Wyniki wyszukiwania - BazTech

1

Retinal vasculature segmentation and measurement framework for color fundus and SLO images

Pachade Samiksha, Porwal Prasanna, Kokare Manesh, Giancardo Luca, Meriaudeau Fabrice

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

865--900

EN

The change in vascular geometry is an indicator of various health issues linked with vision and cardiovascular risk factors. Early detection and diagnosis of these changes can help patients to select an appropriate treatment option when the disease is in its primary phase. Automatic segmentation and quantification of these vessels would decrease the cost and eliminate inconsistency related to manual grading. However, automatic detection of the vessels is challenging in the presence of retinal pathologies and non-uniform illumination, two common occurrences in clinical settings. This paper presents a novel framework to address the issue of retinal blood vessel detection and width measurement under these challenging circumstances and also on two different imaging modalities: color fundus imaging and Scanning Laser Ophthalmoscopy (SLO). In this framework, initially, vessel enhancement is done using linear recursive filtering. Then, a unique combination of morphological operations, background estimation, and iterative thresholding are applied to segment the blood vessels. Further, vessel diameter is estimated in two steps: firstly, vessel centerlines are extracted using the graph-based algorithm. Then, vessel edges are localized from the image profiles, by utilizing spline fitting to obtain vascular orientations and then finding the zero-crossings. Extensive experiments have been carried out on several publicly accessible datasets for vessel segmentation and diameter measurement, i.e., DRIVE, STARE, IOSTAR, RC-SLO and REVIEW dataset. Results demonstrate the competitive and comparable performance than earlier methods. The encouraging quantitative and visual performance of the proposed framework makes it an important component of a decision support system for retinal images.

2

CNN-based superresolution reconstruction of 3D MR images using thick-slice scans

Jurek Jakub, Kocinski Marek, Materka Andrzej, Elgalal Marcin, Majos Agata

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

111--125

EN

Due to inherent physical and hardware limitations, 3D MR images are often acquired in the form of orthogonal thick slices, resulting in highly anisotropic voxels. This causes the partial volume effect, which introduces blurring of image details, appearance of staircase artifacts and significantly decreases the diagnostic value of images. To restore high resolution isotropic volumes, we propose to use a convolutional neural network (CNN) driven by patches taken from three orthogonal thick-slice images. To assess the validity and efficiency of this postprocessing approach, we used 1x1x1 mm3-voxel brain images of different modalities, available via the well known BrainWeb database. They served as a high resolution reference and were numerically preprocessed to create input images of different slice thickness and anatomical orientation, for CNN training, validation and testing. The visual quality of reconstructed images was indeed superior, compared to images obtained by fusion of interpolated thick-slice images, or to images reconstructed with the CNN using a single input MR scan. The significant increase of objectively computed figures of merit, e.g. the Structural Similarity Image Metric, was also noticed. Keeping in mind that any single value of such quality metrics represents a number of psychophysical effects, we applied the CNN trained on brain images for superresolution reconstruction of synthetic and acquired blood vessel tree images. We then used the restored superresolution volumes for estimation of vessel radii. It was demonstrated that vessel radius values derived from superresolution images of simulated vessel trees are significantly more accurate than those obtained from a standard fusion of interpolated thick-slice orthogonal scans. Superiority of the CNN-based superresolution images was also observed for scanner-acquired MR scans according to the evaluated parameters. These three experiments show the efficiency of CNN-based image reconstruction for qualitative and quantitative improvement of its diagnostic quality, as well as illustrates the practical usefulness of transfer learning - networks trained on example images of one kind can be used to restore superresolution images of physically different objects.

3

Automated detection of optic disc contours in fundus images using decision tree classifier

Pathan Sumaiya, Kumar Preetham, Pai Radhika, Bhandary Sulatha V.

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

52--64

EN

Automated segmentation of optic disc in fundus images plays a vital role in computer aided diagnosis (CAD) of eye pathologies. In this paper, a novel method is proposed which detects and excludes the blood vessel for accurate optic disc segmentation. This is achieved in two steps. First, an effective blood vessel detection and exclusion algorithm is developed using directional filter. In the second step, a decision tree classifier is used to obtain an adaptive threshold in order to detect the contour of optic disc. The proposed method aids in computationally robust segmentation of optic disc even in fundus images having illuminations, reflections and exudates. The proposed method is tested on two different datasets which includes 300 fundus images collected from Kasturba Medical College (KMC) Manipal and also the publically available RIM-ONE database. The average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy obtained for KMC images is 91.28 %, 94.17 %, 92.71 %, 99.89 % and 99.61 % respectively. For RIM-ONE database the obtained average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy are 85.30 %, 90.69 %, 93.90 %, 99.39 % and 99.15 % respectively. The obtained segmentation results proves the efficiency of the algorithm to be incorporated in CAD of eye diseases.

4

A hybrid method for blood vessel segmentation in images

Díaz Primitivo, Rodríguez Alma, Cuevas Erik, Valdivia Arturo, Chavolla Edgar, Pérez-Cisneros Marco, Zaldívar Daniel

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 3

814--824

EN

In the last years, image processing has been an important tool for health care. The analysis of retinal vessel images has become crucial to achieving a better diagnosis and treatment for several cardiovascular and ophthalmological deceases. Therefore, an automatic and accurate procedure for retinal vessel and optic disc segmentation is essential for illness detection. This task is extremely hard and time-consuming, often requiring the assistance of human experts with a high degree of professional skills. Several retinal vessel segmentation methods have been developed with satisfactory results. Nevertheless, most of such techniques present a poor performance mainly due to the complex structure of vessels in retinal images. In this paper, an accurate methodology for retinal vessel and optic disc segmentation is presented. The proposed scheme combines two different techniques: the Lateral Inhibition (LI) and the Differential Evolution (DE). The LI scheme produces a new image with enhanced contrast between the background and retinal vessels. Then, the DE algorithm is used to obtain the appropriate threshold values through the minimization of the cross-entropy function from the enhanced image. To evaluate the performance of the proposed approach, several experiments over images extracted from STARE, DRIVE, and DRISHTI-GS databases have been conducted. Simulation results demonstrate a high performance of the proposed scheme in comparison with similar methods reported in the literature.

5

Automatic parameters selection of Gabor filters with the imperialism competitive algorithm with application to retinal vessel segmentation

Farokhian F., Yang C., Demirel H., Wu S., Beheshti I.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 1

246--254

EN

Retinal images play an important role in the early diagnosis of diseases such as diabetes. In the present study, an automatic image processing technique is proposed to segment retinal blood vessels in fundus images. The technique includes the design of a bank of 180 Gabor filters with varying scale and elongation parameters. Furthermore, an optimization method, namely, the imperialism competitive algorithm (ICA), is adopted for automatic parameter selection of the Gabor filter. In addition, a systematic method is proposed to determine the threshold value for reliable performance. Finally, the performance of the proposed approach is analyzed and compared with that of other approaches on the basis of the publicly available DRIVE database. The proposed method achieves an area under the receiver operating characteristic curve of 0.953 and an average accuracy of up to 0.9392. Thus, the results show that the proposed method is well comparable with alternative methods in the literature.

6

Retinal blood vessel segmentation employing image processing and data mining techniques for computerized retinal image analysis

GeethaRamani R., Balasubramanian L.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 1

102--118

EN

Most of the retinal diseases namely retinopathy, occlusion etc., can be identified through changes exhibited in retinal vasculature of fundus images. Thus, segmentation of retinal blood vessels aids in detecting the alterations and hence the disease. Manual segmentation of vessels requires expertise. It is a very tedious and time consuming task as vessels are only a few pixels wide and extend almost throughout entire span of the fundus image. Employing computational approaches for this purpose would help in efficient retinal analysis. The methodology proposed in this work involves sequential application of image pre-processing, supervised and unsupervised learning and image post-processing techniques. Image cropping, color transformation and color channel extraction, contrast enhancement, Gabor filtering and halfwave rectification are sequentially applied during pre-processing stage. A feature vector is formed from the pre-processed images. Principal component analysis is performed on the feature vector. K-means clustering is executed on this outcome to group pixels as either vessel or non-vessel cluster. Out of the two groups, the identified non-vessel group undergoes an ensemble classification process employing root guided decision tree with bagging, while vessel group is left unprocessed as further processing might increase misclassifications of vessels as non-vessels. The resultant segmented image is formed through combining the results of clustering and ensemble classification process. The vessel segmented output from previous phase is post-processed through morphological techniques. The proposed technique is validated on images from publicly available DRIVE database. The proposed methodology achieves an accuracy of 95.36%, which is comparable with the existing blood vessel segmentation techniques.

7

Modeling of temperature field inside the tissue with a blood vessel using the BEM-FDM algorithm

Majchrzak E., Borowska J., Klekot J., Tarasek D.

Prace Naukowe Instytutu Matematyki i Informatyki Politechniki Częstochowskiej

|

2012

|

Vol. 11, nr 4

85-92

EN

The thermal interactions between the blood vessel and surrounding biological tissue are analyzed. The tissue temperature is described by the Pennes equation, while the equation determining the change of blood temperature along the blood vessel is formulated on the basis of adequate energy balance. These equations are coupled by a boundary condition given at the blood vessel wall. The problem is solved using the hybrid algorithm, this means the temperature field in biological tissue is determined by means of the boundary element method (BEM), while the blood temperature is determined by means of the finite difference method (FDM). In the final part the examples of computations are presented.

8

Badania modelu fragmentu systemu naczyń krwionośnych

Bołtrukiewicz M.

Pomiary Automatyka Kontrola

|

2012

|

R. 58, nr 4

344-347

PL

Przedstawiona praca dotyczy modelowania właściwości dynamicznych systemu naczyń krwionośnych. W pracy wykorzystuje się uzyskaną eksperymentalnie transmitancję fragmentu systemu naczyń krwionośnych znajdującego się pomiędzy stawem łokciowym i nadgarstkiem. W artykule rozważa się dwa modele podatnej tętnicy, które są badane w aspekcie dopasowania do danych uzyskanych doświadczalnie. Do dalszych prac zostaje wybrany model charakteryzujący się dużym stopniem dopasowania do danych eksperymentalnych, uwzględniający rzeczywiste zachowanie cieczy w odkształconej podatnie tętnicy.

EN

The paper concerns the modeling of dynamic specificity of blood vessel. The simple physical models of blood vessel part were investigated. In the experiments a PPG signal was used. The optoelectronic sensors were installed on a wrist and forearm. After the acquisition, the obtained samples of the PPG signal were identified by the RLS method. As a result of the experiments the transfer function of the investigated blood vessel part was obtained. This transmittance is described with Eq. (4), and its step response is shown in Fig. 2. In the work two physical models are considered. The structures of these models are shown in Figs.1 and 3. The first one uses the phenomenon of suppressed oscillations, while the second one - the phenomenon of impact of the liquid wave. The transfer functions of the models are described by Eqs. (6) and (13), respectively. In the study compatibility between the obtained transfer function and the physical models was verified. The transfer function of blood vessel and the transfer functions of physical models were compared. Their step responses were compared, too. Finally, the correspondence between the second physical model and the transmittance of the blood vessel part was experimentally proved.

9

Ocena możliwości automatyzacji układu do rozciągania próbek na użytek spektroskopii Ramana

Wilk J., Klonecki-Olech K., Kobielarz M.

Aktualne Problemy Biomechaniki

|

2010

|

z. 4

275--278

PL

Badania ścian naczyń krwionośnych metodą spektroskopii Ramana, pozwalają na badanie zależności między obciążeniem jakiemu poddawana jest tkanka, a jej strukturą. W celu zwiększenia efektywności pomiarów podjęta została próba zautomatyzowania układu służącego do rozciągania próbek poddawanych badaniu.

EN

Study of vessels walls by means of Raman Spectroscopy allows to analyze the relation between load placed upon the tissue and it’s structure. To maximize the effectiveness of measurement, the goal of automation of the tensile tool used in the procedure was undertaken.

10

Wpływ ładunku elektrycznego na potencjał elektrokinetyczny na granicy faz: proteza naczyń krwionośnych-krew

Łowkis B., Zboromirska-Wnukiewicz B., Gryzło K.

Przegląd Elektrotechniczny

|

2008

|

R. 84, nr 10

108-111

PL

W pracy przedstawiono wpływ ładunku elektrycznego na adhezję krwinek płytkowych i poziom białka całkowitego. Wyznaczono potencjał zeta protez nieelektryzowanych i elektretów w roztworach o różnych pH. Zbadano wpływ czasu na potencjał zeta krwi ludzkiej. Określono zachowanie się potencjału zeta na granicy proteza naczyń krwionośnych-krew w funkcji czasu.

EN

Presented work describes influence of charge on blood platelets adhesion and complete protein level. Zeta potential of prostheses and electrets in solutions with different pH was determined. The influence of time on zeta potential of human blood was examined. Also behavior of zeta potential in function of time between blood vessel prosthesis – blood was described.

11

Mineralizacja naczyń krwionośnych w świetle badań fizycznych

Gil A.

Prace Naukowe Akademii im. Jana Długosza w Częstochowie. Edukacja Techniczna i Informatyczna

|

2007

|

T. 2

115-126

12

Experimental analysis of steady and pulsating flows in collapsible walls

Zbiciński I.

Chemical and Process Engineering

|

2007

|

Vol. 28, z. 3

539-546

EN

An experimental set-up to measure the changes of geometry of elastic walls and input and output pressures for constant and pulsating flow reflecting blood flow in human arteries was designed, built and tested. The paper presents the results of extensive experiments of static and pulsating flow parameters as functions of flow rates and pulsation frequencies for various properties of tested tubes. Aperiodic time series of pressure due to occurrence of turbulent flow have been observed.

PL

Przedstawiono wyniki badań eksperymentalnych przepływu statycznego i pulsacyjnego w elastycznych ściankach odwzorowującego przepływ w naczyniach krwionośnych. Zaprojektowano, zbudowano i przetestowano aparaturę umożliwiającą pomiar on-line zmian średnicy badanej rurki wykonanej z elastycznego materiału i ciśnień dynamicznych przed i za badaną próbką w zależności od natężenia prze-pływu i częstotliwości pulsacji. Zaobserwowano m.in. aperiodyczne zależności czasowe ciśnienia i średnicy rurki wynikające z burzliwego charakteru przepływu płynu.

13

Ocena kierunkowych właściwości mechanicznych ścian naczyń krwionośnych

Kobielarz M., Będziński R., Szotek S.

Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska

|

2006

|

z. 30

131-136

PL

Głównym celem tej pracy jest wyznaczenie właściwości mechanicznych ścian zdrowej aorty brzusznej oraz ścian tętniaka aorty brzusznej. W tym celu, przeprowadzono test jednoosiowego rozciągania próbek, które wycinano w dwóch kierunkach: wzdłużnym i obwodowym. Dla wszystkich przebadanych próbek wykreślano charakterystyki σ=f(ε) i wyznaczano dla nich umowny moduł Younga oraz wytrzymałość mechaniczną na rozciąganie. Zaobserwowano, że ściany tętniaka aorty brzusznej w porównaniu ze ścianami zdrowej aorty brzusznej są sztywniejsze.

EN

The maim aim of this research work is appointed mechanical properties of walls of normal abdominal aorta and walls of abdominal aortic aneurysms. In this end of view, the uniaxial tensile tests were performed for each specimen, which were cut out research material in two directions: longitudinal and circumferential. On the basis these tests the stress-strain characteristics were drawn for all specimens and the assumed Young's modules and the tensile strength were assigned. The results indicate that the walls of abdominal aortic aneurysms in comparison with walls of normal abdominal aortas are stiffer.

14

Vascular network description and visualization

Sanko D., Tuzikov A.

Przegląd Elektrotechniczny

|

2005

|

R. 81, nr 3

39-40

EN

This paper describes a technigue of description and visualization of vasculature. Vascular description includes a topology structure, cross section area and volume measurements. Visualization interacting system allows studying extracted data.

PL

W artykule opisano technikę reprezentacji i wizualizacji sieci naczyń krwionośnych. System opisu takiej sieci zawiera strukturę topologiczną, przekroje i pomiary objętości. Współpracujący system wizualizacji umożliwia analizę wydobytych danych.

15

The biomechanics of atherosclerosis development

Makinde O. D., Acho T. M., Sibanda P., Lungu E. M.

Computer Assisted Mechanics and Engineering Sciences

|

2003

|

Vol. 10, No. 1

23-31

EN

In this paper, we investigate the bio-mechanics of atherosclerosis development in human physiology. Blood is modelled as an incompressible fluid of variable viscosity flowing in a slightly diverging channel (i.e. large artery) of small aspect ratio [1]. The hypothetical viewpoint in this work is the existence of relationship between the atherosclerosis development, blood viscosity, flow separation and turning points in the flow field. The problem is tackled by asymptotic approximation and the graphical results are discussed quantitatively.

16

Vascular texture modeling for image interpretation

Krętowski M., Bezy-Wendling J.

Biocybernetics and Biomedical Engineering

|

2003

|

Vol. 23, no. 1

65-79

EN

In this paper, it is shown that pathological changes of vascular networks, inside an extensive organ, influence textures observed on medical images. A 3D, dynamic model of the organ and its vascular system was developed, and it enables to control the tissue perfusion. To render CT scan-like images, the acquisition process was also modeled. The proposed approach is applied to simulate the development of the hepatic vascular system and to induce hyper- and hypo-vascularized lesions inside the liver. The texture analysis of the obtained images is then performed. It shows that textural features can characterize regions changed by pathological processes as far as the acquisition conditions are precisely are presicely controlled.

17

Models for 3d vascular image analysis

Orkisz M., Hernández Hoyos M.

Journal of Medical Informatics & Technologies

|

2001

|

Vol. 2, Part. 1

IP13--IP22

EN

In image processing, models are used to improve robustness of algorithms by introducing a priori knowledge. Deformable models, frequently used in the field of medical images, are described by means of energy functionals with data attachment terms and regularising terms. The regularising terms express constraints relating to the expected shapes. The expected shape of a blood vessel segment in 3D images obtained by Magnetic Resonance Imaging or by helicoidal Computed Tomography is often implicitly described by a generalised cylinder model, i.e. an association of an axis (vessel centreline) and a surface (vessel boundary). In this context, the data attachment terms involve, for candidate points, a measure of the likelihood of being located on the centreline or on the boundary. Such a measure can use models reflecting low-level local photometrical properties of the brightness patterns. This presentation will give an overview of the recently used models and will be illustrated by the authors' contribution.

18

Modelling of pulsatory flows in blood vessels

Dindorf R., Wołkow J.

Acta of Bioengineering and Biomechanics

|

2001

|

Vol. 3, nr 2

15-30

EN

The paper deals with the method of modelling of blood pulsatory flow in the vessels of circulatory system. The method is based upon the solution of wave equation applied in the theory of four-pole. In a graphic presentation of a vessel of distributed parameters, a model of bond graphs with new elements of DB type ise used. Basic physiological simulation experiment using bond graphs was performed. The aim of the experiment was to model the changes of pressure and volume in a left heart-aorta segment.

19

Endothelial cell responses to fluid shear stress

Kamiya A.

Biocybernetics and Biomedical Engineering

|

2000

|

Vol. 20, no. 3

21-33

EN

Implications of vascular endothelial cell (EC) responses to flow-oriented wall shear stress are outlined from the bioengineering viewpoint. These responses regulate the adaptive remodeling of the vascular system including capilIary networks, in a negative feedback mechanism maintaining the shear stress level constant. The preserved set point of the stress is selected so as to optimize the mass transport function of the system. To initiate such shear-dependent responses, EC has a mechano-sensor conjugated with second messengers, one of which is cytoplasmic Ca(2+) transient. The evidence that wall shear stress is the real factor inducing the transient, is visualized from an in vitro flow loading experiment to cultured ECs using mediums differing in viscosity.

PL

W artykule przedstawiono implikacje występowania reakcji komórki śródbłonka na naprężenia ścinające w ścianie naczynia, związane z przepływem płynu. Reakcje te kontrolują adaptację systemu naczyń krwionośnych, łącznie z siecią kapilar, utrzymując naprężenia ścinające na stałym poziomie za pomocą mechanizmu ujemnego sprzężenia zwrotnego. Zadany poziom naprężeń jest tak dobrany, aby optymalizować funkcję transportu masowego układu naczyniowego. W celu inicjacji reakcji, zależnej od poziomu naprężeń ścinających, komórki nabłonka wykorzystują mechano-sensor połączony z innymi "przekaźnikami", z których jednym jest transport wapnia. Dowód, że naprężenia ścinające w ściance naczyń są czynnikiem uruchamiającym ten "transport" jest widoczny podczas badań in vitro mechanizmu przepływu medium o różnej lepkości w hodowli komórek śródbłonka.

20

Numerical solution of pennes bio-heat transfer equation with the blood vessels

Mochnacki B., Majchrzak E., Jasiński M.

Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska

|

1999

|

z. 10

233-236

EN

In the paper the heat transfer within the tissue in the presence of a pair of blood vessels is analyzed. Taking into account the of a blood vessel and inconsiderable change of blood temperature along the vessel one can consider the 2D problem. In order to solve the boundary element method is used. In the final part of the paper the example of computations is presented.

PL

W pracy rozważano przepływ ciepła w tkance biologicznej w obecności pary naczyń krwionośnych. Biorąc pod uwagę wymiary pojedynczego naczynia i niewielką zmianę temperatury krwi na jego długości, zadanie traktowano jako problem 2D. Do rozwiązania wykorzystano metodę elementów brzegowych. W końcowej części pracy przedstawiono przykład obliczeń numerycznych.