The automatic knee-joint soft tissue recognition problem is very relevant due to increasing number of people with knee-joint diseases. It is for this reason that this paper investigates the problem of soft tissue recognition in magnetic resonance imaging (MRI). MRI is useful for knee-joint soft tissue presentation, but usually a doctor cannot see all necessary information in MRI data. Computer MRI analysis makes it possible to process all MRI data and shows additional information for the doctor. This additional information can make it easier to detect invisible injuries of knee-joint soft tissues. Knee-joint soft tissue recognition and analysis are very helpful, especially for osteoarthritis (OA) early diagnostics. Computer OA diagnostics are impossible without segmentation of knee-joint tissues. This publication describes approaches for knee-joint image pre-processing, knee-joint image segmentation, tissue recognition and tissue analysis. To solve tissue analysis task it is important to use biological information of knee-joint structure, physical and biochemical tissue features. Tissue analysis is very useful especially for early diagnostics. It allows starting treatment earlier and therefore reducing the risk of tissue destruction. It is for this reason that this paper investigates the above-mentioned challenges.
The aim of this paper is to describe the new methods for analyzing knee articular cartilage degeneration. The most important aspects regarding research about magnetic resonance imaging, knee joint anatomy, stages of knee osteoarthritis, medical image segmentation and relaxation times calculation. This paper proposes new methods for relaxation times calculation and medical image segmentation. The experimental part describes the most important aspect regarding analysing of articular cartilage relaxation times changing. This part contains experimental results, which show the codependence between relaxation times and organic structure. These experimental results and proposed methods can be helpful for early osteoarthritis diagnostics.
Modern robots can perform uncreative monotonous tasks. One of such tasks is pile manipulation. Computer vision technologies can help robots acquire additional information by analyzing a pile of complex objects. One of such complex objects is a fish. The presented work investigates the problems of complex object analysis using computer vision. This paper addresses the challenges of image pre-processing, image segmentation, fish detection and occlusion detection. This work results can be useful for developing a computer vision system for pile manipulation.
The Colony-Forming Unit (CFU) counting problem remains a complex issue without a universal solution in biomedical and food safety domains. A multitude of sophisticated heuristics and segmentation-driven approaches have been proposed by numerous researchers. Among those, U-Net is the most frequently cited and popular Deep Learning method. The latter approach provides a segmentation output map and requires an additional counting procedure which accounts for unique segmented regions and detected microbial colonies. However, because of pixel-based targets it tends to generate irrelevant artifacts or errant pixels, leading to inaccurate and mixed post-processing results. In response to these challenges, we propose a novel hybrid counting approach, incorporating a multi-loss U-Net reformulation and a post-processing Petri dish localization algorithm. First of all, our unique innovation lies in the multi-loss U-Net reformulation. We introduce an additional loss term at the bottleneck U-Net layer, focusing on delivering an auxiliary signal indicating where to look for distinct CFUs. Second, our novel localization algorithm accurately incorporates an agar plate and its bezel into the CFU counting routines. Finally, our proposition is further enhanced by the integration of a fully automated solution. This comprises a specially designed uniform Petri dish illumination system and a counting web application. The latter application is capable of directly receiving images from the camera, which are subsequently processed, and the segmentation results are sent back to the user. This feature provides an opportunity to correct the CFU counts, offering a feedback loop that contributes to the continued development of the Deep Learning model. Through extensive experimentation, we have found that all probed multi-loss U-Net architectures incorporated in our hybrid approach consistently outperform their single-loss counterparts which utilize exclusively the combination of Tversky and Cross-Entropy training losses at the output U-Net layer. We report further significant improvements by the means of our novel localization algorithm. This reaffirms the effectiveness of our proposed hybrid solution in addressing contemporary challenges of the precise in-vitro CFU counting.
The aim of the doctoral thesis is to develop approaches, methods and algorithms that allow to create digital medical diagnostic systems. Medical image pre-processing, segmentation and analysis are the most important aspects of research. This work investigates a problem of pattern recognition, geometric and texture features analysis. Stages of human body fluids and tissues analysis are described in this work. There are many stages of this analysis: medical image pre-processing; fluids and tissues detection and localization; geometric and texture features calculation; defect or lesion detection. Knee joint anatomy, stages of knee osteoarthritis, medical image processing, magnetic resonance imaging are the most important aspects of research and are described in the theoretical part of the thesis. Six new modules have been developed and are described in the practical part. These new modules have a lot of possibilities: relaxation times calculation; human body fluids and tissues segmentation, features calculation and defect detection; medical image pre-processing and visualization; optimization of medical image processing instruction; textual analysis of patient's information. Geometric, texture and topology features of healthy and injured knee joint fluids and tissues have been defined in the experimental part of the doctoral thesis. Pre-processing methods, segmentation methods, author's pattern recognition modes and image process optimization methods have been compared in several experiments. As a result of the doctoral thesis, the new author's MRI medical image processing system has been developed. This system consists of several new modules. These modules can be useful for knee joint diagnostics and allow starting treatment earlier and therefore reducing the risk of cartilage destruction.
The presented paper investigates the problems of image pre-processing methods for traffic sign recognition. It describes different methods and algorithms that allow to make Traffic Sign Recognition (TSR) systems adaptable for real-life environment and to convert the input information (from the camera) to a usable format for analyzing information about a traffic sign. In the experimental part of the paper the most important aspect regarding the comparison of image pre-processing algorithms is illustrated.
Abstract An asynchronous combinational hardware design flow for commercially available XILINX devices is discussed. It consists of logical and technological stages. At the logical stage, the multi-level logic is optimized using resubstitution procedures. Also, a relaxation procedure is proposed to increase the speed at the reset stage. The optimization produces non-indicative circuits. The conditions of the distributed indication are formulated and the procedure is proposed. The technological stage is based on Webpack place and route software. To ensure stability inside a circuit, timing constraints (less strong than proposed in the literature) are formulated and can be easily satisfied. The simulation shows that resulting circuits are hazard-free ones. A set of benchmarks is processed. Compared to the conventional dual-rail design, the logical optimization reduces the total number of look-up-tables (LUTs) and number of LUTs in a critical path. At the technological stage, the experiments show that before the relaxation, the propagation delay in the set phase is smaller (due to early output) than in the reset phase. It is confirmed that the relaxation increases the speed in the reset phase. Also, the (dynamic) power is higher for the benchmarks optimized for speed.
The examination of knee cartilage degradation by magnetic resonance imaging (MRI) data is essential due to the reduction in physical activity of the population and a rising number of patients with osteoarthritis(OA). The main aim of this publication is to show a new approach for analyzing knee tissue by MRI data. The present paper investigates the problems of relaxation times calculation, medical image segmentation and statistical texture features calculation. Proposed paper describes an approach for medical image segmentation, relaxation times calculation and statistical texture features calculation. An important aspect of analysis of articular cartilage relaxation times changing is illustrated in the experimental part. The experimental part of the publication also describes the dependence between organic structure and relaxation times. The proposed approach the obtained results can be useful for early OA diagnostics.
The problem of automated bacterial colony counting is a very relevant one, due to the high importance of bacteriological analysis. Moreover, this automated counting saves biologists time and improves the accuracy of their experiments. This paper has two aims: to investigate the challenges of automated bacterial colony counting, and to address the joint challenges of petri dish localization and bacterial colony reflections in such dishes. These reflections can seriously reduce the accuracy of automated bacterial colony counting. Therefore, the main aim of this paper is to show new methods for detecting and removing bacterial colony reflections in a petri dish by the use of computer vision. It also proposes new methods for petri dish localization and the digital removal of bacterial colony reflections. Additionally, these methods can be implemented on a mobile platform, such as Android and Raspberry Pi. The experimental part of the paper contains the results, and descriptions of petri dish localization, and detecting and removing bacterial colony reflections. The proposed methods and the data obtained from these experiments significantly improve the accuracy of automated bacterial colony counting.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)