Wyniki wyszukiwania - BazTech

1

Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model

Swiderska-Chadaj Z., Markiewicz T., Gallego J., Bueno G., Grala B., Lorent M.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 6

849--856

EN

The pathologists follow a systematic and partially manual process to obtain histological tissue sections from the biological tissue extracted from patients. This process is far from being perfect and can introduce some errors in the quality of the tissue sections (distortions, deformations, folds and tissue breaks). In this paper, we propose a deep learning (DL) method for the detection and segmentation of these damaged regions in whole slide images (WSIs). The proposed technique is based on convolutional neural networks (CNNs) and uses the U-net model to achieve the pixel-wise segmentation of these unwanted regions. The results obtained show that this technique yields satisfactory results and can be applied as a pre-processing step for automatic WSI analysis in order to prevent the use of the damaged areas in the evaluation processes.

2

MIAP – Web-based platform for the computer analysis of microscopic images to support the pathological diagnosis

Markiewicz T., Korzynska A., Kowalski A., Swiderska-Chadaj Z., Murawski P., Grala B., Lorent M., Wdowiak M., Zak J., Roszkowiak L., Kozlowski W., Pijanowska D.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 4

597--609

EN

The aim of the project is to design and to implement a web-based platform for the computer analysis of microscopic images which support the pathological diagnosis. The use of the platform will be free of charge. It offers: quantitative analysis of staining tissue sample' images, archiving microscopic images, peer consultation, and join work independently from distance between scientific collaborating centers to registered doctors, scientists and students. The use of proposed platform allows: (i) to save pathologists' time spend on quantitative analysis, (ii) to reduce consulting costs by replacing sending of the physical preparations by placing their images (mostly virtual slide) on the platform server, (iii) to increase reproducibility, comparability and objectivity of quantitative evaluations. These effects have a direct impact on improving the effectiveness and decreasing the costs of patients' treatment. This paper presents the main ideas of the project which deliver web-based system working as multi-functional, integrated, modular and scalable computer system. The details of hardware solutions, concept of the workflow in the platform, the programming language and interpreters, the specific tools and algorithms, and the user interfaces are described below. The practical solutions for web-based services in the area of medical image analysis, storage and retrieval are also presented and discussed.

3

Automatic ROI selection in virtual slide images for assessment of pathomorphological diagnostic

Markiewcz T., Świderska Ż., Grala B., Kozłowski W.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 7

1-4

EN

This paper describes the automatic region of interest selection method in virtual slide images for assessment of pathomorphological diagnostic. The proposed method for identification of high concentration of immunopositive cancer cells is based on specimen area recognition, segmentation of the immunopositive cells, local maxima recognition on cell density map and function of penalty to avoid the too high concentration of the selected ROIs. The obtained results confirm, that average 8.6±1.4 of 10 reaction fields chosen manually were compliant regionally with regions selected automatically, which is a high compliance of specimen histological examination.

PL

W pracy zaproponowano metodę automatycznego wyboru obszarów zainteresowań w obrazach wirtualnych preparatów jako narzędzie wspierające diagnostykę patomorfologiczną. Zaproponowane metoda identyfikacji obszarów o wysokiej koncentracji immunododatnich komórek nowotworowych bazuje na wydzielaniu obszaru tkanki z obrazu, segmentacji komórek immunododatnich, wykrywaniu lokalnych maksimów na mapie gęstości rozkładu komórek oraz zaproponowanej funkcji kary w celu uniknięcia nadmiernej koncentracji zwracanych obszarów zainteresowań. Wyniki liczbowe wskazują, iż średnio 8.6±1.4 na 10 wybranych pól manualnie oraz automatycznie jest tożsamych obszarowo, co skutkuje wysoką zgodność oceny histologicznej przypadków.

4

Dydaktyka biblioteczna w uczelniach medycznych w aspekcie kształtowania się edukacji informacyjnej

Grala B.

PTINT Praktyka i Teoria Informacji Naukowej i Technicznej

|

2007

|

T. 15, nr 1

30-36

PL

Rozwój społeczeństwa informacyjnego nie pozostał bez wpływu na biblioteki, zwłaszcza naukowe. Nowoczesne bibliotekarstwo akademickie opiera się na koncepcji edukacyjnej bibliotek i aktywnym udziale w procesie dydaktycznym uczelni. Celem artykułu jest zaprezentowanie stanu dydaktyki bibliotek uczelni medycznych w Polsce w aspekcie edukacji informacyjnej.

EN

The development of the information society had impact on libraries, especially scientific. The modern academic librarianship is based on the educational conception of libraries and the active participation in the teaching process of the college. The purpose of this article is to present the state of the didactics of libraries for the medical schools in Poland in the aspect of ther information education.