Wyniki wyszukiwania - BazTech

1

Endoscopy, video capsule endoscopy, and biopsy for automated celiac disease detection: A review

Jahmunah V., En Wei Koh Joel, Sudarshan Vidya K., Raghavendra U., Gudigar Anjan, Lih Oh Shu, Wen Loh Hui, Faust Oliver, Datta Barua Prabal, Ciaccio Edward J., Rajendra Acharya U.

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 1

82--108

EN

Celiac Disease (CD) is a common ailment that affects approximately 1% of the world population. Automated CD detection can help experts during the diagnosis of this condition at an early stage and bring significant benefits to both patients and healthcare providers. For this purpose, scientists have created automatic and semi-automatic CD diagnostic support systems. In this study, we performed information extraction methods that were found useful for efforts to differentiate CD versus non-CD. To focus the review process, only methods for endoscopy, video capsule endoscopy (VCE) and biopsy image analyses were considered. As described herein, we have learned that statistical and non-linear methods are most important for information extraction. These information extraction tools might benefit clinical workflows by reducing intra- and inter-observer variability. However, bias, introduced by resolving design choices during the creation of diagnostic support systems, may limit the general validity of the performance results, impacting the transferability of study outcomes. Therefore, having am overview of information extraction tools. Together with their general and specific limitations, might be assistive in improving the information extraction process. We hope our review results will provide a foundation for the design of next-generation statistical and nonlinear methods that can be used in CD detection systems. We have also compared various review articles and discussed recommendations to improve CD diagnosis. From this review, it is evident that CD diagnosis is slowly moving away from conventional techniques towards advanced deep learning techniques.

2

Formulation and statistical evaluation of an automated algorithm for locating small bowel tumours in wireless capsule endoscopy

Jagadeesan A., Sivaraman J.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 4

782--793

EN

Wireless capsule endoscopy (WCE) is an imaging modality which is highly reliable in the diagnosis of small bowel tumors. But locating the frames carrying tumors manually from the lengthy WCE is cumbersome and time consuming. A simple algorithm for the automated detection of tumorous frames from WCE is proposed in this work. In the proposed algorithm, local binary pattern (LBP) of the contrast enhanced green channel is used as the textural descriptor of the WCE frames. The features employed to differentiate tumorous and nontumorous frames are skewness (S) and kurtosis (K) of the LBP histogram. The threshold value of the features which offers the trade-off between sensitivity and specificity is identified through Receiver Operating Characteristic (ROC) curve analysis. At the optimum threshold, both the features exhibited a sensitivity of 100% and specificity of 90%. The skewness and kurtosis of the LBP computed from the enhanced green channel of tumorous and nontumorous frames differ significantly ( p « 0.05) with a p-value of 2.2 x 10-16. The proposed method is helpful to reduce the time spent by the doctors for reviewing WCE.

3

Design of wireless power supply optimized structure for capsule endoscopes

Cui Ch., Zhao Q., Li Z.

Journal of Power Technologies

|

2016

|

Vol. 96, nr 2

101--109

EN

Wireless power transmission is an important method for powering wireless capsule endoscopes, but its efficiency is low, especially when the devices move freely in random positions and orientations. To improve the stability and efficiency of the endoscope in vivo, this study designed an optimization method for planar spiral coils utilized in wireless power transfer for capsule endoscopes. An optimized structure using six planar spiral coils was first proposed as the transmitting coil, and the efficiency of a series-parallel wireless power transmission model was analyzed. A theoretical model was then examined for the magnetic field vector distributions of the spiral-type transmitting coil by using an elliptic coordinate system. The relationship between the position of the receiving coil and the coupling coefficient was determined when the position and attitude changed. Finally, the experimental device of the wireless power supply system of the endoscope was designed with a class-E amplifier and Liz coil. The simulation and experimental results showed that the proposed method can generate high intensity magnetic field uniform, which can improve the efficiency of the wireless power transmission in the case of axial deviation and angular misalignment. The experimental results also indicated that the proposed scheme can meet the needs of the power supply of wireless endoscopes.

4

Komputerowa analiza obrazów z endoskopu bezprzewodowego dla diagnostyki medycznej

Szczypiński P. M.

Zeszyty Naukowe. Rozprawy Naukowe / Politechnika Łódzka

|

2012

|

Z. 426

1-142

PL

Jednym z badań medycznych stosowanych w diagnostyce chorób przewodu pokarmowego jest bezprzewodowa endoskopia kapsułkowa. Wynikiem badania jest film, którego interpretacja przeprowadzana przez lekarza wymaga dużego skupienia uwagi, jest długotrwała i męcząca. Wyniki interpretacji nie są powtarzalne - zależą od wiedzy i doświadczenia konkretnego lekarza. Przedmiotem niniejszej monografii są opracowane przez autora metody numeryczne, których celem jest analiza obrazów cyfrowych z endoskopu bezprzewodowego zwiększające powtarzalność, wiarygodność oraz obiektywizm diagnozy medycznej. Mają one ograniczyć nakład pracy lekarza podczas oglądania filmu, zautomatyzować procedurę interpretacji oraz umożliwić analizę ilościową wybranych zmian chorobowych. Zaproponowane rozwiązania pozwalają między innymi na scharakteryzowanie ruchu własnego endoskopu względem przewodu pokarmowego, automatyczną regulację szybkości odtwarzania filmu, rekonstrukcję obrazu powierzchni przewodu pokarmowego, detekcję wybranych zmian chorobowych na podstawie cech barwy i tekstury obrazu oraz segmentację obrazów w celu wyodrębnienia obszarów objętych zmianami patologicznymi. Do najważniejszych osiągnięć opisanych w niniejszej monografii należą: model deformowalny do analizy ruchu własnego kamery, uniwersalna metoda obliczania naprężeń w modelach deformowalnych oraz nowy, szybki algorytm selekcji cech i klasyfikacji trudno rozdzielnych skupień wykorzystujący wielotop wypukły. Wszystkie opracowane metody poddano ocenie jakościowej i ilościowej, w szczególności zbadano ich przydatność do wspomagania interpretacji filmów endoskopowych. Efektem prowadzonych prac są udostępnione w interne-cie programy komputerowe, w których zastosowano opracowane algorytmy: WCE Player do analizy ruchu własnego endoskopu i rekonstrukcji powierzchni przewodu pokarmowego, a także MaZda do analizy cech barwy i tekstury obrazów oraz do klasyfikacji danych.

EN

Wireless capsule endoscopy is one of the medical tests used in diagnosis of gastrointestinal disorders. A result is a video of internal lumen of gastrointestinal tract which interpretation carried out by an expert gastroenterologist requires a lot of attention and is time consuming. The final diagnosis is rarely reproducible - it depends on the knowledge and experience of the diagnostic experience of the expert. The subject of this monograph is presentation and validation of novel algorithms for wireless endoscope video analysis whose purpose is to improve the reproducibility, reliability and objectivity of medical diagnosis. The algorithms are designed to reduce amount of work devoted to watching the movie, to automate the procedure of the data interpretation and to enable a quantitative description of selected lesions. The proposed methods allow to characterize the endoscope's egomotion (using a dedicated deformable model), reconstruct the intestine's internal surface, detect selected lesions (based on color and texture analysis), segment images in order to identify areas of pathological changes and dynamically adapt playback speed. The key achievements presented in this monograph include deformable model of rings for analysis of endoscopic camera egomotion passing through the gastrointestinal tract, versatile method for calculating tensions in the deformable model grid and an efficient algorithm using convex polytopes for feature selection and classification of specifically-shaped clusters. All the developed methods were implemented in a computer programs, and thereafter evaluated qualitatively and quantitatively. The computer programs - WCE Player for egomotion estimation and MaZda for image classification based on color and texture analysis - are available from the internet.

5

Konstrukcja bazy danych dla systemu wspomagania diagnostyki chorób przewodu pokarmowego

Cychnerski J., Brzeski A., Blokus A., Dziubich T., Jędrzejewski M.

Studia Informatica

|

2012

|

Vol. 33, nr 2B

445-456

PL

W artykule krótko przedstawiono charakterystykę procesu diagnostyki chorób przewodu pokarmowego oraz istniejące techniki wspomagania go na bazie analizy zdjęć z badań endoskopowych. Szczegółowo opisano proces tworzenia specjalistycznej bazy danych medycznych, której przeznaczeniem jest wspomaganie procesu uczenia klasyfikatorów chorób przewodu pokarmowego. Na koniec przed-stawiono zebrane w bazie dane oraz uzyskane efekty.

EN

The article briefly presents the process of diagnosing gastrointestinal diseases and discusses existing techniques of supporting it with automatic analysis of video from gastrointestinal examinations. Further, the process of designing a specialized medical database is described. The main goal of the created database is to provide data for the training of automatic classifiers of gastrointestinal diseases. Finally, the collected data and acquired results are presented.

6

Kapsułka endoskopowa nowej generacji

Turcza P., Duplaga M.

Pomiary Automatyka Kontrola

|

2012

|

R. 58, nr 4

331-334

PL

W artykule przedstawiono wyniki prac realizowanych w ramach projektu VECTOR finansowanego w ramach 6 Programu Ramowego Unii Europejskiej w zakresie systemów kompresji i bezprzewodowej transmisji danych i obrazu dedykowanych dla endoskopii kapsułkowej nowej generacji. Opracowany system umożliwia transmisję 24 obrazów na sekundę o rozdzielczości 320x240 przez łącze radiowe o przepustowości 2 Mbit/s. Możliwość długotrwałej pracy kapsułki ma zapewnić układ zasilania bezprzewodowego zdolny dostarczyć do 300 mW mocy.

EN

The paper discusses the outcomes of the European Project VECTOR FP6 concerning image compression and wireless data transmission systems dedicated to a new generation of capsule endoscopy. The overview of the developed system is given in Section 2. The image compressor algorithm, developed within the project, is presented briefly in the first part of Section 3. Next, a new adaptive entropy encoder proposed for it is discussed in detail. The new encoder, in comparison to the previous one, has much lower memory footprint, as it does not use Huffman tables. Simulation results given in Tab. 1 clearly demonstrate that the new encoder, despite its low implementation complexity, outperform the old one. The developed image compressor algorithm was implemented in a single, 65 nm ultra low-power FPGA. It operates with 24 MHz clock and it is able to process a single image frame in 8.2 ms. Its energy consumption amounts to 0.4 mJ per single compressed frame. In Section 4 a wireless transmission system for wireless capsular endoscopy is presented. In this section an improved demodulator for a wireless receiver is also proposed. Section 5 contains the conclusions.