Research progress on wide-field multimodal image of peripheral retinal degeneration / 国际眼科杂志(Guoji Yanke Zazhi)

Peripheral retinal degeneration is a typical lesion in ophthalmic clinical practice. Each type of degeneration affects distinct retinal layers and may lead to sight-threatening complications. Due to its specific location, where current ophthalmic imaging technologies have difficulties observing, the pathogenesis remains unclear despite previous works. This review outlines the characteristics of peripheral retinal degeneration by different wide-field imaging technologies, including ultra-wide field fundus imaging, wide field spectral domain optical coherence tomography, optical coherence tomography angiography and fundus fluorescein angiography, as well as new perspectives on their pathogenesis or pathological characteristics so as to provide new ideas for clinical diagnosis and management. Due to the small size of sample and the lack of prospective and long-term observation of multimodal imaging, it is still impossible to comprehensively evaluate the progression and risk of different types of degeneration. Therefore, it is expected that wide-field multimodal imaging technology will be more widely applied to study the mechanism of peripheral retinal degeneration and guide the clinical practice options.

Utilizing human intelligence in artificial intelligence for detecting glaucomatous fundus images using human-in-the-loop machine learning

Purpose: For diagnosing glaucomatous damage, we have employed a novel convolutional neural network (CNN) from TrueColor confocal fundus images to conquer the black box dilemma in artificial intelligence (AI). This neural network with CNN architecture with human?in?the?loop (HITL) data annotation helps not only in diagnosing glaucoma but also in predicting and locating detailed signs in the glaucomatous fundus, such as splinter hemorrhages, glaucomatous optic atrophy, vertical glaucomatous cupping, peripapillary atrophy, and retinal nerve fiber layer (RNFL) defect. Methods: The training was done on a well?curated private dataset of 1,400 high?resolution confocal fundus images, out of which 1,120 images (80%) were used exclusively for training and 280 images (20%) were used exclusively for testing. A custom trained You Only Look Once version 5 (YOLOv5)?based object detection methodology was used to identify the underlying conditions precisely. Twenty?six predefined medical conditions were annotated by a team of humans (comprising two glaucoma specialists and two optometrists) by using the Microsoft Visual Object Tagging Tool (VoTT) tool. The 280 testing images were split into three groups (90,100, and 90 images) for three test runs done once every 15 days. Results: Test results showed consistent increments in the accuracy, from 94.44% to 98.89%, in predicting the glaucoma diagnosis along with the detailed signs of the glaucomatous fundus. Conclusion: Utilizing human intelligence in AI for detecting glaucomatous fundus images by using HITL machine learning has never been reported in the literature before. This AI model not only has good sensitivity and specificity in accurate glaucoma predictions but is also an explainable AI, thus overcoming the black box dilemma.

Preliminary study on the application of artificial intelligence to identify multiple diseases in ultra-widefield fundus images / 中华眼底病杂志

Objective:To build a small-sample ultra-widefield fundus images (UWFI) multi-disease classification artificial intelligence model, and initially explore the ability of artificial intelligence to classify UWFI multi-disease tasks.Methods:A retrospective study. From 2016 to 2021, 1 608 images from 1 123 patients who attended the Eye Center of the Renmin Hospital of Wuhan University and underwent UWFI examination were used for UWFI multi-disease classification artificial intelligence model construction. Among them, 320, 330, 319, 268, and 371 images were used for diabetic retinopathy (DR), retinal vein occlusion (RVO), pathological myopia (PM), retinal detachment (RD), and normal fundus images, respectively. 135 images from 106 patients at the Tianjin Medical University Eye Hospital were used as the external test set. EfficientNet-B7 was selected as the backbone network for classification analysis of the included UWFI images. The performance of the UWFI multi-task classification model was assessed using the receiver operating characteristic curve, area under the curve (AUC), sensitivity, specificity, and accuracy. All data were expressed using numerical values and 95% confidence intervals ( CI). The datasets were trained on the network models ResNet50 and ResNet101 and tested on an external test set to compare and observe the performance of EfficientNet with the 2 models mentioned above. Results:The overall classification accuracy of the UWFI multi-disease classification artificial intelligence model on the internal and external test sets was 92.57% (95% CI 91.13%-92.92%) and 88.89% (95% CI 88.11%-90.02%), respectively. These were 96.62% and 92.59% for normal fundus, 95.95% and 95.56% for DR, 96.62% and 98.52% for RVO, 98.65% and 97.04% for PM, and 97.30% and 94.07% for RD, respectively. The mean AUC on the internal and external test sets was 0.993 and 0.983, respectively, with 0.994 and 0.939 for normal fundus, 0.999 and 0.995 for DR, 0.985 and 1.000 for RVO, 0.991 and 0.993 for PM and 0.995 and 0.990 for RD, respectively. EfficientNet performed better than the ResNet50 and ResNet101 models on both the internal and external test sets. Conclusion:The preliminary UWFI multi-disease classification artificial intelligence model using small samples constructed in this study is able to achieve a high accuracy rate, and the model may have some value in assisting clinical screening and diagnosis.

Application of artificial intelligence aided diagnosis system of fundus images in the clinical teaching of ophthalmology postgraduates / 中华医学教育探索杂志

In this study, artificial intelligence aided diagnosis system of fundus images was applied to clinical teaching of ophthalmology to explore its role in improving the teaching quality. Taking the clinical teaching of diabetic retinopathy as an example, we analyzed the specific steps, effects and improvement strategies. The results revealed that the course could be more interesting and impressing by using the typical cases provided by the artificial intelligence aided diagnosis system of fundus images. In the meanwhile, this system provided the excellent chances for ophthalmology postgraduates to exercise after class, which deepened their understanding of knowledge and enhanced their learning enthusiasm. The application effect has been affirmed and recognized by students.

Multi-channel conditional generative adversarial networks retinal vessel segmentation algorithm / 中华实验眼科杂志

Objective To propose a model for accurately segmenting blood vessels in medical fundus images. Methods The algorithm of deep learning was used for the task of automatic segmentation of blood vessels in retinal fundus images in this paper. An improved vascular segmentation algorithm was proposed. For the different types of blood vessels in the fundus image, a multi-scale network structure was designed to extract features of both main blood vessels and vessel branches at the same time. Results The segmentation model proposed could achieve good results on all kinds of blood vessels even if they have low contrast and few obvious characteristics. The automatic vessel segmentation of retinal fundus images was implemented, and the performance of the model was evaluated through multiple evaluation indexes which are widely used in the field of medical image segmentation in the test stage. A specificity of 0. 9829,an F1 score of 0. 7944,a G-mean of 0. 8748,an Matthews correlation coefficient(MCC) of 0. 7764 and a specificity of 0. 9782 were obtained on the DRIVE dataset. An F1 score of 0. 7735 and an MCC of 0. 7573 were obtained on the STARE data set. Conclusions The proposed method has a great improvement over the segmentation algorithm of the same task. Furthermore,the results generated by our model can achieve comparable effect with the segmentation of human doctor.

Diabetic retinopathy fundus image generation based on generative adversarial networks / 中华实验眼科杂志

Objective To generate various types of diabetic retinopathy ( DR) fundus images automatically by computer vision algorithm. Methods A method based on deep learning to generate fundus images was proposed,which used the vascular vein of the fundus image and the text description of lesions as the constraint conditions to generate fundus image. The text description was encoded by using a long short-term memory ( LSTM) , and the vascular vein image was encoded by a convolutional neural network (CNN). Then the encoded information was combined and used to generate a fundus image by generative adversarial networks ( GAN ) . Results The results showed that the algorithm can generate realistic fundus images. However, the image detail features were not obvious because the text-encoded recurrent neural network ( RNN ) loss function did not converge well. Conclusions Using the GAN can generate realistic DR fundus images, which has certain application value in expanding medical data. However,the generation of detail features in small areas still needs improvement.

Effect of Cataract Grade according to Wide-Field Fundus Images on Measurement of Macular Thickness in Cataract Patients

PURPOSE: To investigate the effects of cataract grade based on wide-field fundus imaging on macular thickness measured by spectral domain optical coherence tomography (SD-OCT) and its signal-to-noise ratio (SNR). METHODS: Two hundred cataract patients (200 eyes) with preoperative measurements by wide-field fundus imaging and macular SD-OCT were enrolled. Cataract severity was graded from 1 to 4 according to the degree of macular obscuring by cataract artifact in fundus photo images. Cataract grade based on wide-field fundus image, the Lens Opacity Classification System III, macular thickness, and SD-OCT SNR were compared. All SD-OCT B-scan images were evaluated to detect errors in retinal layer segmentation. RESULTS: Cataract grade based on wide-field fundus imaging was positively correlated with grade of posterior subcapsular cataracts (rho = 0.486, p < 0.001), but not with nuclear opalescence or cortical cataract using the Lens Opacity Classification System III. Cataract grade was negatively correlated with total macular thickness (rho = −0.509, p < 0.001) and SD-OCT SNR (rho = −0.568, p < 0.001). SD-OCT SNR was positively correlated with total macular thickness (rho = 0.571, p < 0.001). Of 200 eyes, 97 (48.5%) had segmentation errors on SD-OCT. As cataract grade increased and SD-OCT SNR decreased, the percentage of eyes with segmentation errors on SD-OCT increased. All measurements of macular thickness in eyes without segmentation errors were significantly greater than those of eyes with segmentation errors. CONCLUSIONS: Posterior subcapsular cataracts had profound effects on cataract grade based on wide-field fundus imaging. As cataract grade based on wide-field fundus image increased, macular thickness tended to be underestimated due to segmentation errors in SD-OCT images. Segmentation errors in SD-OCT should be considered when evaluating macular thickness in eyes with cataracts.

Paying attention to the concept and research of pachychoroid disease spectrum / 中华实验眼科杂志

Pachychoroid disease spectrum is a novel concept in ophthalmology upon the development of ocular diagnosis and treatment.Recent breakthroughs and advancements in OCT imaging technology such as enhanceddepth imaging spectral-domain OCT (EDI-OCT) and swept source OCT (SS-OCT) have led to improvements in scanning speed,depth,scanning mode and software.This allows better and more detailed visualization of more posterior and deeper structures such as choroid or sclera.The newly developed EDI-OCT and SS-OCT provide a new basis for the diagnosis and classification of the retinal choroidal diseases.Pachychoroid disease spectrum,a group of chronic persistent choroidal thickening associated with a similar clinical phenotype and pathogenesis of disease were named recently based on higher spatial resolution and more detailed choroidal imaging captured by EDI-OCT or SS-OCT.Ophthalmologists should pay more attentions to this new concept and its relative information.In this paper,the concept,pathogenesis,and phenotype of pachychoroid disease spectrum are emphasized.