Wyniki wyszukiwania - BazTech

1

SVIA dataset: A new dataset of microscopic videos and images for computer-aided sperm analysis

Chen Ao, Li Chen, Zou Shuojia, Rahaman Md Mamunur, Yao Yudong, Chen Haoyuan, Yang Hechen, Zhao Peng, Hu Weiming, Liu Wanli, Grzegorzek Marcin

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 1

204--214

EN

Computer-Aided Sperm Analysis (CASA) is a widely studied topic in the diagnosis and treatment of male reproductive health. Although CASA has been evolving, there is still a lack of publicly available large-scale image datasets for CASA. To fill this gap, we provide the Sperm Videos and Images Analysis (SVIA) dataset, including three different subsets, subset-A, subset-B and subset-C, to test and evaluate different computer vision techniques in CASA. For subset-A, in order to test and evaluate the effectiveness of SVIA dataset for object detection, we use five representative object detection models and four commonly used evaluation metrics. For subset-B, in order to test and evaluate the effectiveness of SVIA dataset for image segmentation, we used eight representative methods and three standard evaluation metrics. Moreover, to test and evaluate the effectiveness of SVIA dataset for object tracking, we have employed the traditional kNN with progressive sperm (PR) as an evaluation metric and two deep learning models with three standard evaluation metrics. For subset-C, to prove the effectiveness of SVIA dataset for image denoising, nine denoising filters are used to denoise thirteen kinds of noise, and the mean structural similarity is calculated for evaluation. At the same time, to test and evaluate the effectiveness of SVIA dataset for image classification, we evaluate the results of twelve convolutional neural network models and six visual transformer models using four commonly used evaluation metrics. Through a series of experimental analyses and comparisons in this paper, it can be concluded that this proposed dataset can evaluate not only the functions of object detection, image segmentation, object tracking, image denoising, and image classification but also the robustness of object detection and image classification models. Therefore, SVIA dataset can fill the gap of the lack of large-scale public datasets in CASA and promote the development of CASA. Dataset is available at: .https://github.com/Demozsj/Detection-Sperm.

2

Dataset enhancement in hair follicle detection: ESENSEI challenge

Jakubik J.

Annals of Computer Science and Information Systems

|

2018

|

Vol. 16

19--22

EN

In this paper, a solution to ESENSEI data mining challenge concerning the analysis of microscopic hair images is described. The task of the challenge was to detect locations of hair follicles in closeup images of a human scalp. The proposed solution is based on a convolutional neural network architecture. To improve generalization performance, we enhance training and test datasets using image transformations applied to both input and output. The chosen transformations are two axis symmetries and switching axes, all of which are possible to apply regardless of resolution without producing interpolation artifacts. Since these can be combined, 2^3 = 8 possible views of each image can be created to expand both training and test data. We demonstrate the effects of dataset enhancement in both training and classifying on results achievable on the competition dataset. The solution placed 2nd in the final challenge evaluation.

3

An ensemble of Deep Convolutional Neural Networks for Marking Hair Follicles on Microscopic Images

Podlodowski Ł., Roziewski Sz., Nurzyński M.

Annals of Computer Science and Information Systems

|

2018

|

Vol. 16

23--28

EN

This paper presents an application of a Convolutional Neural Network as a solution for a task associated with ESENSEI Challenge: Marking Hair Follicles on Microscopic Images. As we show in this paper quality of classification results could be improved not only by changing architecture but also by ensemble networks. In this paper, we present two solutions for the task, the first one based on benchmark convolutional neural network, and the second one, an ensemble of VGG-16 networks. Presented models took first and third places in the final competition leaderboard.

4

Full-automatic computer aided system for stem cell clustering using content-based microscopic image analysis

Li C., Huang X., Jiang T., Xu N.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 3

540--558

EN

Stem cells are very original cells that can differentiate into other cells, tissues and organs, which play a very important role in biomedical treatments. Because of the importance of stem cells, in this paper we propose a full-automatic computer aided clustering system to assist scientists to explore potential co-occurrence relations between the cell differentiation and their morphological information in phenotype. In this proposed system, a multi-stage Content-based Microscopic Image Analysis (CBMIA) framework is applied, including image segmentation, feature extraction, feature selection, feature fusion and clustering techni-ques. First, an Improved Supervised Normalized Cuts (ISNC) segmentation algorithm is newly introduced to partition multiple stem cells into individual regions in an original microscopic image, which is the most important contribution in this paper. Then, based on the seg-mented stem cells, 11 different feature extraction approaches are applied to represent the morphological characteristics of them. Thirdly, by analysing the robustness and stability of the extracted features, Hu and Zernike moments are selected. Fourthly, these two selected features are combined by an early fusion approach to further enhance the properties of the feature representation of stem cells. Finally, k-means clustering algorithm is chosen to classify stem cells into different categories using the fused feature. Furthermore, in order to prove the effectiveness and usefulness of this proposed system, we carry out a series of experiments to evaluate our methods. Especially, our ISNC segmentation obtains 92.4% similarity, 96.0% specificity and 107.8% ration of accuracy, showing the potential of our work.

5

A novel approach for detection and delineation of cell nuclei using feature similarity index measure

John J., Nair M. S., Kumar P. R. A., Wilscy M.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 1

76--88

EN

Accurate image segmentation of cells and tissues is a challenging research area due to its vast applications in medical diagnosis. Seed detection is the basic and most essential step for the automated segmentation of microscopic images. This paper presents a robust, accurate and novel method for detecting cell nuclei which can be efficiently used for cell segmentation. We propose a template matching method using a feature similarity index measure (FSIM) for detecting nuclei positions in the image which can be further used as seeds for segmentation tasks. Initially, a Fuzzy C-Means clustering algorithm is applied on the image for separating the foreground region containing the individual and clustered nuclei regions. FSIM based template matching approach is then used for nuclei detection. FSIM makes use of low level texture features for comparisons and hence gives good results. The performance of the proposed method is evaluated on the gold standard dataset containing 36 images (_8000 nuclei) of tissue samples and also in vitro cultured cell images of Stromal Fibroblasts (5 images) and Human Macrophage cell line (4 images) using the statistical measures of Precision and Recall. The results are analyzed and compared with other state-of-the-art methods in the literature and software tools to prove its efficiency. Precision is found to be comparable and the Recall rate is found to exceed 92% for the gold standard dataset which shows considerable performance improvement over existing methods.

6

Application of content-based image analysis to environmental microorganism classification

Li C., Shirahama K., Grzegorzek M.

Biocybernetics and Biomedical Engineering

|

2015

|

Vol. 35, no. 1

10--21

EN

Environmental microorganisms (EMs) are single-celled or multi-cellular microscopic organ-isms living in the environments. They are crucial to nutrient recycling in ecosystems as they act as decomposers. Occurrence of certain EMs and their species are very informative indicators to evaluate environmental quality. However, the manual recognition of EMs in microbiological laboratories is very time-consuming and expensive. Therefore, in this article an automatic EM classification system based on content-based image analysis (CBIA) techniques is proposed. Our approach starts with image segmentation that determines the region of interest (EM shape). Then, the EM is described by four different shape descriptors, whereas the Internal Structure Histogram (ISH), a new and original shape feature extraction technique introduced in this paper, has turned out to possess the most discriminative properties in this application domain. Afterwards, for each descriptor a support vector machine (SVM) is constructed to distinguish different classes of EMs. At last, results of SVMs trained for all four feature spaces are fused in order to obtain the final classification result. Experimental results certify the effectiveness and practicability of our automatic EM classification system.

7

Equalisation of archival microscopic images from immunohistochemically stained tissue sections

Neumann U., Korzyńska A., Lopez C., Lejeune M., Roszkowiak Ł., Bosch R.

Biocybernetics and Biomedical Engineering

|

2013

|

Vol. 33, no. 1

63--76

EN

A method of image equalisation that reduces non-uniformity of light distribution caused by optical devices and dust on camera sensors is presented. The method explores non-uniformity which occurs in archival images captured by a typical optical set which consists of a light microscope and a digital camera. A sufficient number of images with low density of foreground objects has been used to extract a global map of non-uniformity of the particular microscope and camera. The proposed method consists of two steps: – (1) extraction of the map of non-uniformity based upon a set of chosen images and – (2) correction of images acquired by the optical set. The global map is created based upon a modified value layer, the third layer of HSV colour space. The proposed method has been tested on images of immunohistochemically (IHC) stained samples of a biopsy tissue, and it has been validated using an image segmentation method developed earlier. The results of the light distribution equalization, as well as the equalized images segmentation turn out to be more similar to the reference method results (namely the manual counting results), than the results of the original images segmentation. The equalization method can be used for other types of images, but all of them should be acquired by the same optical set.

8

Computer system for processing of microscopic images

Lebioda M., Rymaszewski J.

Poznan University of Technology Academic Journals. Electrical Engineering

|

2011

|

No. 66

105--111

EN

A computer system for acquisition and processing of microscopic images has been presented in this paper. The main element of the presented system is a CCD camera coupled to the two kinds of microscopes: stereoscopic or metallographic and connected to a PC computer by USB.Acquisition and preparation of images for the qualitative and quantitative analysis is the primary objective of the system. The author's software allows for the realization of different types of the context and non-context operations for detection and identification of the selected fragment of images. The implemented algorithms have been oriented for the metallographic analysis.

9

New image processing algorithms in computer vision systems for phatomorphologic diagnostic

Bieniecki W.

Zeszyty Naukowe. Elektryka / Politechnika Łódzka

|

2006

|

z. 109

5-14

EN

In this paper main contributions of the author`s Ph. D. dissertation are summarized. The aim of the research was to develop two image processing systems for biomedicine: a system of automatic breast cancer nuclei classification and a system for immunoenzymatic lymphocyte response measurement. Standard image processing algorithms are insufficient for the completion of the task, so new algorithms had to be proposed. These include noise removal from color images, enhanced binarization method, pixel classification algorithm and watershed-based segmentation algorithm.

PL

W artykule zaprezentowano najważniejsze osiągnięcia autora pracy doktorskiej. Celem pracy było zaprojektowanie dwóch systemów automatycznego przetwarzania obrazów dla potrzeb biomedycyny: system rozpoznawania komórek tkanki raka piersi i system badania komórek układu odpornościowego po przeszczepie nerki. Istniejące algorytmy przetwarzania obrazu okazały się niewystarczające do realizacji zadania. Autor pracy zaproponował zmodyfikowane algorytmy: usuwanie szumu impulsowego z obrazów barwnych, wieloprzebiegowy algorytm binaryzacji obrazu, metoda klasyfikacji pikseli i algorytm segmentacji oparty o metodę działów wodnych.

10

Mechaniczna wytrzymałość ścian komórek drożdży

Solecki M.

Inżynieria i Aparatura Chemiczna

|

2006

|

Nr 4s

135-136

EN

Single cells of Saccharomyces cerevisiae yeast were subjected to a compression load. A pressure was applied by means of micro-tools controlled by three micro-manipulators. Deformation of microorganisms that caused disruption of cell walls was measured. Strength of yeast cells depending on their geometrical size was described. The distribution of cell size was determined by the computer image analysis method. An ellipsoid was assumed to be a basis for the description of yeast cell shape.

11

Wpływ proporcji składników atmosfery azotującej na strukturę warstwy azotowanej jonowo

Głowacki S., Majchrzak A., Majchrzak W.

Obróbka Plastyczna Metali

|

2005

|

T. 16, nr 2

15-22

PL

Badano skład fazowy i strukturę warstwy azotowanej jonowo w atmosferze H2 - N2, o zawartości azotu wynoszącej: 3; 5; 9 lub 26%. Próbki były wykonane ze stali do azotowania 38HMJ i stali narzędziowej do pracy na gorąco WCL. Przedstawiono wyniki badań warstwy wierzchniej azotowanych próbek za pomocą dyfraktometru rentgenowskiego i świetlnego mikroskopu metalograficznego. Stwierdzono, że wzajemne proporcje azotu i wodoru w atmosferze azotującej mają istotny wpływ na budowę warstwy azotowanej jonowo. Badania rentgenowskie ograniczone były do warstwy o grubości 0,1 mm.

EN

Phase composition and structure of a case ion nitrided in H2-N2 nitriding gas mixture containing 3; 5; 9 or 26 per cent of nitrogen was examined. Tested samples were made of nitriding steel marked 38HMJ and hot-work tool steel marked WCL. Results of X-ray and metallurgical microscopy examination of nitrided case of the samples are presented. It was found that mutual proportions of nitrogen and hydrogen in nitriding atmosphere have significant effect on a structure of the case. X-ray examination was limited to the case thickness of 0.1 mm.

12

Wykorzystanie wiedzy pozyskanej z obrazów mikroskopowych do klasyfikacji cieczy roboczych

Dębska B., Dobrowolski L.

Przemysł Chemiczny

|

2003

|

T. 82, nr 8-9

1275-1278

13

Niejednorodność fazy zbrojącej w kompozytach duralcan przeznaczonych do współpracy ślizgowej

Maszybrocka J., Cybo J.

Zeszyty Naukowe Politechniki Świętokrzyskiej. Mechanika

|

2001

|

Z. 75

127-134

PL

Badaniom poddano trzy gatunki kompozytów Duralcan o zmiennej zawartości fazy Al2O3, przeznaczonych do współpracy ślizgowej w układzie tuleja cylindrowa /pierścień tłokowy silnika spalinwego. Określono wskaźniki oraz rozmieszczenia fazy zbrojącej. Wykazano, że kompozyt o zawartości 10% obj. Al2O3 i wielkości cząstek ok.6 um cechuje się największą niejednorodnością wielkości, a zwłaszcza rozmieszczenia. Tę ostatnią można zaliczyć do kategorii niejednorodności izotropowej w postaci losowo usytuowanych mikroobszarów o niewielkiej liczbie cząstek Al2O3. Stwierdzono, że nasilenie lokalnych nierównomierności określają ilościowo z wystarczającą dokładnością wskaźniki zmienności parametrów, np. NA, NV, NL. Występowanie mikroobszarów o małym udziale Al2O3 może prowadzić do lokalnych sczepień adhezyjnych i pogorszenia współpracy tribologicznej. Problem niejednorodności rozmieszczenia maleje wraz z rosnącą zawartością fazy zbrojącej, prawie zanikając przy udziale FZ przekraczającym 20% objętości.

EN

Three kinds of Duralcan composites with changeable Al2O3, phase contents destined for a sliding cooperation in an arrangement: cylinder sleeve/pistonm ring of a combusation engine were subjected to examinations. Indices of the shape inhomogeneity and of the reinforcing phase size and distribution were determined. It was revealded that a composite with a 10% volume of Al2O3, and particles size of about 6 um is characterizedby the highest inhomogeneity of size and especially of distribution. The latter can be reared in the category of isotropic inhomogeneity in a form of microregions located at random, with an insignificant number of Al2O3 particles. It was found that the intensification of local irregularities is determined quantitatively, with sufficient accuracy, by parameters variability indices, e.g. NA, Vy and Nh. The occurrence of microregions with a small fraction of Al2O3 may lead to local adhesion tacking and deterioration of the tribological cooperation. The problem of the distribution inhomogeneity decreases as the reinforcing phase contents increase and it disappears with the reinforcing phase fraction exceeding a 20% volume.

14

Porównanie rodzajów sterylizacji na podstawie wyników badań mikroskopowych sterylizowanych włókien światłowodowych

Stawarz M., Podbielska H.

Acta Bio-Optica et Informatica Medica. Inżynieria Biomedyczna

|

2001

|

Vol. 7, nr 3-4

123-131

PL

W niniejszej pracy przedstawiono wyniki badań nad wpływem sterylizacji na parametry optyczne włókien światłowodowych. Sterylizację wykonano dwiema technikami: niskotemperaturową (plazmową) i wysokotemperaturową (parową). Badano transmisję światła przez światłowody prostopadle do długiej osi. Transmisję oceniano na podstawie obrazu mikroskopowego odcinków światłowodów, wyznaczając histogramy i luminancje obrazów. Udowodniono, że sterylizacja plazmowa jest mniej niszcząca dla światłowodów niż sterylizacja parowa.

EN

The results of investigation of sterilization influence on optical parameters of fibers are discussed in this work. Two methods of sterilization were applied: low temperature process (plasma sterilization) and high temperature one (by means of hot steam). The light transmission was examined perpendicular to the fiber long axis. The transmission was evaluated basing on the microscopic image of the fiber by calculating the image histogram and luminance. It was stated that plasma sterilization is less damaging to the fiber than this one by hot steam.

15

Zaawansowane zagadnienia komputerowego przetwarzania i analizy obrazu mikroskopowego

Wojnar L.

LAB Laboratoria, Aparatura, Badania

|

2000

|

R. 5, nr 4

34-40

16

Komputerowe przetwarzanie i analiza obrazu mikroskopowego

Wojnar L.

LAB Laboratoria, Aparatura, Badania

|

2000

|

R. 5, nr 3

14-19

17

Computerised system for detecting cell forms in the urine combined with the microscope analysis

Dyszkiewicz A., Koprowski R., Wróbel Z.

Journal of Medical Informatics & Technologies

|

2000

|

Vol. 1

BI 59--65

EN

The study presents the computerised system of urogical monitoring of patients with catheters in their bladders. The phenomenon of capacity resistance which is caused by live cells in solutions under the influence of the low frequency alternating current was used to build a sensor. The sensor indicates the presence of live cells and red or white blood cells in the urine, when the need of an immedicate treatment is obvious. The measuring part of the sensor consists of an induction loop which is adjusted to the measuring of the urine resistance by means of alternating current and the pair of electrodes to measure the resistance by direct current and a digital system for comparing the values of the resistance for alternating and direct current. When any cells forms are present, during the measuring by alternating current capacity resistance is added to the ohm resistance. If the cell forms are present, the capacity resistance does not appear. The mathematical proportion between the resistance values for direct and alternating current is proportional to the amount of cells in the solution. In the calibration process, indications of the ohmometer are compared to the digital microscopic image of the given urine sample. A direct relation between the resistance factor value and the cell concentration in urine is then obtained.

PL

W opracowaniu przedstawiony został skomputeryzowany system nadzoru urologicznego nad pacjentem z wprowadzonym do pęcherza moczowego cewnikiem. Wykorzystując zjawisko reaktancji pojemnościowej generowanej przez żywe komórki w roztworach pod wpływem prądu zmiennego m.cz zbudowany został czujnik reagujący na pojawianie się moczu żywych bakterii, krwinek białych i czerwonych, sygnalizujących potrzebę włączenia natychmiastowego leczenia. Część pomiarowa czujnika zbudowana jest z pary elektrod do pomiaru oporności napięciem stałym lub zmiennym małej częstotliwości oraz układu cyfrowego dokonującego porównania modułu impedancji. W przypadku pojawienia się elementów komórkowych, podczas pomiaru napięciem zmiennym do oporności wyznaczonej dla napięcia stałego dołącza się reaktancja pojemnościowa, natomiast jeżeli elementy morfotyczne nie występują reaktancja pojemnościowa się nie pojawia. Matematyczna proporcja pomiędzy wartością modułu impedancji dla napięcia stałego lub zmiennego m.cz w stosunku do w.cz, jest proporcjonalna do ilości komórek w roztworze. W procesie kalibracji wartość modułu impedancji jest konfrontowana z cyfrowym obrazem mikroskopowym danej próbki moczu, w której dokonujemy obliczeń ilości bakterii lub komórek przypadających na milimetr kwadratowy powierzchni. Uzyskujemy wówczas bezpośrednią zależność wartości współczynnika impedancji od koncentracji komórek w badanym moczu.