Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: image artifact

Sortuj według:

Ogranicz wyniki do:

Learning-based local quality assessment of reflectance confocal microscopy images for dermatology applications

Sikorska Miroslawa, Skalski Andrzej, Wodzinski Marek, Witkowski Alexander, Pellacani Giovanni, Ludzik Joanna

Biocybernetics and Biomedical Engineering

2021

Vol. 41, no. 3

880--890

Background and objective: Skin cancer is one of the most common types of cancer and its early diagnosis significantly reduces patient morbidity and mortality. Reflectance confocal microscopy (RCM) is a modern and non-invasive method of diagnosis that is becoming popular amongst clinical dermatologists. The frequent occurrence of artifacts in the images is one of the most challenging factors in making a diagnosis based on RCM. It impedes the diagnosis process for the dermatologist and makes its automation difficult. In this work, we employ artificial neural networks to propose a local quality assessment system. It allows for the detection of artifacts and non-informative component images both retrospectively or in real-time during the examination. Methods: In this research we address the quality assessment issue by proposing an artificial intelligence-based solution. 612 RCM mosaics were divided into small component images and manually classified in order to train the ResNeXt model in the quality verification context. A trained network was used to create an application that marks individual classes of the component images on the mosaic. Results: We achieved the average classification precision of 0.98 both for the validation and test data sets. In addition, we present local quality assessment statistics of the 1540 cases of skin lesions to show which types of skin lesions most often present with artifacts in their RCM images. Conclusions: In this research we investigate the utility of the deep convolution neural networks for the local quality assessment of the RCM images. We propose an AI-based system that may be effectively used as real-time support for the dermatologist during a RCM examination and as a base for the automation of the diagnostic process.

Kontrola jakości systemów MRI : testy podstawowe

Sokół M., Wicher M., Wochlik I., Bułka J., Machnikowska-Sokołowska M.

Inżynier i Fizyk Medyczny

2016

Vol. 5, nr 6

301--308

Rezonans magnetyczny, od momentu zaistnienia, zajął centralne miejsce wśród technik radiologicznych. O ile jednak w przypadku aparatury rentgenodiagnostycznej obowiązują w zakresie kontroli jakości jednolite zalecenia i przepisy prawne, to nie ma takich wytycznych w odniesieniu do MRI. Procedury kontroli jakości opracowane przez ACR (American College of Radiology) mogą stanowić idealny punkt wyjścia do konstruowania własnego programu kontroli jakości w pracowni MRI. W niniejszej pracy opisano osiem podstawowych testów systemu MRI, takich jak: kontrola współczynnika stosunku sygnału do szumu, częstotliwości rezonansowej, zniekształceń geometrycznych, jednolitości intensywności obrazu, obecności cieni dodatkowych na obrazach, rozdzielczości przestrzennej przy wysokim kontraście, wykrywania obiektów o niskim kontraście, grubości warstwy i położenia warstwy. Testy wykonano przy użyciu fantomu ACR MRI oraz w kilku przypadkach, dla porównania, fantomu GE.

Since its discovery, magnetic resonance imaging (MRI) has been one of the main methods of imaging in radiology. So far, there are not many national or international guidelines for MRI quality assurance (QA) compared to imaging methods that are using ionizing radiation. Thus, the QA procedures developed by the American College of Radiology (ACR) may constitute an ideal starting point for constructing an own MRI QA program. In this study, eight basic test procedures, such as: signal-to-noise ratio, central frequency of the scanner, geometric accuracy, image intensity uniformity, percent signal ghosting, high-contrast resolution, low-contrast object detectability, slice thickness accuracy and slice position accuracy are described. The tests were done using the ACR MRI phantom, however in some of the tests also the GE phantomwas applied, for a sake of comparison.