Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: badanie osadu moczu

Sortuj według:

Ogranicz wyniki do:

Osad moczu jako marketer chorób nerek

Motybel-lwańczuk Elżbieta, Kamińska Joanna, Matowicka-Karna Joanna

Laboratorium Medyczne

2019

nr 1

14--19

Ostre uszkodzenie nerek (AKI, ang. acute kidney injury) jest częstym powikłaniem klinicznym prowadzącym do wystąpienia powikłań i zwiększenia śmiertelności. Tradycyjne markery występujące we krwi i moczu są mało specyficzne w wykrywaniu wczesnego uszkodzenia nerek. Konieczne jest zatem poszukiwanie nowych markerów uszkodzenia nerek, które w sposób nieinwazyjny zobrazują stan tego narządu i pomogą w szybszym włączeniu odpowiedniej terapii farmakologicznej. Badanie osadu moczu dostarcza wielu informacji cennych diagnostycznie i jest pomocne w prognozowaniu u pacjentów z podejrzeniem choroby nerek.

Acute kidney injury (AKI) is a common clinical complication leading to an increase in the occurrence of complications and mortality. Traditional markers present in blood and urine are not very specific in detecting early kidney damage. Therefore, it is necessary to look for new markers of kidney damage that will depict the condition of this organ in a non-invasive manner and help in the faster implementation of appropriate pharmacological therapy. Urine sediment examination provides a lot of diagnostically valuable information and is helpful in prognosing in patients with suspected renal disease.

Object detection based on deep learning for urine sediment examination

Liang Y., Tang Z., Yan M., Liu J.

Biocybernetics and Biomedical Engineering

2018

Vol. 38, no. 3

661--670

Urine sediment examination (USE) is an important topic in kidney disease analysis and it is often the prerequisite for subsequent diagnostic procedures. We propose DFPN(Feature Pyramid Network with DenseNet) method to overcome the problem of class confusion in the USE images that it is hard to be solved by baseline model which is the state-of-the-art object detection model FPN with RoIAlign pooling. We explored the importance of two parts of baseline model for the USE cell detection. First, adding attention module in the network head, and the class-specific attention module has improved mAP by 0.7 points with pretrained ImageNet model and 1.4 points with pre-trained COCO model. Next, we introduced DenseNet to the baseline model(DFPN) for cell detection in USE, so that the input of the network's head own multiple levels of semantic information, compared to the baseline model only has high-level semantic information. DFPN achieves top result with a mAP of 86.9% on USE test set after balancing between the classification loss and bounding-box regression loss, which improve 5.6 points compared to baseline model, and especially erythrocyte's AP is greatly improved from 65.4% to 93.8%, indicating class confusion has been basically resolved. And we also explore the impacts of training schedule and pretrained model. Our method is promising for the development of automated USE.