Ultra-wide-field imaging assessment of small choroidal pigmented lesions using red and green colour channels

Colour fusion effect on deep learning classification of uveal melanoma

BACKGROUND

Reliable differentiation of uveal melanoma and choroidal nevi is crucial to guide appropriate treatment, preventing unnecessary procedures for benign lesions and ensuring timely treatment for potentially malignant cases. The purpose of this study is to validate deep learning classification of uveal melanoma and choroidal nevi, and to evaluate the effect of colour fusion options on the classification performance.

METHODS

A total of 798 ultra-widefield retinal images of 438 patients were included in this retrospective study, comprising 157 patients diagnosed with UM and 281 patients diagnosed with choroidal naevus. Colour fusion options, including early fusion, intermediate fusion and late fusion, were tested for deep learning image classification with a convolutional neural network (CNN). F1-score, accuracy and the area under the curve (AUC) of a receiver operating characteristic (ROC) were used to evaluate the classification performance.

RESULTS

Colour fusion options were observed to affect the deep learning performance significantly. For single-colour learning, the red colour image was observed to have superior performance compared to green and blue channels. For multi-colour learning, the intermediate fusion is better than early and late fusion options.

CONCLUSION

Deep learning is a promising approach for automated classification of uveal melanoma and choroidal nevi. Colour fusion options can significantly affect the classification performance.

Choroidal nevus through a broader vision: Retinal imaging acquisition captured with Broad Line Fundus Imaging technology

OBJECTIVE

To describe the peculiarities in imaging acquisition of fourteen patients with choroidal nevus using the Broad Line Fundus Imaging (BLFI) technology.

METHODS

Single-center, retrospective, cross-sectional analysis.

RESULTS

All images were acquired using the BLFI technology. We have found that choroidal nevus is undetectable in the blue channel (BC) (435-500 nm) and the green channel (GC) (500-585 nm). The only visible changes are related to the drusen, which appeared in BC and GC as light focal dots, correlated to the yellowish foci in the true-color image. On the red channel (RC) (585-640 nm), all lesions revealed the same pattern: a well-defined dark spot, with enhanced contrast, allowing the better visualization, measuring, and characterization of the nevus when compared with the other color channels, including the true-color imaging.

CONCLUSION

BLFI application in choroidal nevus might be helpful at presentation, refining the diagnostic reliability, and monitoring, as it allows for better detection of alterations in the lesions. The peculiarities of the choroidal nevus are better assessed when using the RC due to its longer wavelength and deeper penetration in the retina and choroid.

Color Fusion Effect on Deep Learning Classification of Uveal Melanoma

Background

Reliable differentiation of uveal melanoma and choroidal nevi is crucial to guide appropriate treatment, preventing unnecessary procedures for benign lesions and ensuring timely treatment for potentially malignant cases. The purpose of this study is to validate deep learning classification of uveal melanoma and choroidal nevi, and to evaluate the effect of color fusion options on the classification performance.

Methods

A total of 798 ultra-widefield retinal images of 438 patients were included in this retrospective study, comprising 157 patients diagnosed with UM and 281 patients diagnosed with choroidal nevus. Color fusion options, including early fusion, intermediate fusion and late fusion, were tested for deep learning image classification with a convolutional neural network (CNN). Specificity, sensitivity, F1-score, accuracy, and the area under the curve (AUC) of a receiver operating characteristic (ROC) were used to evaluate the classification performance. The saliency map visualization technique was used to understand the areas in the image that had the most influence on classification decisions of the CNN.

Results

Color fusion options were observed to affect the deep learning performance significantly. For single-color learning, the red color image was observed to have superior performance compared to green and blue channels. For multi-color learning, the intermediate fusion is better than early and late fusion options.

Conclusion

Deep learning is a promising approach for automated classification of uveal melanoma and choroidal nevi, and color fusion options can significantly affect the classification performance.

Is Tumour Thickness Measurement Required for MOLES Scoring of Melanocytic Choroidal Tumours?

Introduction

It can be challenging to distinguish between choroidal naevi and melanomas in the community setting, particularly without access to ultrasonography (US), required to measure the thickness of melanocytic choroidal tumours. We aimed to determine whether thickness measurement is required for MOLES scoring of melanocytic choroidal tumours.

Methods

The dataset of a recent MOLES evaluation was reviewed. Patients were selected for the present study if their MOLES tumour size category was determined by tumour thickness measured with US. The largest basal tumour diameter and tumour thickness were then measured from ultra-widefield fundus images and optical coherence tomography (OCT) images, respectively.

Results

The tumour size category was determined by tumour diameter in 203/222 (91.4%) with no influence of tumour thickness. The tumour thickness influenced the MOLES score in 19/222 (8.6%) patients. In 11/19 patients with OCT measurements of tumour thickness, the US measurement exceeded the OCT by more than 25% in 5 patients, more than 50% in 2 patients, and more than 75% in 1 patient. As a result, the revised tumour thickness based on OCT determined the size category in 4/216 (1.8%) patients. The ultra-widefield fundus images measurements increased the diameter score by 1 in 5 patients. As a result, the revised tumour thickness determined the size category in 4/216 (1.8%) patients. If both the revised diameter and thickness scores were considered, the MOLES score reduced in 4 patients. If both the diameter and thickness scores were considered, the MOLES score reduced in 5 and increased in 1. Only 0.94% (2/211) of melanocytic choroidal tumours assessed with MOLES when using Optos ultra-widefield fundus images diameter and OCT to measure tumour diameter and thickness, respectively, required a change in management from a reduction in MOLES score from 1 to 0.

Discussion/Conclusion

This study suggests that the MOLES category for size is influenced more by the tumour diameter, if it can be measured accurately, than by the thickness. This study suggests ignoring tumour thickness if this cannot be measured accurately with OCT, unless the tumour has a mushroom shape.

Retinal honeycomb appearance and its role in patients with X-linked retinoschisis

BACKGROUND

To investigate the clinical characteristics of retinal honeycomb appearance in a large cohort of patients with X-linked retinoschisis (XLRS) and to determine whether it is associated with complications like retinal detachment (RD) and vitreous hemorrhage (VH).

METHODS

A retrospective observational case series. A chart review of medical records, wide-field fundus imaging, and optical coherence tomography (OCT) was performed on 78 patients (153 eyes) diagnosed with XLRS at Beijing Tongren eye center between Dec 2017 and Feb 2022. The chi-square test or Fisher exact test was performed on the 2 × 2 cross-tabulations of honeycomb appearance and other peripheral retinal findings and complications.

RESULTS

Thirty-eight patients (48.7%), and 60 eyes (39.2%) had a honeycomb appearance of different areas on the fundus. The supratemporal quadrant was the most commonly affected (45 eyes, 75.0%), followed by the infratemporal (23 eyes, 38.3%), the infranasal (10 eyes,16.7%), and supranasal (9 eyes,15.0%). The appearance was significantly associated with peripheral retinoschisis, inner retinal layer break, outer retinal layer break, RD, and rhegmatogenous retinal detachment (RRD) (p < 0.01, p = 0.032, p < 0.01, p = 0.008, p < 0.01, respectively). All the eyes complicated with RRD had the appearance. None of the eyes without the appearance had RRD.

CONCLUSIONS

The data suggest that the honeycomb appearance is not uncommon in patients with XLRS and is more likely to be accompanied by an RRD, and inner and outer layer breaks, thus should be treated with caution and close observation.