• MeSH
• Electronic Data Processing MeSH
• Diagnosis, Computer-Assisted MeSH
• Electroencephalography MeSH
• Publication type
• Comparative Study MeSH

Článek popisuje možnosti zpracování medicínských dat potnoci programu Analyze. Program Analyze představuje propracovaný systém umožňující předzpracování a vizualizaci medicínských dat jak ve 2D, tak v 3D prostoru. v oblasti 2D jsou to nástroje pro konverzi vstupnich dat, filtraci (včetně rychlé Fourierovy a Wavelet transformace), segmentaci a operace s rastrovými obrazy. U prostorového zpracování je možné provádět rekonstrukce dat z paralelních rastrových řezů získaných například Z CT a MRI. Program zahrnuje nástroje pro měření a prezentaci výsledků.

The article deals with the possibilities of processing medical data using the program Analyze. The program Analyze represents a complex system for pre-processing and visualization of medical data in both 2D and 3D space. In 2D mode it represents image conversion, filtering (including fast Fourier and Wavelet transformation), segmentation and operations with raster pictures. In 3D it allows users to reconstruct data from parallel raster slices obtained from CT and MR. The program also comprises tools for measurement and presentation of results.

• MeSH
• Medical Informatics Computing MeSH
• Humans MeSH
• Software MeSH
• Data Display MeSH
• Check Tag
• Humans MeSH

In our paper, we present a performance evaluation of image segmentation algorithms on microscopic image data. In spite of the existence of many algorithms for image data partitioning, there is no universal and 'the best' method yet. Moreover, images of microscopic samples can be of various character and quality which can negatively influence the performance of image segmentation algorithms. Thus, the issue of selecting suitable method for a given set of image data is of big interest. We carried out a large number of experiments with a variety of segmentation methods to evaluate the behaviour of individual approaches on the testing set of microscopic images (cross-section images taken in three different modalities from the field of art restoration). The segmentation results were assessed by several indices used for measuring the output quality of image segmentation algorithms. In the end, the benefit of segmentation combination approach is studied and applicability of achieved results on another representatives of microscopic data category - biological samples - is shown.

• MeSH
• Algorithms * MeSH
• Microscopy * methods   MeSH
• Mice MeSH
• Image Processing, Computer-Assisted methods   standards   MeSH
• Animals MeSH
• Check Tag
• Mice MeSH
• Animals MeSH
• Publication type
• Journal Article MeSH
• Evaluation Study MeSH
• Research Support, Non-U.S. Gov't MeSH

OBJECTIVES: Class imbalance in datasets is one of the challenges of machine learning (ML) in medical image analysis. We employed synthetic data to overcome class imbalance when segmenting bitewing radiographs as an exemplary task for using ML. METHODS: After segmenting bitewings into classes, i.e. dental structures, restorations, and background, the pixel-level representation of implants in the training set (1543 bitewings) and testing set (177 bitewings) was 0.03 % and 0.07 %, respectively. A diffusion model and a generative adversarial network (pix2pix) were used to generate a dataset synthetically enriched in implants. A U-Net segmentation model was trained on (1) the original dataset, (2) the synthetic dataset, (3) on the synthetic dataset and fine-tuned on the original dataset, or (4) on a dataset which was naïvely oversampled with images containing implants. RESULTS: U-Net trained on the original dataset was unable to segment implants in the testing set. Model performance was significantly improved by naïve over-sampling, achieving the highest precision. The model trained only on synthetic data performed worse than naïve over-sampling in all metrics, but with fine-tuning on original data, it resulted in the highest Dice score, recall, F1 score and ROC AUC, respectively. The performance on other classes than implants was similar for all strategies except training only on synthetic data, which tended to perform worse. CONCLUSIONS: The use of synthetic data alone may deteriorate the performance of segmentation models. However, fine-tuning on original data could significantly enhance model performance, especially for heavily underrepresented classes. CLINICAL SIGNIFICANCE: This study explored the use of synthetic data to enhance segmentation of bitewing radiographs, focusing on underrepresented classes like implants. Pre-training on synthetic data followed by fine-tuning on original data yielded the best results, highlighting the potential of synthetic data to advance AI-driven dental imaging and ultimately support clinical decision-making.

• MeSH
• Humans MeSH
• Image Processing, Computer-Assisted * methods   MeSH
• Machine Learning * MeSH
• Dental Implants MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

Úvod: Přístrojově asistované kvantitativní testování senzitivity (QST) se stanovením termických (TPT) a vibračních (VPT) prahů patří v současnosti mezi klíčové metody v diagnostickém algoritmu senzitivních neuropatií. Cílem práce je derivace validních, věkově stratifikovaných normativních dat pro obě QST metodiky. Soubor a metodika: Věkově stratifikovaná normativní data (v podskupinách 20–40, 40–60 a 60+ let) byla derivována z nálezů souborů 88 (TPT), resp. 74 (VPT) zdravých dobrovolníků. Výsledky: Při vyšetření TPT i VPT byla prokázána mírně horší percepce všech testovaných modalit u mužů ve srovnání se ženami a signifikantní věkově podmíněný pokles termických prahů pro chlad (při použití metody Limity byl dolní normální limit (NL) pro jednotlivé věkové kategorie stanoven na úrovni 26,3–25,5–22,8 °C u mužů a 29,1–26,6–21,1 °C u žen) a vzestup prahů pro teplo (horní NL 40,8–44,9–46,2 °C u mužů a 39,5–41,2–48,2 °C u žen) i vibrační čití (horní NL 6,0–12,5–50,3 μm u mužů a 4,0–13,2–33,6 μm u žen). Výška prahu byla ovlivněna také volbou algoritmu testování, tj. byla mírně vyšší v metodách reakčního času (Limity) oproti metodám konstantního stimulu (Úrovně). Závěry: Senzitivní prahy pro teplo, chlad i vibrační čití vykazují signifikantní vliv věku a méně významný vliv pohlaví vyšetřených jedinců na nálezy ve skupině zdravých dobrovolníků. Při hodnocení výsledků obou metod u pacientů se senzitivní neuropatií je tedy vhodné použití věkově stratifikovaných normativních dat pro jednotlivá pohlaví se zohledněním příslušného algoritmu testování.

Introduction: Detection of thermal (TPT) and vibratory (VPT) perception thresholds using the computer-assisted quantitative sensory testing (QST) is currently one of the most important methods for diagnosing sensory neuropathies. The aim of the study was to establish valid, age-stratified normal limits for both the QST methods. Patients and methods: Findings from 88 (TPT) or 74 (VPT) healthy individuals provided the basis for establishing age-stratified normal values in subgroups of patients aged 20–40, 40–60 and 60+ years. Results: Slight but significant differences between men and women and highly significant age-related changes were found for all the TPTs and VPTs with lower cold thresholds and higher warm and vibratory thresholds in men and in older individuals. Using the method of limits, lower normal values for cold TPT were set at 26.3–25.5–22.8 °C for the respective age subgroups of men and 29.1–26.6–21.1 °C for the respective age subgroups of women. Similarly, upper normal limits for warm TPT were set at 40.8–44.9–46.2 °C, respectively, in men and 39.5–41.2–48.2 °C, respectively, in women, and at 6.0–12.5–50.3 μm, respectively, in men and 4.0–13.2–33.6 μm, respectively, in women for VPT. Threshold values also depend on the testing algorithm used, with slightly higher values in reaction time inclusive methods (Limits) compared to reaction time exclusive algorithms (Levels). Conclusions: Cold and warm TPT as well as VPT display significant age-effect and less significant effect of gender on perception threshold values. The evaluation of the VPT and TPT findings in patients with sensory neuropathies should thus be performed using the age- and gender-adjusted normal values for particular testing algorithm.

• Keywords
• senzitivní neuropatie, kvantitativní testování senzitivity, normativní data,
• MeSH
• Diabetic Neuropathies diagnosis   complications   MeSH
• Diagnostic Techniques, Neurological standards   instrumentation   MeSH
• Adult MeSH
• Electrodiagnosis methods   instrumentation   MeSH
• Middle Aged MeSH
• Humans MeSH
• Autonomic Nervous System Diseases diagnosis   complications   MeSH
• Sensation Disorders diagnosis   complications   MeSH
• Pain Threshold classification   MeSH
• Aged MeSH
• Software MeSH
• Vibration adverse effects   MeSH
• Thermosensing MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged MeSH
• Female MeSH

• MeSH
• Electronic Data Processing MeSH
• Diagnosis, Computer-Assisted MeSH
• Electroencephalography classification   MeSH

This paper aims to address the segmentation and classification of lytic and sclerotic metastatic lesions that are difficult to define by using spinal 3D Computed Tomography (CT) images obtained from highly pathologically affected cases. As the lesions are ill-defined and consequently it is difficult to find relevant image features that would enable detection and classification of lesions by classical methods of texture and shape analysis, the problem is solved by automatic feature extraction provided by a deep Convolutional Neural Network (CNN). Our main contributions are: (i) individual CNN architecture, and pre-processing steps that are dependent on a patient data and a scan protocol - it enables work with different types of CT scans; (ii) medial axis transform (MAT) post-processing for shape simplification of segmented lesion candidates with Random Forest (RF) based meta-analysis; and (iii) usability of the proposed method on whole-spine CTs (cervical, thoracic, lumbar), which is not treated in other published methods (they work with thoracolumbar segments of spine only). Our proposed method has been tested on our own dataset annotated by two mutually independent radiologists and has been compared to other published methods. This work is part of the ongoing complex project dealing with spine analysis and spine lesion longitudinal studies.

• MeSH
• Middle Aged MeSH
• Humans MeSH
• Spinal Neoplasms diagnostic imaging   secondary   MeSH
• Neural Networks, Computer * MeSH
• Tomography, X-Ray Computed * MeSH
• Radiographic Image Interpretation, Computer-Assisted methods   MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Imaging, Three-Dimensional * MeSH
• Check Tag
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

Difuzně vážené zobrazení tkání je zásadní součástí vyšetřovacích protokolů magnetické rezonance. Snížení jeho kvality na 3T přístrojích v porovnání s 1, 5T je při použití konvenčních metod náběru dat významné a vyžaduje hledání nových postupů. Technika RESOLVE (REeadout Segmentation Of Long Variable Echo-trains) představuje volbu, která zmenšuje geometrické distorze a poskytuje vyšší prostorové rozlišení obrazu, nicméně při prodloužené době vyšetření.

Diffusion-weighted tissue imaging is very important part of magnetic resonance examination protocols. There is significant decrease of its quality in 3T compared to 1,5T machines if conventional techniques of data collections are used, and new methods are needed to be applied. RESOLVE (REadout Segmentation Of Long Variable Echo-trains) technique represents an option reducing geometric distortions and providing higher spatial resolution, however, with prolonged examination duration.

• Keywords
• technika RESOLVE,
• MeSH
• Diffusion Magnetic Resonance Imaging * methods   MeSH
• Echo-Planar Imaging methods   MeSH
• Humans MeSH
• Tissues MeSH
• Image Enhancement methods   MeSH
• Diffusion Tensor Imaging * methods   MeSH
• Imaging, Three-Dimensional MeSH
• Check Tag
• Humans MeSH
• Publication type
• Review MeSH

This paper describes an evaluation framework that allows a standardized and quantitative comparison of IVUS lumen and media segmentation algorithms. This framework has been introduced at the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop, comparing the results of eight teams that participated. We describe the available data-base comprising of multi-center, multi-vendor and multi-frequency IVUS datasets, their acquisition, the creation of the reference standard and the evaluation measures. The approaches address segmentation of the lumen, the media, or both borders; semi- or fully-automatic operation; and 2-D vs. 3-D methodology. Three performance measures for quantitative analysis have been proposed. The results of the evaluation indicate that segmentation of the vessel lumen and media is possible with an accuracy that is comparable to manual annotation when semi-automatic methods are used, as well as encouraging results can be obtained also in case of fully-automatic segmentation. The analysis performed in this paper also highlights the challenges in IVUS segmentation that remains to be solved.

• MeSH
• Databases, Factual standards   MeSH
• Internationality MeSH
• Image Interpretation, Computer-Assisted methods   standards   MeSH
• Ultrasonography, Interventional methods   standards   MeSH
• Humans MeSH
• Coronary Artery Disease ultrasonography   MeSH
• Reference Values MeSH
• Reproducibility of Results MeSH
• Sensitivity and Specificity MeSH
• Practice Guidelines as Topic * MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Research Support, N.I.H., Extramural MeSH
• Research Support, U.S. Gov't, Non-P.H.S. MeSH

• MeSH
• Algorithms MeSH
• Cells MeSH
• Medical Laboratory Science MeSH
• Models, Theoretical MeSH
• Data Display MeSH