal limiting membrane (ILM) peeling due to stage 4 full-thickness macular hole (FTMH).

Methods

The study included 22 eyes that underwent successful PPV due to FTMH. Both vertical metamorphopsia (VM) and horizontal metamorphopsia (HM) were determined using type 2 M-charts, as well as best-corrected visual acuity (BCVA), microperimetry, and optical coherence tomography (OCT) were performed before PPV and 1 and 6 months postoperatively.

Results

A significant improvement of BCVA and metamorphopsia scores measured by M-charts in particular periods before surgery, 1 and 6 months after PPV, was observed. The VM scores were consistently higher than the HM scores at all assessment times. There was a correlation found between VM and BCVA and microperimetry parameters before surgery. The macular sensitivity (MS) as well as macular integrity index increased from 1 month to 6 months after PPV and were correlated with postoperative visual acuity (VA). There was a correlation found between the hole diameter and MS and P2 parameter 6 months after PPV. There was a correlation found between mean duration of symptoms of FTMH and VA and VM score.

Conclusions

VM scores seem to correlate better than HM scores with preoperative BCVA, microperimetry parameters, and duration of symptoms of the FTMH. VM scores are higher after PPV than HM scores in patients with stage 4 of the FTMH. This trial is registered with NCT03701542.