Vessel extraction techniques and algorithms: a survey

Kirbas, Cemil; Quek, Francis

doi:10.1109/bibe.2003.1188957

Cited by 113 publications

(51 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Daha sonra eşikleme yöntemiyle damar ağacı yapısı ortaya çıkartılmıştır [9]. Ouian ve arkadaşları ise çalışmalarında [10] damar ağacının çıkarımı için morfolojik işleme tekniklerini kullanmışlardır. Öncelikle Top-Hat işlemi ile damarın ince ve kalın bölgeleri belirlenmiş daha sonra yarı eşikleme işlemi kullanılmıştır.…”

Section: Introductionunclassified

Koroner Arterlerin Bölütlenmesi Temelli Bir Karar Destek Sistemi

Selçuk¹,

Tekinalp²,

Alkan³

2016

KSU J. Eng. Sci.

View full text Add to dashboard Cite

ÖZET: Kalbi besleyen koroner arterlerin anatomisinin bilinmesi kalp hastalıklarının tanısında büyük önem arz etmektedir. Koroner arterlerden sağ koroner arter (RCA), sol ana koroner arter (LMCA), sol ön inen arter (LAD) ve sirkumflex arter (Cx) veya alt dallardaki arterlerden birinde meydana gelebilecek bir tıkanmanın büyüklüğü tedavi yöntemi için önem arz etmektedir. Yapılan çalışmada koroner arterlerin bölütlenmesi temelli bir tanı destek sistemi oluşturulmuştur. Bu amaçla, kalp anjiyografi görüntülerine sayısal görüntü işleme teknikleri uygulanarak koroner arterlerde meydana gelen daralmanın yüzdesinin belirlenmesine yönelik bir yazılım geliştirilmiştir. Çalışma uzman kardiyolog gözetiminde gerçekleştirilmiş olup yazılımda elde edilen sonuçlar uzman doktorun elde ettiği sonuçlarla karşılaştırılmıştır. Beş görüntü için %5 ile %12 arasında geri kalanlar için ise %1 ile %5 arasında bir darlık yüzdeleri arasında farkı olduğu gözlemlenmiştir. Çalışmanın bölütleme başarımı ise ZSI (zijdenbos similarity index) başarım belirleme indeksine göre tespit edilmiştir. Elde edilen ZSI değerleri, literatürde oldukça başarılı sayılabilecek (%78-%91 arasında) değerlerdedir. Elde edilen bölütleme sonuçları, önerilen sistemin klinik ve araştırma çalışmalarında tanı destek aracı olarak kullanılabileceğini göstermiştir. Anahtar Kelimeler: Koroner arter, Görüntü işleme, AnjiyoplastiThe Segmentation of the Coronary Arteries Based Decision Support System ABSTRACT: The knowledge of the anatomy of the coronary arteries that feed the heart is of great importance in the diagnosis of heart diseases. Size of a blockage that can occur in right coronary artery (RCA), left main coronary artery (LMCA), left anterior descending artery (LAD) and circumflex artery (Cx) or the one of the arteries in the lower branches is very important for the treatment. In this study, coronary arteries segmentation based diagnostic support system was proposed. For this purpose, a software has been developed for determining the percentage of the contraction occurring in coronary arteries by applying digital image processing techniques to cardiac angiography images. The study has been carried out in the expert supervision of cardiologist and the obtained coronary arteries segmentation results were compared with the manually segmented by the cardiologist. The vascular stenosis ratio differences were observed between %5 to %12 for five images and 1% to 5% for the rest of the data. The segmentation succes of the study was determined by using ZSI (zijdenbos similarity index). The resulting ZSI values (between %78-%91) were between %78 and %91 that can be considered as a successful segmentation in the literature. Obtained segmentation results showed that the proposed system can be used as a diagnostic support tool in clinical and research studies.

show abstract

Section: Introductionunclassified

Koroner Arterlerin Bölütlenmesi Temelli Bir Karar Destek Sistemi

Selçuk¹,

Tekinalp²,

Alkan³

2016

KSU J. Eng. Sci.

View full text Add to dashboard Cite

show abstract

“…the likelihood that a point sits along the centerline of a tubular structure [5,12,17]. Matched filters [1,28], Hessian and Oriented Flux functionals [7,13,14,22], and classification scores derived from steerable filter responses [8,11] have all been used for this purpose.…”

Section: Related Workmentioning

confidence: 99%

Reconstructing Evolving Tree Structures in Time Lapse Sequences

Głowacki

Pinheiro

Türetken

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We propose an approach to reconstructing tree structures that evolve over time in 2D images and 3D image stacks such as neuronal axons or plant branches. Instead of reconstructing structures in each image independently, we do so for all images simultaneously to take advantage of temporal-consistency constraints.We show that this problem can be formulated as a Quadratic Mixed Integer Program and solved efficiently. The outcome of our approach is a framework that provides substantial improvements in reconstructions over traditional single time-instance formulations. Furthermore, an added benefit of our approach is the ability to automatically detect places where significant changes have occurred over time, which is challenging when considering large amounts of data.

show abstract

“…Other studies have employed centerline tracing methods and principal curves [19,20]. The reader may refer to [21] for more related studies in the literature.…”

Section: Introductionmentioning

confidence: 99%

Structure-based level set method for automatic retinal vasculature segmentation

et al. 2014

View full text Add to dashboard Cite

Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection methodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is proposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by utilizing all image channels, generating more efficient results compared to methods utilizing only one (green) channel. A structure-based level set method employing a modified phase map is introduced to obtain accurate skeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the level sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level contour regularization term which is more appropriate than the ones introduced by other methods for vasculature structures. We conducted the experiments on our own dataset, as well as two publicly available datasets. The results show that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art supervised/unsupervised segmentation techniques.

show abstract

Vessel extraction techniques and algorithms: a survey

Cited by 113 publications

References 0 publications

Koroner Arterlerin Bölütlenmesi Temelli Bir Karar Destek Sistemi

Koroner Arterlerin Bölütlenmesi Temelli Bir Karar Destek Sistemi

Reconstructing Evolving Tree Structures in Time Lapse Sequences

Structure-based level set method for automatic retinal vasculature segmentation

Contact Info

Product

Resources

About