Search

Substantiated the relevance of theoretical studies on the use of modern CAD systems, which make it possible to move away from the analytical description of interacting surfaces and focus on the implementation of algorithms for their interaction. The use of geometric modeling tools for virtual imitation cutting of elements involved in the formation of a worm pair is shown. The use of a modified generating surface is shown to introduce errors that inevitably arise when trying to form and use a real worm pair.

All technology instruments use electrical and electronic systems that, before their production, need to be verified via simulation software. A new simulation software called Python for Analog and Mixed Signals (PyAMS) has been programmed. As presented in this paper, the main objective of this software is to simplify the modeling of analog elements and circuits by using the python language to describe design schematics involving libraries, packages, and symbols. PyAMS would be a free software (GNU license). The circuit simulation in PyAMS allows a detailed frequency-domain analysis, DC analysis, and time-domain analysis. The output signals are acquired in different operating points and they are displayed by means of a dedicated waveform editor. The behavioral modeling of analog elements and the simulations results of different test circuits are reported in the text.

Az alábbi cikk röviden összefoglalja a napjainkban alkalmazható tervezést segítő módszereket, mint például az integrált CAD rendszerekben elterjedő topológiai optimalizációt és a generatív tervezést. Az említett módszerek nyújtotta eredményeket egy esettanulmány segítségével mutatjuk be és hasonlítjuk össze.

This paper describes the efforts of St. Petersburg State Marine Technical University in development of Almaz-K CAD system for structural ship design and in the upgrade of FESTA-2020 FEM-based package for rod element analysis to be applied in Almaz-K.

The proposed model of network (decentralized) integration is based on CALS and PLM concepts and minimizes their deficiencies. XML technology is recommended for information transmission between the CAD applications, and a 3D model of the part is used to store the engineering data. This approach is implemented by means of CAM software for the KOMPAS-3D platform. As an example, integration of CAM applications with the ASCON VERTICAL CAPP system is considered.

The article presents the results of a brief comparative analysis of specialized CAD systems used in the furniture industry. In particular, it is noted that the functioning of CAD for mechanical engineering is based on geometric models of design objects, which are a mathematical reflection of information about the properties of forms and structural features of the furniture products. Therefore, such CAD systems can be quickly and relatively easily adapted to solve the problems of the furniture industry. At the same time, specialized CAD furniture products were widely used. This is determined by the engineering and artistic nature of the furniture products. The functional capabilities of most modern furniture CAD systems provides a high level of design automation, including products modeling, the creation of drawings and cutting maps of structural and decorative-facing materials, and the preparation of control programs for automated technological equipment.

With the rapid development of science and technology and the emergence of new technologies, the speed of product upgrading has accelerated, and the life cycle has been significantly shortened, leading to increasingly fierce market competition. Through the analysis of the enterprise product development process, combined with CAD-based product rapid design technology and parametric design technology, this paper proposes a product configuration editor based on three-dimensional software with a visual interface, and combines it with the PDM system. A software system that can be applied to actual product development is formed. Finally, the feasibility of a vehicle steering gear product design process is proved in practice. The research of this article mainly has the following two aspects of academic significance: this article describes the process of product development and design by enterprises under the mass customization production mode. After analyzing the application of CAD technology in the product design process, we studied how to use advanced design knowledge to combine specific three-dimensional CAD software for rapid product design, which can guide manufacturing companies to better carry out product design work. It is proposed to improve and perfect the initial configuration results of products in a specific three-dimensional design environment, and it can communicate with data management systems such as PDM. The configuration results can be edited and modified in the 3D design environment, and when specific parts need to be modified and designed, the parametric module embedded in the 3D design software can be used to design directly, avoiding multiple heterogeneous systems switching back and forth between, shorten the development cycle. In addition, for enterprises, the research in this article is also of great application significance.

Computer aided diagnosis (CAD) has become an important aspect of medical imagology development. This technology has advantages in precise quantitative analysis, reproducibility and physician workload reduction. In this paper, the research literature of computer aided diagnosis based on artificial intelligence has been reviewed, where the typical artificial intelligence algorithm procedure and related technologies in medical image-based CAD system have also been introduced. We also analysed the weaknesses and challenges of the current CAD system, and proposed the solutions and suggestions to counter these deficiencies. The recent study indicates that compared with the traditional supervised learning method, the semi-supervised active learning is more suitable to the practical requirements of clinical tasks. It will significantly reduce the implementation cost of the CAD system. Therefore, we believe that the research and development semi-supervised active learning method are of great significance to the medical image-based CAD system.

Computer-aided diagnosis (CAD) becomes a common tool for identifying diseases, especially various cancers, from medical images. Thus, digital image processing plays a significant role in this research area. This paper concerns with developing an efficient automatic system for the identification of acute lymphoblastic leukemia (ALL) cells. The proposed approach involves two steps. The first step focuses on segmenting the white blood cells (WBCs). In the second step, significant features such as shape, geometrical, statistical, and discrete cosine transform (DCT) are extracted from the segmented cells. Various classification techniques are applied to the extracted features to classify the segmented cells into normal and abnormal cells. The performance of the proposed approach has been evaluated via extensive experiments conducted on the well-known ALL-IDB dataset of microscopic images of blood. The experimental results demonstrate that the proposed approach realizes an accuracy rate 97.45% and outperforms other existing approaches.

Artificial intelligence has illustrated drastic changes in radiology and medical imaging techniques which in turn led to tremendous changes in screening patterns. In particular, advancements in these techniques led to the development of computer aided detection (CAD) strategy. These approaches provided highly accurate diagnostic reports which served as a "second-opinion" to the radiologists. However, with significant advancements in artificial intelligence strategy, the diagnostic and classifying capabilities of CAD system are meeting the levels of radiologists and clinicians. Thus, it shifts the CAD system from second opinion approach to a high utility tool. This article reviews the strategies and algorithms developed using artificial intelligence for the foremost cancer diagnosis and classification which overcomes the challenges in the traditional method. In addition, the possible direction of AI in medical aspects is also discussed in this study.

Objectives CT findings of COVID-19 look similar to other atypical and viral (non-COVID-19) pneumonia diseases. This study proposes a clinical computer-aided diagnosis (CAD) system using CT features to automatically discriminate COVID-19 from non-COVID-19 pneumonia patients. Methods Overall, 612 patients (306 COVID-19 and 306 non-COVID-19 pneumonia) were recruited. Twenty radiological features were extracted from CT images to evaluate the pattern, location, and distribution of lesions of patients in both groups. All significant CT features were fed in five classifiers namely decision tree, K-nearest neighbor, naïve Bayes, support vector machine, and ensemble to evaluate the best performing CAD system in classifying COVID-19 and non-COVID-19 cases. Results Location and distribution pattern of involvement, number of the lesion, ground-glass opacity (GGO) and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features to classify COVID-19 from non-COVID-19 groups. Our proposed CAD system obtained the sensitivity, specificity, and accuracy of 0.965, 93.54%, 90.32%, and 91.94%, respectively, using ensemble (COVIDiag) classifier. Conclusions This study proposed a COVIDiag model obtained promising results using CT radiological routine features. It can be considered an adjunct tool by the radiologists during the current COVID-19 pandemic to make an accurate diagnosis. Key Points • Location and distribution of involvement, number of lesions, GGO and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features between COVID-19 from non-COVID-19 groups. • The proposed CAD system, COVIDiag, could diagnose COVID-19 pneumonia cases with an AUC of 0.965 (sensitivity = 93.54%; specificity = 90.32%; and accuracy = 91.94%). • The AUC, sensitivity, specificity, and accuracy obtained by radiologist diagnosis are 0.879, 87.10%, 88.71%, and 87.90%, respectively. Electronic supplementary material The online version of this article (10.1007/s00330-020-07087-y) contains supplementary material, which is available to authorized users.

Breast cancer is leading cancer among women for the past 60 years. There are no effective mechanisms for completely preventing breast cancer. Rather it can be detected at its earlier stages so that unnecessary biopsy can be reduced. Although there are several imaging modalities available for capturing the abnormalities in breasts, mammography is the most commonly used technique, because of its low cost. Computer-Aided Detection (CAD) system plays a key role in analyzing the mammogram images to diagnose the abnormalities. CAD assists the radiologists for diagnosis. This paper intends to provide an outline of the state-of-the-art machine learning algorithms used in the detection of breast cancer developed in recent years. We begin the review with a concise introduction about the fundamental concepts related to mammograms and CAD systems. We then focus on the techniques used in the diagnosis of breast cancer with mammograms.

Papillary breast lesions include a wide spectrum of pathologies ranging from benign to malignant. The word papillary originates from finger-like projections, or papules, which are seen when these lesions are projected under a microscope. Papillary breast lesions have an array of radiological features at presentations; hence differentiation between benign and malignant based on imaging features is challenging. Histopathological diagnosis is crucial for the distinction and further management of the lesions. Traditionally, tumor and ductal excision is the treatment of choice for malignant and atypical or benign papilloma with imaging discordance. However, current clinical practice guidance advocates complete surgical excision, even for asymptomatic and purely benign papillomas diagnosed on core needle biopsy, as they are highly associated with atypia and malignant upstage on subsequent surgery. Computer aided diagnosis (CAD) is a non-invasive method of diagnosing medical signals/images using advanced image processing followed by soft computing techniques. In this study, we have developed a non-invasive CAD system for differentiating benign versus malignant papillary breast lesions using bi-dimensional empirical mode decomposition (BEMD) and the discrete cosine transform (DCT) followed by locality sensitive discriminant analysis (LSDA). The developed model is validated using a large collection of ultrasound images of papillary breast lesions, and achieved a maximum performance of 98.63% accuracy. We have also developed a breast papillary index, which may in the future be used as a substitute for the conventional soft computing techniques. The developed model can be utilized as a tool to assist radiologists in their routine clinical practice after validation with a larger database.

To evaluate the performance of a deep learning-based computer-aided diagnosis (CAD) system at detecting pulmonary nodules on CT by comparing radiologists’ readings with and without CAD. A total of 120 chest CT images were randomly selected from patients with suspected lung cancer. The gold standard of nodules ≥ 3 mm was established by a panel of three expert radiologists. Two less experienced radiologists read the images without and afterward with CAD system. Their reading times were recorded. The radiologists’ sensitivity increased from 20.9% to 38.0% with the introduction of CAD. The positive predictive value (PPV) decreased from 70.5% to 61.8%, and the F1-score increased from 32.2% to 47.0%. The sensitivity significantly increased from 13.7% to 32.4% for small nodules (3–6 mm) and from 33.3% to 47.6% for medium nodules (6–10 mm). CAD alone showed a sensitivity of 70.3%, a PPV of 57.9%, and an F1-score of 63.5%. Reading time decreased by 11.3% with the use of CAD. CAD improved the less experienced radiologists’ sensitivity in detecting pulmonary nodules of all sizes, especially including a significant improvement in the detection of clinically important-sized medium nodules (6–10 mm) as well as small nodules (3–6 mm) and reduced their reading time.

Knowledge-based engineering (KBE) systems allow an easy adaption of designed artefacts to new functional or design requirements and automating routine design tasks. In the following article the author wants to focus on the three main concepts of linking CAD and KBE and answer the research questions (1) in which way is integration, embedding and coupling of KBE to a standard CAD system like Autodesk Inventor available and (2) how can the single approaches be compared in terms of modelling effort, user competences and system performance.

Designing computer-assisted diagnosis (CAD) systems that can precisely identify lesions from mammography images would be useful for clinicians. Considering the morphological variation in breast cancer, it is necessary to extract robust features from the mammogram. Here, we propose a mass detection CAD system that is based on Faster R-CNN. First, we applied a novel convolution network in the backbone of Faster R-CNN, namely deformable convolution network (DCN), which improves the detection of lesions with varying shapes and sizes. Second, the original Faster R-CNN uses the output of the last layer of the backbone as a single-scale feature map. To facilitate the detection of small lesions, we used a multiscale feature pyramid network of multiple cross-scale connections between the different output layers of the backbone, called the neural architecture search-feature pyramid network (NAS-FPN). Thus, we were able to integrate the best features into the model. We then evaluated our method by using the datasets the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INbreast, respectively. Our method yielded a true positive rate of 0.9345 at 2.2805 false positive per image on CBIS-DDSM and a true positive rate of 0.9554 at 0.3829 false positive per image on INbreast. Graphical abstract.

Nowadays, virtual try-on is an irreplaceable technology in fashion industry, so it is very important to prove virtual try-on matching with the real garments. Therefore, the aim of this research was to compare garment fit using virtual try-on and scanning technologies. For this reason, garment visual appearance and distance ease between straight fit dress and mannequin in respect to fabrics properties were investigated. Women mannequins in different sizes were scanned by 3D scanner VITUS Smart XXL without and with the real straight fit dresses made from five different woven fabrics. Fabrics mechanical properties were defined by KES-F. Scanned mannequins were covered with the same size and fabric virtual dresses by Modaris 3D (CAD Lectra). Distance ease of virtual and scanned garments was compared in bust and waist cross-sections. It was defined that distance ease values at bust girth of real and virtual dresses differed till 29.9 % (1.16 cm), while at waist varied from 7.3 % (0.51 cm) to 47.3 % (4.30 cm) because of wrinkles in this area. Generally, appearance of the virtual dresses was similar to real dresses with some differences in garment shape fluency, however by increasing of the mannequin size, similarities decreased. It was assumed that very high shear rigidity G could not be very well reflected in 3D CAD system, therefore differences between virtual and real dresses appearance occurred. The general appearance and form of bust and waist cross-sections of virtual dresses with fabric 03 had less similarities comparing with real dresses due to high G value. So, comparative study showed that the accuracy of virtual try-on was quite useful comparing to real garments, if shear rigidity of fabrics was lower than 1.6 N/m*º and tensile strain in warp direction was higher than 1.80 %.

Focus of this work is to recognize standards and further features directly from 3D CAD models. For this reason, a neural network was trained to recognize nine classes of machine elements. After the system identified a part as a standard, like a hexagon head screw after the DIN EN ISO 8676, it accesses the geometrical information of the CAD system via the Application Programming Interface (API). In the API, the system searches for necessary information to describe the part appropriately. Based on this information standardized parts can be recognized in detail and supplemented with further information.

The scientific literature reveals that recent trends in the construction of mobile robots investigate design and manufacturing directions at lower costs, including the printed 3D ones. This article presents the design of an autonomous four wheeled mobile robot with unconventional drive system. The design of the robot was performed in Inventor CAD system and it was manufactured by employment of the 3D print method from ABS. It is used a special control system based on Arduino 32. The drive of the four wheeled mobile robot is servo without potentiometer. The robot is equipped with two sensors for distance measurement. The control system of the mobile robot is programmed in C++ language. The tests showed correct operation of the control system and drive system at a robot speed around 350 mm/s.

Az ipar számos területének folyamatos fejlődése hatására, mint például a korszerű gyártóeszközök, az anyagtechnológia a számítógép és a szoftveres fejlettség lehetővé teszi a megszokott gyártástechnológiák körének bővítését. Az alábbiak közé sorolható az additív gyártástechnológia, amely új lehetőséget nyújt a mindennapi termékek előállítására, ezáltal a piaci igények kiszolgálására. Az integrált CAD rendszerek évtizedek óta elfoglalták helyüket a terméktervezés- és fejlesztés folyamatában, amely részben megreformálta a klasszikus tervezéstani módszereket és azon lépéseit.

Screening helps to reduce mortality in the breast cancers. Mammography is a screening procedure used to detect breast cancer at an early stage. Computer-aided detection (CAD) systems can help in mammograms examination. Automatic differentiation between benign and malignant mammographic masses is a challenging task, due to high variability in mass structures. That is why, CAD systems frequently misdiagnose breast cancer. This paper presents a new CAD approach for mass detection in digital mammograms. The purpose of the proposed approach is to improve the discrimination between benign mass and malignant mass by reinforcing their statistics texture features. To achieve this aim, a new step based on super-resolution reconstruction is added to multistage CAD system. The proposed approach gives very good results comparing to other recent works. It achieves 96.7% classification accuracy using the MIAS (Mammography Image Analysis Society) dataset. This work shows that a super-resolution based approach improves the performance of the evaluated texture methods and thus outperforms benign/malignant mass classification for digital mammograms.

The vision to generate Assembly Sequences directly from a virtual 3D model is linked to some unsolved challenges. One of these challenges is the generation of the Assembly Graphs. This approach is based on a 3D Model of a product assembly and Assembly Features generated from a CAD system. The Assembly Graph is described by AutomationML (Automation Markup Language). AutomationML is a neutral data format to describe real plant components. The focus of this work is to generate automatically an Assembly Graphs by just using information from CAD systems.

The subject of research is the process of designing a conveyor belt. The authors consider parameterization in geometric modeling of parts and components of equipment and the creation of custom libraries in Compass 3D as a means of reducing the complexity and improving the quality of the design process. The preliminary design is the design stage of the development of design documentation and aims to determine the fundamental design solutions for a general idea of the device, operating principles and dimensions of the product. It is advisable to develop a preliminary design before the stage of developing a technical project and creating design documentation. Today, at all stages of work on the project, modern computer-aided design (CAD) systems are used, which not only accelerate the design process, but also make it possible to demonstrate to the customer the finished project at the stage of making technical decisions. This allows making timely changes in accordance with the requirements of the customer and to carry out high-quality preparation of the project for its implementation. The volume and time for further stages of work depend on the timing of the presentation of the preliminary design, therefore, the use of three-dimensional modeling parametrization in CAD is an effective way for designing engineering objects. Parameterization when working with 3D models allows you to get a set of typical product designs based on a once-created model by changing the set values of the variables, which significantly reduces the time spent on the project.

This paper describes the simulation of a 45° angle collision of a modelled electric scooter frame including suspension with a non-deformable wall using the finite element method. Includes creation of a CAD geometric model using the surface method with the necessary components and constraints modelled in Abaqus CAE. During the crash test simulations, the frame was found to pose no danger to the driver in a 45° angle crash simulation at 45 km/h. However, in a 45° angle impact at 85 km/h there is a risk of crushing the rider's leg.

Industrijska izrada muških poslovnih odijela po individualnim mjerama, poznata kao masovno šivanje po mjeri (eng. mass customization) sve je više zastupljena na tržištu, pa se sa svrhom ubrzanja procesa konstrukcije pripreme razvijaju parametarski krojevi u računalnim programskim paketima, koji se brzo mogu prilagoditi tjelesnim mjerama kupca. U teorijskom dijelu rada analizirane su glavne i pomoćne tjelesne mjere potrebne za konstrukciju muškog sakoa i hlača, prikazana je podjela tipova tijela prema stasu, uzrastu i držanju tijela te sukladno tome i devijacije koje se manifestiraju na odjeći tijekom nošenja uzrokovane tjelesnim nepravilnostima ili odstupanjima od standardnih mjera. Uspoređene su metode razvoja parametarskih krojeva u računalnim programskim paketima Modulate i Modaris Expert i prikazane su ključne funkcije programskog paketa Modaris Expert korištene u eksperimentalnom dijelu rada. Dio rada realiziran je u suradnji s tvrtkom Varteks, korištenjem programskog paketa Modaris Expert proizvođača Lectra, u kojem je razvijen parametarski kroj muškog sakoa i hlača za prilagodbu prema individualnim tjelesnim mjerama. Razvijeni kroj prilagođen je mjerama skeniranog 3D modela tijela, a kako bi se verificirao razvoj i prilagodba kroja model je prikazan računalnom 3D simulacijom u sustavu Optitex., The industrial production of men's business suits made to measure known as mass customization (mass tailoring) is increasingly growing in the market. To speed up the process of pattern making, parametric patterns are being developed by using specialized computer softwares in which patterns can be quickly adjusted to the customer's body measures. In the theoretical part of the work the main and auxiliary body measures necessary for pattern making of men's jacket and pants have been analyzed, the division of body types and body posture have been presented, and accordingly, the deviations manifested on the clothes during wear caused by body irregularities or deviations from the standard measures. Different methods of developing parametric patterns in a computer softwares Modulate and Modaris Expert have been compared, and the key functions of the software Modaris Expert used in experimental part of the work have been presented. Part of the work was realized in cooperation with the Varteks company, using software Modaris Expert by Lectra to develop the parametric pattern of men's suit and pants that can be adjusted to individual body measures. The developed parametric patterns were adjusted to the body measures of the scanned 3D body model. In order to verify the development and adjustment of the parametric pattern, the model has been shown as 3D computer simulation in the Optitex system.

This paper presents an approach for developing the programming and offline simulation systems for low-cost industrial robots in the MatLab/Simulink environment. The approach is presented in the example of a virtual model of a 4-axis robot with hybrid kinematics intended for manipulation tasks. The industrial robot with hybrid kinematics consists of the well-known 5R planar parallel mechanism to which two serial axes have been added. The programming system developed in a MatLab environment involves generating G-code programs based on given pick and place points. The virtual model included in the simulation system is configured in the Simulink environment based on the CAD model of the robot and its kinematic structure. The kinematic model and the inverse kinematic problem have to be included in the virtual model to realize the motion of the virtual robot. The system of programming and simulation has been verified through several examples that include object manipulation to perform various tasks.

Unlike many other works, where authors are usually focused on one or two quality criteria, the current manuscript, which is a generalization of the article [35] published in Russian, offers a multi-criteria approach to the assessment of the shape quality of curves that constitute component parts of the surfaces used for the computer modelling of object shapes in various types of design. Based on the analysis of point particle motion along a curved path, requirements for the quality of functional curves are proposed: a high order of smoothness, a minimum number of curvature extrema, minimization of the maximum value of curvature and its variation rate, minimization of the potential energy of the curve, and aesthetic analysis from the standpoint of the laws of technical aesthetics. The authors do not set themselves the task of giving a simple and precise mathematical definition of such curves. On the contrary, this category can include various curves that meet certain quality criteria, the refinement and addition of which is possible in the near future. Engineering practice shows that quality criteria can change over time, which does not diminish the need to develop multi-criteria methods for assessing the quality of geometric shapes. Technical issues faced during edge rounding in 3D models that affect the quality of industrial design product shape have been reviewed as an example of the imperfection of existing CAD systems.

The paper presents approaches to computer-aided design of low-thrust thrust rocket engines using an extensive knowledge base that allows making basic technical decisions that determine the conceptual design of the engine, based on the developed algorithm of this process. The procedure of creating an electronic 3D-model of a low-thrust rocket engine fueled by gaseous oxygen-hydrogen in the environment of the graphical complex UNIGRAPHICS is described. 3D electronic models of the main elements of a rocket engine with a thrust of P=25N were obtained, with subsequent virtual assembly of all components, including the components comprised in the knowledge base, providing the development, among other things, of design documentation, creation of a production environment based on an electronic engine model, preparation for the product manufacturing and the manufacturing proper.

Digital 3D scanning technology of the CAD / CAM system was used to increase the accuracy of the stump depth of the examined teeth. Collapsible plaster models were made for each clinical case and scanned in the CAD system - digital volume scanner. Using this technology on a 3D model to determine the exact depth of preparation of the stump. It was found that the study by digital volume scanning to determine and verify the depth of preparation of the examined teeth by orthopaedists, allows a more accurate and careful approach to the rationality of retraction for fixed orthopaedic structures.

Background: Computer-aided diagnosis (CAD) systems are being applied to the ultrasonographic diagnosis of malignant thyroid nodules, but it remains controversial whether the systems add any accuracy for radiologists. Objective: To determine the accuracy of CAD systems in diagnosing malignant thyroid nodules. Methods: PubMed, EMBASE, and the Cochrane Library were searched for studies on the diagnostic performance of CAD systems. The diagnostic performance was assessed by pooled sensitivity and specificity, and their accuracy was compared with that of radiologists. The present systematic review was registered in PROSPERO (CRD42019134460). Results: Nineteen studies with 4,781 thyroid nodules were included. Both the classic machine learning- and the deep learning-based CAD system had good performance in diagnosing malignant thyroid nodules (classic machine learning: sensitivity 0.86 [95% CI 0.79–0.92], specificity 0.85 [95% CI 0.77–0.91], diagnostic odds ratio (DOR) 37.41 [95% CI 24.91–56.20]; deep learning: sensitivity 0.89 [95% CI 0.81–0.93], specificity 0.84 [95% CI 0.75–0.90], DOR 40.87 [95% CI 18.13–92.13]). The diagnostic performance of the deep learning-based CAD system was comparable to that of the radiologists (sensitivity 0.87 [95% CI 0.78–0.93] vs. 0.87 [95% CI 0.85–0.89], specificity 0.85 [95% CI 0.76–0.91] vs. 0.87 [95% CI 0.81–0.91], DOR 40.12 [95% CI 15.58–103.33] vs. DOR 44.88 [95% CI 30.71–65.57]). Conclusions: The CAD systems demonstrated good performance in diagnosing malignant thyroid nodules. However, experienced radiologists may still have an advantage over CAD systems during real-time diagnosis.

The article presents structural specifications and conceptual analysis of the test car body equipped with a hybrid power transmission system. The test car is constructed by students of the Faculty of Technical Sciences of the University of Warmia and Mazury in Olsztyn. Works dedicated to designing and construction of a car body aim at the increase of safety and improvement of aesthetics of the constructed vehicle with simultaneous maintenance of its operational and test functionality. The article presents a simplified analysis of the distribution of pressure around the body for several suggested concepts and selected technologies of production of the test car body. The paper presents results of computer simulations, of the pressure distribution and the remaining aspects of assessment of the car body functionality.

U okviru diplomskog rada istražen je pojam multiplikacije ili umnožavanja te njegova pojavnost i načini na koji se pojavljuje u modi. Dan je osvrt na istaknute modne dizajnere koji su se bavili istraživanjem multiplikacije odjeće. U okviru eksperimentalnog dijela rada računalno je kreirana kolekcija ženske odjeće multipliciranjem pojedinih elemenata na modelima odjevnih predmeta. Primjenom računalnog konstruiranja i modeliranja razrađeni su krojni dijelovi za modele u kolekciji ženske odjeće, a primjenom CLO 3D programa istražene su mogućnosti definiranja parametara i realistične 3D simulacije kolekcije odjeće. Na temelju provedenog istraživanja ostvareni su rezultati po svim segmentima te su analizirane mogućnosti primjene CLO 3D programa u procesu računalnog razvoja modela u odnosu na komercijalne CAD sustave za računalno projektiranje odjeće. U završnoj fazi, izrađen je jedan komplet odjeće iz računalno projektirane kolekcije ženske odjeće., This thesis explores the concept of multiplication, appearance and the ways in which it appears in fashion. The review is given on a famous fashion designers who are known for working in research of the multiplication in creating of clothing models. As part of the experiment in this work, a collection of women's clothing it was created created by computer by multiplying individual elements on clothing pieces. By applying computer construction and modeling, cutting parts they are elaborated for models in collection. By applying the CLO 3D program, they were explored the possibilities of defining parameters and realistic 3D simulation of the clothing collection. Based on conducted research of applying CLO 3D programs in the process of computer model development in relation to commercial CAD systems for computer-aided clothing design,results were achieved in all segments and the possibilities of using this program were analyzed. In the final phase, one set of clothes from a computer designed collection of women's clothing will be made.

Heart auscultation is an inexpensive and fundamental technique to effectively diagnose cardiovascular disease. However, due to relatively high human error rates even when auscultation is performed by an experienced physician, and due to the not universal availability of qualified personnel, e.g. in developing countries, many efforts are made worldwide to propose computational tools for detecting abnormalities in heart sounds. The large heterogeneity of achievable data quality and devices, the variety of possible heart pathologies, and a generally poor signal-to-noise ratio make this problem very challenging. We present an accurate classification strategy for diagnosing heart sounds based on (1) automatic heart phase segmentation, (2) state-of-the art filters drawn from the field of speech synthesis (mel-frequency cepstral representation) and (3) an ad hoc multi-branch, multi-instance artificial neural network based on convolutional layers and fully connected neuronal ensembles which separately learns from each heart phase hence implicitly leveraging their different physiological significance. We demonstrate that it is possible to train our architecture to reach very high performances, e.g. an area under the curve of 0.87 or a sensitivity of 0.97. Our machine-learning-based tool could be employed for heartsound classification, especially as a screening tool in a variety of situations including telemedicine applications. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

[Abstract] Background The health crisis resulting from the global COVID-19 pandemic highlighted more than ever the need for rapid, reliable and safe methods of diagnosis and monitoring of respiratory diseases. To study pulmonary involvement in detail, one of the most common resources is the use of different lung imaging modalities (like chest radiography) to explore the possible affected areas. Methods The study of patient characteristics like sex and age in pathologies of this type is crucial for gaining knowledge of the disease and for avoiding biases due to the clear scarcity of data when developing representative systems. In this work, we performed an analysis of these factors in chest X-ray images to identify biases. Specifically, 11 imbalance scenarios were defined with female and male COVID-19 patients present in different proportions for the sex analysis, and 6 scenarios where only one specific age range was used for training for the age factor. In each study, 3 different approaches for automatic COVID-19 screening were used: Normal vs COVID-19, Pneumonia vs COVID-19 and Non-COVID-19 vs COVID-19. The study was validated using two public chest X-ray datasets, allowing a reliable analysis to support the clinical decision-making process. Results The results for the sex-related analysis indicate this factor slightly affects the system in the Normal VS COVID-19 and Pneumonia VS COVID-19 approaches, although the identified differences are not relevant enough to worsen considerably the system. Regarding the age-related analysis, this factor was observed to be influencing the system in a more consistent way than the sex factor, as it was present in all considered scenarios. However, this worsening does not represent a major factor, as it is not of great magnitude. Conclusions Multiple studies have been conducted in other fields in order to determine if certain patient characteristics such as sex or age influenced these deep learning systems. However, to the best of our knowledge, this study has not been done for COVID-19 despite the urgency and lack of COVID-19 chest x-ray images. The presented results evidenced that the proposed methodology and tested approaches allow a robust and reliable analysis to support the clinical decision-making process in this pandemic scenario. This research was funded by Instituto de Salud Carlos III, Government of Spain, DTS18/00136 research project; Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018-095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research project with reference PID2019-108435RB-I00; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; postdoctoral grant ref. ED481B 2021/059; Axencia Galega de Innovación (GAIN), Xunta de Galicia, grant ref. IN845D 2020/38; CITIC, Centro de Investigación de Galicia ref. ED431G 2019/01, receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%) Xunta de Galicia; ED431C 2020/24 Xunta de Galicia; ED481B 2021/059 Xunta de Galicia; IN845D 2020/38 Xunta de Galicia; ED431G 2019/01