microscopic images Dotaz Zobrazit nápovědu
Při získávání mikroskopických obrazů o velmi vysokém rozlišení metodou skladu výsledného obrazu z jednotlivých dílů jsme narazili na některé problémy. Mezi nimi byla nutnost refokusace hiezi jednotlivými dílky. S tím souvisely problémy se spojením obrazů, které si vzájemně zcela neodpovídaly a oblast spojení byla zřetelná. Byl vyvinut prograin překonávající některé problémy pri spojování obrazových dílků, který pracuje se všemi díly naráz a hledá optimální pořadí spojení dílů. Jednotlivé dílky spojuje strmým gradientem, který probíhá po náhodně generované křivce. Program dává dobré výsledky i pri spojení obrazů s pozadím či otvory ve snímané tkáni. Metoda postupného snímání a následné montáže obrazu byla využita i pro snímání sbírky kožnich lymfomů ve spolupráci s Institutem pro dermatologii Univerzitní nemocnice v Curychu. Takto vzniklá digitální sbírka je veřejně k dispozici jako kapitola šesté verze Hypertextového atlasu dermatopatologie na www.muni.cz/atlases.
Composing microscopic images of very high resolution from several paris posed some problems. One of them was the necessity to adjust the focusing level when moving fi'om one part to another. Re-focusing lead to problems with joining the image parts, which did not correspond exactly, and the area of image fusion was noticeable. A computer program was developed to overcome these problems. Our program worked with all the image parts together to find their optimal order for image fusion. Individual image parts were joined using a steep gradient running along a randomly generated curve. This method gave good results even in images with background or holes in the tissue. The method of composing large images from individual parts was used for digitizing the skin lymphoma collection of the Institute of Dermatology, University Hospital, Zurich. This collection of digital images is a part of the 6th version of Hypertext atlas of Dermatopathology at www.muni.cz/atlases.
Clinical islet transplantation programs rely on the capacities of individual centers to quantify isolated islets. Current computer-assisted methods require input from human operators. Here we describe two machine learning algorithms for islet quantification: the trainable islet algorithm (TIA) and the nontrainable purity algorithm (NPA). These algorithms automatically segment pancreatic islets and exocrine tissue on microscopic images in order to count individual islets and calculate islet volume and purity. References for islet counts and volumes were generated by the fully manual segmentation (FMS) method, which was validated against the internal DNA standard. References for islet purity were generated via the expert visual assessment (EVA) method, which was validated against the FMS method. The TIA is intended to automatically evaluate micrographs of isolated islets from future donors after being trained on micrographs from a limited number of past donors. Its training ability was first evaluated on 46 images from four donors. The pixel-to-pixel comparison, binary statistics, and islet DNA concentration indicated that the TIA was successfully trained, regardless of the color differences of the original images. Next, the TIA trained on the four donors was validated on an additional 36 images from nine independent donors. The TIA was fast (67 s/image), correlated very well with the FMS method (R2=1.00 and 0.92 for islet volume and islet count, respectively), and had small REs (0.06 and 0.07 for islet volume and islet count, respectively). Validation of the NPA against the EVA method using 70 images from 12 donors revealed that the NPA had a reasonable speed (69 s/image), had an acceptable RE (0.14), and correlated well with the EVA method (R2=0.88). Our results demonstrate that a fully automated analysis of clinical-grade micrographs of isolated pancreatic islets is feasible. The algorithms described herein will be freely available as a Fiji platform plugin.
- MeSH
- algoritmy MeSH
- automatizace MeSH
- krysa rodu rattus MeSH
- Langerhansovy ostrůvky * cytologie MeSH
- lidé MeSH
- počítačové zpracování obrazu * MeSH
- potkani Wistar MeSH
- strojové učení MeSH
- transplantace Langerhansových ostrůvků * MeSH
- zvířata MeSH
- Check Tag
- krysa rodu rattus MeSH
- lidé MeSH
- zvířata MeSH
Mikroskopická polyangiitída (MPA) je zriedkavá, systémová, nekrotizujúca, ANCA (Anti‑Neutrophil Cytoplasmic Antibodies) asociovaná vaskulitída s postihnutím malých ciev, bez dôkazu nekrotizujúceho granulomatózneho zápalu. Stanovenie diagnózy mikroskopickej polyangiitídy je často náročné vzhľadom na jej prezentáciu súborom nešpecifických symptómov. Na našej klinike sme toto ochorenie diagnostikovali u 35‑ročného pacienta, ktorý bol k nám prijatý pre migrujúce artritídy s febrilitami a papulóznym exantémom. Touto kazuistikou chceme poukázať na dôležitosť zváženia aj takých zriedkavých ochorení akým je, MPA v rámci diferenciálno‑diagnostického procesu najmä v prípade pacientov prezentujúcich sa nešpecifickými symptómami vzhľadom na vysokú mortalitu tohto ochorenia bez adekvátnej liečby.
Microscopic polyangiitis is a rare, systemic, necrotizing, pauci-immune, ANCA associated small vessel vasculitis, with no evidence of granulomatous inflammation. Diagnosing microscopic polyangiitis is often difficult because of it's presentation by a number of non-specific symptoms. We treated a 35-year old patient, who was admitted for migrating arthritis and fever with papulous rash. In this case, we want to point out the importance of considering the diagnosis of MPA and similar rare diseases in the process of differential diagnosis, mainly in patients presenting with non-specific symptoms, because the mortality of this disease without adequate treatment is alarmingly high.
- MeSH
- ANCA-asociované vaskulitidy * diagnóza patofyziologie terapie MeSH
- diagnostické zobrazování metody MeSH
- dospělí MeSH
- glomerulonefritida diagnóza terapie MeSH
- klinické laboratorní techniky MeSH
- lidé MeSH
- mikroskopická polyangiitida * diagnóza patofyziologie terapie MeSH
- pankreatitida diagnóza terapie MeSH
- výsledek terapie MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- mužské pohlaví MeSH
- Publikační typ
- kazuistiky MeSH
Background: Tuberculosis (TB) is a major cause of illness and death in many countries, especially in Asia and Africa. Repeated tests of microscopic examination are needed to be performed for early detection of the disease. Hence there is a need to automate the diagnostic process for improvement in the sensitivity and accuracy of the test. Objective: To automate the decision support system for tuberculosis digital images using histogram based statistical features and evolutionary based extreme learning machines. Materials and methods: The sputum smear positive and negative images recorded under standard image acquisition protocol are subjected to histogram based feature extraction technique. Most significant features are selected using student ‘t’ test. These significant features are further used as input to the differential evolutionary extreme learning machine classifier. Results: Results demonstrate that the histogram based significant features are able to differentiate TB positive and negative images with a higher specificity and accuracy. Conclusion: The methodology used in this work seems to be useful for the automated analysis of TB sputum smear images in mass screening disorders such as pulmonary tuberculosis.
Experimental pathology, ISSN 0232-2862 suppl. 9, 1984
123 s. : il., tab., grafy
- MeSH
- algoritmy MeSH
- automatizované zpracování dat MeSH
- mikroskopie metody trendy MeSH
- počítačové zpracování obrazu normy MeSH
- software MeSH
- Publikační typ
- přehledy MeSH
