Enhancement of blood vessels in digital fundus photographs via the application of multiscale line operators

Farnell, Damian J. J.; Hatfield, F. N.; Knox, Paul C.; Reakes, M.; Spencer, Stephan M.; Parry, D. G.; Harding, Simon

doi:10.1016/j.jfranklin.2008.04.009

Cited by 104 publications

(43 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Points on the evaluated centerline are marked as T P M ov if there is at least one point on the GS at a distance less than the radius, otherwise they are marked as F P ov . [68] 40 CFP ARIA [137] 143 CFP CHASE [138] 28 CFP HRF [139] 45 CFP IMAGERET [140] 219 The overlap until first error (OF ) is the ratio of the number of T P R ov before the first error (T P R of ) and the overall number of reference points (N R):…”

Section: Evaluation Metricsmentioning

confidence: 99%

Blood vessel segmentation algorithms — Review of methods, datasets and evaluation metrics

Moccia

Momi

Hadji

et al. 2018

Computer Methods and Programs in Biomedicine

471

263

View full text Add to dashboard Cite

Abstract-Background: Blood vessel segmentation is a topic of high interest in medical image analysis since the analysis of vessels is crucial for diagnosis, treatment planning and execution, and evaluation of clinical outcomes in different fields, including laryngology, neurosurgery and ophthalmology. Automatic or semiautomatic vessel segmentation can support clinicians in performing these tasks. Different medical imaging techniques are currently used in clinical practice and an appropriate choice of the segmentation algorithm is mandatory to deal with the adopted imaging technique characteristics (e.g. resolution, noise and vessel contrast).Objective: This paper aims at reviewing the most recent and innovative blood vessel segmentation algorithms. Among the algorithms and approaches considered, we deeply investigated the most novel blood vessel segmentation including machine learning, deformable model, and tracking-based approaches.Method: This paper analyzes more than 100 articles focused on blood vessel segmentation methods. For each analyzed approach, summary tables are presented reporting imaging technique used, anatomical region and performance measures employed. Benefits and disadvantages of each method are highlighted.Discussion: Despite the constant progress and efforts addressed in the field, several issues still need to be overcome. A relevant limitation consists in the segmentation of pathological vessels. Unfortunately, not consistent research effort has been addressed to this issue yet. Research is needed since some of the main assumptions made for healthy vessels (such as linearity and circular cross-section) do not hold in pathological tissues, which on the other hand require new vessel model formulations. Moreover, image intensity drops, noise and low contrast still represent an important obstacle for the achievement of a high-quality enhancement. This is particularly true for optical imaging, where the image quality is usually lower in terms of noise and contrast with respect to magnetic resonance and computer tomography angiography. Conclusion:No single segmentation approach is suitable for all the different anatomical region or imaging modalities, thus the primary goal of this review was to provide an up to date source of information about the state of the art of the vessel segmentation algorithms so that the most suitable methods can be chosen according to the specific task.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

Blood vessel segmentation algorithms — Review of methods, datasets and evaluation metrics

Moccia

Momi

Hadji

et al. 2018

Computer Methods and Programs in Biomedicine

471

263

View full text Add to dashboard Cite

show abstract

“…The dataset used was composed of images from 4 different databases which included some of the categories under study: ARIA [23]- [25], STARE [26]- [28], E-OPHTHA [29], [30] and DIAGNOS [15]. ARIA database is formed by 143 colour fundus images (768 × 576 pixels), which are organised into three classes: age-related macular degeneration (AMD) subjects (n=23), healthy control-group subjects (n=61), and diabetic subjects (n=59).…”

Section: A Materialsmentioning

confidence: 99%

Retinal Disease Screening Through Local Binary Patterns

Morales

Engan

Naranjo

et al. 2017

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Morales, S.; Engan, K.; Naranjo Ornedo, V.; Colomer, A. (2015). Abstract-This work investigates discrimination capabilities in the texture of fundus images to differentiate between pathological and healthy images. For this purpose, the performance of Local Binary Patterns (LBP) as a texture descriptor for retinal images has been explored and compared with other descriptors such as LBP filtering (LBPF) and local phase quantization (LPQ). The goal is to distinguish between diabetic retinopathy (DR), agerelated macular degeneration (AMD) and normal fundus images analysing the texture of the retina background and avoiding a previous lesion segmentation stage. Five experiments (separating DR from normal, AMD from normal, pathological from normal, DR from AMD and the three different classes) were designed and validated with the proposed procedure obtaining promising results. For each experiment, several classifiers were tested. An average sensitivity and specificity higher than 0.86 in all the cases and almost of 1 and 0.99, respectively, for AMD detection were achieved. These results suggest that the method presented in this paper is a robust algorithm for describing retina texture and can be useful in a diagnosis aid system for retinal disease screening.

show abstract

“…Cornforth et al dan D.J.J. Farnell [18,19]. Gaussian lowpass filter [20] yang serupa dengan gaussian kernel [14].…”

Section: Penyeragaman Tingkat Pencahayaanunclassified

“…Median filter dapat digunakan sama halnya mean filter, yakni untuk mereduksi noise seperti yang tertera pada penelitian A.M. Aibinu et al dan D.J.J. Farnell [15,19]. Selain itu median filter juga dapat digunakan untuk mengestimasi background dari citra fundus retina [21].…”

Section: Penyeragaman Tingkat Pencahayaanunclassified

See 1 more Smart Citation

Review Algoritma Segmentasi Pembuluh Darah Pada Citra Fundus Retina Mata Untuk Membantu Diagnosis Diabetic Retinopathy

Putra¹,

Tjandrasa²,

Suciati³

2012

JUTI

View full text Add to dashboard Cite

ABSTRAKKata Kunci: diabetic retinopathy, citra fundus retina, pembuluh darah. PENDAHULUANDiabetic Retinopathy merupakan salah satu penyakit pada retina mata yang disebabkan oleh diabetes. Penyakit ini menyebabkan keabnormalan pada retina, dan dalam kondisi terparah akan menyebabkan kebutaan. Beberapa faktor yang menyebabkan diabetic retinopathy antara lain durasi terkena penyakit diabetes, umur, tingkat tekanan darah, masa puber, kehamilan dan lain-lain [1].Durasi waktu dari penderita diabetes adalah faktor resiko terpenting dari penyakit ini. Dalam pasien yang didiagnosa mengidap penyakit diabetes sebelum usia 30 tahun, peluang munculnya diabetic retinopathy sekitar 50% setelah 10 tahun dan 90% setelah 30 tahun. Diabetic retinopathy jarang berkembang setelah 5 tahun dari serangan diabetes atau sebelum masa puber. Sekitar 5% dari diabetes tipe 2 juga mengidap diabetic retinopathy [2]. Gambar 1 merupakan pembuluh darah yang tampak dalam citra fundus retina mata.. Gambar 2 merupakan struktur anatomi dari retina mata. Dari Gambar 2 dapat terlihat, bagian-bagian dari retina mata (pembuluh darah, optic disc, dan macula) termasuk gejala-gejala dari penyakit diabetic retinopathy (exudates dan hemorrhage).Pembuluh darah merupakan salah satu faktor penting dalam pendeteksian penyakit diabetic retinopathy. Pada dasarnya kelainan pada retina mata yang disebabkan oleh penyakit diabetic retinopathy merupakan kelainan-kelainan yang ada pada pembuluh darah retina mata [3,4]. Salah satu contoh gejala diabetic retinopathy yang dapat dilihat dari pembuluh darah antara lain munculnya microaneurysm dan hemorrhage yang disebabkan adanya tonjolan yang ada pada pembuluh darah dalam retina mata [5]. Oleh karena itu diperlukannya suatu metode untuk segmentasi pembuluh darah yang tepat dan baik agar tonjolan yang ada pada pembuluh darah dalam retina dapat terdeteksi secara jelas.Berbagai penelitian mengenai segmentasi pembuluh darah telah dilakukan oleh beberapa peneliti dalam beberapa tahun terakhir. Beberapa makalah yang digunakan sebagai acuan dalam penelitian ini terlihat pada Gambar 3. Dari Gambar 3 terlihat bahwa makalah yang terbanyak dipakai dalam penelitian ini adalah makalah yang dipublikasikan pada tahun 2012. Makalah ini berjumlah 12, merupakan 23% dari jumlah makalah yang dipakai dalam penelitian ini. Hasil penelitian mereka dapat disimpulkan bahwa pada dasarnya metode untuk segmentasi pembuluh darah pada citra fundus retina mata terdiri dari 3 tahap, yakni: preprocessing, segmentasi dan postprocessing.Makalah ini disusun sebagai berikut. Pada bagian pertama dijelaskan mengenai segmentasi pembuluh darah pada diabetic retinopathy. Pada bagian kedua dijelaskan mengenai preprocessing yang digunakan dalam algoritma segmentasi pembuluh darah. Pada bagian ketiga dijelaskan mengenai proses segmentasi yang digunakan. Proses segmentasi ini terbagi menjadi tiga, yakni image based, pattern recognition based dan vessel tracking/tracing. Pada bagian keempat dijelaskan

show abstract

Enhancement of blood vessels in digital fundus photographs via the application of multiscale line operators

Cited by 104 publications

References 33 publications

Blood vessel segmentation algorithms — Review of methods, datasets and evaluation metrics

Blood vessel segmentation algorithms — Review of methods, datasets and evaluation metrics

Retinal Disease Screening Through Local Binary Patterns

Review Algoritma Segmentasi Pembuluh Darah Pada Citra Fundus Retina Mata Untuk Membantu Diagnosis Diabetic Retinopathy

Contact Info

Product

Resources

About