Optimizing the OCTA layer fusion option for deep learning classification of diabetic retinopathy

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.

Differential Capillary and Large Vessel Analysis Improves OCTA Classification of Diabetic Retinopathy

Purpose

This study aimed to investigate the impact of distinctive capillary-large vessel (CLV) analysis in optical coherence tomography angiography (OCTA) on the classification performance of diabetic retinopathy (DR).

Methods

This multicenter study analyzed 212 OCTA images from 146 patients, including 28 controls, 36 diabetic patients without DR (NoDR), 31 with mild non-proliferative DR (NPDR), 28 with moderate NPDR, and 23 with severe NPDR. Quantitative features were derived from the whole image as well as the parafovea and perifovea regions. A support vector machine classifier was employed for DR classification. The accuracy and area under the receiver operating characteristic curve were used to evaluate the classification performance, utilizing features derived from the whole image and specific regions, both before and after CLV analysis.

Results

Differential CLV analysis significantly improved OCTA classification of DR. In binary classifications, accuracy improved by 11.81%, rising from 77.45% to 89.26%, when utilizing whole image features. For multiclass classifications, accuracy increased by 7.55%, from 78.68% to 86.23%. Incorporating features from the whole image, parafovea, and perifovea further improved binary classification accuracy from 83.07% to 93.80%, and multiclass accuracy from 82.64% to 87.92%.

Conclusions

This study demonstrated that feature changes in capillaries are more sensitive during DR progression, and CLV analysis can significantly improve DR classification performance by extracting features that are specific to large vessels and capillaries in OCTA. Incorporating regional features further improves DR classification accuracy. Differential CLV analysis promises better disease screening, diagnosis, and treatment outcome assessment.

Assessing spectral effectiveness in color fundus photography for deep learning classification of retinopathy of prematurity

Significance

Retinopathy of prematurity (ROP) poses a significant global threat to childhood vision, necessitating effective screening strategies. This study addresses the impact of color channels in fundus imaging on ROP diagnosis, emphasizing the efficacy and safety of utilizing longer wavelengths, such as red or green for enhanced depth information and improved diagnostic capabilities.

Aim

This study aims to assess the spectral effectiveness in color fundus photography for the deep learning classification of ROP.

Approach

A convolutional neural network end-to-end classifier was utilized for deep learning classification of normal, stage 1, stage 2, and stage 3 ROP fundus images. The classification performances with individual-color-channel inputs, i.e., red, green, and blue, and multi-color-channel fusion architectures, including early-fusion, intermediate-fusion, and late-fusion, were quantitatively compared.

Results

For individual-color-channel inputs, similar performance was observed for green channel (88.00% accuracy, 76.00% sensitivity, and 92.00% specificity) and red channel (87.25% accuracy, 74.50% sensitivity, and 91.50% specificity), which is substantially outperforming the blue channel (78.25% accuracy, 56.50% sensitivity, and 85.50% specificity). For multi-color-channel fusion options, the early-fusion and intermediate-fusion architecture showed almost the same performance when compared to the green/red channel input, and they outperformed the late-fusion architecture.

Conclusions

This study reveals that the classification of ROP stages can be effectively achieved using either the green or red image alone. This finding enables the exclusion of blue images, acknowledged for their increased susceptibility to light toxicity.

Differential artery-vein analysis improves the OCTA classification of diabetic retinopathy

This study investigates the impact of differential artery-vein (AV) analysis in optical coherence tomography angiography (OCTA) on machine learning classification of diabetic retinopathy (DR). Leveraging deep learning for arterial-venous area (AVA) segmentation, six quantitative features, including perfusion intensity density (PID), blood vessel density (BVD), vessel area flux (VAF), blood vessel caliber (BVC), blood vessel tortuosity (BVT), and vessel perimeter index (VPI) features, were derived from OCTA images before and after AV differentiation. A support vector machine (SVM) classifier was utilized to assess both binary and multiclass classifications of control, diabetic patients without DR (NoDR), mild DR, moderate DR, and severe DR groups. Initially, one-region features, i.e., quantitative features extracted from the entire OCTA, were evaluated for DR classification. Differential AV analysis improved classification accuracies from 78.86% to 87.63% and from 79.62% to 85.66% for binary and multiclass classifications, respectively. Additionally, three-region features derived from the entire image, parafovea, and perifovea, were incorporated for DR classification. Differential AV analysis further enhanced classification accuracies from 84.43% to 93.33% and from 83.40% to 89.25% for binary and multiclass classifications, respectively. These findings highlight the potential of differential AV analysis in augmenting disease diagnosis and treatment assessment using OCTA.

Correlations between Retinal Microvascular Parameters and Clinical Parameters in Young Patients with Type 1 Diabetes Mellitus: An Optical Coherence Tomography Angiography Study

OBJECTIVES

In the current study, we investigated the correlations between retinal microvascular parameters using optical coherence tomography angiography (OCTA) and clinical parameters for a group of 69 young patients with type 1 diabetes mellitus (T1DM).

MATERIALS AND METHODS

This retrospective, exploratory study enrolled 69 patients between 5 years old and 30 years old who met the inclusion criteria. All the study participants underwent a comprehensive ophthalmic examination and OCTA scans for the evaluation of the retinal microcirculation. The retinal OCTA parameters were correlated with the following clinical parameters: the patient's age at the onset of the disease, the duration of T1DM, the BMI at the time of enrollment in the study, the HbA1C values at onset, the mean values of HbA1C over the period of monitoring the disease and the degree of DKA at onset.

RESULTS

For the study group, the foveal avascular zone (FAZ) area and perimeter correlated positively with the mean value of HbA1C (Pearson correlation, Sig.2-Tailed Area: 0.044; perimeter: 0.049). The total vessel density in the superficial capillary plexus (SCP) correlated negatively with the duration of T1DM, based on the superior and inferior analyzed areas (Spearman correlation, Sig.2-Tailed SCP in total region: 0.002; SCP in the superior region: 0.024; SCP in the inferior region: 0.050). The foveal thickness also correlated negatively with the levels of diabetic ketoacidosis (DKA) at onset (Spearman correlation, Sig.2-Tailed: 0.034) and the levels of HbA1C at onset (Spearman correlation, Sig.2-Tailed: 0.047). Further on, the study patients were distributed into two groups according to the duration of the disease: group 1 included 32 patients with a duration of T1DM of less than 5 years, and group 2 included 37 patients with a duration of T1DM of more than 5 years. Independent t-tests were used to compare the OCTA retinal parameters for the two subgroups. While the FAZ-related parameters did not show significant statistical differences between the two groups, the vessel densities in both the SCP and DCP were significantly lower in group 2.

CONCLUSIONS

Our data suggest that specific alterations in OCTA imaging biomarkers correlate with various clinical parameters: the FAZ area and perimeter increase with higher mean values of HbA1C, leading to poor metabolic control. Moreover, the SCP total vessel density decreases as the duration of T1DM increases. Regarding the vessel densities in the SCP and the DCP, they decrease with a duration of the disease of more than 5 years.

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.

OCT-angiography based artificial intelligence-inferred fluorescein angiography for leakage detection in retina [Invited]

Optical coherence tomography angiography (OCTA) covers most functions of fluorescein angiography (FA) when imaging the retina but lacks the ability to depict vascular leakage. Based on OCTA, we developed artificial intelligence-inferred-FA (AI-FA) to delineate leakage in eyes with diabetic retinopathy (DR). Training data of 19,648 still FA images were prepared from FA-photo and videos of 43 DR eyes. AI-FA images were generated using a convolutional neural network. AI-FA images achieved a structural similarity index of 0.91 with corresponding real FA images in DR. The AI-FA generated from OCTA correctly depicted vascular occlusion and associated leakage with enough quality, enabling precise DR diagnosis and treatment planning. A combination of OCT, OCTA, and AI-FA yields more information than real FA with reduced acquisition time without risk of allergic reactions.