A Novel Fuzzy-Based Thresholding Approach for Blood Vessel Segmentation from Fundus Image

Wahid, Farha Fatina; Raju, G; Joseph, Shijo M.; Swain, Debabrata; Das, Om Prakash; Acharya, Biswaranjan

doi:10.12720/jait.14.2.185-192

“…It is crucial to accurately identify different lesions across different phases despite variations in image quality and eye movement. Also, most of the methods presented in the Literature have not been tested in real patients (4,14,20,22,23,25,26). (28,29).…”

Section: Discussionmentioning

confidence: 99%

“…In case of vascular leakage and hemorrhage fading in the late phase of FFA images, the threshold is estimated by taking the mean of the maximum and minimum in the class with the smallest canter and the middle canter as per the distance matrix (24). The proposed method in retinal fundus image uses the combination of the Fuzzy C mean clustering and Contrast limited adaptive histogram equalization (CLAHE) based on three-level thresholding (25). We used this method after applying all quality improvement methods (HE, CLAHE, RMSHE, Proposed Method (CLAHE+RMSHE)).…”

Section: Fuzzy-based Segmentationmentioning

confidence: 99%

A high-accuracy segmentation Hybrid method for retinal blood vessel detection in Fluorescein Angiography images of real Diabetic Retinopathy patients

Zare,

Ramezanzadeh,

Shoeibi

et al. 2024

Preprint

0

View full text Add to dashboard Cite

This study aims to develop an advanced automatic method to enhance the accuracy of blood vessel segmentation in Fundus Fluorescein angiography FFA images of patients with real Diabetic retinopathy (DR) during both early and late phases. A prospective randomized study of 280 eyes of 87 DR patients at various stages was included in this study. our approach involved using four different image enhancement techniques (Histogram equalization (HE), CLAHE, RMSHE, Proposed method (CLAHE+RMSHE)) and for each enhancement except HE, four thresholding methods including the proposed method (Modified Active Contour(MAC)+ IsoData), C-mean Fuzzy, Isodata, and MAC + otsu thresholding that are commonly used in eye fundus images across different datasets. The effectiveness of segmentation was evaluated using three metrics: Dice (early: 0.84±0.05, late:0.84±0.03), Jaccard (early:0.73±0.06, late:0.74±0.05), and BF score (early:0.98±0.02, late:0.97±0.02). We found that the RMSHE method was more effective in the late phase, while the combined CLAHE+RMSHE method worked better in the early phase. The best segmentation results for both early and late phases were achieved using a blood vessel segmentation approach based on the MAC + IsoData thresholding.

show abstract

“…It is crucial to accurately identify different lesions across different phases despite variations in image quality and eye movement. Also, most of the methods presented in the Literature have not been tested in real patients (4,14,20,22,23,25,26). (28,29).…”

Section: Discussionmentioning

confidence: 99%

A High-Accuracy Segmentation Hybrid Method For Retinal Blood Vessel Detection In Fluorescein Angiography Images Of Real Diabetic Retinopathy Patients

Ramezanzadeh,

Shoeibi,

Shariati

et al. 2024

Preprint

0

View full text Add to dashboard Cite

This study aims to develop an advanced automatic method to enhance the accuracy of blood vessel segmentation in Fundus Fluorescein angiography FFA images of patients with real Diabetic retinopathy (DR) during both early and late phases. A prospective randomized study of 280 eyes of 87 DR patients at various stages was included in this study. our approach involved using four different image enhancement techniques (Histogram equalization (HE), CLAHE, RMSHE, Proposed method (CLAHE+RMSHE)) and for each enhancement except HE, four thresholding methods including the proposed method (Modified Active Contour(MAC)+ IsoData), C-mean Fuzzy, Isodata, and MAC + otsu thresholding that are commonly used in eye fundus images across different datasets. The effectiveness of segmentation was evaluated using three metrics: Dice (early: 0.84±0.05, late:0.84±0.03), Jaccard (early:0.73±0.06, late:0.74±0.05), and BF score (early:0.98±0.02, late:0.97±0.02). We found that the RMSHE method was more effective in the late phase, while the combined CLAHE+RMSHE method worked better in the early phase. The best segmentation results for both early and late phases were achieved using a blood vessel segmentation approach based on the MAC + IsoData thresholding.

show abstract

“…In case of vascular leakage and hemorrhage fading in the late phase of FFA images, the threshold is estimated by taking the mean of the maximum and minimum in the class with the smallest canter and the middle canter as per the distance matrix (24). The proposed method in retinal fundus image uses the combination of the Fuzzy C mean clustering and Contrast limited adaptive histogram equalization (CLAHE) based on threelevel thresholding (25). We used this method after applying all quality improvement methods (HE, CLAHE, RMSHE, Proposed Method (CLAHE+RMSHE)).…”

Section: Fuzzy-based Segmentationmentioning

confidence: 99%

“…It is crucial to accurately identify different lesions across different phases despite variations in image quality and eye movement. Also, most of the methods presented in the Literature have not been tested in real patients(4,14,20,22,23,25,26).By comparing early and late phases imaging sequences, ophthalmologist can track lesions such as microaneurysms and leaks to determine appropriate treatments. The registration of these phases, image quality enhancement, and extraction of vascular features in diagnosis and appropriate treatment are very important.…”

mentioning

confidence: 99%

A High-Accuracy Segmentation Hybrid Method For Retinal Blood Vessel Detection In Fluorescein Angiography Images Of Real Diabetic Retinopathy Patients

Ramezanzadeh,

Shoeibi,

Shariati

et al. 2024

Preprint

0

View full text Add to dashboard Cite

This study aims to develop an advanced automatic method to enhance the accuracy of blood vessel segmentation in Fundus Fluorescein angiography FFA images of patients with real Diabetic retinopathy (DR) during both early and late phases. A prospective randomized study of 280 eyes of 87 DR patients at various stages was included in this study. our approach involved using four different image enhancement techniques (Histogram equalization (HE), CLAHE, RMSHE, Proposed method (CLAHE+RMSHE)) and for each enhancement except HE, four thresholding methods including the proposed method (Modified Active Contour(MAC)+ IsoData), C-mean Fuzzy, Isodata, and MAC + otsu thresholding that are commonly used in eye fundus images across different datasets. The effectiveness of segmentation was evaluated using three metrics: Dice (early: 0.84±0.05, late:0.84±0.03), Jaccard (early:0.73±0.06, late:0.74±0.05), and BF score (early:0.98±0.02, late:0.97±0.02). We found that the RMSHE method was more effective in the late phase, while the combined CLAHE+RMSHE method worked better in the early phase. The best segmentation results for both early and late phases were achieved using a blood vessel segmentation approach based on the MAC + IsoData thresholding.

show abstract

A Novel Fuzzy-Based Thresholding Approach for Blood Vessel Segmentation from Fundus Image

Cited by 24 publications

References 0 publications

A high-accuracy segmentation Hybrid method for retinal blood vessel detection in Fluorescein Angiography images of real Diabetic Retinopathy patients

A high-accuracy segmentation Hybrid method for retinal blood vessel detection in Fluorescein Angiography images of real Diabetic Retinopathy patients

A High-Accuracy Segmentation Hybrid Method For Retinal Blood Vessel Detection In Fluorescein Angiography Images Of Real Diabetic Retinopathy Patients

A High-Accuracy Segmentation Hybrid Method For Retinal Blood Vessel Detection In Fluorescein Angiography Images Of Real Diabetic Retinopathy Patients

Contact Info

Product

Resources

About