Arifur Rahman

Bio: Arifur Rahman is an academic researcher. The author has contributed to research in topics: Feature selection & Evolutionary algorithm. The author has an hindex of 1, co-authored 2 publications receiving 5 citations.

Automated Detection of Diabetic Retinopathy using Deep Residual Learning

Abstract: Significant amount of people suffer from Diabetic Retinopathy (DR), which is one of the major causes of vision loss. The incidence of this disease is even higher due to not being diagnosed at the right time. On numerous occasions, due to neglect and poor care, diabetic retinopathy can lead to significant damage to the eyes. That is why, early diagnosis of eye diseases, proper treatment and care for the disease can prevent vision loss. Referral of eyes with diabetic retinopathy for advanced assessment and treatment would aid in reducing the chances of vision loss, allowing proper diagnoses. The purpose of this study is to develop resilient and flexible diagnostic techniques for the detection of DR and to identify dynamic DR grading using residual networks to facilitate the network training that are significantly intense than previously used networks. Even though lots of research has been done on DR, its identifications remains challenging due to time and space complexity along with higher accuracy specificity. Here, a residual learning framework has been proposed that overcomes the challenges while efficiently detecting DR. Hence, using a high-end Graphics Processor Unit (GPU) the model has been trained on the publicly available Kaggle dataset and empirical evidence has been provided in order to support the results with a sensitivity of 95.6% and an accuracy of 93.20%.

BFSSGA: Enhancing the Performance of Genetic Algorithm using Boosted Filtering Approach

Abstract: Modern microarray chips can hold gene information from thousands of genes and hundreds of individuals and the main challenge of an effective feature selection method is to identify most useful genes from the whole dataset. Removal of less informative genes helps to alleviate the effects of noise and redundancy and simplifies the task of disease classification and prediction of medical conditions such as cancer. Genetic Algorithm (GA) based wrapper model performs well but suffers from over-fitting problem and the initial population is large and random. Traditional approaches use a filter based preprocessing step to reduce the dimension of the data on which GA operates and as filtering methods on its own has shown to introduce redundant features, in this paper Boosted Feature Subset Selection (BFSS) which is a boosted t-score filter method, is used as a preprocessing step. The gene subset provided by BFSS is fed to a Genetic Algorithm which reduces the feature subset in smaller numbers and helps to generate a better optimal subset of genes. The proposed hybrid approach is applied on leukemia, colon and lung cancer benchmarked datasets and have shown better results than other well-known approaches. General Terms Pattern Recognition, Feature Selection, Microarray Data Analysis, Evolutionary Algorithm.

Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans

Abstract: It is a well-known fact that diabetic retinopathy (DR) is one of the most common causes of visual impairment between the ages of 25 and 74 around the globe. Diabetes is caused by persistently high blood glucose levels, which leads to blood vessel aggravations and vision loss. Early diagnosis can minimise the risk of proliferated diabetic retinopathy, which is the advanced level of this disease, and having higher risk of severe impairment. Therefore, it becomes important to classify DR stages. To this effect, this paper presents a weighted fusion deep learning network (WFDLN) to automatically extract features and classify DR stages from fundus scans. The proposed framework aims to treat the issue of low quality and identify retinopathy symptoms in fundus images. Two channels of fundus images, namely, the contrast-limited adaptive histogram equalization (CLAHE) fundus images and the contrast-enhanced canny edge detection (CECED) fundus images are processed by WFDLN. Fundus-related features of CLAHE images are extracted by fine-tuned Inception V3, whereas the features of CECED fundus images are extracted using fine-tuned VGG-16. Both channels’ outputs are merged in a weighted approach, and softmax classification is used to determine the final recognition result. Experimental results show that the proposed network can identify the DR stages with high accuracy. The proposed method tested on the Messidor dataset reports an accuracy level of 98.5%, sensitivity of 98.9%, and specificity of 98.0%, whereas on the Kaggle dataset, the proposed model reports an accuracy level of 98.0%, sensitivity of 98.7%, and specificity of 97.8%. Compared with other models, our proposed network achieves comparable performance.

DiaNet: A Deep Learning Based Architecture to Diagnose Diabetes Using Retinal Images Only

Abstract: Diabetes is one of the leading fatal diseases globally, putting a huge burden on the global healthcare system. Early diagnosis of diabetes is hence, of utmost importance and could save many lives. However, current techniques to determine whether a person has diabetes or has the risk of developing diabetes are primarily reliant upon clinical biomarkers. In this article, we propose a novel deep learning architecture to predict if a person has diabetes or not from a photograph of his/her retina. Using a relatively small-sized dataset, we develop a multi-stage convolutional neural network (CNN)-based model DiaNet that can reach an accuracy level of over 84% on this task, and in doing so, successfully identifies the regions on the retina images that contribute to its decision-making process, as corroborated by the medical experts in the field. This is the first study that highlights the distinguishing capability of the retinal images for diabetes patients in the Qatari population to the best of our knowledge. Comparing the performance of DiaNet against the existing clinical data-based machine learning models, we conclude that the retinal images contain sufficient information to distinguish the Qatari diabetes cohort from the control group. In addition, our study reveals that retinal images may contain prognosis markers for diabetes and other comorbidities like hypertension and ischemic heart disease. The results led us to believe that the inclusion of retinal images into the clinical setup for the diagnosis of diabetes is warranted in the near future.

Risk Factors and Comorbidities Associated to Cardiovascular Disease in Qatar: A Machine Learning Based Case-Control Study

Abstract: Cardiovascular disease (CVD) is reported to be the leading cause of mortality in the middle eastern countries, including Qatar. But no comprehensive study has been conducted on the Qatar specific CVD risk factors identification. The objective of this case-control study was to develop machine learning (ML) model distinguishing healthy individuals from people having CVD, which could ultimately reveal the list of potential risk factors associated to CVD in Qatar. To the best of our knowledge, this study considered the largest collection of biomedical measurements representing the anthropometric measurements, clinical biomarkers, bioimpedance, spirometry, VICORDER readings, and behavioral factors of the CVD group from Qatar Biobank (QBB). CatBoost model achieved 93% accuracy, thereby outperforming the existing model for the same purpose. Interestingly, combining multimodal datasets into the proposed ML model outperformed the ML model built upon currently known risk factors for CVD, emphasizing the importance of incorporating other clinical biomarkers into consideration for CVD diagnosis plan. The ablation study on the multimodal dataset from QBB revealed that physio-clinical and bioimpedance measurements have the most distinguishing power to classify these two groups irrespective of gender and age of the participants. Multiple feature subset selection techniques confirmed known CVD risk factors (blood pressure, lipid profile, smoking, sedentary life, and diabetes), and identified potential novel risk factors linked to CVD-related comorbidities such as renal disorder (e.g., creatinine, uric acid, homocysteine, albumin), atherosclerosis (intima media thickness), hypercoagulable state (fibrinogen), and liver function (e.g., alkaline phosphate, gamma-glutamyl transferase). Moreover, the inclusion of the proposed novel factors into the ML model provides better performance than the model with traditional known risk factors for CVD. The association of the proposed risk factors and comorbidities are required to be investigated in clinical setup to understand their role in CVD better.

A Generic Adaptive Multi-Gene-Set Genetic Algorithm (AMGA)

Abstract: Genetic algorithms have been used extensively in solving complex solution-space search problems. However, certain problems can include multiple sub-problems in which multiple searches through distinct solution-spaces are required before the final solution combining all the sub-solutions is found. This paper presents a generic design of genetic algorithms which can be used for solving complex solution-space search problems that involve multiple sub-solutions. Such problems are very difficult to solve using basic genetic algorithm designs that utilize a single gene-set per chromosome. The suggested algorithm presents a generic solution which utilizes both multi-gene-set chromosomes, and an adaptive gene mutation rate scheme. The results presented from experiments done using an automatic graphical user interface generation case study, show that the suggested algorithm is capable of producing successful solutions where the common single-gene-set design fails.

Categorization of Diabetic Retinopathy using Deep Learning Techniques

Abstract: Diabetic retinopathy is a disease that infects the vision of human eyes suffering from diabetes. It affects the blood vessels of soft tissues at retina, which is located at the backside of the eyes. This disease is evaluated by the physicians based on the retinal images of patients. Detection of the disease initiates human-intensive work for medical practitioners with monetary expenses also. Recent research works have identified that the use of deep learning methods for automatic detection of diabetic retinopathy helps the experts to make quick decision about the patient’s health conditions. In this paper, automated detection of diabetic retinopathy using deep belief networks has been presented which process the retinal images of patients and provides accurate diagnosis of categories of diabetic retinopathy. The proposed method has been trained and tested with Convolutional Neural Networks and Deep Belief Networks. The confidence level of diagnosis is computed and 94.69% with 96.01% are achieved in the detection of Proliferative diabetic retinopathy using CNN and DBN based on the features of data.