1
|
Lyu X, Jajal P, Tahir MZ, Zhang S. Fractal dimension of retinal vasculature as an image quality metric for automated fundus image analysis systems. Sci Rep 2022; 12:11868. [PMID: 35831401 PMCID: PMC9279448 DOI: 10.1038/s41598-022-16089-3] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2021] [Accepted: 07/04/2022] [Indexed: 11/21/2022] Open
Abstract
Automated fundus screening is becoming a significant programme of telemedicine in ophthalmology. Instant quality evaluation of uploaded retinal images could decrease unreliable diagnosis. In this work, we propose fractal dimension of retinal vasculature as an easy, effective and explainable indicator of retinal image quality. The pipeline of our approach is as follows: utilize image pre-processing technique to standardize input retinal images from possibly different sources to a uniform style; then, an improved deep learning empowered vessel segmentation model is employed to extract retinal vessels from the pre-processed images; finally, a box counting module is used to measure the fractal dimension of segmented vessel images. A small fractal threshold (could be a value between 1.45 and 1.50) indicates insufficient image quality. Our approach has been validated on 30,644 images from four public database.
Collapse
Affiliation(s)
- Xingzheng Lyu
- College of Computer Science and Technology, Zhejiang University, 38 Zheda Road, Hangzhou, 310027, China.
| | - Purvish Jajal
- Department of Electrical and Computer Engineering, University of Alberta, Edmonton, T6G 1H9, Canada
| | - Muhammad Zeeshan Tahir
- College of Computer Science and Technology, Zhejiang University, 38 Zheda Road, Hangzhou, 310027, China
| | - Sanyuan Zhang
- College of Computer Science and Technology, Zhejiang University, 38 Zheda Road, Hangzhou, 310027, China
| |
Collapse
|
2
|
|
3
|
WANG XUEWEI, ZHANG SHULIN, LIANG XIAO, ZHENG CHUN, ZHENG JINJIN, Sun MINGZHAI. A CNN-BASED RETINAL IMAGE QUALITY ASSESSMENT SYSTEM FOR TELEOPHTHALMOLOGY. J MECH MED BIOL 2019. [DOI: 10.1142/s0219519419500301] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/02/2023]
Abstract
Oculopathy is a widespread disease among people of all ages around the world. Teleophthalmology can facilitate the ophthalmological diagnosis for less developed countries that lack medical resources. In teleophthalmology, the assessment of retinal image quality is of great importance. In this paper, we propose a no-reference retinal image assessment system based on DenseNet, a convolutional neural network architecture. This system classified fundus images into good and bad quality or five categories: adequate, just noticeable blur, inappropriate illumination, incomplete optic disc, and opacity. The proposed system was evaluated on different datasets and compared to the applications based on other two networks: VGG-16 and GoogLenet. For binary classification, the good-and-bad binary classifier achieves an AUC of 1.000, and the degradation-specified classifiers that distinguish one specified degradation versus the rest achieve AUC values of 0.972, 0.990, 0.982, 0.982 for four categories, respectively. The multi-classification based on DenseNet achieves an overall accuracy of 0.927, which is significantly higher than 0.549 and 0.757 obtained using VGG-16 and GoogLeNet, respectively. The experimental results indicate that the proposed approach produces outstanding performance in retinal image quality assessment and is worth applying in ophthalmological telemedicine applications. In addition, the proposed approach is robust to the image noise. This study fills the gap of multi-classification in retinal image quality assessment.
Collapse
Affiliation(s)
- XUEWEI WANG
- Department of Precision Machinery and Instrumentation, University of Science and Technology of China, Hefei 230022, P. R. China
| | - SHULIN ZHANG
- Department of Precision Machinery and Instrumentation, University of Science and Technology of China, Hefei 230022, P. R. China
| | - XIAO LIANG
- School of Mechanical Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, P. R. China
| | - CHUN ZHENG
- The 105 Hospital of PLA, Hefei 230031, P. R. China
| | - JINJIN ZHENG
- Department of Precision Machinery and Instrumentation, University of Science and Technology of China, Hefei 230022, P. R. China
| | - MINGZHAI Sun
- Department of Precision Machinery and Instrumentation, University of Science and Technology of China, Hefei 230022, P. R. China
| |
Collapse
|
4
|
Jiménez-García J, Romero-Oraá R, García M, López-Gálvez MI, Hornero R. Combination of Global Features for the Automatic Quality Assessment of Retinal Images. ENTROPY 2019; 21:e21030311. [PMID: 33267025 PMCID: PMC7514792 DOI: 10.3390/e21030311] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2019] [Revised: 03/14/2019] [Accepted: 03/18/2019] [Indexed: 02/02/2023]
Abstract
Diabetic retinopathy (DR) is one of the most common causes of visual loss in developed countries. Computer-aided diagnosis systems aimed at detecting DR can reduce the workload of ophthalmologists in screening programs. Nevertheless, a large number of retinal images cannot be analyzed by physicians and automatic methods due to poor quality. Automatic retinal image quality assessment (RIQA) is needed before image analysis. The purpose of this study was to combine novel generic quality features to develop a RIQA method. Several features were calculated from retinal images to achieve this goal. Features derived from the spatial and spectral entropy-based quality (SSEQ) and the natural images quality evaluator (NIQE) methods were extracted. They were combined with novel sharpness and luminosity measures based on the continuous wavelet transform (CWT) and the hue saturation value (HSV) color model, respectively. A subset of non-redundant features was selected using the fast correlation-based filter (FCBF) method. Subsequently, a multilayer perceptron (MLP) neural network was used to obtain the quality of images from the selected features. Classification results achieved 91.46% accuracy, 92.04% sensitivity, and 87.92% specificity. Results suggest that the proposed RIQA method could be applied in a more general computer-aided diagnosis system aimed at detecting a variety of retinal pathologies such as DR and age-related macular degeneration.
Collapse
Affiliation(s)
- Jorge Jiménez-García
- Biomedical Engineering Group, University of Valladolid, Paseo de Belén 15, 47011 Valladolid, Spain
- Correspondence: ; Tel.: +34-983-18-47-16
| | - Roberto Romero-Oraá
- Biomedical Engineering Group, University of Valladolid, Paseo de Belén 15, 47011 Valladolid, Spain
| | - María García
- Biomedical Engineering Group, University of Valladolid, Paseo de Belén 15, 47011 Valladolid, Spain
| | - María I. López-Gálvez
- Biomedical Engineering Group, University of Valladolid, Paseo de Belén 15, 47011 Valladolid, Spain
- Department of Ophthalmology, Hospital Clínico Universitario de Valladolid, Avenida Ramón y Cajal 3, 47003 Valladolid, Spain
- Instituto de Oftalmobiología Aplicada, University of Valladolid, Paseo de Belén 17, 47011 Valladolid, Spain
| | - Roberto Hornero
- Biomedical Engineering Group, University of Valladolid, Paseo de Belén 15, 47011 Valladolid, Spain
- Instituto de Investigación en Matemáticas (IMUVA), University of Valladolid, 47011 Valladolid, Spain
- Instituto de Neurociencias de Castilla y León (INCYL), University of Salamanca, 37007 Salamanca, Spain
| |
Collapse
|
5
|
Abdel-Hamid L, El-Rafei A, El-Ramly S, Michelson G, Hornegger J. Retinal image quality assessment based on image clarity and content. JOURNAL OF BIOMEDICAL OPTICS 2016; 21:96007. [PMID: 27637005 DOI: 10.1117/1.jbo.21.9.096007] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/22/2016] [Accepted: 08/29/2016] [Indexed: 06/06/2023]
Abstract
Retinal image quality assessment (RIQA) is an essential step in automated screening systems to avoid misdiagnosis caused by processing poor quality retinal images. A no-reference transform-based RIQA algorithm is introduced that assesses images based on five clarity and content quality issues: sharpness, illumination, homogeneity, field definition, and content. Transform-based RIQA algorithms have the advantage of considering retinal structures while being computationally inexpensive. Wavelet-based features are proposed to evaluate the sharpness and overall illumination of the images. A retinal saturation channel is designed and used along with wavelet-based features for homogeneity assessment. The presented sharpness and illumination features are utilized to assure adequate field definition, whereas color information is used to exclude nonretinal images. Several publicly available datasets of varying quality grades are utilized to evaluate the feature sets resulting in area under the receiver operating characteristic curve above 0.99 for each of the individual feature sets. The overall quality is assessed by a classifier that uses the collective features as an input vector. The classification results show superior performance of the algorithm in comparison to other methods from literature. Moreover, the algorithm addresses efficiently and comprehensively various quality issues and is suitable for automatic screening systems.
Collapse
Affiliation(s)
- Lamiaa Abdel-Hamid
- Misr International University, Department of Electronics and Communication, Faculty of Engineering, Ismalia Road km28, Cairo, Egypt
| | - Ahmed El-Rafei
- Ain Shams University, Department of Engineering Physics and Mathematics, Faculty of Engineering, 1 El-Sarayat Street, Abbasia, Cairo 11517, Egypt
| | - Salwa El-Ramly
- Ain Shams University, Department of Electronics and Communication, Faculty of Engineering, 1 El-Sarayat Street, Abbasia, Cairo 11517, Egypt
| | - Georg Michelson
- Friedrich-Alexander University of Erlangen-Nuremberg, Department of Ophthalmology, Schwabachanlage 6, Erlangen 91054, GermanyeTalkingeyes & More GmbH, Medical Valley Center, Erlangen 91052, Germany
| | - Joachim Hornegger
- Friedrich-Alexander University of Erlangen-Nuremberg, Pattern Recognition Lab, Department of Computer Science, Martensstr. 3, Erlangen 91058, Germany
| |
Collapse
|
6
|
Torok Z, Peto T, Csosz E, Tukacs E, Molnar AM, Berta A, Tozser J, Hajdu A, Nagy V, Domokos B, Csutak A. Combined Methods for Diabetic Retinopathy Screening, Using Retina Photographs and Tear Fluid Proteomics Biomarkers. J Diabetes Res 2015; 2015:623619. [PMID: 26221613 PMCID: PMC4499636 DOI: 10.1155/2015/623619] [Citation(s) in RCA: 31] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/02/2023] Open
Abstract
Background. It is estimated that 347 million people suffer from diabetes mellitus (DM), and almost 5 million are blind due to diabetic retinopathy (DR). The progression of DR can be slowed down with early diagnosis and treatment. Therefore our aim was to develop a novel automated method for DR screening. Methods. 52 patients with diabetes mellitus were enrolled into the project. Of all patients, 39 had signs of DR. Digital retina images and tear fluid samples were taken from each eye. The results from the tear fluid proteomics analysis and from digital microaneurysm (MA) detection on fundus images were used as the input of a machine learning system. Results. MA detection method alone resulted in 0.84 sensitivity and 0.81 specificity. Using the proteomics data for analysis 0.87 sensitivity and 0.68 specificity values were achieved. The combined data analysis integrated the features of the proteomics data along with the number of detected MAs in the associated image and achieved sensitivity/specificity values of 0.93/0.78. Conclusions. As the two different types of data represent independent and complementary information on the outcome, the combined model resulted in a reliable screening method that is comparable to the requirements of DR screening programs applied in clinical routine.
Collapse
Affiliation(s)
- Zsolt Torok
- Department of Computer Graphics and Image Processing, Bioinformatics Research Group, Faculty of Informatics, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
- Department of Ophthalmology, Faculty of Medicine, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
- Astridbio Technologies Inc., 439 University Avenue, Toronto, ON, Canada M5G 1Y8
- *Zsolt Torok:
| | - Tunde Peto
- NIHR Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, 162 City Road, London EC1V 2PD, UK
| | - Eva Csosz
- Department of Biochemistry and Molecular Biology, Proteomics Core Facility, Faculty of Medicine, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
| | - Edit Tukacs
- Department of Computer Graphics and Image Processing, Bioinformatics Research Group, Faculty of Informatics, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
- Astridbio Technologies Inc., 439 University Avenue, Toronto, ON, Canada M5G 1Y8
| | - Agnes M. Molnar
- Centre for Research on Inner City Health, Keenan Research Centre, Li Ka Shing Knowledge Institute, St Michael's Hospital, 30 Bond Street, Toronto, ON, Canada M5B 1W8
| | - Andras Berta
- Department of Ophthalmology, Faculty of Medicine, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
- InnoTears Ltd., Szent Anna Utca 37/1. 2. em. 1, Debrecen 4024, Hungary
| | - Jozsef Tozser
- Department of Biochemistry and Molecular Biology, Proteomics Core Facility, Faculty of Medicine, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
- InnoTears Ltd., Szent Anna Utca 37/1. 2. em. 1, Debrecen 4024, Hungary
| | - Andras Hajdu
- Department of Computer Graphics and Image Processing, Bioinformatics Research Group, Faculty of Informatics, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
| | - Valeria Nagy
- Department of Ophthalmology, Faculty of Medicine, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
| | - Balint Domokos
- Astridbio Technologies Inc., 439 University Avenue, Toronto, ON, Canada M5G 1Y8
| | - Adrienne Csutak
- Department of Ophthalmology, Faculty of Medicine, University of Debrecen, Egyetem tér 1, Debrecen 4032, Hungary
- InnoTears Ltd., Szent Anna Utca 37/1. 2. em. 1, Debrecen 4024, Hungary
| |
Collapse
|
7
|
Ganesan K, Martis RJ, Acharya UR, Chua CK, Min LC, Ng EYK, Laude A. Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images. Med Biol Eng Comput 2014; 52:663-72. [DOI: 10.1007/s11517-014-1167-5] [Citation(s) in RCA: 42] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2013] [Accepted: 06/11/2014] [Indexed: 11/24/2022]
|
8
|
Veiga D, Pereira C, Ferreira M, Gonçalves L, Monteiro J. Quality evaluation of digital fundus images through combined measures. J Med Imaging (Bellingham) 2014; 1:014001. [PMID: 26158021 DOI: 10.1117/1.jmi.1.1.014001] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2013] [Revised: 02/14/2014] [Accepted: 03/10/2014] [Indexed: 11/14/2022] Open
Abstract
The evaluation of image quality is an important step before an automatic analysis of retinal images. Several conditions can impair the acquisition of a good image, and minimum image quality requirements should be present to ensure that an automatic or semiautomatic system provides an accurate diagnosis. A method to classify fundus images as low or good quality is presented. The method starts with the detection of regions of uneven illumination and evaluates if the segmented noise masks affect a clinically relevant area (around the macula). Afterwards, focus is evaluated through a fuzzy classifier. An input vector is created extracting three focus features. The system was validated in a large dataset (1454 fundus images), obtained from an online database and an eye clinic and compared with the ratings of three observers. The system performance was close to optimal with an area under the receiver operating characteristic curve of 0.9943.
Collapse
Affiliation(s)
- Diana Veiga
- University of Minho , Centro Algoritmi, Azurém, Guimarães 4800-025, Portugal ; ENERMETER , Parque Industrial de Celeirós 2ª Fase, Lugar de Gaião, Lotes 5/6, Braga 4705-025, Portugal
| | - Carla Pereira
- ENERMETER , Parque Industrial de Celeirós 2ª Fase, Lugar de Gaião, Lotes 5/6, Braga 4705-025, Portugal
| | - Manuel Ferreira
- University of Minho , Centro Algoritmi, Azurém, Guimarães 4800-025, Portugal ; ENERMETER , Parque Industrial de Celeirós 2ª Fase, Lugar de Gaião, Lotes 5/6, Braga 4705-025, Portugal
| | - Luís Gonçalves
- Oftalmocenter , Rua Francisco Ribeiro de Castro, n° 205, Azurém, Guimarães 4800-045, Portugal
| | - João Monteiro
- University of Minho , Centro Algoritmi, Azurém, Guimarães 4800-025, Portugal
| |
Collapse
|