Explainable Artificial Intelligence Enabled TeleOphthalmology for Diabetic Retinopathy Grading and Classification

被引:11
|
作者
Obayya, Marwa [1 ]
Nemri, Nadhem [2 ]
Nour, Mohamed K. [3 ]
Al Duhayyim, Mesfer [4 ]
Mohsen, Heba [5 ]
Rizwanullah, Mohammed [6 ]
Zamani, Abu Sarwar [6 ]
Motwakel, Abdelwahed [6 ]
机构
[1] Princess Nourah Bint Abdulrahman Univ, Coll Engn, Dept Biomed Engn, POB 84428, Riyadh 11671, Saudi Arabia
[2] King Khalid Univ, Coll Sci & Art Mahayil, Dept Informat Syst, Abha 62529, Saudi Arabia
[3] Umm Al Qura Univ, Coll Comp & Informat Syst, Dept Comp Sci, Mecca 24382, Saudi Arabia
[4] Prince Sattam Bin Abdulaziz Univ, Coll Sci & Humanities Aflaj, Dept Comp Sci, Al Kharj 16278, Saudi Arabia
[5] Future Univ Egypt, Fac Comp & Informat Technol, Dept Comp Sci, New Cairo 11835, Egypt
[6] Prince Sattam Bin Abdulaziz Univ, Dept Comp & Self Dev, Al Kharj 16278, Saudi Arabia
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 17期
关键词
telemedicine; diabetic retinopathy; fundus images; deep learning; teleophthalmology;
D O I
10.3390/app12178749
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Recently, Telehealth connects patients to vital healthcare services via remote monitoring, wireless communications, videoconferencing, and electronic consults. By increasing access to specialists and physicians, telehealth assists in ensuring patients receive the proper care at the right time and right place. Teleophthalmology is a study of telemedicine that provides services for eye care using digital medical equipment and telecommunication technologies. Multimedia computing with Explainable Artificial Intelligence (XAI) for telehealth has the potential to revolutionize various aspects of our society, but several technical challenges should be resolved before this potential can be realized. Advances in artificial intelligence methods and tools reduce waste and wait times, provide service efficiency and better insights, and increase speed, the level of accuracy, and productivity in medicine and telehealth. Therefore, this study develops an XAI-enabled teleophthalmology for diabetic retinopathy grading and classification (XAITO-DRGC) model. The proposed XAITO-DRGC model utilizes OphthoAI IoMT headsets to enable remote monitoring of diabetic retinopathy (DR) disease. To accomplish this, the XAITO-DRGC model applies median filtering (MF) and contrast enhancement as a pre-processing step. In addition, the XAITO-DRGC model applies U-Net-based image segmentation and SqueezeNet-based feature extractor. Moreover, Archimedes optimization algorithm (AOA) with a bidirectional gated recurrent convolutional unit (BGRCU) is exploited for DR detection and classification. The experimental validation of the XAITO-DRGC method can be tested using a benchmark dataset and the outcomes are assessed under distinct prospects. Extensive comparison studies stated the enhancements of the XAITO-DRGC model over recent approaches.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] The Role of Teleophthalmology in the Management of Diabetic Retinopathy
    Salongcay, Recivall P.
    Silva, Paolo S.
    [J]. ASIA-PACIFIC JOURNAL OF OPHTHALMOLOGY, 2018, 7 (01): : 17 - 21
  • [22] Enhancing Early Detection of Diabetic Retinopathy Through the Integration of Deep Learning Models and Explainable Artificial Intelligence
    Alavee, Kazi Ahnaf
    Hasan, Mehedi
    Zillanee, Abu Hasnayen
    Mostakim, Moin
    Uddin, Jia
    Alvarado, Eduardo Silva
    Diez, Isabel de la Torre
    Ashraf, Imran
    Samad, Md Abdus
    [J]. IEEE ACCESS, 2024, 12 : 73950 - 73969
  • [23] Deep learning enabled optimized feature selection and classification for grading diabetic retinopathy severity in the fundus image
    Dayana, A. Mary
    Emmanuel, W. R. Sam
    [J]. NEURAL COMPUTING & APPLICATIONS, 2022, 34 (21): : 18663 - 18683
  • [24] Deep learning enabled optimized feature selection and classification for grading diabetic retinopathy severity in the fundus image
    Dayana, A. Mary
    Emmanuel, W. R. Sam
    [J]. Neural Computing and Applications, 2022, 34 (21) : 18663 - 18683
  • [25] Artificial Intelligence (AI) Enabled Pre-Screening for Diabetic Retinopathy (DR) Clinical Trials
    Barrett, Nancy
    Slater, Robert
    Channa, Roomasa
    Domalpally, Amitha
    Blodi, Barbara A.
    [J]. INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2022, 63 (07)
  • [26] Deep learning enabled optimized feature selection and classification for grading diabetic retinopathy severity in the fundus image
    A. Mary Dayana
    W. R. Sam Emmanuel
    [J]. Neural Computing and Applications, 2022, 34 : 18663 - 18683
  • [27] An explainable artificial intelligence-enabled electrocardiogram analysis model for the classification of reduced left ventricular function
    Katsushika, Susumu
    Kodera, Satoshi
    Sawano, Shinnosuke
    Shinohara, Hiroki
    Setoguchi, Naoto
    Tanabe, Kengo
    Higashikuni, Yasutomi
    Takeda, Norifumi
    Fujiu, Katsuhito
    Daimon, Masao
    Akazawa, Hiroshi
    Morita, Hiroyuki
    Komuro, Issei
    [J]. EUROPEAN HEART JOURNAL - DIGITAL HEALTH, 2023, 4 (03): : 254 - 264
  • [28] Artificial intelligence for diabetic retinopathy screening: a review
    Grzybowski, Andrzej
    Brona, Piotr
    Lim, Gilbert
    Ruamviboonsuk, Paisan
    Tan, Gavin S. W.
    Abramoff, Michael
    Ting, Daniel S. W.
    [J]. EYE, 2020, 34 (03) : 451 - 460
  • [29] Detection and classification of retinal lesions for grading of diabetic retinopathy
    Akram, M. Usman
    Khalid, Shehzad
    Tariq, Anam
    Khan, Shoab A.
    Azam, Farooque
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2014, 45 : 161 - 171
  • [30] Artificial intelligence in diabetic retinopathy: Bibliometric analysis
    Poly, Tahmina Nasrin
    Islam, Md. Mohaimenul
    Walther, Bruno Andreas
    Lin, Ming Chin
    Li, Yu-Chuan
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2023, 231