Fundus Pictures Research Articles

Diabetic Retinopathy Classification Using Deep Learning

One of the main causes of adult blindness and a frequent consequence of diabetes is diabetic retinopathy (DR). To avoid visual loss, DR must be promptly identified and classified. In this article, we suggest an automated DR detection and classification method based on deep learning applied to fundus pictures. The suggested technique uses transfer learning for classification. On a dataset of 3,662 fundus images with real-world DR severity labels, we trained and validated our model. According to our findings, the suggested technique successfully detected and classified DR with an overall accuracy of 78.14%. Our model fared better than other recent cutting-edge techniques, illuminating the promise of deep learning-based strategies for DR detection and management. Our research indicates that the suggested technique may be employed as a screening tool for DR in a clinical environment, enabling early illness diagnosis and prompt treatment.

Detection of Diabetic Retinopathy Through Identification of Blood Vessel Thickness Using-FOFF

Diabetes is one of the main problems in today's medical industry. Identification and diagnosis of the eye condition brought on by diabetes' elevated blood sugar levels are crucial. The motive of the work is to present a useful technique for system diagnosis utilizing a retinal fundus picture. A four-stage implementation paradigm is created in this study. Initially the input image is pre-processed, secondly blood vessel segmentation is performed; thirdly feature extraction and finally classification. In this paper an effective methodology is utilized by introducing meta heuristic algorithm. In the entire process, blood vessel segmentation (BVS)contributes a crucial part in DR detection for which a firefly optimized frangi filter (FOFF) is designed in this paper. The process of categorization comes last. The classifiers K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are employed. The performance of system is evaluated by computing the accuracy and precision. The results are compared between the two utilized classifiers. The SVM performance is good with an accuracy of 95.5% and KNN having an accuracy of 91.6%.

Comparison of Image Enhancement Methods for Diabetic Retinopathy Screening

The most common factor contributing to visual abnormalities that result in blindness is known as diabetic retinopathy (DR). Retinal fundus scanning, a non-invasive method that is integral to the picture pre-processing phase, can be used to identify and monitor DR. Low intensity, irregular lighting, and inhomogeneous color are some of the main issues with DR fundus photographs. Analysis of aberrant characteristics on retinal fundus images to identify diabetic retinopathy is one of the key responsibilities of image enhancement. However, a variety of approaches have been created and it is unknown whether one is best suited for use with images of the retinal fundus. This study investigated various image enhancement methods in order to see aberrant abnormalities on retinal fundus pictures more clearly. This study investigated various image enhancement methods in order to see aberrant abnormalities on retinal fundus pictures more clearly. The contrast-limited adaptive histogram equalization (CLAHE) method, the gray-level slicing method, the median filtering method, and the low light method are image improvement methods used to enhance images of the retinal fundus. The parameters Natural Image Quality Evaluator (NIQE), Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and entropy will be used to assess each image enhancement technique's performance. An ophthalmologist from Sains University Hospital (HUSM) provided the image data. The findings indicate that while each technique has its own benefits, the CLAHE technique, with a standard deviation MSE of 0.0004, is the best.

DCNN-based embedded models for parallel diagnosis of ocular diseases

An automated system for detecting ocular diseases with computer-aided tools is essential to identify different eye disorders through fundus pictures. This is because diagnosing ocular illnesses manually is a complicated, time-consuming, and error-prone process. In this research, two multi-label embedded architectures based on a deep learning strategy were proposed for ocular disease recognition and classification. The ODIR (Ocular Disease Intelligent Recognition) dataset was adopted for those models. The suggested designs were implemented as parallel systems. The first model was developed as a parallel embedded system that leverages transfer learning to implement its classifiers. The implementation of these classifiers utilized the deep learning network from VGG16, while the second model was introduced with a parallel architecture, and its classifiers were implemented based on newly proposed deep learning networks. These networks were notable for their small size, limited layers, speedy response, and accurate performance. Therefore, the new proposed design has several benefits, like a small classification network size (20 % of VGG16), enhanced speed, and reduced energy consumption, as well as the suitability for IoT applications that support smart systems like Raspberry Pi and Self-powered components, which possess the ability to function as long as a charged battery is available. The highest accuracy of 0.9974 and 0.96 has been obtained in both proposed models for Myopia ocular disease detection and classification. Compared to research that had been presented in the same field, the performance accuracy of each of the two models shown was high. The P3448-0000 Jetson Nano Developer Kit is used to implement both of the proposed embedded models

A comprehensive computer-aided system for an early-stage diagnosis and classification of diabetic macular edema

Diabetic macular edema (DME) is a condition of retinal swelling due to the accumulation of leaked plasma in the extracellular space in the retina, known as the macula. DME is a chronic progressive retinal disorder that likely results in permanent complete blindness. The early signs of DME are not discernible by merely suspecting the fundus picture with the naked eye. Therefore, a computer-assisted diagnostic system could aid ophthalmologists in screening, diagnosing, and treating DME. This study proposes an efficient and complete model for early diagnosis and staging of DME. To overcome the challenges in precise localization of fovea, blood vessel network extraction, and accurate lesion segmentation, improved image relative subtraction, Gabor wavelet filter, and novel advanced fuzzy c-means clustering algorithms are introduced, respectively. Finally, the Bayesian classifier using the Gaussian function with expectation maximization is used for DME grading. The accurate optic disc and fovea localization, exudates’ segmentation, and classification improved the overall system’s performance. The proposed model achieves an average accuracy of 96.17%, 98.60%, 97.85%, and 98.80% for optic disc detection, fovea localization, exudates segmentation, and DME classification, respectively. The performance of the proposed model compared to the competitive studies illustrates the superiority of the suggested methodology.

IoT-Based Federated Learning Model for Hypertensive Retinopathy Lesions Classification

Traditional classification algorithms struggle to categorize hypertensive retinopathy (HR) lesions correctly because they lack obvious characteristics. A regional IoT-enabled federated learning-based HR categorization approach (IoT-FHR) incorporating global and local attributes is suggested as a solution to this issue. The local feature arterial and venous nicking (AVN) classification model is fused with the overall IoT-FHR classification model to enhance the effect of the classification of IoT-FHR. The AVN classification model’s local lesion characteristics and the IoT-FHR classification model’s global lesion characteristics were combined using feature mean. After that, the results of the global IoT-FHR classification model are averaged with the results of the local AVN classification model. An easy neural network receives its input from the final outcome. The probability value of IoT-FHR in the fundus image is output by the sigmoid classifier after the neural network’s two fully connected and one dropout layer. The AVN classification makes a new kind of intersection detection algorithm suggestion. To determine the intersection points, the algorithm applies a logical and operation to the classified arteries and veins. It takes HR fundus pictures and extracts AVN image blocks using the region of interest extraction approach. The accuracy, sensitivity, and specificity of the suggested fusion model are 93.50%, 69.83%, and 98.33%, respectively, when tested on a private dataset. It is clear from the experiments and results that the suggested model leads the currently used methods when the single-stage classification model is compared with them.

Diabetic retinopathy feature extraction images based on confusion neural network

<p class="15">The diagnosis of diabetic retinopathy depends on the evaluation of retinal fundus pictures. The current methods have been successful in extracting features from fundus images, but due to the complex blood vessel distribution in these images and the presence of a great deal of noise, simple methods based on threshold segmentation and clustering are vulnerable to feature loss during the extraction process. For example, the small blood vessels in the fundus are lost, and the branches of blood vessels are blurred. In addition, the noise in medical images is mainly distributed in the high-frequency area of the image. The proposed method to segment the retinal fundus vessels in the DRIVE and STARE datasets, the average accuracy of this method is 95.45% and 94.81%, respectively, and the sensitivity and specificity are 73.35%, 75.39% and 97.34%, 95.75%. In addition, compared with related methods, the proposed method has higher segmentation accuracy, and after segmentation, the fundus blood vessels have higher integrity, clear structure, and less loss of small blood vessels.</p>

Возможность фармакологической коррекции NMDA-индуцированной эксайтотоксичности сетчатки производными 3-гидроксипиридина

Relevance. Glaucoma is the leading cause of blindness worldwide. Among all pathological mechanisms, a special role is assigned to glutamate excitotoxicity, which accompanies a number of pathological conditions of the retina. The aim of this work was to study the pharmacological activity of compounds of 3-hydroxypyridine derivatives in a model of NMDA-induced retinal degeneration. Material and methods. The introduction of the compounds was carried out in the prophylactic mode of administration. 7 days after the model, ophthalmoscopic changes in the fundus and the level of microcirculation were assessed. Research results. According to the results of the study, it was found that the compound LHT 6-20 had the highest activity. Compound LHT 6-20 at a dose of 25.5 mg/ kg in a model of neurodegenerative retinal damage induced by intravitreal administration of NMDA in rats with a prophylactic administration regimen provides an improvement in the fundus picture by 15.4%, relative to the group with a pathology model, which has a statistically a significant difference (p < 0.05), an increase in the level of microcirculation in the retina by 14.1% relative to the group with the model, while the indicator has a statistically significant difference from the group with pathology (p < 0.05), but does not differ from the reference drug (p > 0.05). Keywords: derivatives of 3-hydroxypyridine, NMDA, excitotoxicity, retina, rats, the level of microcirculation, ophthalmoscopy

Коррекция нейродегенеративных повреждений сетчатки производными диметиламиноэтанола

Glaucoma occupies a leading place among the pathologies of the eye, leading to irreversible consequences. Many researchers assign glutamate excitotoxicity a key role in retinal neurodegeneration. This allows us to consider the model of NMDA-induced retinal degeneration as one of the main ones in experimental studies aimed at studying the neuroprotective properties of compounds. We have studied the pharmacological activity of dimethylaminoethanol derivatives in the model of NMDA-induced retinal excitotoxicity. 7 days after the modeling of the pathology, ophthalmoscopic changes in the fundus and the level of microcirculation were assessed. According to the results of the study, it was found that the compound under the laboratory code DMAE 10-19 had the highest activity. The introduction of the compound provided an improvement in the picture of the fundus by 24.4 %, relative to the group with a pathology model, which is a significant difference (p < 0.05). And also there was an increase in the level of microcirculation in the retina, up to 625.4 p.u., which is 37.6 % higher than in the group with the pathology model (p < 0.05). Thus, it was found that the compound under the laboratory code DMAE 10-19 has the highest pharmacological activity, which is characterized by an improvement in the fundus picture and an increase in the level of microcirculation in the retina. Keywords: dimethylaminoethanol derivatives, NMDA, excitotoxicity, retina, rats, the level of microcirculation, ophthalmoscopy

A bi-directional Long Short-Term Memory-based Diabetic Retinopathy detection model using retinal fundus images

Images of the retina are widely used for diagnosing fundus disease. Low-quality retinal photos make it hard for computer-aided diagnosis systems and ophthalmologists to make a clinical diagnosis. In ophthalmology, precision medicine is based partly on the quality of retinal images. Diabetic Retinopathy (DR) is a common complication of diabetes mellitus that causes iris damage. It is difficult to detect and, if not detected early, can result in blindness. Convolutional neural networks are gaining popularity as an effective deep learning (DL) approach for medical image analysis. This study suggests using deep learning approaches at various stages of the fundus image-based diagnostic pipeline for diabetic retinopathy (DR). Many fields, including medical image classification, have adopted DL representations. Using retinal fundus images, we propose a bi-directional extended short-term memory-based diabetic retinopathy detection model. By examining images of the retinal fundus, the Bi-directional Long Short-Term Memory (LSTM) method can detect and classify various grades of DR. As a preprocessing step, the proposed model uses the Multiscale Retinex with Chromaticity Preservation (MSRCP) method to increase the difference of fundus pictures and progress the short difference of medicinal views. To prepare satisfactory results for image processing, multiscale retinex with chromaticity preservation is used. However, choosing the parameters’ values, such as the Gaussian scales, gain, offset, etc., is the main difficulty with the retinex algorithm. To achieve a practical effect, these parameters must be adjusted. The main goal of the suggested method is to obtain the ideal values for the parameters used in the MSRCP algorithm. Also, photos that have already been processed are used to make feature vectors with the help of an efficient net-based feature extractor that uses deep learning. Many experiments use the benchmark Methods to Evaluate Segmentation and Indexing Techniques in the Field of Retinal Ophthalmology (MESSIDOR) dataset. The results are analyzed in terms of various evaluation factors. The results show that the Bi-LSTM-MSRCP technique is better at diagnosing DR than more modern methods.

Delayed Sympathetic Ophthalmia Involving Posterior Segment a Dilemma: A Case Report

We report a case of 11 year old young girl referred with complaint of right sided photophobia and pain following faucet induced trauma to left eye 3 months ago, followed by loss of sight in left eye. Patient presented to us with prepthisical left eye and anterior segment uveitis in right eye. Fundus picture revealed cream colour white nodules confirmed as Dalen Fuchs on fundus fluorescein angiography and presence of hypereflective lesions placed at level of retinal pigment epithelium with disruption of the inner and outer segment (IS/OS) junction on spectral domain optical coherence tomography. Ultrasonogram-B-scan confirmed closed funnel retinal detachment in traumatized left eye and increased choroidal thickness in sympathizing right eye. She underwent orbital computerized axial tomography scan to rule out intraocular foreign body. She was diagnosed as a case of delayed sympathetic ophthalmia. Subsequently she was put on intensive topical with oral steroids and immunesuppressive therapy constituted with oral azathioprine and methotrexate continued for one year and tapered on resolution of presenting signs. At final follow up sympathizing eye was quiescent and sympathetic eye was prepthisical. Sympathetic ophthalmia needs to be distinguished from other ocular auto-immune disorder such as Vogt Koyanagi Harada disease and Acute Multifocal Pigment Placoid Epitheliopathy to which it bears striking resemblance. As these disorders have variable response to treatment with widely differing outcome one must keep that in view while managing them. It is important to remember as the treatment is prolonged recurrences and patient drop outs are commonly noted.

A Comprehensive Analysis of Various Delineation method for Exudates in Fundus Images using Miniaturized Pi Board

In current decades, employing clinical imagery analysis to automatically segregate exudates from color fundus pictures has proven to be a difficult endeavor. This paper compares the efficacy of several picture delineation techniques using a Raspberry Pi chip. By employing various techniques to regular publically accessible samples, the optimum delineation methodology is selected, while efficacy is measured using characteristics such as resemblance factors, implementation duration, sensitivity, as well as specificity. The source hue ocular pictures are initially obtained using publicly available resources. Gaussian distortion, impulse distortion, and speckle distortion could all be present in such pictures. As a result, a pre-processing approach is used to the source pictures in effort to reduce the distortion and boost brightness. After that, several delineation methods such as a thresholding technique, mean-shift algorithm, watershed algorithm, distance transform, K-means clustering, Fuzzy C-Means grouping approach and Active Contour Model are used to segment the normal and abnormal region in color fundus images. The Fuzzy C-Means grouping approach yields higher delineation precision yet requires longer execution time, according to the findings.

International publication trends in the application of artificial intelligence in ophthalmology research: an updated bibliometric analysis.

The literature on artificial intelligence (AI)-related topics has been expanding rapidly over the last two decades, showing that AI is a crucial force in advancing ophthalmology. This analysis aims to provide a dynamic and longitudinal bibliometric analysis of AI-related ophthalmic papers. The Web of Science was searched to retrieve papers regarding the application of AI in ophthalmology published in the English language up to May 2022. The variables were analyzed using Microsoft Excel 2019 and GraphPad Prism 9. Data visualization was performed using VOSviewer and CiteSpace. In this study, a total of 1,686 publications were analyzed. Recently, AI-related ophthalmology research has increased exponentially. China was the most productive country in this research field, with 483 articles, but the United States of America (446 publications) contributed most to the sum of citations and the H-index. The League of European Research Universities, Ting DSW, and Daniel SW were the most prolific institution and researchers. This field is primarily concerned with diabetic retinopathy (DR), glaucoma, optical coherence tomography, and the classification and diagnosis of fundus pictures. Current hotspots in AI research include deep learning, diagnosing and predicting systemic disorders by fundus images, incidence and progression of ocular diseases, and outcome prediction. This analysis thoroughly reviews AI-related research in ophthalmology to help academics better comprehend the growth and possible practice consequences of AI. The association between eye and systemic biomarkers, telemedicine, real-world studies, and the development and application of new AI algorithms, such as visual converters, will continue to be research hotspots over the next few years.

A STUDY ON RETINITIS PIGMENTOSA AS A CAUSE OF BLINDNESS IN PATIENTS ATTENDING REGIONAL EYE HOSPITAL, KURNOOL FOR BLIND CERTIFICATE

Aim: To study Retinitis Pigmentosa as a cause of blindness in patients attending Regional Eye Hospital, Kurnool for blind certificate. Methods: A total of 1020 patients of all age groups attending to Regional Eye Hospital, Kurnool for blind certificate during the period August 2020 to August 2022 were included and examined which include visual acuity testing using Snellen chart, refraction, slit lamp biomicroscopy,intra ocular pressure measurement using Goldmann Applanation Tonometer,fundus examinationwith indirect ophthalmoscope, visual field testing using Humphrey field analyser. Fundus picture was taken using Zeiss fundus camera. Patients having retinal pathology were exclusively included in the study and others were excluded. Results: Out of 1020 patients, 40 patients had Retinitis Pigmentosa with involvement of both eyes. Of these 40 patients, 23 were males and 17 were females indicating that males were more commonly affected than females. 6 patients had 100% disability, 10 patients had 75% disability, 24 patients had 40% disability. Conclusion: Retinitis Pigmentosa is one among the non-treatable cause of blindness which results due to consanguineous marriages as it is an inherited eye disease.

GLAUCOMA DETECTION SYSTEM ON THE BASIS COMBINING NB and RF CLASSIFIERS

A group of vision-impairing eye conditions known as glaucoma damages the optic nerve, which is essential for clear vision. Frequently, the result is abnormally high ocular pressure. One of the leading causes of blindness in adults over 60 is glaucoma. However, it is more prevalent in older persons of all ages. Glaucoma must be diagnosed as soon as possible. This paper presents the Glaucoma Detection System (GDS), which combines classifiers. For the purpose of glaucoma detection, the GAD system employs the Naive Bayes (NB) and Random Forest (RF) classifiers. The major function of the optic disc and cup is to find anomalies in fundus pictures. The optic cup and optic disc are first extracted from the input fundus pictures, and a region of interest (ROI) is then found.

GabROP: Gabor Wavelets-Based CAD for Retinopathy of Prematurity Diagnosis via Convolutional Neural Networks.

One of the most serious and dangerous ocular problems in premature infants is retinopathy of prematurity (ROP), a proliferative vascular disease. Ophthalmologists can use automatic computer-assisted diagnostic (CAD) tools to help them make a safe, accurate, and low-cost diagnosis of ROP. All previous CAD tools for ROP diagnosis use the original fundus images. Unfortunately, learning the discriminative representation from ROP-related fundus images is difficult. Textural analysis techniques, such as Gabor wavelets (GW), can demonstrate significant texture information that can help artificial intelligence (AI) based models to improve diagnostic accuracy. In this paper, an effective and automated CAD tool, namely GabROP, based on GW and multiple deep learning (DL) models is proposed. Initially, GabROP analyzes fundus images using GW and generates several sets of GW images. Next, these sets of images are used to train three convolutional neural networks (CNNs) models independently. Additionally, the actual fundus pictures are used to build these networks. Using the discrete wavelet transform (DWT), texture features retrieved from every CNN trained with various sets of GW images are combined to create a textural-spectral-temporal demonstration. Afterward, for each CNN, these features are concatenated with spatial deep features obtained from the original fundus images. Finally, the previous concatenated features of all three CNN are incorporated using the discrete cosine transform (DCT) to lessen the size of features caused by the fusion process. The outcomes of GabROP show that it is accurate and efficient for ophthalmologists. Additionally, the effectiveness of GabROP is compared to recently developed ROP diagnostic techniques. Due to GabROP's superior performance compared to competing tools, ophthalmologists may be able to identify ROP more reliably and precisely, which could result in a reduction in diagnostic effort and examination time.

Effect of Highly Active Antiretroviral Therapy on Fundus Images and Retinal Microvessel Diameter in HIV/AIDS Patients

We aimed to investigate whether there were changes in fundus picture and retinal microvascularity of patients with human immunodeficiency virus (HIV)/acquired immune deficiency syndrome (AIDS) who were treated with highly active antiretroviral therapy (HAART). From July 2015 to November 2016, 130 HIV/AIDS patients were collected by the Yunnan Institute of Traditional Chinese Medicine, including 63 treatment-naïve patients and 67 that received HAART for 12 months. Fundus picture lesions, retinal microvascular diameters, CD4+ T lymphocyte count and HIV-1 plasma viral loads were compared between the two groups. The recruited patients were mainly young and middle-aged, with more males than females. There were no significant differences in smoking history, comorbidities and opportunistic infections between the two groups. According to the analysis results from SPSS 20.0 software, the number of CD4+ T lymphocytes in the treated patients (563.34±2.56 cells/μL) increased significantly (P=0.009) as compared with untreated patients (451.37±2.10 cells/μL), and the HIV-1 plasma viral load reduced considerably (4794 vs 0 copy/mL, P=0.000). No significant differences were observed from the fundus picture of patients after effective HAART therapy, including the retinal artery diameter, venous diameter and arteriovenous diameter ratio.

IM-EDRD from Retinal Fundus Images Using Multi-Level Classification Techniques

In recent years, there has been a significant increase in the number of people suffering from eye illnesses, which should be treated as soon as possible in order to avoid blindness. Retinal Fundus images are employed for this purpose, as well as for analysing eye abnormalities and diagnosing eye illnesses. Exudates can be recognised as bright lesions in fundus pictures, which can be the first indicator of diabetic retinopathy. With that in mind, the purpose of this work is to create an Integrated Model for Exudate and Diabetic Retinopathy Diagnosis (IM-EDRD) with multi-level classifications. The model uses Support Vector Machine (SVM)-based classification to separate normal and abnormal fundus images at the first level. The input pictures for SVM are pre-processed with Green Channel Extraction and the retrieved features are based on Gray Level Co-occurrence Matrix (GLCM). Furthermore, the presence of Exudate and Diabetic Retinopathy (DR) in fundus images is detected using the Adaptive Neuro Fuzzy Inference System (ANFIS) classifier at the second level of classification. Exudate detection, blood vessel extraction, and Optic Disc (OD) detection are all processed to achieve suitable results. Furthermore, the second level processing comprises Morphological Component Analysis (MCA) based image enhancement and object segmentation processes, as well as feature extraction for training the ANFIS classifier, to reliably diagnose DR. Furthermore, the findings reveal that the proposed model surpasses existing models in terms of accuracy, time efficiency, and precision rate with the lowest possible error rate.

Strategy for Rapid Diabetic Retinopathy Exposure Based on Enhanced Feature Extraction Processing

In the modern world, one of the most severe eye infections brought on by diabetes is known as diabetic retinopathy, which will result in retinal damage, and, thus, lead to blindness. Diabetic retinopathy can be well treated with early diagnosis. Retinal fundus images of humans are used to screen for lesions in the retina. However, detecting DR in the early stages is challenging due to the minimal symptoms. Furthermore, the occurrence of diseases linked to vascular anomalies brought on by DR aids in diagnosing the condition. Nevertheless, the resources required for manually identifying the lesions are high. Similarly, training for Convolutional Neural Networks is more time-consuming. This proposed research aims to improve diabetic retinopathy diagnosis by developing an enhanced deep learning model for timely DR identification that is potentially more accurate than existing CNN-based models. The proposed model will detect various lesions from retinal images in the early stages. First, characteristics are retrieved from the retinal fundus picture and put into the EDLM for classification. For dimensionality reduction, EDLM is used. Additionally, the classification and feature extraction processes are optimized using the stochastic gradient descent optimizer. The EDLM effectiveness is assessed on the KAG GLE dataset with 3459 retinal images, and results are compared over VGG16, VGG19, RESNET18, RESNET34, and RESNET50.

Relevance Mapping based CNN model with OSR-FCA Technique for Multi-label DR Classification

In computer vision, multi-label classification (MLC) is especially important for medical picture analysis. We use MLC to classify diverse stages of diabetic retinopathy (DR) using colour fundus pictures of varying brightness and contrast. As a result, ophthalmologists can now identify the early warning symptoms of DR and the varying stages of DR, allowing them to begin therapy sooner and prevent further difficulties. Using the outlier-based shallow regularization fuzzy clustering approach (OSR-FCA), for classification we present a deep learning method in this paper's picture segmentation task. The fundamental feature of the proposed system is the ability to identify and analyse different degenerative changes in the retina that occur alongside the progression of DR without requiring the patient to undergo costly diagnostic procedures like dye injections. Photographs are first resized, converted to grayscale, cleaned of noise, and the contrast increased by the use of histogram equalization adopting the CLAHE method. The clipping limit of CLAHE is optimized by the help of the rat optimization algorithm, which is applied throughout the histogram process. In addition, a Gaussian metric regularization to the objective function in OSR-FCA is a great way to enhance clustering approaches that use fuzzy membership with sparseness which is based on neutrosophic set. This research proposes a new approach called Relevance Mapping on Multi-Class Label (RMMCL) for locating and viewing regions of interest (ROI) inside a segmented picture. These representations give better explanations for the predictions of the DL model founded on a convolutional neural network-(CNN). The validation of two ML datasets showed the projected model outperformed the existing models by achieving an average correctness of 97.27 percent over five stages of the IDRID dataset.