Lacerace plíce je jedním ze závažných důsledků jak tupých, tak penetrujících traumat hrudníku. Autoři referují o 16 případech těchto poranění diagnostikovaných a operačně léčených na vlastním pracovišti v uplynulých pěti letech. Ze čtyř pětin se jednalo o následek tupého úrazu hrudníku, a to převážně v důsledku dopravních nehod. U 12 osob byla plicní lacerace součástí závažného polytraumatu, polovina z nich si vyžádala anatomickou plicní resekci. Naopak všechna tři penetrující poranění bylo možno ošetřit pouze suturou, resp. klínovitou plicní resekcí, jedenkrát s využitím miniinvazivní metodiky. Pooperační komplikace přežívajících nemocných byly řídké a nevynutily si operační revizi. Během operace či bezprostředně po ní zemřeli 4 muži (25 %), vždy pro mnohočetná poranění neslučitelná se životem. Míra poškození plicního parenchymu byla v souboru přímo úměrná velikosti zraňujícího násilí, hluboké ruptury byly ve všech případech součástí polytraumatu. Optimálním operačním přístupem, především při vícečetných a hlubokých laceracích, se jeví různé typy torakotomie, indikace pro videotorakoskopii jsou řídké. V rámci vlastního ošetření plicních ruptur se upřednostňují záchovné zákroky. Ve sdělení jsou diskutovány i další aspekty diagnostiky a léčby lacerací plic.

Lung laceration is one of the most serious consequences of both blunt, and penetrating trauma of the thorax. The authors described 16 cases diagnosed and surgically treated at their clinic over last five years. In about 80 % of cases, the laceration was a consequence of blunt trauma to the thorax, caused mainly by a traffic accident. In 12 patients lung laceration was part of serious polytrauma, and anatomic lung resection was necessary in one half of these cases. In contrast, all 3 cases of penetrating trauma could be treated only using sutures, or by wedge-shaped lung resection in one patient using a miniinvasive method. Postoperative complications in surviving patients were rare and operative revision was unnecessary. During or immediately after operation 4 male patients died (25 %), in all cases from multiple trauma incompatible with life. The extent of lung parenchyma damage in our group was proportional to the extent of force of the injury. Deep ruptures were in all cases a part of polytrauma. The optimal surgical method, espe-cially in multiple and deep lacerations, seems to be various types of thoracotomy, indications for videothoracoscopy occur rarely. In the frame-work for the proper treatment of lung ruptures, saving procedures are preferred. Other aspects of diagnoses and therapy of lung lacerations are also discussed.

• MeSH
• Algorithms MeSH
• Accidents, Traffic MeSH
• Adult MeSH
• Lacerations etiology   surgery   complications   MeSH
• Middle Aged MeSH
• Humans MeSH
• Adolescent MeSH
• Lung surgery   MeSH
• Thoracic Injuries diagnosis   etiology   surgery   MeSH
• Lung Injury MeSH
• Thoracotomy utilization   MeSH
• Video-Assisted Surgery MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Adolescent MeSH
• Male MeSH
• Female MeSH
• Publication type
• Review MeSH

• Publication type
• Abstracts MeSH

Autoři se snaží najít optimální diagnostický algoritmus při podezření na nádor VIII.hlavového nervu. Nesprávná či pozdní diagnóza může zapříčinit nejen těžké poškození zdraví,případně i smrt pacienta, ale může mít i nepříjemné forenzní důsledky pro ošetřujícího lékaře.Autoři preferují co nejrychlejší, přímočarý a pokud možno co nejekonomičtější diagnostický postup. Subjektivní nadprahové audiometrické testy mají omezenou diagnostickou hodnotu. Objektivní audiometrické testy, zejména BERA a měření stapediálních reflexů, jsou pro diagnózuretrokochleární léze podstatně významnější. Při důvodném podezření na nádor VIII. hlavovéhonervu, či obecně na nádor v oblasti mostomozečkového úhlu, je indikováno vyšetření nukleárnímagnetickou rezonancí (MRI).Autoři navrhují následující diagnostický algoritmus:1. ORL vyšetření, včetně otomikroskopie.2. Prahový tonový audiogram a při symetrickém sluchu či velmi malém interaurálním rozdíluslovní audiogram do sluchátek pro každé ucho zvlášť.3. Tympanometrii s vyšetřením stapediálních reflexů (ipsi i kontra), včetně reflex decay testu.4. Vyšetření akusticky evokovaných potenciálů mozkového kmene (BERA).5. Vestibulární vyšetření (vždy při projevech narušené rovnováhy).6. MRI, je-li podle výsledků BERA nebo vyšetření vestibulárního podezření na retrokochleární lézi.Autoři se domnívají, že by bylo přínosné stanovit jednoznačný a závazný diagnostický postup připodezření na nádor VIII. hlavového nervu. Při jeho dodržení by bylo možné zabránit pozdnídiagnóze i eventuálním nepříjemným forenzním následkům.

The authors try to find an optimal diagnostic algorithm in suspected tumours of the VIIIth cranial nerve. Incorrect or late diagnosis can cause not only severe damage to health or even death but may have also unpleasant forensic consequences for the attending physician. The authors prefer a quick, direct and if possible economical diagnostic procedure. Subjective suprathreshold audiometric tests are of limited diagnostic value. Objective audiometric tests. in particular BERA and examination of stapedial reflex are more significant for the diagnosis of a retrocochlear lesion. In case of sustantiated suspicion of a tumour of the VIIIth nerve or a tumour in the area of the pontocerebellar angle examination by magnetic resonance (MRI) is indicated. The authors recommend the following diagnostic algorithm: 1. ORL examination incl. otomicroscopy 2. Pure tone audiogram and in case of symmetrical hearing or a very small interaural difference a verbal audiogram into earphones separately for each ear. 3. Tympanometry with examination of stapedial reflexes (ipsi and contra) incl. the reflex decay test. 4. Examination of acustically evoked potentials of the brain stem (BERA). 5. Vestibular examination (always in case of impaired equilibrium). 6. MRI if according to results of BERA or vestibular examination a retrocochlear lesion is suspected. The authors assume that it be useful to define an uneqivocal and mandatory diagnostic procedure in suspected tumours of the VIIIth cranial nerve. This woud help to prevent late diagnosis and possible unpleasant forensic sequelae.

• MeSH
• Algorithms MeSH
• Diagnostic Techniques and Procedures MeSH
• Diagnosis MeSH
• Cranial Nerve Neoplasms diagnosis   MeSH

The A* - Algorithm for heuristic search is applied to construct a Neural Network structure (NS) that optimally fits the structure of data to be learned. In this way, the user of Neural Networks (NN) is able to avoid the empirical testing of different structures. The method given here is applied to the recognition of different patterns derived from the EEG of an epileptic patient.

• MeSH
• Algorithms * MeSH
• Electroencephalography * classification   MeSH
• Epilepsy diagnosis   MeSH
• Humans MeSH
• Neural Networks, Computer * MeSH
• Pattern Recognition, Automated * MeSH
• Check Tag
• Humans MeSH

BACKGROUND: Device-based algorithms offer the potential for automated optimization of cardiac resynchronization therapy (CRT), but the process for accepting them into clinical use is currently still ad-hoc, rather than based on pre-clinical and clinical testing of specific features of validity. We investigated how the QuickOpt-guided VV delay (VVD) programming performs against the clinical and engineering heuristic of QRS complex shortening by CRT. METHODS: A prospective, 2-center study enrolled 37 consecutive patients with CRT. QRS complex duration (QRSd) was assessed during intrinsic atrioventricular conduction, synchronous biventricular pacing, and biventricular pacing with QuickOpt-proposed VVD. The measurements were done manually by electronic calipers in signal-averaged and magnified 12-lead QRS complexes. RESULTS: Native QRSd was 174 ± 22 ms. Biventricular pacing with empiric AVD and synchronous VVD resulted in QRSd 156 ± 20 ms, a significant narrowing from the baseline QRSd by 17 ± 27 ms, P = 0.0003. In 36 of 37 patients, the QuickOpt algorithm recommended left ventricular preexcitation with VVD of 42 ± 18 ms (median 40 ms; interquartile range 30-55 ms, P <0.00001). QRSd in biventricular pacing with QuickOpt-based VVD was significantly longer compared with synchronous biventricular pacing (168 ± 25 ms vs. 156 ± 20 ms; difference 12 ± 11ms; P <0.00001). This prolongation correlated with the absolute VVD value (R = 0.66, P <0.00001). CONCLUSIONS: QuickOpt algorithm systematically favours a left-preexcitation VVD which translates into a significant prolongation of the QRSd compared to synchronous biventricular pacing. There is no reason to believe that a manipulation that systematically widens QRSd should be considered to optimize physiology. Device-based CRT optimization algorithms should undergo systematic mechanistic pre-clinical evaluation in various scenarios before they are tested in large clinical studies.

• MeSH
• Algorithms MeSH
• Electrocardiography MeSH
• Humans MeSH
• Prospective Studies MeSH
• Cardiac Resynchronization Therapy * methods   MeSH
• Heart Failure * therapy   MeSH
• Treatment Outcome MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

Cíl. Cílem studie bylo posoudit možnosti IRIS (iterativní rekonstrukce v obrazovém prostoru) algoritmu z hlediska redukce šumu v obraze a efektivní dávky. Metoda. Bylo vyhodnoceno celkem 85 pacientů, kteří podstoupili CT vyšetření (plic, břicha a mozku) s rekonstrukcí snímků pomocí IRIS algoritmu, a podobná skupina 95 pacientů, jejichž snímky byly rekonstruovány filtrovanou zpětnou projekcí (FBP). Referenční součin proudu a expozičního času byl pro skupinu s IRIS algoritmem v původních užívaných protokolech snižován tak, aby kvalita snímku na základě subjektivního posouzení radiologa byla zachována. Obě skupiny byly porovnány z hlediska množství šumu na snímku, poměru signálu a šumu a efektivní dávky, kterou pacient během vyšetření obdrží. Výsledky. Ukázalo se, že u vyšetření břicha je možné radiační zátěž pacienta snížit až o 50 %, aniž by došlo ke zhoršení kvality snímku. Na druhou stranu pro vyšetření mozku se podařilo dosáhnout snížení průměrné efektivní dávky pouze o 23 %. Závěr. Z tohoto důvodu by měla obdobná měření a optimalizace vždy předcházet uvedení nového rekonstrukčního algoritmu do klinické praxe.

Aim. The aim of this study was to assess the possibilities of IRIS (Iterative reconstruction in Image Space) algorithm in noise reduction and potential dose reduction. Method. A total of 85 patients clinically underwent CT examination (chest, abdomen, brain) with IRIS reconstruction and similar groups of 95 patients with Filtered Back Projection (FBP) reconstruction were evaluated. The reference tube current product in original CT protocols was modified for IRIS algorithm according to the subjective image quality. Two reconstruction algorithms were compared in terms of image noise, signal to noise ratio and effective dose. Results. It was demonstrated that with the novel approach the mean effective dose reduction up to 50% for CT examination of the abdomen did not lead to image quality degradation. However, to retain the quality of CT images of the brain it was accomplished mean effective dose reduction only of 23%. Conclusion. For this reason such measurements and similar optimization should precede to introduction of any new reconstruction algorithm into clinical routine.

• Keywords
• CT, efektivní dávka,
• MeSH
• Algorithms MeSH
• Artifacts MeSH
• Radiation Dosage MeSH
• Diagnostic Imaging methods   instrumentation   trends   MeSH
• Humans MeSH
• Tomography, X-Ray Computed methods   trends   MeSH
• Image Processing, Computer-Assisted methods   trends   utilization   MeSH
• Quality Control MeSH
• Software trends   MeSH
• Statistics as Topic MeSH
• Body Weight MeSH
• Outcome and Process Assessment, Health Care MeSH
• Check Tag
• Humans MeSH

Objective.The current practices of designing neural networks rely heavily on subjective judgment and heuristic steps, often dictated by the level of expertise possessed by architecture designers. To alleviate these challenges and streamline the design process, we propose an automatic method, a novel approach to enhance the optimization of neural network architectures for processing intracranial electroencephalogram (iEEG) data.Approach.We present a genetic algorithm, which optimizes neural network architecture and signal pre-processing parameters for iEEG classification.Main results.Our method improved the macroF1 score of the state-of-the-art model in two independent datasets, from St. Anne's University Hospital (Brno, Czech Republic) and Mayo Clinic (Rochester, MN, USA), from 0.9076 to 0.9673 and from 0.9222 to 0.9400 respectively.Significance.By incorporating principles of evolutionary optimization, our approach reduces the reliance on human intuition and empirical guesswork in architecture design, thus promoting more efficient and effective neural network models. The proposed method achieved significantly improved results when compared to the state-of-the-art benchmark model (McNemar's test,p≪ 0.01). The results indicate that neural network architectures designed through machine-based optimization outperform those crafted using the subjective heuristic approach of a human expert. Furthermore, we show that well-designed data preprocessing significantly affects the models' performance.

• MeSH
• Electroencephalography methods   MeSH
• Electrocorticography * MeSH
• Humans MeSH
• Neural Networks, Computer * MeSH
• Signal Processing, Computer-Assisted MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

MOTIVATION: G-quadruplex is a DNA or RNA form in which four guanine-rich regions are held together by base pairing between guanine nucleotides in coordination with potassium ions. G-quadruplexes are increasingly seen as a biologically important component of genomes. Their detection in vivo is problematic; however, sequencing and spectrometric techniques exist for their in vitro detection. We previously devised the pqsfinder algorithm for PQS identification, implemented it in C++ and published as an R/Bioconductor package. We looked for ways to optimize pqsfinder for faster and user-friendly sequence analysis. RESULTS: We identified two weak points where pqsfinder could be optimized. We modified the internals of the recursive algorithm to avoid matching and scoring many sub-optimal PQS conformations that are later discarded. To accommodate the needs of a broader range of users, we created a website for submission of sequence analysis jobs that does not require knowledge of R to use pqsfinder. AVAILABILITY AND IMPLEMENTATION: https://pqsfinder.fi.muni.cz, https://bioconductor.org/packages/pqsfinder. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

• MeSH
• Algorithms MeSH
• G-Quadruplexes * MeSH
• Genome MeSH
• RNA MeSH
• Software MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

Diet, stress, genetics, and a sedentary lifestyle may all contribute to heart disease rates. Although recent studies propose comprehensive automated diagnostic systems, these systems tend to focus on one aspect, such as feature selection, prioritization, or predictive accuracy. A more complete approach that considers all of these factors can improve the efficiency of a cardiac prediction system. This study uses an appropriate strategy to overcome potential network design problems, design challenges, overfitting, and lack of robustness that can interfere with system performance. The research introduces an ideally designed deep trust network called ID-DTN to improve system performance. The Ruzzo-Tompa method is used to eliminate noncontributory features. The Seagull Optimization Algorithm (SOA) is introduced to optimize the trust depth network to achieve optimal network design. The study scrutinizes the deep trust network (ID-DTN) and the restricted Boltzmann machine (RBM) and sheds light on the system's operation. This proposal can optimize both network architecture and feature selection, which is the main novelty. The proposed method is analyzed using the below-mentioned metrics: Matthew's correlation coefficient, F1 score, accuracy, sensitivity, specificity, and accuracy. ID-DTN performs well compared to other state-of-the-art methods. The validation results confirm that the proposed method improves the prediction accuracy to 97.11% and provides reliable recommendations for patients with cardiovascular disease.

• MeSH
• Algorithms * MeSH
• Humans MeSH
• Heart Diseases * diagnosis   MeSH
• Neural Networks, Computer MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

• MeSH
• Algorithms MeSH
• Artifacts MeSH
• Diagnostic Imaging MeSH
• Echocardiography methods   utilization   MeSH
• Humans MeSH
• Mathematical Concepts MeSH
• Microcomputers MeSH
• Statistics as Topic MeSH
• Models, Theoretical * MeSH
• Ultrasonography * methods   utilization   MeSH
• Image Enhancement * MeSH
• Check Tag
• Humans MeSH