Aim: To automatically predict the stability of carotid artery plaque from standard B-mode transversal ultrasound images using deep learning. A reliable predictor would reduce the need for fol low-up examination and pharmacological and surgical treatment. . Methods: A region of interest containing the carotid artery was automatically localized. An adversarial segmentation method was trained on a combination of a small pixelwise annotated dataset and a larger weakly annotated dataset. A multicriterion regression with automatic weight adaptation was applied to predict a series of clinically relevant attributes, including the plaque width increase over 3 years. . Results: The current plaque width could be estimated with a high correlation (rho = 0.32) and a very high statistical significance. The estimated future increase of the plaque width was correlated less (rho = 0.22) but statistically significantly (P < 0.01). The correlation between automatic and expert assessments of echogenicity, smoothness and calcification was even smaller. . Conclusion: We confirmed a relationship between the plaque appearance in ultrasound and the probability of its future growth, but it is too weak to be used in clinical practice as the sole predictor of the plaque stability.

Carotid plaque composition represents one of the main risk factors of future ischemic stroke. MRI provides excellent soft tissue contrast that can distinguish plaque characteristics. Our objective was to analyze the diagnostic accuracy of MRI imaging in the detection of carotid plaque characteristics compared to histology in patients with symptomatic and asymptomatic carotid atherosclerosis through a systematic review. After prospective registration in PROSPERO (ID CRD42022329690), Medline Ovid, Embase.com, Cochrane Library, and Web of Science Core were searched without any search limitation up to May 27, 2022 to identify eligible articles. Of the 8168 studies, 53 (37 × 1.5 T MRI, 17 × 3 T MRI) evaluated MRI accuracy in the detection of 13 specific carotid plaque characteristics in 169 comparisons. MRI demonstrated high diagnostic accuracy for detection of calcification (3 T MRI: mean sensitivity 92%/mean specificity 90%; 1.5 T MRI: mean sensitivity 81%/mean specificity 91%), fibrous cap (1.5 T: 89%/87%), unstable plaque (1.5 T: 89%/87%), intraplaque hemorrhage (1.5 T: 86%/88%), and lipid-rich necrotic core (1.5 T: 89%/79%). MRI also proved to have a high level of tissue discrimination for the carotid plaque characteristics investigated, allowing potentially for a better risk assessment and follow-up of patients who may benefit from more aggressive treatments. These results emphasize the role of MRI as the first-line imaging modality for comprehensive assessment of carotid plaque morphology, particularly for unstable plaque. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

AIMS:There is increasing evidence that plaque instability in the extracranial carotid artery may lead to an increased stroke risk independently of the degree of stenosis. We aimed to determine diagnostic accuracy of vulnerable and stable plaque using noninvasive imaging modalities when compared to histology in patients with symptomatic and asymptomatic carotid atherosclerosis. METHODS AND RESULTS:Medline Ovid, Embase, Cochrane Library, and Web of Science were searched for diagnostic accuracy of noninvasive imaging modalities (CT, MRI, US) in the detection of 1) vulnerable/stable plaque, and 2) vulnerable/stable plaque characteristics, compared to histology. The quality of included studies was assessed by QUADAS-2 and univariate and bivariate random-effect meta-analyses were performed. We included 36 vulnerable and 5 stable plaque studies in the meta-analysis, and out of 211 plaque characteristics from remaining studies, we classified 169 as vulnerable and 42 as stable characteristics (28 CT, 120 MRI, 104 US characteristics). We found that MRI had high accuracy [90% (95% CI: 82-95%)] in the detection of vulnerable plaque, similar to CT [86% (95% CI: 76-92%); P > 0.05], whereas US showed less accuracy [80% (95% CI: 75-84%); P = 0.013]. CT showed high diagnostic accuracy in visualizing characteristics of vulnerable or stable plaques (89% and 90%) similar to MRI (86% and 89%; P > 0.05); however, US had lower accuracy (77%, P < 0.001 and 82%, P > 0.05). CONCLUSION:CT and MRI have a similar, high performance in detecting vulnerable carotid plaques, whereas US showed significantly less diagnostic accuracy. Moreover, MRI visualized all vulnerable plaque characteristics allowing for a better stroke risk assessment. REGISTRATION:PROSPERO ID CRD42022329690.

Matching MRI brain images between patients or mapping patients' MRI slices to the simulated atlas of a brain is key to the automatic registration of MRI of a brain. The ability to match MRI images would also enable such applications as indexing and searching MRI images among multiple patients or selecting images from the region of interest. In this work, we have introduced robustness, accuracy and cumulative distance metrics and methodology that allows us to compare different techniques and approaches in matching brain MRI of different patients or matching MRI brain slice to a position in the brain atlas. To that end, we have used feature detection methods AGAST, AKAZE, BRISK, GFTT, HardNet, and ORB, which are established methods in image processing, and compared them on their resistance to image degradation and their ability to match the same brain MRI slice of different patients. We have demonstrated that some of these techniques can correctly match most of the brain MRI slices of different patients. When matching is performed with the atlas of the human brain, their performance is significantly lower. The best performing feature detection method was a combination of SIFT detector and HardNet descriptor that achieved 93% accuracy in matching images with other patients and only 52% accurately matched images when compared to atlas.

Diagnostic ultrasound (US) and magnetic resonance imaging (MRI) are important medical imaging methods in modern radiology. Our research is focused on imaging brain structures in neurology. In this paper we present differences of digital image analysis of the substantia nigra (SN) between US and MRI using the same algorithm. In the past, we developed an application for analyzing substantia nigra echogenicity in BMODE US images. Our developed application is based on a principle of binary thresholding in Region of Interest (ROI) to evaluate echogenicity grade. Increased echogenicity of SN is one of important markers for Parkinson�s Disease (PD) progress. The goal of this paper is to analyze if the same principle used for US B-MODE imaging is also applicable for different MR sequences to find out SN changes. From the achieved results detectable SN changes using MRI are possible at least as a complementary examination to US imaging. We need to prove if echogenicity index (called Echo-Index) is well reproducible value between two different MR sequences; SWI and T2-TSE; how to distinguish between pathological SN and normal anatomy. In the first pilot analysis, it seems that the principle of Echo-Index measurement could be a starting point to create a new large clinical study in this field. Totally 23 MR images from two different sequences (T1 and T2) were analyzed in this pilot study. However, it seems that Echo-Index cannot distinguish normal and diseased SN.

We describe an automatic pipeline for processing ultrasound images of the carotid artery, consisting of image type classification, carotid artery localization, segmentation, feature descriptor extraction, and plaque stability classification. The aim is to distinguish between stable (safe) and progressive (dangerous) atherosclerotic plaques from a single standard ultrasound transversal or longitudinal B-mode examination. The processing pipeline uses modern deep CNN techniques, while the descriptors are based on geometry and wavelets to characterize texture. When testing on a large dataset of 28718 images from 413 patients, we found that our automatically calculated descriptors are statistically significantly different between the two classes with a very high significance level, p < 10−3 . We have also created a random forest-based classifier to distinguish between progressive and stable plaques, although its accuracy remains low (61 ∼ 62%).

Výsledek ilustruje principy a specifika vybraných mapových děl použivaných na uzemi Ceske republiky s doplňujicim komentařem. Digitalni ekvivalent mapy bude dostupný take prostřednictvim internetu. Výsledek bude sloužit jako výukový material ilustrujici principy kladu listů zakladnich mapových děl použivaných na uzemi Ceske republiky jak laicke, tak odborne veřejnosti.

Certifikovana metodika pro tvorbu metadat pro indexy mapových děl je zaměřena na urceni požadovaných metadat přislusejicich k danemu indexu mapoveho dila za ucelem jejich nasledne využiti v procesu katalogizace primarně starých map. Uvedene je ovsem možne zobecnit na vsechny mapova dila s kladem mapových listů.

Z 99378 nových karcinomů kolorekta u mužů a 78977 u žen, evidovaných v registru nadorů CR v letech 1976-2005, bylo 14860 karcinomu kolorekta u mužů a 11142 u žen spojeno s výskytem jiných zhoubných novotvarů.

Z 30 166 připadů leukemii, evidovaných v ceskem registru nadorů v letech 1976–2005 bylo 3 937 vicecetných připadů spojeno s výskytem jiných novotvarů. Z nich se 2 450 (62,2 %) vyskytlo u mužů a 1 487 (37,8 %) u žen, tj. 14,7% připadů u mužů a 11 % u žen ze vsech evidovaných leukemii. Po 1 715 primarnich leukemiich bylo diagnostikovano 2 064 jiných novotvarů a před 2 222 naslednými leukemiemi 2 642 jiných primarnich nadorů. Ze 14 krajů se ve třech vyskytlo 35,5 % vicecetných leukemii (Jihomoravský a Severomoravský kraj, Praha). V průměru za 4,9 roku u mužů a 5,5 roku u žen nasledovalo 35,1 % nadorů kůže a melanom, 16,9 % nadorů travicich, 13 % dýchacich a 8,4 % mocových cest. Ocekavaný nizký pocet pokrocilých klinických stadii u nasledných nadorů se nepotvrdil: u mužů zahrnoval 43,8 % nadorů dutiny ustni, 41,5 % dýchacich, 34,2% travicich, 10,6 % mocových cest a 15,7 % pohlavnich organů; u žen 39,4 % dýchacich, 30,6 % mocových, 30 % travicich cest a 28,2 % pohlavnich organů, 25 % prsů, 25 % dutiny ustni. Bohužel mnoho klinických stadii nebylo v registru nahlaseno. Před naslednými leukemiemi bylo nejvice primarnich karcinomů kůže a melanomu u 43,6 % připadů jako ukazatel maligniho stavu. Do řijna 2007 přeživalo u mužů jen 12,4 % primarnich a 10,3 % nasledných leukemii, respektive 19,7 % a 14 % u žen. Kolik dalsich novotvarů se vyskytne u osmi tisic přeživajicich s leukemii, ocekavaných v roce 2015? Rozbory vicecetných novotvarů by mohly osvětlit mechanizmy jejich vzniku a poskytnout nahled na dispenzarni peci a preventivni opatřeni, ze kterých budou mit prospěch rostouci pocty onkologicky nemocných v remisi.

The aim of the poster is to present ongoing process of cataloguing, digitization and accessibility old map archive on Institute of Geography, Faculty of Science, Masaryk University and introduce tools developed for old map cataloguing and processing. This contribution was created with the support of the Ministry of Culture of the Czech Republic, Nr. DF11P01OVV003: TEMAP: Technology for access to Czech map collections: methodology and software for protection and re-use of national cartographic heritage.

Mezi 171 850 připady rakoviny plic zaznamenanými v Narodnim onkologickem registru Ceske republiky mezi roky 1976 a 2005 lze najit 15 331 připadů vicecetných nadorů, ktere zahrnuji 3 904 primarnich připadů rakoviny plic (3 245 u mužů a 659 u žen) a 11 427 nasledných připadů rakoviny plic (8 744 u mužů a 2 683 u žen).

V tuzemsku i v zahranici je patrna výrazna veřejna objednavkana integrovane zapojeni řady vědnich oborů pro zajistěnikrizoveho managementu. Pro podporu vcasneho a efektivnihorozhodovani v mimořadných a připadně krizových situacich jsoupotřeba aktualni geograficke informace, jejich přehlednecleněni a rychlý a snadný přistup k nim. V souvislosti suvedenou situaci byl v ramci Laboratoře geoinformatiky akartografie na Geografickem ustavu PřF MU v Brně řesen výzkumnýzaměr „Dynamicka geovizualizace v krizovem managementu(GEOKRIMA)“. Zaměr se komplexně zabýval procesem vzniku,aktualizace, generalizace a přenosu geoinformaci k uživateli ajejich kartografickou vizualizaci. Přispěvek popisuje konceptadaptivni kartograficke vizualizace, ktera je novým metodickýmpostupem pro uživatelsky orientovane a snadněji pochopitelnevizualizace geografických dat a informaci. Jsou prezentovanyjak konceptualni zaklady adaptivni vizualizace vcetně možnýchmetod a faktorů ovlivňujicich adaptaci. Nasledně je navrženatechnologicka aplikace v podobě kontextove webove mapoveslužby. Využiti adaptivnich metod je dokumentovano na přikladuscenaře „Povodeň“ a pro připad senzorových měřeni.

Of 1,486,984 new cancers registered in the Czech Cancer Registry in 1976-2005, 290,312 (19.5%) were multiple malignant neoplasms (MMNs), of which there were 65,292 primary and 89,796 subsequent cases in men and 59,970 primary and 75,254 subsequent cases in women. The duplicities were higher in women, and the triplicities and others (3–6 MMNs) were higher in men. The most frequent diagnoses were the primary cancers of skin, gastrointestinal and urinary tract, male genital organs, respiratory tract in men, and cancers of skin, breast, female genital organs, and gastrointestinal tract in women. The analysis of the early and advanced clinical stages shows that the number of subsequent advanced stages increased after primary advanced stages. Their time-age-space distributions visualized maps of MMNs in 14 Czech regions. These results support the improvement of algorithms of dispensary care for the early detection of the subsequent neoplasms.

The effectiveness of decision-making processes in the agricultural domain can be improved by integrating current local environmental and agromonitoring with the Geographic Information System (GIS) and wireless sensor networks (WSNs). The presented paper describes conceptual approaches to context-based cartographic visualization methods for agricultural and metrological data acquired by WSN and a portal prototype for integrated visualization.Each sensor used for agricultural applications has a location and can be placed within a broader spatial context. In our study, sensor characteristics (soil temperature and moisture, atmospheric temperature and moisture) were automatically monitored at frequent intervals and these readings were aggregated with geospatial data from both local and remote (Web Map Service) sources. An experimental portal for the integration and visualization of sensor data and geospatial data was designed and prototyped on the basis of an open source interoperable platform. Conceptual approaches were successfully implemented on four experimental small-plot fields planted with different crop species and operated using different soil tillage practices. Experimental fields were situated in the southeast of the Czech Republic. Very Long range Identification Tag (VLIT) technology was used for wireless communication. Sensor observations verified differences in agrometeorological variables for the conventional tillage of soil and the no-tillage variant. Contextual cartographic visualization was successfully deployed for map view, dynamic cartographic symbology, and the dynamic measurement chart.