1
|
Yao HY, Tseng KW, Nguyen HT, Kuo CT, Wang HC. Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage. J Clin Med 2020; 9:jcm9061613. [PMID: 32466524 PMCID: PMC7356238 DOI: 10.3390/jcm9061613] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2020] [Revised: 05/18/2020] [Accepted: 05/25/2020] [Indexed: 12/17/2022] Open
Abstract
A methodology that applies hyperspectral imaging (HSI) on ophthalmoscope images to identify diabetic retinopathy (DR) stage is demonstrated. First, an algorithm for HSI image analysis is applied to the average reflectance spectra of simulated arteries and veins in ophthalmoscope images. Second, the average simulated spectra are categorized by using a principal component analysis (PCA) score plot. Third, Beer-Lambert law is applied to calculate vessel oxygen saturation in the ophthalmoscope images, and oxygenation maps are obtained. The average reflectance spectra and PCA results indicate that average reflectance changes with the deterioration of DR. The G-channel gradually decreases because of vascular disease, whereas the R-channel gradually increases with oxygen saturation in the vessels. As DR deteriorates, the oxygen utilization of retinal tissues gradually decreases, and thus oxygen saturation in the veins gradually increases. The sensitivity of diagnosis is based on the severity of retinopathy due to diabetes. Normal, background DR (BDR), pre-proliferative DR (PPDR), and proliferative DR (PDR) are arranged in order of 90.00%, 81.13%, 87.75%, and 93.75%, respectively; the accuracy is 90%, 86%, 86%, 90%, respectively. The F1-scores are 90% (Normal), 83.49% (BDR), 86.86% (PPDR), and 91.83% (PDR), and the accuracy rates are 95%, 91.5%, 93.5%, and 96%, respectively.
Collapse
Affiliation(s)
- Hsin-Yu Yao
- Department of Ophthalmology, Kaohsiung Armed Forced General Hospital, Kaohsiung City 80284, Taiwan;
| | - Kuang-Wen Tseng
- Department of Medicine, Mackay Medical College, 46, Sec. 3, Zhongzheng Rd., Sanzhi Dist., New Taipei 25245, Taiwan;
| | - Hong-Thai Nguyen
- Department of Mechanical Engineering and Center for Innovative Research on Aging Society (CIRAS), National Chung Cheng University, 168, University Rd., Min Hsiung, Chia Yi 62102, Taiwan;
| | - Chie-Tong Kuo
- Department of Optometry and Innovation Incubation Center, Shu-Zen Junior College of Medicine and Management, Kaohsiung 821, Taiwan;
| | - Hsiang-Chen Wang
- Department of Mechanical Engineering and Center for Innovative Research on Aging Society (CIRAS), National Chung Cheng University, 168, University Rd., Min Hsiung, Chia Yi 62102, Taiwan;
- Correspondence:
| |
Collapse
|
2
|
Khan KB, Khaliq AA, Jalil A, Iftikhar MA, Ullah N, Aziz MW, Ullah K, Shahid M. A review of retinal blood vessels extraction techniques: challenges, taxonomy, and future trends. Pattern Anal Appl 2018. [DOI: 10.1007/s10044-018-0754-8] [Citation(s) in RCA: 39] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
|
3
|
Zhao Y, Zheng Y, Liu Y, Zhao Y, Luo L, Yang S, Na T, Wang Y, Liu J. Automatic 2-D/3-D Vessel Enhancement in Multiple Modality Images Using a Weighted Symmetry Filter. IEEE TRANSACTIONS ON MEDICAL IMAGING 2018; 37:438-450. [PMID: 28952938 DOI: 10.1109/tmi.2017.2756073] [Citation(s) in RCA: 37] [Impact Index Per Article: 6.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
Automated detection of vascular structures is of great importance in understanding the mechanism, diagnosis, and treatment of many vascular pathologies. However, automatic vascular detection continues to be an open issue because of difficulties posed by multiple factors, such as poor contrast, inhomogeneous backgrounds, anatomical variations, and the presence of noise during image acquisition. In this paper, we propose a novel 2-D/3-D symmetry filter to tackle these challenging issues for enhancing vessels from different imaging modalities. The proposed filter not only considers local phase features by using a quadrature filter to distinguish between lines and edges, but also uses the weighted geometric mean of the blurred and shifted responses of the quadrature filter, which allows more tolerance of vessels with irregular appearance. As a result, this filter shows a strong response to the vascular features under typical imaging conditions. Results based on eight publicly available datasets (six 2-D data sets, one 3-D data set, and one 3-D synthetic data set) demonstrate its superior performance to other state-of-the-art methods.
Collapse
|
4
|
Zhao Y, Zhao J, Yang J, Liu Y, Zhao Y, Zheng Y, Xia L, Wang Y. Saliency driven vasculature segmentation with infinite perimeter active contour model. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2016.07.077] [Citation(s) in RCA: 44] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
5
|
Rogge H, Artelt N, Endlich N, Endlich K. Automated segmentation and quantification of actin stress fibres undergoing experimentally induced changes. J Microsc 2017; 268:129-140. [PMID: 28806482 DOI: 10.1111/jmi.12593] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2016] [Accepted: 05/23/2017] [Indexed: 12/21/2022]
Abstract
The actin cytoskeleton is a main component of cells and it is crucially involved in many physiological processes, e.g. cell motility. Changes in the actin organization can be effected by diseases or vice versa. Due to the nonuniform pattern, it is difficult to quantify reasonable features of the actin cytoskeleton for a significantly high cell number. Here, we present an approach capable to fully segment and analyse the actin cytoskeleton of 2D fluorescence microscopic images with a special focus on stress fibres. The extracted feature data include length, width, orientation and intensity distributions of all traced stress fibres. Our approach combines morphological image processing techniques and a trace algorithm in an iterative manner, classifying the segmentation result with respect to the width of the stress fibres and in nonfibre-like actin. This approach enables us to capture experimentally induced processes like the condensation or the collapse of the actin cytoskeleton. We successfully applied the algorithm to F-actin images of cells that were treated with the actin polymerization inhibitor latrunculin A. Furthermore, we verified the robustness of our algorithm by a sensitivity analysis of the parameters, and we benchmarked our algorithm against established methods. In summary, we present a new approach to segment actin stress fibres over time to monitor condensation or collapse processes.
Collapse
Affiliation(s)
- H Rogge
- Department of Anatomy and Cell Biology, University Medicine Greifswald, Greifswald, Germany
| | - N Artelt
- Department of Anatomy and Cell Biology, University Medicine Greifswald, Greifswald, Germany
| | - N Endlich
- Department of Anatomy and Cell Biology, University Medicine Greifswald, Greifswald, Germany
| | - K Endlich
- Department of Anatomy and Cell Biology, University Medicine Greifswald, Greifswald, Germany
| |
Collapse
|
6
|
Rodrigues LC, Marengoni M. Segmentation of optic disc and blood vessels in retinal images using wavelets, mathematical morphology and Hessian-based multi-scale filtering. Biomed Signal Process Control 2017. [DOI: 10.1016/j.bspc.2017.03.014] [Citation(s) in RCA: 67] [Impact Index Per Article: 9.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
7
|
Hashimoto R, Uchiyama Y, Uchimura K, Koutaki G, Inoue T. Morphology filter bank for extracting nodular and linear patterns in medical images. Int J Comput Assist Radiol Surg 2016; 12:617-625. [PMID: 27858248 DOI: 10.1007/s11548-016-1503-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2016] [Accepted: 11/07/2016] [Indexed: 10/20/2022]
Abstract
PURPOSE Using image processing to extract nodular or linear shadows is a key technique of computer-aided diagnosis schemes. This study proposes a new method for extracting nodular and linear patterns of various sizes in medical images. METHODS We have developed a morphology filter bank that creates multiresolution representations of an image. Analysis bank of this filter bank produces nodular and linear patterns at each resolution level. Synthesis bank can then be used to perfectly reconstruct the original image from these decomposed patterns. RESULTS Our proposed method shows better performance based on a quantitative evaluation using a synthesized image compared with a conventional method based on a Hessian matrix, often used to enhance nodular and linear patterns. In addition, experiments show that our method can be applied to the followings: (1) microcalcifications of various sizes in mammograms can be extracted, (2) blood vessels of various sizes in retinal fundus images can be extracted, and (3) thoracic CT images can be reconstructed while removing normal vessels. CONCLUSIONS Our proposed method is useful for extracting nodular and linear shadows or removing normal structures in medical images.
Collapse
Affiliation(s)
- Ryutaro Hashimoto
- Graduate School of Science and Technology, Kumamoto University, 2-39-1, Kurokami, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8555, Japan
| | - Yoshikazu Uchiyama
- Department of Medical Physics, Faculty of Life Science, Kumamoto University, 4-24-1 Kuhonji, Kumamoto, Kumamoto, 862-0976, Japan.
| | - Keiichi Uchimura
- Graduate School of Science and Technology, Kumamoto University, 2-39-1, Kurokami, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8555, Japan
| | - Gou Koutaki
- Graduate School of Science and Technology, Kumamoto University, 2-39-1, Kurokami, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8555, Japan
| | - Tomoki Inoue
- Graduate School of Science and Technology, Kumamoto University, 2-39-1, Kurokami, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8555, Japan
| |
Collapse
|
8
|
Frucci M, Riccio D, Sanniti di Baja G, Serino L. Severe: Segmenting vessels in retina images. Pattern Recognit Lett 2016. [DOI: 10.1016/j.patrec.2015.07.002] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
9
|
A fully automatic method for segmenting retinal artery walls in adaptive optics images. Pattern Recognit Lett 2016. [DOI: 10.1016/j.patrec.2015.10.011] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
10
|
Yin B, Li H, Sheng B, Hou X, Chen Y, Wu W, Li P, Shen R, Bao Y, Jia W. Vessel extraction from non-fluorescein fundus images using orientation-aware detector. Med Image Anal 2015; 26:232-42. [PMID: 26474120 DOI: 10.1016/j.media.2015.09.002] [Citation(s) in RCA: 58] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2014] [Revised: 09/08/2015] [Accepted: 09/14/2015] [Indexed: 11/18/2022]
Abstract
The automatic extraction of blood vessels in non-fluorescein eye fundus images is a tough task in applications such as diabetic retinopathy screening. However, vessel shapes have complex variations, and accurate modeling of retinal vascular structures is challenging. We have therefore developed a new approach to accurately extract blood vessels in non-fluorescein fundus images using an orientation-aware detector (OAD). The detector was designed according to the intrinsic property of vessels being locally oriented and having linearly elongated structures. We employ the OAD to extract vessel shapes with no assumptions on parametric orientations of vessel shapes. The orientations of vessels can be efficiently modeled by the energy distribution of Fourier transformation. Accordingly, both wide and thin vessels can be extracted with two-scale segmentation in which line operators are applied in large scale and the Gabor filter bank is applied in small scale. A post-processing technique, based on the path opening operation, is applied to eliminate false responses to nonvascular areas, such as retinal structures (optic disc and macula) and pathologies (exudates, hemorrhages,and microaneurysms). This makes the detector robust and structure-aware. By achieving a competitive CAL measurement of 80.82% for the DRIVE database and 68.94% for the STARE, the experimental results demonstrated that the OAD approach outperforms existing segmentation methods. Furthermore, the proposed approach effectively works with non-fluorescein fundus images and proves highly accurate and robust in complicated regions such as the central reflex, close vessels, and crossover points, despite a high level of illumination noise in the original data.
Collapse
Affiliation(s)
- Benjun Yin
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Huating Li
- Department of Endocrinology and Metabolism, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai Clinical Center for Diabetes, Shanghai Diabetes Institute, Shanghai Key Laboratory of Diabetes Mellitus, Shanghai Key Clinical Center for Metabolic Disease, Shanghai 200240, China
| | - Bin Sheng
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
| | - Xuhong Hou
- Department of Endocrinology and Metabolism, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai Clinical Center for Diabetes, Shanghai Diabetes Institute, Shanghai Key Laboratory of Diabetes Mellitus, Shanghai Key Clinical Center for Metabolic Disease, Shanghai 200240, China
| | - Yan Chen
- Department of Ophthalmology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai 200240, China
| | - Wen Wu
- Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macao
| | - Ping Li
- Department of Mathematics and Information Technology, The Hong Kong Institute of Education, Hong Kong
| | - Ruimin Shen
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Yuqian Bao
- Department of Endocrinology and Metabolism, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai Clinical Center for Diabetes, Shanghai Diabetes Institute, Shanghai Key Laboratory of Diabetes Mellitus, Shanghai Key Clinical Center for Metabolic Disease, Shanghai 200240, China
| | - Weiping Jia
- Department of Endocrinology and Metabolism, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai Clinical Center for Diabetes, Shanghai Diabetes Institute, Shanghai Key Laboratory of Diabetes Mellitus, Shanghai Key Clinical Center for Metabolic Disease, Shanghai 200240, China
| |
Collapse
|
11
|
Zhao Y, Rada L, Chen K, Harding SP, Zheng Y. Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal Images. IEEE TRANSACTIONS ON MEDICAL IMAGING 2015; 34:1797-807. [PMID: 25769147 DOI: 10.1109/tmi.2015.2409024] [Citation(s) in RCA: 151] [Impact Index Per Article: 16.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/15/2023]
Abstract
Automated detection of blood vessel structures is becoming of crucial interest for better management of vascular disease. In this paper, we propose a new infinite active contour model that uses hybrid region information of the image to approach this problem. More specifically, an infinite perimeter regularizer, provided by using L(2) Lebesgue measure of the γ -neighborhood of boundaries, allows for better detection of small oscillatory (branching) structures than the traditional models based on the length of a feature's boundaries (i.e., H(1) Hausdorff measure). Moreover, for better general segmentation performance, the proposed model takes the advantage of using different types of region information, such as the combination of intensity information and local phase based enhancement map. The local phase based enhancement map is used for its superiority in preserving vessel edges while the given image intensity information will guarantee a correct feature's segmentation. We evaluate the performance of the proposed model by applying it to three public retinal image datasets (two datasets of color fundus photography and one fluorescein angiography dataset). The proposed model outperforms its competitors when compared with other widely used unsupervised and supervised methods. For example, the sensitivity (0.742), specificity (0.982) and accuracy (0.954) achieved on the DRIVE dataset are very close to those of the second observer's annotations.
Collapse
|
12
|
Barbalata C, Mattos LS. Laryngeal Tumor Detection and Classification in Endoscopic Video. IEEE J Biomed Health Inform 2014; 20:322-32. [PMID: 25438330 DOI: 10.1109/jbhi.2014.2374975] [Citation(s) in RCA: 27] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
The development of the narrow-band imaging (NBI) has been increasing the interest of medical specialists in the study of laryngeal microvascular network to establish diagnosis without biopsy and pathological examination. A possible solution to this challenging problem is presented in this paper, which proposes an automatic method based on anisotropic filtering and matched filter to extract the lesion area and segment blood vessels. Lesion classification is then performed based on a statistical analysis of the blood vessels' characteristics, such as thickness, tortuosity, and density. Here, the presented algorithm is applied to 50 NBI endoscopic images of laryngeal diseases and the segmentation and classification accuracies are investigated. The experimental results show the proposed algorithm provides reliable results, reaching an overall classification accuracy rating of 84.3%. This is a highly motivating preliminary result that proves the feasibility of the new method and supports the investment in further research and development to translate this study into clinical practice. Furthermore, to our best knowledge, this is the first time image processing is used to automatically classify laryngeal tumors in endoscopic videos based on tumor vascularization characteristics. Therefore, the introduced system represents an innovation in biomedical and health informatics.
Collapse
|
13
|
Mookiah MRK, Acharya UR, Chua CK, Lim CM, Ng EYK, Laude A. Computer-aided diagnosis of diabetic retinopathy: a review. Comput Biol Med 2013; 43:2136-55. [PMID: 24290931 DOI: 10.1016/j.compbiomed.2013.10.007] [Citation(s) in RCA: 165] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2013] [Revised: 09/27/2013] [Accepted: 10/04/2013] [Indexed: 11/29/2022]
Abstract
Diabetes mellitus may cause alterations in the retinal microvasculature leading to diabetic retinopathy. Unchecked, advanced diabetic retinopathy may lead to blindness. It can be tedious and time consuming to decipher subtle morphological changes in optic disk, microaneurysms, hemorrhage, blood vessels, macula, and exudates through manual inspection of fundus images. A computer aided diagnosis system can significantly reduce the burden on the ophthalmologists and may alleviate the inter and intra observer variability. This review discusses the available methods of various retinal feature extractions and automated analysis.
Collapse
|
14
|
ROSATI SAMANTA, BALESTRA GABRIELLA, MOLINARI FILIPPO. FEATURE SELECTION APPLIED TO THE TIME-FREQUENCY REPRESENTATION OF MUSCLE NEAR-INFRARED SPECTROSCOPY (NIRS) SIGNALS: CHARACTERIZATION OF DIABETIC OXYGENATION PATTERNS. J MECH MED BIOL 2012. [DOI: 10.1142/s0219519412400131] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Diabetic patients might present peripheral microcirculation impairment and might benefit from physical training. Thirty-nine diabetic patients underwent the monitoring of the tibialis anterior muscle oxygenation during a series of voluntary ankle flexo-extensions by near-infrared spectroscopy (NIRS). NIRS signals were acquired before and after training protocols. Sixteen control subjects were tested with the same protocol. Time-frequency distributions of the Cohen's class were used to process the NIRS signals relative to the concentration changes of oxygenated and reduced hemoglobin. A total of 24 variables were measured for each subject and the most discriminative were selected by using four feature selection algorithms: QuickReduct, Genetic Rough-Set Attribute Reduction, Ant Rough-Set Attribute Reduction, and traditional ANOVA. Artificial neural networks were used to validate the discriminative power of the selected features. Results showed that different algorithms extracted different sets of variables, but all the combinations were discriminative. The best classification accuracy was about 70%. The oxygenation variables were selected when comparing controls to diabetic patients or diabetic patients before and after training. This preliminary study showed the importance of feature selection techniques in NIRS assessment of diabetic peripheral vascular impairment.
Collapse
Affiliation(s)
- SAMANTA ROSATI
- Biolab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, 10129, Italy
| | - GABRIELLA BALESTRA
- Biolab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, 10129, Italy
| | - FILIPPO MOLINARI
- Biolab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, 10129, Italy
| |
Collapse
|