Classification of diabetic retinopathy using stacked machine learning approach on low resource dataset

被引:1
作者
Sengupta, Diganta [1 ,2 ]
Mondal, Subhash [1 ]
De Kumar, Anish [1 ]
Sur, Pretha [1 ]
机构
[1] Meghnad Saha Inst Technol, Dept Comp Sci & Engn, Kolkata, India
[2] Meghnad Saha Inst Technol, Dept Comp Sci & Business Syst, Kolkata, India
关键词
Diabetic retinopathy; Machine learning; Low resource dataset; Stacking; Classification;
D O I
10.1007/s11334-022-00473-3
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This study focuses on classification of Diabetic Retinopathy (DR) using Machine Learning (ML) algorithms on low resource dataset. We conduct the computation on a publicly available dataset comprising of just 19 features detailing 1151 instances. We deploy eight popular ML algorithms for classification and observe the best accuracy of 77.8%, and an F1-Score of 0.712 using the Logistic Regression algorithm. Further stacking of all the ML algorithms present an accuracy of 81.3% with an F1-Score of 0.784. Moreover, the confusion matrix reflects false negative values of about 12% only (37 points out of 306 instances). The results fare better in comparison with prior art. Prior art in this context relates to those proposals which are purely ML based. A certain amount of proposals in classification of DR exhibit initial feature extraction using Deep Learning (DL) models followed by classification using ML algorithms. We exclude these proposals containing partly engaged DL models. The performance metrics used in our evaluation of our proposed model are accuracy, precision, recall, F1-Score, Cohen-Kappa score, and RoC-AuC curve. Our model being based purely on ML algorithms perform the task much faster than the DL counterparts.
引用
收藏
页码:29 / 37
页数:9
相关论文
共 50 条
[31]   Recognition of Diabetic Retinopathy Levels Using Machine Learning [J].
Kalyani, Kanak ;
Damdoo, Rina ;
Sanghavi, Jignyasa .
BIOSCIENCE BIOTECHNOLOGY RESEARCH COMMUNICATIONS, 2020, 13 (14) :138-141
[32]   Optimized hybrid machine learning approach for smartphone based diabetic retinopathy detection [J].
Shubhi Gupta ;
Sanjeev Thakur ;
Ashutosh Gupta .
Multimedia Tools and Applications, 2022, 81 :14475-14501
[33]   Machine Learning Approach for Detection of Diabetic Retinopathy with Improved Pre-Processing [J].
Sharma, Ayushi ;
Shinde, Swapnil ;
Shaikh, Imran Ismail ;
Vyas, Madhav ;
Rani, Soumya .
2021 IEEE INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION, AND INTELLIGENT SYSTEMS (ICCCIS), 2021, :517-522
[34]   Enhancing diabetic retinopathy classification using deep learning [J].
Alwakid, Ghadah ;
Gouda, Walaa ;
Humayun, Mamoona ;
Jhanjhi, N. Z. .
DIGITAL HEALTH, 2023, 9
[35]   DREAM: Diabetic Retinopathy Analysis Using Machine Learning [J].
Roychowdhury, Sohini ;
Koozekanani, Dara D. ;
Parhi, Keshab K. .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2014, 18 (05) :1717-1728
[36]   Classifying Diabetic Retinopathy using CNN and Machine Learning [J].
Lahmar, Chaymaa ;
Idri, Ali .
PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES (BIOIMAGING), VOL 2, 2021, :52-62
[37]   Diabetic Retinopathy using Morphological Operations and Machine Learning [J].
Lachure, Jayakumar ;
Deorankar, A. V. ;
Lachure, Sagar ;
Gupta, Swati ;
Jadhav, Romit .
2015 IEEE INTERNATIONAL ADVANCE COMPUTING CONFERENCE (IACC), 2015, :617-622
[38]   LBP and Machine Learning for Diabetic Retinopathy Detection [J].
de la Calleja, Jorge ;
Tecuapetla, Lourdes ;
Auxilio Medina, Ma ;
Barcenas, Everardo ;
Urbina Najera, Argelia B. .
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2014, 2014, 8669 :110-117
[39]   A Deep Learning Model for Diabetic Retinopathy Classification [J].
Touati, Mohamed ;
Nana, Laurent ;
Benzarti, Faouzi .
DIGITAL TECHNOLOGIES AND APPLICATIONS, ICDTA 2023, VOL 2, 2023, 669 :159-168
[40]   Early Detection and Classification of Diabetic Retinopathy: A Deep Learning Approach [J].
Youldash, Mustafa ;
Rahman, Atta ;
Alsayed, Manar ;
Sebiany, Abrar ;
Alzayat, Joury ;
Aljishi, Noor ;
Alshammari, Ghaida ;
Alqahtani, Mona .
AI, 2024, 5 (04) :2586-2617