1
|
Naing SL, Aimmanee P. Automated optic disk segmentation for optic disk edema classification using factorized gradient vector flow. Sci Rep 2024; 14:371. [PMID: 38172282 PMCID: PMC10764308 DOI: 10.1038/s41598-023-50908-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Accepted: 12/27/2023] [Indexed: 01/05/2024] Open
Abstract
One significant ocular symptom of neuro-ophthalmic disorders of the optic disk (OD) is optic disk edema (ODE). The etiologies of ODE are broad, with various symptoms and effects. Early detection of ODE can prevent potential vision loss and fatal vision problems. The texture of edematous OD significantly differs from the non-edematous OD in retinal images. As a result, techniques that usually work for non-edematous cases may not work well for edematous cases. We propose a fully automatic OD classification of edematous and non-edematous OD on fundus image collections containing a mixture of edematous and non-edematous ODs. The proposed algorithm involved localization, segmentation, and classification of edematous and non-edematous OD. The factorized gradient vector flow (FGVF) was used to segment the ODs. The OD type was classified using a linear support vector machine (SVM) based on 27 features extracted from the vessels, GLCM, color, and intensity line profile. The proposed method was tested on 295 images with 146 edematous cases and 149 non-edematous cases from three datasets. The segmentation achieves an average precision of 88.41%, recall of 89.35%, and F1-Score of 86.53%. The average classification accuracy is 99.40% and outperforms the state-of-the-art method by 3.43%.
Collapse
Affiliation(s)
- Seint Lei Naing
- School of Information, Computer, and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, 131 Moo 5, Tiwanon Rd, Bangkadi, Meung, Patumthani, 12000, Thailand
| | - Pakinee Aimmanee
- School of Information, Computer, and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, 131 Moo 5, Tiwanon Rd, Bangkadi, Meung, Patumthani, 12000, Thailand.
| |
Collapse
|
3
|
Ashraf MN, Hussain M, Habib Z. Review of Various Tasks Performed in the Preprocessing Phase of a Diabetic Retinopathy Diagnosis System. Curr Med Imaging 2021; 16:397-426. [PMID: 32410541 DOI: 10.2174/1573405615666190219102427] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2018] [Revised: 12/31/2018] [Accepted: 01/20/2019] [Indexed: 12/15/2022]
Abstract
Diabetic Retinopathy (DR) is a major cause of blindness in diabetic patients. The increasing population of diabetic patients and difficulty to diagnose it at an early stage are limiting the screening capabilities of manual diagnosis by ophthalmologists. Color fundus images are widely used to detect DR lesions due to their comfortable, cost-effective and non-invasive acquisition procedure. Computer Aided Diagnosis (CAD) of DR based on these images can assist ophthalmologists and help in saving many sight years of diabetic patients. In a CAD system, preprocessing is a crucial phase, which significantly affects its performance. Commonly used preprocessing operations are the enhancement of poor contrast, balancing the illumination imbalance due to the spherical shape of a retina, noise reduction, image resizing to support multi-resolution, color normalization, extraction of a field of view (FOV), etc. Also, the presence of blood vessels and optic discs makes the lesion detection more challenging because these two artifacts exhibit specific attributes, which are similar to those of DR lesions. Preprocessing operations can be broadly divided into three categories: 1) fixing the native defects, 2) segmentation of blood vessels, and 3) localization and segmentation of optic discs. This paper presents a review of the state-of-the-art preprocessing techniques related to three categories of operations, highlighting their significant aspects and limitations. The survey is concluded with the most effective preprocessing methods, which have been shown to improve the accuracy and efficiency of the CAD systems.
Collapse
Affiliation(s)
| | - Muhammad Hussain
- Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia
| | - Zulfiqar Habib
- Department of Computer Science, COMSATS University Islamabad, Lahore, Pakistan
| |
Collapse
|
4
|
Hasan MK, Alam MA, Elahi MTE, Roy S, Martí R. DRNet: Segmentation and localization of optic disc and Fovea from diabetic retinopathy image. Artif Intell Med 2020; 111:102001. [PMID: 33461693 DOI: 10.1016/j.artmed.2020.102001] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2020] [Revised: 11/22/2020] [Accepted: 12/06/2020] [Indexed: 12/18/2022]
Abstract
BACKGROUND AND OBJECTIVE In modern ophthalmology, automated Computer-aided Screening Tools (CSTs) are crucial non-intrusive diagnosis methods, where an accurate segmentation of Optic Disc (OD) and localization of OD and Fovea centers are substantial integral parts. However, designing such an automated tool remains challenging due to small dataset sizes, inconsistency in spatial, texture, and shape information of the OD and Fovea, and the presence of different artifacts. METHODS This article proposes an end-to-end encoder-decoder network, named DRNet, for the segmentation and localization of OD and Fovea centers. In our DRNet, we propose a skip connection, named residual skip connection, for compensating the spatial information lost due to pooling in the encoder. Unlike the earlier skip connection in the UNet, the proposed skip connection does not directly concatenate low-level feature maps from the encoder's beginning layers with the corresponding same scale decoder. We validate DRNet using different publicly available datasets, such as IDRiD, RIMONE, DRISHTI-GS, and DRIVE for OD segmentation; IDRiD and HRF for OD center localization; and IDRiD for Fovea center localization. RESULTS The proposed DRNet, for OD segmentation, achieves mean Intersection over Union (mIoU) of 0.845, 0.901, 0.933, and 0.920 for IDRiD, RIMONE, DRISHTI-GS, and DRIVE, respectively. Our OD segmentation result, in terms of mIoU, outperforms the state-of-the-art results for IDRiD and DRIVE datasets, whereas it outperforms state-of-the-art results concerning mean sensitivity for RIMONE and DRISHTI-GS datasets. The DRNet localizes the OD center with mean Euclidean Distance (mED) of 20.23 and 13.34 pixels, respectively, for IDRiD and HRF datasets; it outperforms the state-of-the-art by 4.62 pixels for IDRiD dataset. The DRNet also successfully localizes the Fovea center with mED of 41.87 pixels for the IDRiD dataset, outperforming the state-of-the-art by 1.59 pixels for the same dataset. CONCLUSION As the proposed DRNet exhibits excellent performance even with limited training data and without intermediate intervention, it can be employed to design a better-CST system to screen retinal images. Our source codes, trained models, and ground-truth heatmaps for OD and Fovea center localization will be made publicly available upon publication at GitHub.1.
Collapse
Affiliation(s)
- Md Kamrul Hasan
- Department of Electrical and Electronic Engineering, Khulna University of Engineering & Technology, Khulna 9203, Bangladesh.
| | - Md Ashraful Alam
- Department of Electrical and Electronic Engineering, Khulna University of Engineering & Technology, Khulna 9203, Bangladesh.
| | - Md Toufick E Elahi
- Department of Electrical and Electronic Engineering, Khulna University of Engineering & Technology, Khulna 9203, Bangladesh.
| | - Shidhartho Roy
- Department of Electrical and Electronic Engineering, Khulna University of Engineering & Technology, Khulna 9203, Bangladesh.
| | - Robert Martí
- Computer Vision and Robotics Institute, University of Girona, Spain.
| |
Collapse
|
6
|
Porwal P, Pachade S, Kokare M, Deshmukh G, Son J, Bae W, Liu L, Wang J, Liu X, Gao L, Wu T, Xiao J, Wang F, Yin B, Wang Y, Danala G, He L, Choi YH, Lee YC, Jung SH, Li Z, Sui X, Wu J, Li X, Zhou T, Toth J, Baran A, Kori A, Chennamsetty SS, Safwan M, Alex V, Lyu X, Cheng L, Chu Q, Li P, Ji X, Zhang S, Shen Y, Dai L, Saha O, Sathish R, Melo T, Araújo T, Harangi B, Sheng B, Fang R, Sheet D, Hajdu A, Zheng Y, Mendonça AM, Zhang S, Campilho A, Zheng B, Shen D, Giancardo L, Quellec G, Mériaudeau F. IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge. Med Image Anal 2019; 59:101561. [PMID: 31671320 DOI: 10.1016/j.media.2019.101561] [Citation(s) in RCA: 69] [Impact Index Per Article: 13.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2019] [Revised: 09/09/2019] [Accepted: 09/16/2019] [Indexed: 02/07/2023]
Abstract
Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on "Diabetic Retinopathy - Segmentation and Grading" was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.
Collapse
Affiliation(s)
- Prasanna Porwal
- Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India; School of Biomedical Informatics, University of Texas Health Science Center at Houston, USA.
| | - Samiksha Pachade
- Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India; School of Biomedical Informatics, University of Texas Health Science Center at Houston, USA
| | - Manesh Kokare
- Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India
| | | | | | | | - Lihong Liu
- Ping An Technology (Shenzhen) Co.,Ltd, China
| | | | - Xinhui Liu
- Ping An Technology (Shenzhen) Co.,Ltd, China
| | | | - TianBo Wu
- Ping An Technology (Shenzhen) Co.,Ltd, China
| | - Jing Xiao
- Ping An Technology (Shenzhen) Co.,Ltd, China
| | | | | | - Yunzhi Wang
- School of Electrical and Computer Engineering, University of Oklahoma, USA
| | - Gopichandh Danala
- School of Electrical and Computer Engineering, University of Oklahoma, USA
| | - Linsheng He
- School of Electrical and Computer Engineering, University of Oklahoma, USA
| | - Yoon Ho Choi
- Samsung Advanced Institute for Health Sciences & Technology (SAIHST), Sungkyunkwan University, Seoul, Republic of Korea
| | - Yeong Chan Lee
- Samsung Advanced Institute for Health Sciences & Technology (SAIHST), Sungkyunkwan University, Seoul, Republic of Korea
| | - Sang-Hyuk Jung
- Samsung Advanced Institute for Health Sciences & Technology (SAIHST), Sungkyunkwan University, Seoul, Republic of Korea
| | - Zhongyu Li
- Department of Computer Science, University of North Carolina at Charlotte, USA
| | - Xiaodan Sui
- School of Information Science and Engineering, Shandong Normal University, China
| | - Junyan Wu
- Cleerly Inc., New York, United States
| | | | - Ting Zhou
- University at Buffalo, New York, United States
| | - Janos Toth
- University of Debrecen, Faculty of Informatics 4002 Debrecen, POB 400, Hungary
| | - Agnes Baran
- University of Debrecen, Faculty of Informatics 4002 Debrecen, POB 400, Hungary
| | | | | | | | | | - Xingzheng Lyu
- College of Computer Science and Technology, Zhejiang University, Hangzhou, China; Machine Learning for Bioimage Analysis Group, Bioinformatics Institute, A*STAR, Singapore
| | - Li Cheng
- Machine Learning for Bioimage Analysis Group, Bioinformatics Institute, A*STAR, Singapore; Department of Electric and Computer Engineering, University of Alberta, Canada
| | - Qinhao Chu
- School of Computing, National University of Singapore, Singapore
| | - Pengcheng Li
- School of Computing, National University of Singapore, Singapore
| | - Xin Ji
- Beijing Shanggong Medical Technology Co., Ltd., China
| | - Sanyuan Zhang
- College of Computer Science and Technology, Zhejiang University, Hangzhou, China
| | - Yaxin Shen
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China
| | - Ling Dai
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China
| | | | | | - Tânia Melo
- INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal
| | - Teresa Araújo
- INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal; FEUP - Faculty of Engineering of the University of Porto, Porto, Portugal
| | - Balazs Harangi
- University of Debrecen, Faculty of Informatics 4002 Debrecen, POB 400, Hungary
| | - Bin Sheng
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China
| | - Ruogu Fang
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, USA
| | | | - Andras Hajdu
- University of Debrecen, Faculty of Informatics 4002 Debrecen, POB 400, Hungary
| | - Yuanjie Zheng
- School of Information Science and Engineering, Shandong Normal University, China
| | - Ana Maria Mendonça
- INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal; FEUP - Faculty of Engineering of the University of Porto, Porto, Portugal
| | - Shaoting Zhang
- Department of Computer Science, University of North Carolina at Charlotte, USA
| | - Aurélio Campilho
- INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal; FEUP - Faculty of Engineering of the University of Porto, Porto, Portugal
| | - Bin Zheng
- School of Electrical and Computer Engineering, University of Oklahoma, USA
| | - Dinggang Shen
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, USA; Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, Republic of Korea
| | - Luca Giancardo
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, USA
| | | | - Fabrice Mériaudeau
- Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Malaysia; ImViA/IFTIM, Université de Bourgogne, Dijon, France
| |
Collapse
|
11
|
Muangnak N, Aimmanee P, Makhanov S. Automatic optic disk detection in retinal images using hybrid vessel phase portrait analysis. Med Biol Eng Comput 2017; 56:583-598. [PMID: 28836125 DOI: 10.1007/s11517-017-1705-z] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2016] [Accepted: 08/03/2017] [Indexed: 01/23/2023]
Abstract
We propose vessel vector-based phase portrait analysis (VVPPA) and a hybrid between VVPPA and a clustering method proposed earlier for automatic optic disk (OD) detection called the vessel transform (VT). The algorithms are based primarily on the location and direction of retinal blood vessels and work equally well on fine and poor quality images. To localize the OD, the direction vectors derived from the vessel network are constructed, and points of convergence of the resulting vector field are examined by phase portrait analysis. The hybrid method (HM) uses a set of rules acquired from the decision model to alternate the use of VVPPA and VT. To identify the OD contour, the scale space (SS) approach is integrated with VVPPA, HM, and the circular approximation (SSVVPPAC and SSHMC). We test the proposed combination against state-of-the-art OD detection methods. The results show that the proposed algorithms outperform the benchmark methods, especially on poor quality images. Specifically, the HM gets the highest accuracy of 98% for localization of the OD regardless of the image quality. Testing the segmentation routines SSVVPPAC and SSHMC against the conventional methods shows that SSHMC performs better than the existing methods, achieving the highest PPV of 71.81% and the highest sensitivity of 70.67% for poor quality images. Furthermore, the HM can supplement practically any segmentation model as long as it offers multiple OD candidates. In order to prove this claim, we test the efficiency of the HM in detecting retinal abnormalities in a real clinical setting. The images have been obtained by portable lens connected to a smart phone. In detecting the abnormalities related to diabetic retinopathy (DR), the algorithm provided 94.67 and 98.13% for true negatives and true positives, respectively.
Collapse
Affiliation(s)
- Nittaya Muangnak
- Sirindhorn International Institute of Technology, Thammasat University, 131 Moo 5, Tiwanont Road, Bangkadi, Muang, Pathum Thani, 12000, Thailand
| | - Pakinee Aimmanee
- Sirindhorn International Institute of Technology, Thammasat University, 131 Moo 5, Tiwanont Road, Bangkadi, Muang, Pathum Thani, 12000, Thailand.
| | - Stanislav Makhanov
- Sirindhorn International Institute of Technology, Thammasat University, 131 Moo 5, Tiwanont Road, Bangkadi, Muang, Pathum Thani, 12000, Thailand
| |
Collapse
|