DFTSA-Net: Deep Feature Transfer-Based Stacked Autoencoder Network for DME Diagnosis

被引:20
作者
Atteia, Ghada [1 ]
Abdel Samee, Nagwan [1 ,2 ]
Zohair Hassan, Hassan [3 ]
机构
[1] Princess Nourah Bint Abdulrahman Univ, Coll Comp & Informat Sci, Informat Technol Dept, Riyadh 11461, Saudi Arabia
[2] Misr Univ Sci & Technol, Comp Engn Dept, Giza 12511, Egypt
[3] Alfaisal Univ, Coll Engn, Dept Mech Engn, Takhassusi St,POB 50927, Riyadh 11533, Saudi Arabia
关键词
diabetic macular edema; retinal fundus image; deep learning; pretrained convolutional neural network; autoencoder; transfer learning; DIABETIC MACULAR EDEMA; RETINOPATHY; IMAGES;
D O I
10.3390/e23101251
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Diabetic macular edema (DME) is the most common cause of irreversible vision loss in diabetes patients. Early diagnosis of DME is necessary for effective treatment of the disease. Visual detection of DME in retinal screening images by ophthalmologists is a time-consuming process. Recently, many computer-aided diagnosis systems have been developed to assist doctors by detecting DME automatically. In this paper, a new deep feature transfer-based stacked autoencoder neural network system is proposed for the automatic diagnosis of DME in fundus images. The proposed system integrates the power of pretrained convolutional neural networks as automatic feature extractors with the power of stacked autoencoders in feature selection and classification. Moreover, the system enables extracting a large set of features from a small input dataset using four standard pretrained deep networks: ResNet-50, SqueezeNet, Inception-v3, and GoogLeNet. The most informative features are then selected by a stacked autoencoder neural network. The stacked network is trained in a semi-supervised manner and is used for the classification of DME. It is found that the introduced system achieves a maximum classification accuracy of 96.8%, sensitivity of 97.5%, and specificity of 95.5%. The proposed system shows a superior performance over the original pretrained network classifiers and state-of-the-art findings.
引用
收藏
页数:17
相关论文
共 39 条
[1]  
Abbas Q, 2020, INT J MED RES HEALTH, V9, P54
[2]  
Al-Bander B., 2016, P OPHTH MED IM AN IN, P121
[3]   Automatic Feature Learning Method for Detection of Retinal Landmarks [J].
Al-Bander, Baidaa ;
Al-Nuaimy, Waleed ;
Al-Taee, Majid A. ;
Al-Ataby, Ali ;
Zheng, Yalin .
2016 9TH INTERNATIONAL CONFERENCE ON DEVELOPMENTS IN ESYSTEMS ENGINEERING (DESE 2016), 2016, :13-18
[4]  
Alloghani M, 2020, STUD COMPUT INTELL, V855, P113, DOI 10.1007/978-3-030-28553-1_6
[5]   Machine learning techniques for diabetic macular edema (DME) classification on SD-OCT images [J].
Alsaih, Khaled ;
Lemaitre, Guillaume ;
Rastgoo, Mojdeh ;
Massich, Joan ;
Sidibe, Desire ;
Meriaudeau, Fabrice .
BIOMEDICAL ENGINEERING ONLINE, 2017, 16
[6]  
Awais M, 2017, IEEE I C SIGNAL IMAG, P489, DOI 10.1109/ICSIPA.2017.8120661
[7]  
Chan GCY, 2018, 2018 INTERNATIONAL CONFERENCE ON INTELLIGENT AND ADVANCED SYSTEM (ICIAS 2018) / WORLD ENGINEERING, SCIENCE & TECHNOLOGY CONGRESS (ESTCON)
[8]  
Chan GCY, 2017, IEEE I C SIGNAL IMAG, P493, DOI 10.1109/ICSIPA.2017.8120662
[9]   One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes [J].
Chen, Shumei ;
Yu, Jianbo ;
Wang, Shijin .
JOURNAL OF PROCESS CONTROL, 2020, 87 :54-67
[10]   Diabetic retinopathy and diabetic macular edema - Pathophysiology, screening, and novel therapies [J].
Ciulla, TA ;
Amador, AG ;
Zinman, B .
DIABETES CARE, 2003, 26 (09) :2653-2664