Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm

AIM:To conduct a classification study of high myopic maculopathy(HMM)using limited datasets,including tessellated fundus,diffuse chorioretinal atrophy,patchy chorioretinal atrophy,and macular atrophy,and minimize annotation costs,and to optimize the ALFA-Mix active learning algorithm and apply it to HMM classification.METHODS:The optimized ALFA-Mix algorithm(ALFAMix+)was compared with five algorithms,including ALFA-Mix.Four models,including Res Net18,were established.Each algorithm was combined with four models for experiments on the HMM dataset.Each experiment consisted of 20 active learning rounds,with 100 images selected per round.The algorithm was evaluated by comparing the number of rounds in which ALFA-Mix+outperformed other algorithms.Finally,this study employed six models,including Efficient Former,to classify HMM.The best-performing model among these models was selected as the baseline model and combined with the ALFA-Mix+algorithm to achieve satisfactor y classification results with a small dataset.RESULTS:ALFA-Mix+outperforms other algorithms with an average superiority of 16.6,14.75,16.8,and 16.7 rounds in terms of accuracy,sensitivity,specificity,and Kappa value,respectively.This study conducted experiments on classifying HMM using several advanced deep learning models with a complete training set of 4252 images.The Efficient Former achieved the best results with an accuracy,sensitivity,specificity,and Kappa value of 0.8821,0.8334,0.9693,and 0.8339,respectively.Therefore,by combining ALFA-Mix+with Efficient Former,this study achieved results with an accuracy,sensitivity,specificity,and Kappa value of 0.8964,0.8643,0.9721,and 0.8537,respectively.CONCLUSION:The ALFA-Mix+algorithm reduces the required samples without compromising accuracy.Compared to other algorithms,ALFA-Mix+outperforms in more rounds of experiments.It effectively selects valuable samples compared to other algorithms.In HMM classification,combining ALFA-Mix+with Efficient Former enhances model performance,further demonstrating the effectiveness of ALFA-Mix+.

A Semantic Adversarial Network for Detection and Classification of Myopic Maculopathy

The diagnosis of eye disease through deep learning (DL) technologyis the latest trend in the field of artificial intelligence (AI). Especially indiagnosing pathologic myopia (PM) lesions, the implementation of DL is adifficult task because of the classification complexity and definition system ofPM. However, it is possible to design an AI-based technique that can identifyPM automatically and help doctors make relevant decisions. To achieve thisobjective, it is important to have adequate resources such as a high-qualityPM image dataset and an expert team. The primary aim of this research isto design and train the DLs to automatically identify and classify PM intodifferent classes. In this article, we have developed a new class of DL models(SAN-FSL) for the segmentation and detection of PM through semanticadversarial networks (SAN) and few-short learning (FSL) methods, respectively.Compared to DL methods, the conventional segmentation methodsuse supervised learning models, so they (a) require a lot of data for trainingand (b) fixed weights are used after the completion of the training process.To solve such problems, the FSL technique was employed for model trainingwith few samples. The ability of FSL learning in UNet architectures is beingexplored, and to fine-tune the weights, a few new samples are being providedto the UNet. The outcomes show improvement in the detection area andclassification of PM stages. Betterment in the result is observed by sensitivity(SE) of 95%, specificity (SP) of 96%, and area under the receiver operatingcurve (AUC) of 98%, and the higher F1-score is achieved using 10-fold crossvalidation.Furthermore, the obtained results confirmed the superiority of theSAN-FSL method.

Visualized analysis of research on myopic traction maculopathy based on CiteSpace

AIM:To analyze the global scientific output concerning myopic traction maculopathy(MTM)and to summarize the research frontiers and hot topics of MTM related researches.METHODS:Data were collected for bibliometric and visualization analyses from Web of Science(WOS)Core Collection.Exported records were analyzed for titles,publication years,research institutions,journal names,authors,keywords,and abstracts using CiteSpace software version 6.1.RESULTS:A total of 839 related studies were analyzed,the publication volume increased annually,with Asia the most active region of MTM research.Optical coherence tomography angiography,optical coherence tomography,macular hole,high myopia,macular buckling were identified as the focus of the current research.Progression,association,classification and shape were identified as the major research frontiers.CONCLUSION:MTM is a major cause of visual loss in pathological myopic eyes.During the preceding 17y,the number of annual publications in MTM research increased gradually.Studies on the progression nature of MTM,genome-wide association study and proper classification of MTM might still be the frontiers of MTM researches.

Diagnosis and treatment of myopic traction maculopathy

In recent years, the broad application of optical coherence tomography and vitrectomy, combined with research efforts in maculopathy in high myopia have provided many achievements, such as the new classification of myopic traction maculopathy (MTM). Here, we review the latest developments in the diagnosis and treatment of MTM, including its conception, clinical characteristics, pathogenesis, clinical stages, and the options for surgical treatment.

Measurements of the parapapillary atrophy area and other fundus morphological features in high myopia with or without posterior staphyloma and myopic traction maculopathy

AIM:To investigate the affecting factors of parapapillary gamma and delta zones and other fundus morphological features in high myopia.METHODS:Seventy high myopia patients were included in this retrospective observational study and 47 patients were female.Patients were divided into three groups:no posterior staphyloma(no PS),PS with myopic traction maculopathy(PS with MTM),and PS without MTM using 3-dimensional magnetic resonance imaging and optical coherence tomography.MTM patients were fur ther classified into three types[epiretinal membrane,macular hole,and macular retinoschisis(MRS)].Diameters of the gamma and delta zones were measured among other morphometric variables using fundus photographs.RESULTS:Of the 70 individuals(127 eyes),the mean age was 57.46±13.56y.In univariate analysis,morphological features changed most dramatically in PS with MTM patients,who had the largest gamma zone diameters,the largest disk-fovea distance(DFD)and disk-fovea angle,and the smallest angle kappa and vertical distance of temporal arterial arcade.However,their horizontal delta zone diameter was smaller than in the patients with PS yet without MTM.In multivariate analysis,with axial length(AL)and age adjusted,the horizontal diameter in the delta zone of the PS without MTM group was still significantly larger than in the PS with MTM group(P=0.024).Comparing the three subtypes of MTM patients,the diameters of the gamma zone and DFD in MRS group were the largest.CONCLUSION:The characteristics of the gamma and delta zones change inconsistently in different stages of high myopia.These changes may be associated with anatomical changes caused by local traction.Factors such as PS,AL and age play an important role.These findings may provide a hint about the pathogenesis of traction in high myopia.

Resolving Myopic Foveoretinal Detachment by Fovea-Saving Internal Limiting Membrane Peeling: A Case-Series Report

Background: In highly myopic eyes, myopic foveoschisis (MF), the earliest stage of myopic traction maculopathy (MTM), is present in up to 34% of patients with pathologic myopia and slowly progresses to form foveoretinal detachment (FRD) or macular hole (MH) with or without macular hole retinal detachment (MHRD) as a part of its natural history. Aim: To describe the microstructural and functional results in three highly myopic eyes that underwent macular surgery for early-stage MTM. The last postoperative structural findings were correlated with the final vision and macular automated microperimetry evaluation. Methods: We retrospectively reviewed three highly myopic eyes that underwent successful fovea-saving internal limiting membrane (FS-ILM) macular surgery for chronic FRD at Oftalmologia Integral ABC, Mexico City, Mexico. We performed postoperative multimodal microstructural and functional evaluations, including SD-OCT, SS-OCT, and microperimetric macular examinations. Results: There was a substantial difference between best-corrected visual acuity (BCVA) preoperatively and postoperatively in all three cases. Postoperative surgery was associated with significant improvement in visual acuity confirmed using a paired-sample permutation test. The mean presurgical BCVA value (LogMAR;mean ± SE) was ~0.83 ± 0.15, and the postsurgical value was ~0.43 ± 0.52 (P = 0.00065). The myopic foveoretinal detachment evaluation was ~7.3 ± 3.5 months, with a mean postoperative follow-up time of ~14 ± 4.08 months. Furthermore, postoperative multimodal imaging tests demonstrated an abnormal microstructural foveal SS-OCT pattern without evidence of macular hole (MH) development at the postoperative follow-up. Macular microperimetry confirmed a subclinical reduced macula threshold sensitivity with an anomalous retinal sensitivity analysis map and a stable central foveal fixation site. Conclusions: Even with the successful microstructural disappearance of myopic macular detachment, the last multidisciplinary functional and structural assessments demonstrated different subclinical macular alterations.

Review on current concepts of myopia and its control strategies

Myopia poses a significant burden on the healthcare system,economy and quality of life.It is an emerging global public health challenge and requires interventions to delay or stop onset and progression.With changing times and evidence,the concepts of myopia are changing along with the treatment and control strategies.Behavioural modifications including increased outdoors time and reduced near work,optical and pharmaceutical management options are reviewed.This paper presents a current overview on the concepts of myopia,and is expected to summarize updates on myopia control methods.

Pathologic myopia

Pathologic myopia is the major cause of the loss of the best-corrected visual acuity(BCVA)worldwide,especially in East Asian countries.The loss of BCVA is caused by the development of myopic macula patchy,myopic traction macula patchy,and myopic optic neuropathy(or glaucoma).The development of such vision-threatening complications is caused by eye deformity,characterized by a formation of posterior staphyloma.The recent advance in ocular imaging has greatly facilitated the clarification of pathologies and pathogenesis of pathological myopia and myopia-related complications.These technologies include ultra-wide field fundus imaging,swept-source optical coherence tomography,and 3D MRI.In addition,the new treatments such as anti-VEGF therapies for myopic choroid all neovascularization have improved the outcome of the patients.Swept-source OCT showed that some of the lesions of myopic maculopathy were not simply chorioretinal atrophy but were Bruch’s membrane holes.Features of myopic traction maculopathy have been analyzed extensively by using OCT.The understanding the pathophysiology of complications of pathologic myopia is considered useful for better management of this blinding eye disease.