Enhanced Detection of Referable Diabetic Retinopathy via DCNNs and Transfer Learning

被引：2

作者：

Yip, Michelle Yuen Ting ^{[1
,2
]}

Lim, Zhan Wei ^{[4
]}

Lim, Gilbert ^{[4
]}

Nguyen Duc Quang ^{[2
]}

Hamzah, Haslina ^{[3
]}

Ho, Jinyi ^{[3
]}

Bellemo, Valentina ^{[2
]}

Xie, Yuchen ^{[2
]}

Lee, Xin Qi ^{[2
]}

Lee, Mong Li ^{[4
]}

Hsu, Wynne ^{[4
]}

Wong, Tien Yin ^{[1
,2
,3
]}

Ting, Daniel Shu Wei ^{[1
,2
,3
]}

机构：

[1] Natl Univ Singapore, Duke NUS Med Sch, Singapore, Singapore

[2] Singapore Eye Res Inst, Singapore, Singapore

[3] Singapore Natl Eye Ctr, Singapore, Singapore

[4] Natl Univ Singapore, Sch Comp, Singapore, Singapore

来源：

COMPUTER VISION - ACCV 2018 WORKSHOPS | 2019年 / 11367卷

关键词：

Deep learning; Convolutional neural networks; Diabetic retinopathy; DEEP; IMAGES; VALIDATION; DATASET; SYSTEM;

D O I：

10.1007/978-3-030-21074-8_23

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A clinically acceptable deep learning system (DLS) has been developed for the detection of diabetic retinopathy by the Singapore Eye Research Institute. For its utility in a national screening programme, further enhancement was needed. With newer deep convolutional neural networks (DCNNs) being introduced and technological methodology such as transfer learning gaining recognition for better performance, this paper compared the performance of the DCNN used in the original DLS, VGGNet, with newer DCNNs, ResNet and Ensemble, with transfer learning. The DLS performance improved with higher AUC, sensitivity and specificity with the adoption of the newer DCNNs and transfer learning.

引用

页码：282 / 288

页数：7

共 50 条

[41] Automatic Detection of Diabetic Hypertensive Retinopathy in Fundus Images Using Transfer Learning
Nagpal, Dimple
Alsubaie, Najah
Soufiene, Ben Othman
Alqahtani, Mohammed S.
Abbas, Mohamed
Almohiy, Hussain M.
APPLIED SCIENCES-BASEL, 2023, 13 (08):
[42] Transfer Learning for Diabetic Retinopathy Detection: A Study of Dataset Combination and Model Performance
Mutawa, A. M.
Alnajdi, Shahad
Sruthi, Sai
APPLIED SCIENCES-BASEL, 2023, 13 (09):
[43] Transfer learning based robust automatic detection system for diabetic retinopathy grading
Bhardwaj, Charu
Jain, Shruti
Sood, Meenakshi
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (20): : 13999 - 14019
[44] VALIDATION OF A RISK STRATIFICATION ALGORITHM FOR PROGRESSION TO REFERABLE DIABETIC RETINOPATHY
Aldington, S.
Stratton, I. M.
Gazis, T.
Sivaprasad, S.
Russell, G.
Scanlon, P. H.
EUROPEAN JOURNAL OF OPHTHALMOLOGY, 2015, 25 (03) : E13 - E13
[45] The Diagnosis of Diabetic Retinopathy: A Transfer Learning Approach
Noor, Farhan Nabil Mohd
Majeed, Anwar P. P. Abdul
Razman, Mohd Azraai Mod
Khairuddin, Ismail Mohd
Isa, Wan Hasbullah Mohd
2021 21ST INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS 2021), 2021, : 596 - 601
[46] Recognition of Diabetic Retinopathy Basedon Transfer Learning
Wu, Yuchen
Hu, Ze
2019 IEEE 4TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA ANALYSIS (ICCCBDA), 2019, : 398 - 401
[47] Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach
Wang, Yueye
Shi, Danli
Tan, Zachary
Niu, Yong
Jiang, Yu
Xiong, Ruilin
Peng, Guankai
He, Mingguang
FRONTIERS IN MEDICINE, 2021, 8
[48] Predicting progression to referable diabetic retinopathy from retinal images and screening data using deep learning
Nderitu, Paul
do Rio, Joan Nunez
Webster, Laura
Mann, Samantha
Hopkins, David
Cardoso, Jorge
Modat, Marc
Bergeles, Christos
Jackson, Timothy L.
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2022, 63 (07)
[49] Predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy using deep learning
Nderitu, Paul
do Rio, Joan M. Nunez
Webster, Laura
Mann, Samantha
Cardoso, M. Jorge
Modat, Marc
Hopkins, David
Bergeles, Christos
Jackson, Timothy L.
COMMUNICATIONS MEDICINE, 2024, 4 (01):
[50] Advanced Edge Detection Techniques for Enhanced Diabetic Retinopathy Diagnosis Using Machine Learning
Basarab, M. R.
Ivanko, K. O.
VISNYK NTUU KPI SERIIA-RADIOTEKHNIKA RADIOAPARATOBUDUVANNIA, 2024, (97): : 67 - 75

← 1 2 3 4 5 →