Insight into the Brain: Application of the Retinal Microvasculature as a Biomarker for Cerebrovascular Diseases through Optical Coherence Tomography Angiography

Wang, Liang; Shah, Serena; Llaneras, Cristina Nicole; Goldhardt, Raquel

doi:10.1007/s40135-023-00320-z

Cited by 1 publication

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the fact that changes in retinal microvasculature can reflect internal carotid artery (17)(18)(19), Junlong Qu (16) proposed a multimodal fusion predicting model based on fundus images and clinical indices, which can detect carotid artery stenosis automatically. Although the model's accuracy (74.82%) is not high enough, the research confirmed that predicting CIMT for patients with T2DM from fundus images using deep neural networks is a potential method (16).…”

Section: Introductionmentioning

confidence: 99%

A Siamese ResNeXt network for predicting carotid intimal thickness of patients with T2DM from fundus images

Gong,

Fu,

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

ObjectiveTo develop and validate an artificial intelligence diagnostic model based on fundus images for predicting Carotid Intima-Media Thickness (CIMT) in individuals with Type 2 Diabetes Mellitus (T2DM).MethodsIn total, 1236 patients with T2DM who had both retinal fundus images and CIMT ultrasound records within a single hospital stay were enrolled. Data were divided into normal and thickened groups and sent to eight deep learning models: convolutional neural networks of the eight models were all based on ResNet or ResNeXt. Their encoder and decoder modes are different, including the standard mode, the Parallel learning mode, and the Siamese mode. Except for the six unimodal networks, two multimodal networks based on ResNeXt under the Parallel learning mode or the Siamese mode were embedded with ages. Performance of eight models were compared via the confusion matrix, precision, recall, specificity, F1 value, and ROC curve, and recall was regarded as the main indicator. Besides, Grad-CAM was used to visualize the decisions made by Siamese ResNeXt network, which is the best performance.ResultsPerformance of various models demonstrated the following points: 1) the RexNeXt showed a notable improvement over the ResNet; 2) the structural Siamese networks, which extracted features parallelly and independently, exhibited slight performance enhancements compared to the traditional networks. Notably, the Siamese networks resulted in significant improvements; 3) the performance of classification declined if the age factor was embedded in the network. Taken together, the Siamese ResNeXt unimodal model performed best for its superior efficacy and robustness. This model achieved a recall rate of 88.0% and an AUC value of 90.88% in the validation subset. Additionally, heatmaps calculated by the Grad-CAM algorithm presented concentrated and orderly mappings around the optic disc vascular area in normal CIMT groups and dispersed, irregular patterns in thickened CIMT groups.ConclusionWe provided a Siamese ResNeXt neural network for predicting the carotid intimal thickness of patients with T2DM from fundus images and confirmed the correlation between fundus microvascular lesions and CIMT.

show abstract