Search

Nieinwazyjna diagnostyka nowotworów skóry jest niezwykle potrzebna. W ostatnich latach bardzo dużym zainteresowaniem w diagnostyce chorób skóry cieszą się głębokie sieci neuronowe i transfer learning. Artykuł zawiera wybrane podstawy głębokich sieci neuronowych, ich ciekawe zastosowania stworzone w ostatnich latach, pozwalające na klasyfikację zmian skórnych z dostępnych obrazów dermatoskopowych.

Skin diseases diagnosed with dermatoscopy are becoming more and more common. The use of computerized diagnostic systems becomes extremely effective. Non-invasive methods of diagnostics, such as deep neural networks, are an increasingly common tool studied by scientists. The article presents an overview of selected main issues related to the multi-class classification process: the stage of database selection, initial image processing, selection of the learning data set, classification tools, network training stage and obtaining final results. The described actions were implemented using available deep neural networks. The article pay attention to the final results of available models, such as effectiveness, specificity, classification accuracy for different numbers of classes and available data sets.

In recent years, new psychoactive substances (NPS) have become a popular alternative to traditional drugs. In the European Union Early Warning System of European Monitoring Centre for Drugs and Drug Addiction (EMCDDA) the number of NPS increases each year. These substances known as legal highs or designer drugs are popular in particular among young people, mostly due to their price and availability. They are usually made in China and then sold in online stores. The variability of these substances and the lack of knowledge of their chemical structure and their metabolic changes pose a great challenge for toxicological analysis. Deaths caused by these drugs are underestimated due to their occurrence as a mixture of multiple drugs, further causing analytical problems. Difficulties in detecting NPS are also noticeable at diagnosis of intoxication, which carries the risk of misinterpretation and improper treatment. Rapid and inexpensive immunoassays used for drug detection have not yet been used in the identification of NPS. This is due to the dynamic changes on the drug market, which make it difficult to create appropriately sensitive and selective screening tests to identify an unknown substance. The production of specific antibodies takes a long time, often exceeding the duration of the presence of the substance in the illicit market. Scientists believe that mass spectrometry-based methods should be used to search for NPS in biological samples because they are sensitive and allow the determination of a specific compound with proper reliability. The use of high-resolution mass spectrometry (HRMS) in the context of screening may be a future strategy and alternative to classic drug tests. Nevertheless, the cost and time-consuming nature of this method currently exclude its use in routine diagnostics. An additional difficulty in carrying out identification is the presence of NPS in body fluids at low concentrations and frequently a short half-life time. In this article, we pay attention to the current analytical problems related to the detection of NPS.

Inversion of the uterus is defined as the turning inside out of the fundus into the uterine cavity. According to the literature, uterine inversion occurs in 1/20,000 or even 1/1,584 deliveries. Mortality rates following acute uterine inversion were reported by some authors to have been as high as 80%. Therefore, it is very important to make an early diagnosis. The shorter the time between the moment of uterine inversion and its repositioning, the better the results of conservative treatment, and bigger chance of avoiding surgical management. The article presents two cases of patients hospitalised in 2010 – 2011 in the Gynaecologic and Obstetrics Department of the Regional Polyclinic Hospital in Kalisz, Central Poland, diagnosed with acute uterine inversion in accordance with the applicable classification. Surgical management was applied in one of the patients. The other patient was managed in a conservative manner. Both women were discharged from the hospital in a good general condition.

Abstract. Melanoma is currently one of the most dangerous skin diseases, in addition many others appear in the population. Scientists are developing techniques for early non-invasive skin lesions diagnosis from dermatoscopic images, for this purpose neural networks are increasingly used. Many tools are being developed to allow for faster implementation of the network, including the Keras package. . The article presents selected methods of diagnosing skin diseases, including the process of classification, features selection, extracting the skin lesion from the whole image.The described methods have been implemented using deep neural networks available in the Keras package. The article draws attention to the effectiveness, specificity, accuracy of classification based on available data sets, attention was paid to tools that allow for more effective operation of algorithms.

The article provides an overview of selected applications of deep neural networks in the diagnosis of skin lesions from human dermatoscopic images, including many dermatological diseases, including very dangerous malignant melanoma. The lesion segmentation process, features selection and classification was described. Application examples of binary and multiclass classification are given. The described algorithms have been widely used in the diagnosis of skin lesions. The effectiveness, specificity, and accuracy of classifiers were compared and analysed based on available datasets.

Obecnie spektrofotometria jest obiecującym narzędziem do nieinwazyjnego badania właściwości optycznych ludzkiej skóry. Otrzymane podczas badania widma poddawane są wnikliwej analizie dzięki opracowanym przez wielu naukowców modeli. Opracowane modele wielowarstwowe mają na celu oddać najwierniej procesy zachodzące w skórze, jej warstwy i istotne elementy. Diagnozowanych jest wiele chorób skóry: bielactwo, naczyniaki, znamiona skórne, czerniak. Artykuł przedstawia przegląd ciekawych rozwiązań z użyciem spektrofotometrii w procesie diagnostyki chorób skóry.

Surface-mount technology is now widely used in the production of many components. The development of the miniaturised electronics industry forces the development of increasingly accurate inspection methods. X-ray and computed tomography are methods to accurately assess the quality of a circuit board. The article discusses the basics of image formation of the tested electronics, the development of the design of the devices used and examples of x-ray, computed tomography applications.

Obecnie stosuje się wiele metod selekcji cech. Cieszą się coraz większym zainteresowaniem badaczy. Oczywiście niektóre metody są stosowane częściej. W artykule zostały opisane podstawy działania algorytmów opartych na selekcji. Metody selekcji cech należące dzielą się na trzy kategorie: metody filtrowe, metody opakowujące, metody wbudowane. Zwrócono szczególnie uwagę na znalezienie przykładów zastosowań opisanych metod w diagnostyce czerniaka skóry.

Technologia montażu powierzchniowego jest obecnie szeroko stosowana w produkcji zespołów obwodów drukowanych w przemyśle elektronicznym. Zyskała ona bardzo wielu zwolenników. Miniaturyzacja komponentów elektronicznych wymusiła wprowadzenie maszyn wizualnej kontroli poprawności montażu, bardziej dokładnych i szybszych niż ludzkie oko, lupa czy mikroskop. Automatyczna Inspekcja Optyczna (AOI) to proces kontroli wykrywania wad i błędów w początkowym procesie produkcji obwodów drukowanych. Staje się nieodzownym elementem montażu kontraktowego, wpływając na zwiększenie jakości oferowanych usług i efektywności produkcji. Wykorzystywane są w niej nowe konstrukcje głowic pomiarowych, miniaturyzacja sprzętu, oprogramowanie przetwarzące otrzymane obrazy płytek, skomplikowane algorytmy przekształcania obrazu.

A non-routine, comprehensive protocol for characterization of emerging new psychoactive substances (NPS) including chemical structures, impurities, as well as crystal structures, has been developed to facilitate the work of law enforcement agencies. A set of NPS has been synthesized, identified, and characterized by various analytical methods in order to be used as certified reference standards (CRMs). Seven selected compounds (5-IT, NM-2201, MT-45, AB-CHMINACA, UR-144, 5F-PB-22, and 4-CMC) were synthesized on the laboratory scale, then the process was upscaled to semi-technical. All products were analyzed by electrospray Q/TOF-MS/MS for molecular structure identification. The presence of by-products, as well as metal impurities, arising from the performed syntheses, were characterized by reversed phase liquid chromatography (RP-HPLC) with DAD and Q/TOF-MS detection and inductively-coupled plasma with quadrupole mass spectrometer (ICP-QMS), respectively. Additionally, the crystal structures of UR-144, NM-2201, 5F-PB-22, and 4-CMC have been determined by single-crystal and powder X-ray diffraction.

Melanoma is one of the fastest spreading cancers. The aim of the article is to segment the skin lesions from human skin dermatoscopic images covered by melanoma. Threshold segmentation was used, which allows a single skin lesion to be analyzed. It shows the four areas of each based on their color. The created software monitors the border of skin lesion areas. Segmentation and analysis of the resulting images with different areas of skin change was carried out in the Matlab software.

The article contains a review of selected classification methods of dermatoscopic images with human skin lesions, taking into account various stages of dermatological disease. The described algorithms are widely used in the diagnosis of skin lesions, such as artificial neural networks (CNN, DCNN), random forests, SVM, kNN classifier, AdaBoost MC and their modifications. The effectiveness, specificity and accuracy of classifications based on the same data sets were also compared and analyzed.

Główne wyniki opracowania RETwix zostały przedstawione w artykule. RETwix jest uniwersalnym sprzętem i oprogramowaniem do badań laboratoryjnych, które można wykorzystać do badania zarówno komponentów elektronicznych, jak i dowolnych procesów elektrycznych, termicznych, chemicznych lub biochemicznych. W tym celu zostały wykorzystane czujniki, aktuatory i przetworniki sygnału Analog Front-End. RETwix zawiera dwa urządzenia CV-LAB (Capacitance & Voltage LABoratory) oraz UA-LAB (Universal Analog LABoratory). Zostały opisane osobliwości budowy oraz przykłady zastosowania RETwix.

Rationale: With increasing number of complex medical patients with renal transplant who get pregnant, clinicians need to be aware of abdominal compartment syndrome which may masquerade as acute renal allograft injury in pregnancy. Presenting concerns of the patient: A 34-year-old nulliparous Caucasian female with end-stage renal disease (ESRD) due to type 1 diabetes mellitus who received a simultaneous pancreas-kidney transplant (SPK) in 2006 and then after rejection of renal allograft another, kidney-only allograft from a donation after circulatory death became pregnant in May 2013 with dichorionic, diamniotic twins without reproductive technology, and during pregnancy, she developed two episodes of acute injury to the renal allograft. Diagnoses: End-stage renal disease secondary to type I diabetes, acute renal allograft injury, tacrolimus toxicity, abdominal pain. Interventions (including prevention and lifestyle): She received intravenous hydration, medications contributing to renal failure were held, and pain and nauseas were controlled appropriately. Abdominal compartment syndrome was managed by maintaining intravascular pressure and optimizing regional and systemic vascular perfusion by appropriate fluid balance, evacuating intraluminal contents by decompressing gastrointestinal system, and improving abdominal wall compliance by using appropriate analgesics, sedation, and patient positioning. Outcomes: With advancing pregnancy, the patient developed progressive abdominal pain, nausea, leg edema, and rising creatinine that were not responsive to ongoing therapies and required delivery via Cesarean section at 31 weeks of gestational age. Lessons learned: In the era of increasing number of pregnant renal transplant patients with multiple medical issues, we need organized approach to diagnosis of acute renal allograft injury in pregnancy and we need to consider abdominal compartment syndrome as one of the causes.

A fit for purpose analytical protocol was designed towards searching for low molecular weight seleno-compounds in sprouts. Complementary analytical techniques were used to collect information enabling the characterization of selenium speciation. Conceiving the overall characterization of the behavior of selenium, inductively plasma optical mass spectrometry (ICP-MS) was used to determine the total selenium content in entire sprouts as well as in selected extracts or chromatographic fractions. Then, high-performance liquid chromatography combined with ICP-MS (HPLC-ICP-MS) was used to evaluate the presence of inorganic and organic seleno-compounds, with the advantages of being very sensitive towards selenium, but limited by available selenium standard compounds. Finally, ultra-high performance liquid chromatography electrospray ionization triple quadrupole mass spectrometry (UHPLC-ESI-QqQ-MS/MS) and UHPLC-ESI-Orbitrap-MS/MS were used for the confirmation of the identity of selected compounds and identification of several unknown compounds of selenium in vegetable sprouts (sunflower, onion, radish), respectively. Cultivation of plants was designed to supplement sprouts with selenium by using solutions of selenium (IV) at the concentration of 10, 20, 40, and 60 mg/L. The applied methodology allowed to justify that vegetable sprouts metabolize inorganic selenium to a number of organic derivatives, such as seleno-methylselenocysteine (SeMetSeCys), selenomethionine (SeMet), 5′-seleno-adenosine, 2,3-DHP-selenolanthionine, Se-S conjugate of cysteine-selenoglutathione, 2,3-DHP-selenocysteine-cysteine, 2,3-DHP-selenocysteine-cysteinealanine, glutathione-2,3-DHP-selenocysteine, gamma-Glu-MetSeCys or glutamyl-glycinyl-N-2,3-DHP-selenocysteine.

W niniejszej pracy dokonano przeglądu głównych możliwych zastosowań struktur z przewodów w różnych dziedzinach inżynierii radiowej. Struktury z przewodów posiadają unikalne właściwości. Istnieje wiele podejść do wytwarzania struktur o różnych kształtach i zastosowaniach od zakresu częstotliwości mikrofalowych do optycznych. Struktury składające się z równoległych przewodników są wykorzystywane do transmisji fal wąskopasmowych i szerokopasmowych fal elektromagnetycznych w urządzeniach fotowoltaicznych, transferu obrazów, endoskopii i wielu innych. Konstrukcje z przewodów, takie jak hiperłącza oraz z losowym rozmieszczeniem przewodów, mogą być wykorzystywane do projektowania anten działających w szerokim zakresie częstotliwości.

Istotnym aspektem analizy obrazów medycznych jest dostrzeżenie roli procesu segmentacji poszczególnych struktur anatomicznych. Proces ten pozwala na ukazanie najistotniejszych pod względem diagnostycznym szczegółów. Dzięki segmentacji obszarów zainteresowania (ROI) możliwe jest odpowiednie dostosowanie metod dalszej analizy obrazów uwzględniając specyfikę wybranych elementów. Proces ten znalazł rozległe zastosowanie w diagnostyce medycznej. W artykule przedstawiono wykorzystanie segmentacji przez progowanie, przez rozrost regionów oraz przez wykrywanie krawędzi, w celu wyodrębnienia interesujących użytkownika części ludzkiego mózgu. Wykorzystano serie obrazów MRI (rezonans magnetyczny). Celem badań było opracowanie metod, które pozwolą porównać skuteczność różnych typów segmentacji struktur anatomicznych mózgu w dwóch wymiarach. Zaprezentowane metody pokazują różny wpływ wybranych rodzajów segmentacji, masek czy parametrów na dokładniejsze ukazanie poszczególnych elementów ludzkiego mózgu.

W artykule zostały przedstawione wyniki badań eksperymentalnych czułości wzroku ludzkiego na promieniowanie impulsowe diod LED o różnych kolorach światła przy jednakowych rozpraszanych na nich mocach elektrycznych. Za pomocą macierzy RGB określa się wielkości mocy rozpraszanej na diodach LED macierzy, przy których wynikające promieniowanie diod LED jest odbierane jako białe. W tak określonych mocach elektrycznych została zbadana czułość ludzkiego widzenia na pulsacyjne promieniowanie każdej z diod LED matrycy RGB. Charakterystyka widmowa badanej diody RGB LED została sprawdzona pod kątem obecności dodatkowych składowych widmowych. Uzyskane wyniki umożliwią opracowanie systemów ukrytej transmisji informacji za pomocą światła białego, którego składowe widmowe mają charakter informacyjny.

Efforts to construct an effective brain-computer interface (BCI) system based on Steady State Visual Evoked Potentials (SSVEP) commonly focus on sophisticated mathematical methods for data analysis. The role of different stimulus features in evoking strong SSVEP is less often considered and the knowledge on the optimal stimulus properties is still fragmentary. The goal of this study was to provide insight into the influence of stimulus characteristics on the magnitude of SSVEP response. Five stimuli parameters were tested: size, distance, colour, shape, and presence of a fixation point in the middle of each flickering field. The stimuli were presented on four squares on LCD screen, with each square highlighted by LEDs flickering with different frequencies. Brighter colours and larger dimensions of flickering fields resulted in a significantly stronger SSVEP response. The distance between stimulation fields and the presence or absence of the fixation point had no significant effect on the response. Contrary to a popular belief, these results suggest that absence of the fixation point does not reduce the magnitude of SSVEP response. However, some parameters of the stimuli such as colour and the size of the flickering field play an important role in evoking SSVEP response, which indicates that stimuli rendering is an important factor in building effective SSVEP based BCI systems.

This article concerns one of the most important problems of brain-computer interfaces (BCI) based on Steady State Visual Evoked Potentials (SSVEP), that is the selection of the a-priori most suitable frequencies for stimulation. Previous works related to this problem were done either with measuring systems that have little in common with actual BCI systems (e.g., single flashing LED) or were presented on a small number of subjects, or the tested frequency range did not cover a broad spectrum. Their results indicate a strong SSVEP response around 10 Hz, in the range 13-25 Hz, and at high frequencies in the band of 40-60 Hz. In the case of BCI interfaces, stimulation with frequencies from various ranges are used. The frequencies are often adapted for each user separately. The selection of these frequencies, however, was not yet justified in quantitative group-level study with proper statistical account for inter-subject variability. The aim of this study is to determine the SSVEP response curve, that is, the magnitude of the evoked signal as a function of frequency. The SSVEP response was induced in conditions as close as possible to the actual BCI system, using a wide range of frequencies (5-30 Hz, in step of 1 Hz). The data were obtained for 10 subjects. SSVEP curves for individual subjects and the population curve was determined. Statistical analysis were conducted both on the level of individual subjects and for the group. The main result of the study is the identification of the optimal range of frequencies, which is 12-18 Hz, for the registration of SSVEP phenomena. The applied criterion of optimality was: to find the largest contiguous range of frequencies yielding the strong and constant-level SSVEP response.