Area and volume ratios for prediction of visual outcome in idiopathic macular hole

Choroidal hypertransmission width on optical coherence tomography: a prognostic biomarker in idiopathic macular hole surgery

PURPOSE

To test the hypothesis that optical coherence tomography (OCT) choroidal hypertransmission width (CHW) is a prognostic biomarker in idiopathic macular hole (MH) surgery METHODS: Retrospective cohort study of consecutive patients undergoing successful pars plana vitrectomy for idiopathic MH. We collected demographic, clinical, and OCT variables at the preoperative and last available visits. Two investigators assessed the following OCT parameters: MH minimum diameter, base diameter, CHW, ellipsoid zone, and external limiting membrane status (absent vs. present). Delta CHW was calculated as the difference between CHW and MH minimum diameter. Linear models were used to investigate factors associated with postoperative best-corrected visual acuity (BCVA) and BCVA change.

RESULTS

Thirty-six eyes (36 patients) with a median (interquartile range (IQR)) follow-up of 9 (8-11) months were included. The median BCVA (IQR) improved from 0.75 (1-0.6) logMAR preoperatively to 0.2 (0.6-0.1) logMAR at the last visit (p < 0.001). Preoperative MH minimum diameter (for a 10-μm increase, estimate (standard error (SE)): 0.009 (0.003) logMAR, p = 0.003), base diameter (for a 10-μm increase, 0.003 (0.001) logMAR, p = 0.032), CHW (for a 10-μm increase, 0.008 (0.002) logMAR, p < 0.001), and delta CHW (for a 10-μm increase, 0.013 (0.005) logMAR, p = 0.009) were significantly associated with postoperative BCVA. The proportion of variance explained was the highest for MH CHW (R2 0.35), followed by minimum MH diameter (R2 0.24), delta CHW (R2 0.19), and MH base diameter (R2 0.14). None of the study variables was associated with delta BCVA.

CONCLUSION

Preoperative CHW is associated with postoperative visual acuity in patients undergoing successful idiopathic MH surgery and may be a useful OCT prognostic biomarker.

The impact of preoperative parameters on postoperative foveal displacement in idiopathic macular hole

This study examined the effect of vitrectomy combined with internal limiting membrane (ILM) peeling on foveal displacement in 42 eyes with idiopathic macular hole (IMH). A retrospective analysis was conducted to measure various macular hole parameters before surgery, including basal diameter, minimum diameter, hole height, and areas affected by traction such as macular hole area (MHA), macular hole cystoid space area (MHCSA), macular hole retinal area (MHRA), and total area (TA). The results showed a postoperative shift of the fovea towards the optic disc in all cases. Notably, the extent of foveal displacement was significantly linked to the preoperative basal diameter (rs = 0.405, P = 0.008) but not to other preoperative parameters or postoperative visual acuity. Furthermore, the study found that the temporal side of the macular hole was more affected by traction than the nasal side preoperatively, leading to greater postoperative displacement (All P < 0.05).

OIMHS: An Optical Coherence Tomography Image Dataset Based on Macular Hole Manual Segmentation

Macular holes, one of the most common macular diseases, require timely treatment. The morphological changes on optical coherence tomography (OCT) images provided an opportunity for direct observation of the disease, and accurate segmentation was needed to identify and quantify the lesions. Developments of such algorithms had been obstructed by a lack of high-quality datasets (the OCT images and the corresponding gold standard macular hole segmentation labels), especially for supervised learning-based segmentation algorithms. In such context, we established a large OCT image macular hole segmentation (OIMHS) dataset with 3859 B-scan images of 119 patients, and each image provided four segmentation labels: retina, macular hole, intraretinal cysts, and choroid. This dataset offered an excellent opportunity for investigating the accuracy and reliability of different segmentation algorithms for macular holes and a new research insight into the further development of clinical research for macular diseases, which included the retina, lesions, and choroid in quantitative analyses.

Prediction of postoperative visual acuity in patients with age-related cataracts using macular optical coherence tomography-based deep learning method

Background

To predict postoperative visual acuity (VA) in patients with age-related cataracts using macular optical coherence tomography-based deep learning method.

Methods

A total of 2,051 eyes from 2,051 patients with age-related cataracts were included. Preoperative optical coherence tomography (OCT) images and best-corrected visual acuity (BCVA) were collected. Five novel models (I, II, III, IV, and V) were proposed to predict postoperative BCVA. The dataset was randomly divided into a training (n = 1,231), validation (n = 410), and test set (n = 410). The performance of the models in predicting exact postoperative BCVA was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The performance of the models in predicting whether postoperative BCVA was improved by at least two lines in the visual chart (0.2LogMAR) was evaluated using precision, sensitivity, accuracy, F1 and area under curve (AUC).

Results

Model V containing preoperative OCT images with horizontal and vertical B-scans, macular morphological feature indices, and preoperative BCVA had a better performance in predicting postoperative VA, with the lowest MAE (0.1250 and 0.1194LogMAR) and RMSE (0.2284 and 0.2362LogMAR), and the highest precision (90.7% and 91.7%), sensitivity (93.4% and 93.8%), accuracy (88% and 89%), F1 (92% and 92.7%) and AUCs (0.856 and 0.854) in the validation and test datasets, respectively.

Conclusion

The model had a good performance in predicting postoperative VA, when the input information contained preoperative OCT scans, macular morphological feature indices, and preoperative BCVA. The preoperative BCVA and macular OCT indices were of great significance in predicting postoperative VA in patients with age-related cataracts.

Surgical classification for large macular hole: based on different surgical techniques results: the CLOSE study group

BACKGROUND

The CLOSE study group proposes an updated surgical classification for large macular holes based on a systematic review of new treatments. Recently, many new techniques have been introduced to treat large full-thickness macular holes (FTMH); although the indications are not clear. An updated surgical classification is needed to help surgical decision-making.

METHODS

We gathered published series by the CLOSE Study Group members and from literature search until June 2021. Techniques included: internal limiting membrane peeling (ILM peeling), ILM flaps, macular hydrodissection (macular hydro), human amniotic membrane graft (hAM), and autologous retinal transplantation (ART). Within each technique, chi-square test assessed association between the minimal linear diameter (MLD) (in µm) and closure rate; the postoperative best-corrected visual acuity (BCVA) gains were compared among groups.

RESULTS

Data extraction included 31 published articles: total of 1135 eyes. Eyes were divided into the following groups: ILM peel (n: 683), ILM Flap (n: 233), macular hydrodissection (n: 64), hAM (n: 59), and ART (n: 96). The initial BCVA and size were heterogenous between the groups. ILM peel showed the best results in large FTMH ≤ 535 µm (closure rate 96.8%); adjusted mean BCVA: 0.49 (LogMAR) with a statistical difference among groups. Large FTMH between 535 and 799 µm: ILM flap technique showed better results (closure rate 99.0%); adjusted mean BCVA: 0.67(LogMAR); also with a statistical difference. For large FTMH ≥ 800 µm more invasive techniques are required. Use of hAM, macular hydrodissection and ART showed higher closure rates for this category (100%, 83.3% and 90.5% respectively), and adjusted mean BCVA varied from 0.76 to 0.89. Although there was no statistical difference between those techniques for this group due to the smaller number of cases.

CONCLUSIONS

The CLOSE study group demonstrated the potential usefulness of a new surgical classification for large FTMHs and propose OCT biomarkers for use in clinical practice and future research. This new classification demonstrated that Large (400-550 µm) and X-Large (550-800 µm) holes can be treated highly successfully with ILM peel and ILM flap techniques, respectively. Further studies are necessary for the larger FTMHs (XX-Large and Giant), using the CLOSE classification, in order to determine which technique is better suited for each hole size and characteristics.

Predicting Visual Improvement After Macular Hole Surgery: A Combined Model Using Deep Learning and Clinical Features

Purpose

The purpose of this study was to assess the feasibility of deep learning (DL) methods to enhance the prediction of visual acuity (VA) improvement after macular hole (MH) surgery from a combined model using DL on high-definition optical coherence tomography (HD-OCT) B-scans and clinical features.

Methods

We trained a DL convolutional neural network (CNN) using pre-operative HD-OCT B-scans of the macula and combined with a logistic regression model of pre-operative clinical features to predict VA increase ≥15 Early Treatment Diabetic Retinopathy Study (ETDRS) letters at 6 months post-vitrectomy in closed MHs. A total of 121 MHs with 242 HD-OCT B-scans and 484 clinical data points were used to train, validate, and test the model. Prediction of VA increase was evaluated using the area under the receiver operating characteristic curve (AUROC) and F1 scores. We also extracted the weight of each input feature in the hybrid model.

Results

All performances are reported on the held-out test set, matching results obtained with cross-validation. Using a regression on clinical features, the AUROC was 80.6, with an F1 score of 79.7. For the CNN, relying solely on the HD-OCT B-scans, the AUROC was 72.8 ± 14.6, with an F1 score of 61.5 ± 23.7. For our hybrid regression model using clinical features and CNN prediction, the AUROC was 81.9 ± 5.2, with an F1 score of 80.4 ± 7.7. In the hybrid model, the baseline VA was the most important feature (weight = 59.1 ± 6.9%), while the weight of HD-OCT prediction was 9.6 ± 4.2%.

Conclusions

Both the clinical data and HD-OCT models can predict postoperative VA improvement in patients undergoing vitrectomy for a MH with good discriminative performances. Combining them into a hybrid model did not significantly improve performance.

Translational Relevance

OCT-based DL models can predict postoperative VA improvement following vitrectomy for MH but fusing those models with clinical data might not provide improved predictive performance.

Optical Coherence Tomography based indices in predicting functional outcome of macular hole surgery: A retrospective chart review

Objectives:

The objective of this study was to assess the utility of novel macular hole indices of Optical Coherence Tomography (OCT) and predicting the functional outcome of surgery.

Methods:

This was a retrospective chart review of 28 eyes who underwent surgery for idiopathic Full Thickness Macular Hole (FTMH) at The Aga Khan University Hospital (AKUH), Karachi from January 2016 to March 2020. Data of preoperative OCTs were recovered from data server of OCT machine. Measurements of the pre-operative OCTs were calculated using caliper function of OCT software by two independent technicians. Parameters included Macular Hole Index (MHI), Traction Hole Index (THI), Hole Form Factor (HFF) and Diameter Hole Index (DHI) were recorded. Receiver operating characteristic (ROC) curve was used to evaluate the performance of DHI, THI, HFF and MHI for improved BCVA after surgery, by looking at sensitivity, specificity and area under curve (AUC). P-value of <0.05 was considered significant.

Results:

Out of 30 eyes, final data analysis was done for 28 eyes. Mean age was 61.5 ± 6.2 years. Mean pre-operative and 6 months post-operative LogMAR best corrected visual acuity (BCVA) was 0.84 ± 0.23 and 0.32 ± 0.30 (p-value <0.001). Area under the curve with 95% confidence interval estimated for DHI, THI, HFF, and MHI was [0.750 (0.559 to 0.889)], [0.827 (0.637 to 0.943)], [0.846 (0.660 to 0.954)], [0.827 (0.637 to 0.943)]. Cut off values for predicting good functional outcome (post-op BCVA equal or better that 0.4) for DHI, THI, HFF and MHI were 0.454, 1.086, 0.856 and 0.501 respectively. All ROC value of less than 0.5 were considered unlikely to predict functional outcomes with macular hole indices.

Conclusion:

Novel macular hole indices can be used as a tool to predict the functional outcomes of macular hole surgery. Larger studies may be required to assess their wider effectiveness.

Macular hole morphology and measurement using an automated three-dimensional image segmentation algorithm

Objective

Full-thickness macular holes (MH) are classified principally by size, which is one of the strongest predictors of anatomical and visual success. Using a three-dimensional (3D) automated image processing algorithm, we analysed optical coherence tomography (OCT) images of 104 MH of patients, comparing MH dimensions and morphology with clinician-acquired two-dimensional measurements.

Methods and Analysis

All patients underwent a high-density central horizontal scanning OCT protocol. Two independent clinicians measured the minimum linear diameter (MLD) and maximum base diameter. OCT images were also analysed using an automated 3D segmentation algorithm which produced key parameters including the respective maximum and minimum diameter of the minimum area (MA) of the MH, as well as volume and surface area.

Results

Using the algorithm-derived values, MH were found to have significant asymmetry in all dimensions. The minima of the MA were typically approximately 90° to the horizontal, and differed from their maxima by 55 μm. The minima of the MA differed from the human-measured MLD by a mean of nearly 50 μm, with significant interobserver variability. The resultant differences led to reclassification using the International Vitreomacular Traction Study Group classification in a quarter of the patients (p=0.07).

Conclusion

MH are complex shapes with significant asymmetry in all dimensions. We have shown how 3D automated analysis of MH describes their dimensions more accurately and repeatably than human assessment. This could be used in future studies investigating hole progression and outcome to help guide optimum treatments.

Preoperative prognostic factors for macular hole surgery: Which is better?

AIM:

This study aims to evaluate the prognostic factors of different optical coherence tomography (OCT) parameters as well as the tamponade used in surgery, on postoperative anatomical and functional success.

METHODS:

Twenty-nine eyes of 27 patients were included in this study. A three-port 23-gauge pars plana vitrectomy was performed on all eyes with peeling of the internal limiting membrane by visualization with brilliant blue dye by the same surgeon (E.U). Apical diameter (AD), base diameter (BD), and height (H) were manually measured by the same retina specialist (E.U) with using the software on OCT machine. Macular hole index (MHI), tractional hole index, diameter hole index, and macular hole volume (MHV) were calculated. The correlation between predictive factors and postoperative best corrected visual acuity (BCVA) was evaluated.

RESULTS:

A statistically significant positive correlation was observed between preoperative BCVA, AD, BD, MHV, and postoperative BCVA scores. A statistically significant negative correlation was observed between preoperative MHI and postoperative BCVA scores (r = −0.676, P = 0.001). The strongest positive correlation was between BD and postoperative BCVA (logMAR) (r = 0.732, P = 0.001). The visual improvement was statistically better in patients treated with C3F8 than SF6.

CONCLUSION:

BD and MHV could be used as a strong predictive OCT parameters of postoperative functional success.