Jak na każdym kongresie RSNA, tak i tym razem dało się odczuć, że jest to najważniejsza radiologiczna impreza na świecie. To tu pokazywane są najnowsze urządzenia obrazujące, to tu, podczas wykładów i prezentacji, najsilniej wypływają zarówno najnowsze trendy rozwojowe, jak i najpoważniejsze problemy związane z obrazowaniem medycznym.
Jeśli ktoś chce działać na zasadzie widzenia tylko czerni i bieli – nie powinien „bawić się” w medycynę. Na żadnym poziomie jej stosowania. Medycyna jest sztuką, nie poddającą się prostym, sztywnym kryteriom działania. Może dlatego w niektórych krajach nie zaleca się w tym obszarze działalności człowieka stosowania norm ISO. Systemy zapewnienia jakości i zarządzania ryzykiem – tak, ale sztywne reguły, procedury i normy – nie.
The current pandemic situation has made it important for everyone to wear masks. Digital image forensics plays an important role in preventing medical fraud and in object detection. It is helpful in avoiding the high-risk situations related to the health and security of the individuals or the society, including getting the proper evidence for identifying the people who are not wearing masks. A smart system can be developed based on the proposed soft computing technique, which can be helpful to detect precisely and quickly whether a person wears a mask or not and whether he/she is carrying a gun. The proposed method gave 100% accurate results in videos used to test such situations. The system was able to precisely differentiate between those wearing a mask and those not wearing a mask. It also effectively detects guns, which can be used in many applications where security plays an important role, such as the military, banks, etc.
W pracy przedstawiono opracowanie prototypu aplikacji umożliwiającej przegląd i przetwarzanie trójwymiarowych (3D) obrazów medycznych. Aplikacja umożliwia płynne wyświetlanie przekrojów 2D obiektu wzdłuż każdej z osi (x,y,z) oraz za pomocą algorytmu renderingu wolumetrycznego pozwala na wyświetlenie obiektu w 3D. Dodatkowo poprzez wykorzystanie efektu odbicia na ścianach bryły o kształcie ściętego ostrosłupa aplikacja umożliwia uzyskanie obrazu 3D, jako wizualizacji przestrzennej. Praca zawiera dokładny opis algorytmu generującego tekstury 2D i 3D pozwalające na wyświetlenie obiektu, omówienie funkcjonalności wraz z instrukcją użytkowania, a także na przykładzie wykorzystania zestawu deweloperskiego Jetson Nano 2GB propozycję konfiguracji zestawu prototypowego do wyświetlania obrazów medycznych. W podsumowaniu pracy omówiono pomysł wykorzystania aplikacji w celach edukacyjnych oraz możliwości dalszego jej rozwoju.
EN
The article presents the development of a prototype of an application enabling the review and processing of medical images. The application enables the smooth display of 2D sections of an object along each axis (x, y, z) and, using the volumetric rendering algorithm, it enables the object to be displayed in 3D. In addition, by using the reflection effect on the walls of a solid in the shape of a truncated pyramid, the application allows you to obtain a 3D image as a 3D visualization. The work contains a detailed description of the algorithm that generates 2D and 3D textures that allow displaying the object, discusses the functionality with the instructions for use, and uses the Jetson Nano 2GB development kit as an example, a proposal to configure a prototype set for displaying medical images. The summary of the work presents the idea of using the application for educational purposes and the possibility of its further development.
Recently, hospitals have undergone major changes. Minimally invasive surgery is becoming more common, and numerous innovations are emerging, such as interventional radiology (IVR) and hybrid surgery. In order to keep pace with changes in this extremely dynamic field, scientist keep working on the development of imaging technology and the improvement of image display devices and new compounds acting as contrast agent (CA). In medicine, metals are used for diagnostic and therapeutic purposes. Inorganic elements are increasingly used as contrast agents in medical imaging due to their unique physicochemical properties. In this review, we would like to focus on the latest literature reports that contain information on Gd(III), W(IV), Mn(II), Eu(III) and 99mTc used in medical diagnostics.
6
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
This work presents a method for measuring and reconstructing human lungs using a waistcoat with an integrated impedance tomograph. The reconstructions obtained make it possible to follow the patient's breathing and, in the case of a 3D model, to determine whether there is fluid in the patient's lungs. The numerical model involves minimising the functional, determining the simulation and the form of the sensitivity matrix. In order to perform the tests, a portable impedance tomography system for biomedical applications was constructed, consisting of a measuring belt and a portable device made of flexible material with 32 round electrodes installed. This solution allows imaging of lung lesions by defining a model and solving the inverse problem using the finite element method.
PL
Praca przedstawia metodę pomiaru i rekonstrukcji ludzkich płuc przy użyciu kamizelki z wbudowanym tomografem impedancyjnym. Uzyskane rekonstrukcje pozwalają na śledzenie oddychania pacjenta a w przypadku 3D model pozwala stwierdzić czy w płucach pacjenta znajduje się płyn. Model numeryczny polega na minimalizacji funkcjonału, wyznaczaniu symulacji i postaci macierzy wrażliwości. W celu wykonania badań skonstruowano przenośny system tomografii impedancyjnej do zastosowań biomedycznych składający się z pasa pomiarowego oraz przenośnego urządzenia wykonane z elastycznego materiału z zainstalowanymi 32 okrągłymi elektrodami. Takie rozwiązanie umożliwia obrazowanie zmian w płucach poprzez zdefiniowanie modelu i rozwiązując problem odwrotny z wykorzystaniem metody elementów skończonych.
7
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The compression of image using analyzing techniques give us q high quality in the reconstructed image however in the case of transmission produce a sensitive (to the channel noise) image .In this paper we are going to use combination between error detection , source and channel coding with unequal distribution in the code rate our approach shows a high efficiency and optimization in the use of the code rate using Whale Algorithm (WA) (minimization in the redundant bits) compared to other approaches. The results of the work carried out in this article are mainly focused on the medical images compression by the (DWT+SPIHT) method, which, in fact, allow a significant reduction for data. We are also interested in the transmission of these images on an channel in a way that can provide a high bit rate with good transmission quality, by exploiting the channel coding technique, which is effective in combating the noise introduced during the transmission of these images.
PL
Kompresja obrazu przy użyciu technik analitycznych daje nam q wysoką jakość rekonstruowanego obrazu, jednak w przypadku transmisji wytwarzamy obraz wrażliwy (na szum kanału). przy nierównym rozkładzie współczynnika kodowania nasze podejście wykazuje wysoką wydajność i optymalizację w wykorzystaniu współczynnika kodowania przy użyciu algorytmu wieloryba (WA) (minimalizacja w nadmiarowych bitach) w porównaniu z innymi podejściami. Wyniki prac przeprowadzonych w niniejszym artykule koncentrują się głównie na kompresji obrazów medycznych metodą (DWT+SPIHT), która w rzeczywistości pozwala na znaczną redukcję danych. Interesuje nas również transmisja tych obrazów na kanale w sposób, który może zapewnić wysoką przepływność przy dobrej jakości transmisji, wykorzystując technikę kodowania kanałów, która skutecznie zwalcza szumy wprowadzane podczas transmisji tych obrazów.
8
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
This paper presents a new 3D segmentation algorithm for lung segmentation tasks on CT series. The algorithm consists of a 2D stage (for each slice) which is performed parallelly and 3D postprocessing after merging to 3D. The 2D stage consists of 2D preprocessing, Chan - Vese segmentation, and 2D postprocessing. This algorithm was tested on the set of 60 CT series containing labelled data enable to its assessment. The results of the algorithm are close to deep learning approaches. This algorithm will be an element of a commercial expert system for medical applications where some patient assessment will be necessary based on segmented human organs.
PL
Ten artykuł prezentuje nowy algorytm segmentacji 3D do zadań segmentacji płuc na seriach z tomografii komputerowej. Ten algorytm składa się z etapu 2D (dla każdego przekroju) który jest wykonywany równolegle i post-processingu 3D po scaleniu wyników do 3D. Etap 2D składa się z pre-processingu 2D, segmentacji Chan – Vese I post-processingu 2D. Algorytm był przetestowany na zbiorze 60 serii obtazów z tomografii komputerowej zawierających zaetykietowane dane co umożliwiło jego ocenę. Wyniki algorytmu są przybliżonej dokładności do rozwiązań deep learning. Algorytm ten będzie elementem komercyjnego system ekspertowego do zastosowań medycznych, gdzie niezbędna będzie ocena pacienta bazując na segmentowanych organach człowieka.
9
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Medical imaging is a useful tool for disease detection and diagnostic imaging technology has enabled early diagnosis of medical conditions. Manual image analysis methods are labor-intense and they are susceptible to intra as well as inter-observer variability. Automated medical image analysis techniques can overcome these limitations. In this review, we investigated Transfer Learning (TL) architectures for automated medical image analysis. We discovered that TL has been applied to a wide range of medical imaging tasks, such as segmentation, object identification, disease categorization, severity grading, to name a few. We could establish that TL provides high quality decision support and requires less training data when compared to traditional deep learning methods. These advantageous properties arise from the fact that TL models have already been trained on large generic datasets and a task specific dataset is only used to customize the model. This eliminates the need to train the models from scratch. Our review shows that AlexNet, ResNet, VGGNet, and GoogleNet are the most widely used TL models for medical image analysis. We found that these models can understand medical images, and the customization refines the ability, making these TL models useful tools for medical image analysis.
10
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The objective and automated detection of pneumonia represents a serious challenge in medical imaging, because the signs of the illness are not obvious in CT or X-ray scans. Further on, it is also an important task, since millions of people die of pneumonia every year. The main goal of this paper is to propose a solution for the above mentioned problem, using a novel deep neural network architecture. The proposed novelty consists in the use of dropout in the convolutional part of the network. The proposed method was trained and tested on a set of 5856 labeled images available at one of Kaggle’s many medical imaging challenges. The chest X-ray images (anterior-posterior) were selected from retrospective cohorts of pediatric patients, aged between one and five years, from Guangzhou Women and Children’s Medical Center, Guangzhou, China. Results achieved by our network would have placed first in the Kaggle competition with the following metrics: 97.2% accuracy, 97.3% recall, 97.4% precision and AUC ₌ 0:982, and they are competitive with current state-of-the-art solutions.
11
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
TheCOVID-19 epidemic has been causing a global problem since December 2019.COVID-19 is highly contagious and spreads rapidly throughout the world. Thus, early detection is essential. The progression of COVID-19 lung illness has been demonstrated to be aided by chest imaging. The respiratory system is the most vulnerable component of the human body to the COVID virus. COVID can be diagnosed promptly and accurately using images from a chest X-ray and a computed tomography scan. CT scans are preferred over X-rays to rule out other pulmonary illnesses, assist venous entry, and pinpoint any new heart problems. The traditional and trending tools are physical, time-inefficient, and not more accurate. Many techniques for detecting COVID utilizing CT scan images have recently been developed, yet none of them can efficiently detect COVID at an early stage. We proposed a two-dimensional Flexible analytical wavelet transform (FAWT) based on a novel technique in this work. This method is decomposed pre-processed images into sub-bands. Then statistical-based relevant features are extracted, and principal component analysis (PCA) is used to identify robust features. After that, robust features are ranked with the help of the Student’s t-value algorithm. Finally, features are applied to Least Square-SVM (RBF) for classification. According to the experimental outcomes, our model beat state-of-the-art approaches for COVID classification. This model attained better classification accuracy of 93.47%, specificity 93.34%, sensitivity 93.6% and F1-score 0.93 using tenfold cross-validation.
Artykuł ma na celu zapoznanie się z rekonstrukcją i odszumianiem obrazu za pomocą sieci neuronowej typu VAE (Variational Auto-Encoder). W pracy zostanie dokonana analiza porównawcza pod kątem błędów rekonstrukcji i występujących na obrazie anomalii. Posłużono się zbiorem obrazów TK mózgu (Visible Female CT), aby pokazać, jak wygląda rekonstrukcja i odszumianie metodą Variational Autoencoder.
EN
This paper aims to learn about image reconstruction and de-noising using Variational Encoder (VAE) neural network. The paper will make a comparative analysis in terms of reconstruction errors and anomalies present in the image. A collection of brain CT images (Visible Female CT) is used to show how reconstruction and de-noising by Variational Autoencoder method.
W artykule przedstawiono, na czym polega tomografia transmisyjna i emisyjna oraz zaprezentowano dwa fantomy dedykowane do każdej z tych technik. Fantom Shepp-Logana i fantom Jaszczaka są niezwykle przydatnymi modelami w projektowaniu i testowaniu algorytmów rekonstrukcyjnych. Przedstawiono także z punktu matematycznego, jak zaprojektować jeden z nich.
EN
This paper describes what transmission and emission tomography are and presents two phantoms dedicated to each of these techniques. The Shepp-Logan phantom and the Jaszczak phantom are extremely useful models in designing and testing reconstruction algorithms. It is shown from a mathematical point of view how to design one of them.
Recently, the analysis of medical imaging is gaining substantial research interest, due to advancements in the computer vision field. Automation of medical image analysis can significantly improve the diagnosis process and lead to better prioritization of patients waiting for medical consultation. This research is dedicated to building a multi-feature ensemble model which associates two independent methods of image description: textural features and deep learning. Different algorithms of classification were applied to single-phase computed tomography images containing 8 subtypes of renal neoplastic lesions. The final ensemble includes a textural description combined with a support vector machine and various configurations of Convolutional Neural Networks. Results of experimental tests have proved that such a model can achieve 93.6% of weighted F1-score (tested in 10-fold cross validation mode). Improvement of performance of the best individual predictor totalled 3.5 percentage points.
For brain tumour treatment plans, the diagnoses and predictions made by medical doctors and radiologists are dependent on medical imaging. Obtaining clinically meaningful information from various imaging modalities such as computerized tomography (CT), positron emission tomography (PET) and magnetic resonance (MR) scans are the core methods in software and advanced screening utilized by radiologists. In this paper, a universal and complex framework for two parts of the dose control process – tumours detection and tumours area segmentation from medical images is introduced. The framework formed the implementation of methods to detect glioma tumour from CT and PET scans. Two deep learning pre-trained models: VGG19 and VGG19-BN were investigated and utilized to fuse CT and PET examinations results. Mask R-CNN (region-based convolutional neural network) was used for tumour detection – output of the model is bounding box coordinates for each object in the image – tumour. U-Net was used to perform semantic segmentation – segment malignant cells and tumour area. Transfer learning technique was used to increase the accuracy of models while having a limited collection of the dataset. Data augmentation methods were applied to generate and increase the number of training samples. The implemented framework can be utilized for other use-cases that combine object detection and area segmentation from grayscale and RGB images, especially to shape computer-aided diagnosis (CADx) and computer-aided detection (CADe) systems in the healthcare industry to facilitate and assist doctors and medical care providers.
16
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Ultrasound imaging is one of the primary modalities used for diagnosing a multitude of medical conditions affecting organs and soft tissues the body. Unlike X-rays, which use ionizing radiation, ultrasound imaging utilizes non-hazardous acoustic waves and is widely preferred by doctors. However, ultrasound imaging sometimes requires substantial manual effort in the identification of organs during real-time scanning. Also, it is a challenging task if the scanning performed by an unskilled clinician does not comprise adequate information about the organ, leading to an incorrect diagnosis and thereby fatal consequences. Hence, the automated organ classification in such scenarios can offer potential benefits. In this paper, We propose a convolutional neural network-based architecture (CNNs), precisely, a transfer learning approach using ResNet, VGG, GoogleNet, and Inception models for accurate classification of abdominal organs namely kidney, liver, pancreas, spleen, and urinary bladder. The performance of the proposed framework is analyzed using in-house developed dataset comprising of 1906 ultrasound images. Performance analysis shows that the proposed framework achieves a classification accuracy and F1 score of 98.77% and 98.55%, respectively, on an average. Also, we provide the performance of the proposed architecture in comparison with the state-of-the-art studies.
Przedstawione w niniejszym artykule nowe podejście do rejestracji obrazu łączy dwie zupełnie różne modalności obrazów medycznych w podczerwieni: obrazy termowizyjne najcieplejszych miejsc izolowanych i miejsc najzimniejszych.
In this review, the most important complex compounds of ruthenium, gold, vanadium, chromium, bismuth, technetium were selected, and then their most important applications were described in medicine. Ruthenium has been identified as a metal with potential medical use, useful in cancer chemotherapy. The possibility of using its chemical behavior by developing complexes activated for cytotoxic activity through a mechanism of reduction in tumor tissue was discovered. Among the new anti-cancer drugs based on complex compounds, gold compounds have gained a lot of interest. This is due to their strong inhibitory effect on the growth of cancer cells and the observation that many compounds inhibit the enzyme thioredoxin reductase. This enzyme is important for the proliferation of cancerous tissues, and its inhibition is associated with the release of anti-mitochondrial effects. Clinical tests have shown that vanadium compounds can be used as anti-diabetic drugs with low toxicity. However, the therapeutic concentration range is very narrow, just a few micromoles of the compound are enough to cause apoptosis, necrosis and inflammation of healthy cells. Chromium improves the glucose system in people with hypoglycemia or hyperglycemia. Vanadium compounds mainly used to create potential drugs are inorganic compounds such as vanadates(V), vanadyl cation(IV), vanadium oxide(V) and a number of compounds containing organic ligands. Among the metal complexes, chromium(III) picolinate has successfully become a nutrient used to prevent high blood sugar levels. One of the most commonly used bismuth(III) compounds is bismuth subsalicylate. It is one of the few bismuth compounds regularly used to treat various gastrointestinal complaints, including duodenal ulcers. 99mTc injected into the body, depending on its chemical form and molecular structure, concentrates in the examined organ and emits a quantum that allows imaging of the organ through flat scintigraphic or emission processes. The role of complex compounds in medical imaging is largely based on the creation of radiopharmaceuticals for early detection of diseases and cancer radiotherapy. Radiopharmaceuticals are radionuclide-containing drugs and are routinely used in nuclear medicine to diagnose or treat a variety of diseases.
19
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Głębokie uczenie jest podkategorią uczenia maszynowego, które polega na tworzeniu wielowarstwowych sieci neuronowych, naśladując tym samym wykonywanie zadań przez ludzki mózg. Algorytmy głębokiego uczenia są ułożone według rosnącej złożoności, dlatego możliwe jest stworzenie systemów do analizy dużych zbiorów danych. Proces uczenia odbywa się bez nadzoru, a program buduje samodzielnie zestaw cech do rozpoznania. Artykuł przybliża na czym polega owa klasyfikacja obrazu tomograficznego.
EN
Deep learning is a subcategory of machine learning, which involves the creation of multilayer neural networks, mimicking the performance of tasks by the human brain. Deep learning algorithms are arranged according to increasing complexity, so it is possible to create systems to analyze large data sets. The learning process takes place unsupervised, and the program builds a set of features to recognize. The article presents the classification of the tomographic image.
The aim of this article was to determine the effect of principal component analysis on the results of classification of spongy tissue images. Four hundred computed tomography images of the spine (L1 vertebra) were used for the analyses. The images were from fifty healthy patients and fifty patients diagnosed with osteoporosis. The obtained tissue image samples with a size of 50x50 pixels were subjected to texture analysis. As a result, feature descriptors based on a grey level histogram, gradient matrix, RL matrix, event matrix, autoregressive model and wavelet transform were obtained. The results obtained were ranked in importance from the most important to the least important. The first fifty features from the ranking were used for further experiments. The data were subjected to the principal component analysis, which resulted in a set of six new features. Subsequently, both sets (50 and 6 traits) were classified using five different methods: naive Bayesian classifier, multilayer perceptrons, Hoeffding Tree, 1-Nearest Neighbour and Random Forest. The best results were obtained for data on which principal components analysis was performed and classified using 1-Nearest Neighbour. Such an algorithm of procedure allowed to obtain a high value of TPR and PPV parameters, equal to 97.5%. In the case of other classifiers, the use of principal component analysis worsened the results by an average of 2%.
PL
Celem niniejszego artykułu było określenie wpływu analizy głównych składowych na wyniki klasyfikacji obrazów tkanki gąbczastej. Do analiz wykorzystano czterysta obrazów tomografii komputerowej kręgosłupa (kręg L1). Obrazy pochodziły od pięćdziesięciu zdrowych pacjentów oraz pięćdziesięciu pacjentów ze zdiagnozowaną osteoporozą. Uzyskane próbki obrazowe tkanki o wymiarze 50x50 pikseli poddano analizie tekstury. W wyniku tego otrzymano deskryptory cech oparte na histogramie poziomów szarości, macierzy gradientu, macierzy RL, macierzy zdarzeń, modelu autoregresji i transformacie falkowej. Otrzymane wyniki ustawiono w rankingu ważności od najistotniejszej do najmniej ważnej. Pięćdziesiąt pierwszych cech z rankingu wykorzystano do dalszych eksperymentów. Dane zostały poddane analizie głównych składowych wskutek czego uzyskano zbiór sześciu nowych cech. Następnie oba zbiory (50 i 6 cech) zostały poddane klasyfikacji przy użyciu pięciu różnych metod: naiwnego klasyfikatora Bayesa, wielowarstwowych perceptronów, Hoeffding Tree, 1-Nearest Neighbour and Random Forest. Najlepsze wyniki uzyskano dla danych, na których przeprowadzono analizę głównych składowych i poddano klasyfikacji za pomocą 1-Nearest Neighbour. Taki algorytm postępowania pozwolił na uzyskanie wysokiej wartości parametrów TPR oraz PPV, równych 97,5%. W przypadku pozostałych klasyfikatorów zastosowanie analizy głównych składowych pogorszyło wyniki średnio o 2%.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.