Wyniki wyszukiwania - BazTech

1

Quantification of the ilio-femoral arteries tortuosity and data cluster modelling for preoperative examination

Markiewicz Tomasz, Dziekiewicz Miroslaw

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 4

1123--1136

EN

Detecting spatial tortuosity and atherosclerotic changes of the ilio-femoral arteries are crucial for planning endovascular access. The aim of this study was to find a reliable quantification procedure of arterial lumen and tortuosity to qualify patients for a suitable endovascular procedure. We conducted computed tomographic angiography in 76 patients. All ilio-femoral segments of the arterial tree were visualized using Osirix Dicom Viewer software to help qualify the patients to one of two groups: with possible or non-recommended vascular access. The same tomograms were then analyzed with image processing algorithms to perform ilio-femoral artery segmentation and quantification. We chose a set of arterial tortuosity and lumen measuring methods, such as the modified Gustafson-Kessel clustering algorithm and Support Vector Machine classifier, to automatically classify arterial-tree regions. The two 2D feature spaces were selected with the modified Gustafson-Kessel clusterization to create a combined model to assign around 2/3 cases to the access groups with high specificity (more than 88%) whereas the remaining patients were selected for re-evaluation. We concluded that the novel modification of the Gustafson-Kessel clustering algorithm is more suitable to the highly inseparable data than commonly used approaches. To identify ilio-femoral access limitations, we recommend more complex decision model. This study confirmed high usability of our chosen methodology in the quantitative examination of arteries for endovascular access planning.

2

U-Net based frames partitioning and volumetric analysis for kidney detection in tomographic images

Les Tomasz

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 3

art. no. e137051

EN

This work presents an automatic system for generating kidney boundaries in computed tomography (CT) images. This paper presents the main points of medical image processing, which are the parts of the developed system. The U-Net network was used for image segmentation, which is now widely used as a standard solution for many medical image processing tasks. An innovative solution for framing the input data has been implemented to improve the quality of the learning data as well as to reduce the size of the data. Precision-recall analysis was performed to calculate the optimal image threshold value. To eliminate false-positive errors, which are a common issue in segmentation based on neural networks, the volumetric analysis of coherent areas was applied. The developed system facilitates a fully automatic generation of kidney boundaries as well as the generation of a three-dimensional kidney model. The system can be helpful for people who deal with the analysis of medical images, medical specialists in medical centers, especially for those who perform the descriptions of CT examination. The system works fully automatically and can help to increase the accuracy of the performed medical diagnosis and reduce the time of preparing medical descriptions.

3

Smartphone-Based Color Measurement of Tooth Shade Guide in Clinical Lighting Conditions

Radziun Agnieszka, Doniec Rafał, Sieciński Szymon, Piaseczna Natalia, Mocny-Pachońska Katarzyna, Cieślik-Wegemund Marta, Duraj Konrad, Tanasiewicz Marta, Tkacz Ewaryst

Annals of Computer Science and Information Systems

|

2021

|

Vol. 25

409--413

EN

Caries is a common disease of hard tissues of teeth which results in dental cavities, which are usually replaced by dental filling. Matching the color of a dental filling is usually a subjective assessment. In this study we conducted a color analysis of GC Gradia Direct shade guide in the lighting conditions of the dental office. Color measurement was performed using Color Grab mobile app and the results were acquired as values of RGB and HSV values. The results indicate the possibility of identifying each shade of tooth by the most prominent changes in RGB, and/or HSV components.

4

Enabling Autonomous Medical Image Data Annotation: A human-in-the-loop Reinforcement Learning Approach

da Cruz Leonardo, Sierra-Franco César, Silva-Calpa Greis, Raposo Alberto

Annals of Computer Science and Information Systems

|

2021

|

Vol. 25

271--279

EN

Deep learning techniques have shown significant contributions to several fields, including medical image analysis. For supervised learning tasks, the performance of these techniques depends on a large amount of training data as well as labeled data. However, labeling is an expensive and time-consuming process. With this limitation, we introduce a new approach based on Deep Reinforcement Learning (DRL) to cost-effective annotation in a set of medical data. Our approach consists of a virtual agent to automatically label training data, and a human-in-the-loop to assist in the training of the agent. We implemented the Deep Q-Network algorithm to create the virtual agent and adopted the method mentioned above, which employs human advice to the virtual agent. Our approach was evaluated on a set of medical X-ray data in different use cases, where the agent was required to create new annotations in the form of bounding boxes from unlabeled data. Results show that an agent training with advice positively impacts obtaining new annotations from a data set with scarce labels. This result opens up new possibilities for advancing the study and implementing autonomous approaches with human advice to create a cost-effective annotation in data sets for computer-aided medical image analysis.

5

Instance Segmentation Model Created from Three Semantic Segmentations of Mask, Boundary and Centroid Pixels Verified on GlaS Dataset

Malík Peter, Krištofík Štefan, Knapová Kristína

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

569--576

EN

Segmentation is the key computer vision task in modern medicine applications. Instance segmentation became the prevalent way to improve segmentation performance in recent years. This work proposes a novel way to design an instance segmentation model that combines 3 semantic segmentation models dedicated for foreground, boundary and centroid predictions. It contains no detector so it is orthogonal to a standard instance segmentation design and can be used to improve the performance of a standard design. The presented custom designed model is verified on the Gland Segmentation in Colon Histology Images dataset.

6

Quantitative impact of label noise on the quality of segmentation of brain tumors on MRI scans

Marcinkiewicz Michał, Mrukwa Grzegorz

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

61--65

EN

Over the last few years, deep learning has proven to be a great solution to many problems, such as image or text classification. Recently, deep learning-based solutions have outperformed humans on selected benchmark datasets, yielding a promising future for scientific and real-world applications. Training of deep learning models requires vast amounts of high quality data to achieve such supreme performance. In real-world scenarios, obtaining a large, coherent, and properly labeled dataset is a challenging task. This is especially true in medical applications, where high-quality data and annotations are scarce and the number of expert annotators is limited. In this paper, we investigate the impact of corrupted ground-truth masks on the performance of a neural network for a brain tumor segmentation task. Our findings suggest that a) the performance degrades about 8% less than it could be expected from simulations, b) a neural network learns the simulated biases of annotators, c) biases can be partially mitigated by using an inversely-biased dice loss function.

7

Machine-learning at the service of plastic surgery: a case study evaluating facial attractiveness and emotions using R language

Štěpánek Lubomír, Měšťák Jan, Kasal Pavel

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

107--112

EN

Since the plastic surgery should consider that facial impression is always dependent on current facial emotion, it came to be verified how precise classification of facial images into sets of defined facial emotions is.

8

A fast and robust level set motion-assisted deformable registration method for volumetric CT guided lung intervention

Kim D., Kim N., Lee S., Seo J. B.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 3

439--447

EN

This paper describes the accurate deformable registration method for image-guided lung interventions, including lung nodule biopsy and radiofrequency ablation of lung tumours. A level set motion assisted deformable registration method for computed tomography (CT) images was proposed and its accuracy and speed were compared with those of other conventional methods. Fifteen 3D CT images obtained from lung biopsy patients were scanned. Each scan consisted of diagnostic and preoperative CT images. Each deformable registration method was initially evaluated with a landmark-based affine registration algorithm. Various deformable registration methods such as level set motion, demons, diffeomorphic demons, and b-spline were compared. Visual assessment by two expert thoracic radiologists using five scales showed an average visual score of 3.2 for level set motion deformable registration, whereas scores were below 3 for other deformable registration methods. In the qualitative assessment, the level set motion algorithm showed better results than those obtained with other deformable registration methods. A level set motion based deformable registration algorithm was effective for registering diagnostic and preoperative volumetric CT images for image-guided lung intervention.

9

An algorithm for joint and bone localization in USG images of rheumatoid arthritis

Popowicz A., Kurek A. R.

Studia Informatica

|

2016

|

Vol. 37, nr 3B

7--19

EN

The assessment of degree of joint inflammation using USG imaging is a challenging task, and thus the results may differ between experts. Therefore, the evaluation of images by a computer program may be a vital solution for objective assessment of disease progression. In this paper an original pipeline, developed for precise estimation of bone line and joint location in USG images, is proposed. The presented set of methods provides valuable input for further classification tools, which will aim at identification and rating of the degree of joint inflammation.

PL

Ocena stopnia zapalenia stawów palców dłoni z wykorzystaniem obrazów USG jest zwykle trudnym zadaniem i może być różna w zależności od eksperta analizującego obrazy. Z tego względu analiza wykorzystująca program komputerowy stanowić może obiektywny wskaźnik progresu choroby. W artykule zaprezentowano zestaw procedur przetwarzania obrazów, umożliwiający wykrycie położenia kości oraz stawu w obrazach USG. Wyniki zwracane przez algorytm stanowią istotną podstawę do dalszych kroków, mających na celu wykrycie oraz gradację stopnia zapalenia.

10

Modelowanie realistycznej przestrzeni operacyjnej na podstawie obrazów dicom

Leniowski R., Meissner J.

Acta Bio-Optica et Informatica Medica. Inżynieria Biomedyczna

|

2016

|

Vol. 22, nr 4

245--260

PL

Praca przedstawia metody modelowania realistycznej przestrzeni medycznej na podstawie danych diagnostyki obrazowej zgodnych ze standardem DICOM. Zawiera krótki przegląd współczesnych zastosowań trójwymiarowych wizualizacji w medycynie oraz opisuje metodę pozwalającą na odczytywanie zdjęć diagnostyki obrazowej zapisanych w plikach DICOM. Dla ciągu dwuwymiarowych obrazów następuje wyznaczenie konturów ludzkich narządów. Kontury łączy się względem osi Z i w efekcie otrzymuje się trójwymiarowa siatkę obiektów w przestrzeni ograniczonej powierzchnią skóry. Jednym z tych obiektów jest również przestrzeń operacyjna. Implementację komputerową metody wykonano w języku C++ przy wykorzystaniu bibliotek SFML, SFGUI, Boost, DCMTK oraz OpenGL. Aplikacja odczytuje ciągi zdjęć procedury diagnostycznej, a następnie określa granice interesującego obszaru, wylicza wierzchołki węzłowe siatki modelu trójwymiarowego i renderuje scenę.

EN

The aim of this work was to develop methods that are able to model realistic surgical site, using DICOM-compliant images. The theoretical issues include significance of 3D visualizations in modern medicine for diagnostic and surgical use. The practical part of this work has been focused on creating a C++ application, using SFML, SFGUI, DCMTK, boost, and OpenGL libraries for reading sequences of images stored in DICOM standard files, and then using them for tracing contours of human organs. Contours were then used for 3D visualization of surgical site. patient.

11

Rough sets in identification of cellular automata for medical image processing

Płaczek B.

Journal of Medical Informatics & Technologies

|

2013

|

Vol. 22

161--168

EN

In this paper a method is proposed which enables identification of cellular automata (CA) that extract low-level features in medical images. The CA identification problem includes determination of neighbourhood and transition rule on the basis of training images. The proposed solution uses data mining techniques based on rough sets theory. Neighbourhood is detected by reducts calculations and rule-learning algorithms are applied to induce transition rules for CA. Experiments were performed to explore the possibility of CA identification for boundary detection, convex hull transformation and skeletonization of binary images. The experimental results show that the proposed approach allows finding CA rules that are useful for extraction of specific features in microscopic images of blood specimens.

12

CAD system for automatic analysis of CT perfusion maps

Hachaj T., Ogiela M. R.

Opto-Electronics Review

|

2011

|

Vol. 19, No. 1

95-103

EN

In this article, authors present novel algorithms developed for the computer-assisted diagnosis (CAD) system for analysis of dynamic brain perfusion, computer tomography (CT) maps, cerebral blood flow (CBF), and cerebral blood volume (CBV). Those methods perform both quantitative analysis [detection and measurement and description with brain anatomy atlas (AA) of potential asymmetries/lesions] and qualitative analysis (semantic interpretation of visualized symptoms). The semantic interpretation (decision about type of lesion: ischemic/hemorrhagic, is the brain tissue at risk of infraction or not) of visualized symptoms is done by, so-called, cognitive inference processes allowing for reasoning on character of pathological regions based on specialist image knowledge. The whole system is implemented in.NET platform (C# programming language) and can be used on any standard PC computer with.NET framework installed.

13

Semi-automatic count of hepatic stellate cells from microscopic in-vitro images by modeling elliptical nuclei

Bołdak C., Sadowski M., Jaroszewicz J.

Zeszyty Naukowe Politechniki Białostockiej. Informatyka

|

2008

|

Z. 3

23-38

EN

A new method of semi-automatic liver cell counting is presented. Instead of segmenting the cells bodies (not regular and fragmented in some stages of the cells life) it localizes the cells nuclei which are bright, homogeneous and elliptical structures with darker body (body fragments) on their circumference. The nuclei are modeled by ellipses which can be found in two manners: by local region growing algorithm and by reconstruction of the ellipse equation from its contour points. The found ellipses set is then downsized (since all possible ellipses are initially considered) by eliminating the closest one to another and the worst ones by mean of a special fitness function. The method is implemented as a visual, multiplatform JAVA application, easy to use in the scientific every-day work. It is evaluated on real microscopic in-vitro images of the hepatic stellate cells.

PL

W artykule tym zaprezentowana jest nowa, półautomatyczna metoda zliczania komórek wątroby. Zamiast skupiać sięna ciałach komórek (w niektórych fazach ich życia nieregularnych i pofragmentowanych) lokalizuje ona ich jądra, które są jasnymi, jednolitymi i eliptycznymi strukturami otoczonymi przez ciemniejsze ciało (lub jego fragmenty). Jądra komórek są modelowane na 2 sposoby: przez lokalny algorytm rozrostu obszaru i przez odtworzenie równania elipsy z jej punktów na obwodzie.Wśród wszystkich znalezionych elips (początkowa każda jej potencjalna lokalizacja jest brana pod uwagę) wybierane są lokalnie najlepsze oraz te, których dopasowanie, mierzone specjalną funkcją, jest powyżej pewnego progu. Metoda została zaimplementowana jako graficzna, wieloplatformowa, przyjazna dla użytkownika aplikacja w języku JAVA. Jej działanie zostało ocenione na rzeczywistych mikroskopowych obraz in-vitro komórek wątroby.

14

An iterative programmable graphics process unit based on ray casting approach for virtual endoscopy system

Yuan F.

Optica Applicata

|

2008

|

Vol. 38, nr 3

519-530

EN

In this paper, a fast graphics process unit (GPU) based ray casting algorithm is presented to improve image quality. A linear interpolation is used to estimate the intersection between a ray and isosurfaces. Thus, resampling artefacts is greatly reduced and the performance is not influenced. An iterative estimation is presented to further improve image quality. According to the distance the ray goes across, z values in the z-buffer are modified to implement hiding of hybrid scenes. Experimental results show that the algorithm can produce high quality images at interactive frame rates and implement hiding of hybrid scenes very well.

15

Medical image compression and analysis using wavelet modulus maxima decomposition

Bialasiewicz J. T., Redmond L. S.

Machine Graphics and Vision

|

2007

|

Vol. 16, No. 3/4

221-235

EN

A method of highly effective biomedical image compression that includes the reconstruction process with a good convergence rate is presented in the paper. It represents an image in the form of its wavelet modulus maxima decomposition. The technique allows the compressed image representation to include only those wavelet transform coefficients that correspond to the wavelet transform modulus maxima that are determined for each resolution level. The proposed approach to analysis of medical images uses the wavelet modulus maxima decomposition to enhance image features that are not visually apparent. The transient behavior of pixel intensities (that corresponds to edges and singular points) is used for image enhancement. The detection of edges is realized by detecting modulus maxima in a two-dimensional dyadic wavelet transform at the proper scale. This approach to image analysis aims at determining structures of the diseased tissue that are represented by the image edges. It is expected that this technique will help with early detection of cancer when routine interpretation of CT scans is inconclusive and biopsy would be required.

16

A method of poorly visible left cardiac ventricle's boundary enhancement

Kulikowski J.K., Przytulska M., Wierzbicka D.

Biocybernetics and Biomedical Engineering

|

2000

|

Vol. 20, no. 4

21-33

EN

Examination of a left cardiac ventricle's shape and volume belongs to routine methods used in advanced cardiac diagnosis. For this purpose X-ray and/or USG cardiac images are used, not only due to their low cost, but also due to the fact that they make possible an examination of long image series representing the heart contractility process. Unfortunately, the quality of USG images is usually low. There is described here a method of poorly visible left cardiac ventricle's boundary enhancement. It belongs to a class of methods based on a multi-step continuous closed contours formation and fitting principIe. The class of contours under consideration is described by a model equation based on trigonometric series. The basic part of contour restoring algorithm is equivalent to a one of finding a solution of an optimisation problem with non-linear goal function and linear constraints. The constraints make us able to take into account medical indications in problem solving. Finally, some remarks about a possibility of using the method to heart contractility investigation are given.

PL

Badanie kształtu i objętości lewej komory serca należy do rutynowych metod stosowanych w diagnostyce kardiologicznej. Do tego celu używa się rentgenowskich lub ultrasonograficznych zobrazowań serca, zarówno ze względu na ich relatywnie niską cenę, jak i ze względu na to, iż umożliwiają one analizę dłuższych serii obrazów przedstawiających proces kurczliwości serca. Niestety, jakość zobrazowań ultrasonograficznych jest zazwyczaj zła. W artykule przedstawiono metodę wyznaczania słabo widocznych obrysów lewej komory serca. Należy ona do klasy metod opartych na zasadzie wielokrokowego formowania i dopasowywania ciągłego konturu do badanego obrazu. Klasa rozważanych konturów jest opisana przez równanie modelowe w postaci szeregu trygonometrycznego. Podstawowa część algorytmu odtwarzania obrysu jest równoważna procedurze poszukiwania rozwiązania problemu optymalizacyjnego z nieliniową funkcją celu i z liniowymi ograniczeniami. Ograniczenia stwarzają możliwość uwzględnienia w rozwiązaniu wskazówek medycznych. W części końcowej zamieszczono uwagi dotyczące możliwości wykorzystania metody w badaniach kurczliwości lewej komory serca.

17

3D thinning and its applications to medical image processing

Palágyi K., Sorantin E., Halmai C., Kuba A.

TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk

|

1999

|

Vol. 3, No 4

397-408

EN

A skeleton is a frequently-used feature to represent the general form of an object. The importance of this region-based shape feature is growing in medical image processing, too. This paper summarizes the major skeletonization approaches, the 3D parallel thinning methodologies and some emerging medical applications. An application to calculate the cross-sectional profiles of blood vessels is also presented.