Techniques of medical image processing and analysis accelerated by high-performance computing: a systematic literature review

Medical image processing and analysis techniques play a significant role in diagnosing diseases. Thus, during the last decade, several noteworthy improvements in medical diagnostics have been made based on medical image processing techniques. In this article, we reviewed articles published in the most important journals and conferences that used or proposed medical image analysis techniques to diagnose diseases. Starting from four scientific databases, we applied the PRISMA technique to efficiently process and refine articles until we obtained forty research articles published in the last five years (2017–2021) aimed at answering our research questions. The medical image processing and analysis approaches were identified, examined, and discussed, including preprocessing, segmentation, feature extraction, classification, evaluation metrics, and diagnosis techniques. This article also sheds light on machine learning and deep learning approaches. We also focused on the most important medical image processing techniques used in these articles to establish the best methodologies for future approaches, discussing the most efficient ones and proposing in this way a comprehensive reference source of methods of medical image processing and analysis that can be very useful in future medical diagnosis systems.

Human kind is exposed to large amounts of data. According to statistics, more than 80% of information received by humans comes from the visual system. Therefore, image information processing is not only an important research topic but also a challenging task. The unique information processing mechanism of the human visual system provides it with fast, accurate, and efficient image processing capabilities. At present, many advanced image analysis and processing techniques have been widely used in image communication, geographic information systems, medical image analysis, and virtual reality. However, there is still a large gap between these technologies and the human visual system. Therefore, building an image system research mechanism based on the biological vision system is an attractive but difficult target. Although it is a challenge, it can also be considered as an opportunity which utilizes biologically inspired ideas. Meanwhile, through the integration of neural biology, biological perception mechanisms, and computer science and mathematical science, related research can bridge biological vision and computer vision. Finally, the biologically inspired image analysis and processing system is expected to be built on the basis of further consideration of the learning mechanism of the human brain.

In general, image analysis techniques have been used to analyse images from single 2D sensors, for example 2D images created from an infrared camera. This paper introduces sensory images that are constructed from several 1D sensors, for example a sensory image created from several force sensors on a robot arm. These images are abstract and may not have any visual meaning. In this paper, some transformations from sensor data to sensory images are explained and some of the image processing and analysis techniques that can be applied to such images are discussed. Experimental results are also presented. >

This study deals with an evaluation of the sewing thread consumptions relative to the basic stitches shapes. Indeed, lockstitch type 301, three-overegged stitch type 504, chain stitch type 401 and safety stitch (five overegged stitch) type 516 are considered for this investigation. Hence, the overall analyzed consumption values are compared and discussed using different methods such as statistical, geometrical modelling and image analysis techniques. By classifying the comparative results, those obtained using image analysis and geometrical modelling techniques seem relevant. In fact, based on the differences investigated between experimental and theoretical consumptions, explained as error in percentage values, the image analysis technique is appears as the best method to evaluate the consumed thread amount. Even though, the errors are ranged from 0 to 3.89%, from 0.01 to 18.83% and from 0.17 to 18.98% for the image analysis, geometrical modelling and the statistical methods, respectively. These findings proved that the image analysis method presents the lowest error values; furthermore, it can be widely used by industrial to predict and evaluate the consumption values.

In this study the feasibility of using the latest image capture, processing, and analysis techniques in the oyster embryo-larval development (OEL) test was assessed. This initially involved determining whether the OEL test could be carried out in multiwell plates (which would assist in the application of the image analysis technique), based on data from tests with the reference toxicant zinc and industrial effluents. The study then ascertained which of the 31 image analysis parameters of the Image Pro Plus software used was most appropriate for differentiating between the D larvae and non-D larvae at the end of the test procedure in a manner similar to that of visual observations. On the basis of the zinc reference toxicant and effluent test data derived in this study, the OEL test can be effectively carried out in 24 chamber multiwell plates, which provides the opportunity to count objects with image analysis software. The use of the image analysis parameters area and size (length) in combination resulted in mean control abnormalities and EC50 values in zinc reference toxicant tests which were not significantly different statistically from corresponding values derived using visual observations. Discrimination using the area and length parameters may be improved by the inclusion of other parameters in a suite of measurements which would reduce interference from extraneous material or lighting artefacts. Furthermore, the use of multiwell plates and image analysis can eliminate the variability associated with sub-sampling and inter-operator differences in the counts of D larvae and non-D larvae which is evident with the current visual observation method.

Musculoskeletal disorders such as osteoarthritis, bone fractures, osteoporosis, or ligament injuries are highly prevalent conditions affecting muscles, bones, joints, and adjacent connective tissues. In 2020, they affected over 1.63 billion people worldwide (GBD 2021 Other Musculoskeletal Disorders Collaborators, 2023). Musculoskeletal disorders cause various symptoms such as pain and mobility limitations, and they have a tremendous impact on the quality of life of an individual imposing a large economic burden to a society (Liu et al., 2022;Parto et al., 2023). The underlying pathophysiological processes and clinical manifestations vary depending on the affected tissue and specific disorder.Imaging provides visualization of the anatomy and physiological processes of the body and plays an important role in the diagnostics of musculoskeletal disorders both in clinical practice and research. Conventional radiography and computed tomography (CT) are usually used to assess changes in the mineralized tissues, such as subchondral bones, whereas magnetic resonance imaging (MRI) is best suited for assessing changes in the soft tissues, for example damage in tendons, ligaments, menisci, and cartilage. Novel imaging, image processing, and image analysis techniques have a great potential to enable earlier diagnosis and deeper understanding of musculoskeletal disorders and pathophysiological processes related to them (Kijowski and Fritz 2023) The aim of this Research Topic was to collect articles showcasing applications of novel and innovative imaging, image processing, and image analysis techniques for assessing musculoskeletal disorders and the underlying pathophysiological processes. Although musculoskeletal conditions can affect various joints, and no specific restrictions were placed on this research topic, the articles included in this research topic focused on disorders involving the spine, spinal joints, and associated muscles.

Handbook of Medical Imaging, Processing and Analysis: Edited by Isaac N. Bankman, PhD, Academic Press, 2000, ISBN 0-12-077790-8, 901 pp.

Investigation of the fabric evolution and the stress-transmission behaviour of sands based on X-ray μCT images

Retinal image analysis: Concepts, applications and potential

The decreasing cost of computing power and the introduction of low cost imaging boards justifies the increasing number of applications of digital image processing techniques in the area of biomedicine. There is however a large software gap to be fulfilled, between the application and the equipment. The requirements to bridge this gap are twofold: good knowledge of the hardware provided and its interface to the host computer, and expertise in digital image processing and analysis techniques. A software package incorporating these two requirements was developped using the C programming language, in order to create a user friendly image processing programming environment. The software package can be considered in two different ways: as a data structure adapted to image processing and analysis, which acts as the backbone and the standard of communication for all the software; and as a set of routines implementing the basic algorithms used in image processing and analysis. Hardware dependency is restricted to a single module upon which all hardware calls are based. The data structure that was built has four main features: hierchical, open, object oriented, and object dependent dimensions. Considering the vast amount of memory needed by imaging applications and the memory available in small imaging systems, an effective image memory management scheme was implemented. This software package is being used for more than one and a half years by users with different applications. It proved to be an efficient tool for helping people to get adapted into the system, and for standardizing and exchanging software, yet preserving flexibility allowing for users' specific implementations. The philosophy of the software package is discussed and the data structure that was built is described in detail.

Computer aided erosions and osteophytes detection based on hand radiographs

Recent developments for acquiring and distributing remotely-sensed data have greatly increased data availability to the user community. The past two decades have witnessed an explosion in data acquisition by a variety of ground, airborne and orbital sensors. The popularization of Unmanned Aerial Systems (UAS) and the development of reduced cost orbital platforms should guarantee that even higher data volumes will be available to future analysts. The past decades also saw the opening of image data archives (e.g., Landsat, CBERS, Sentinel), making access to a rich database of moderate resolution satellite images a reality across the globe. This increased volume and variety of remotely-sensed data increases the demand for methods and procedures for data handling and information extraction. This chapter describes recent efforts to expand the analyst’s data processing toolset and includes the theory and strategies used in manipulating remotely-sensed data by digital systems. The text focuses on presenting algorithms and techniques for image processing and analysis and emphasizes recent developments not covered by previous editions of the ASPRS Manual of Remote Sensing. Although the main topics covered by the chapter involve the direct processing of images, the text also covers concepts involved in processing remote sensing data that may not have been collected or stored as images, such as spectral curves acquired by spectroradiometers. Several sections of this chapter match this description, including Spectral Vegetation Indices and Spectral Mixture Analysis. Image processing includes not only the analysis of images, but also the necessary steps involved in preparing images for analysis, such as geometric correction, atmospheric correction and several techniques associated with image enhancement. Spectral indices resulting from the combination of multiple spectral bands are presented, with emphasis on the description of vegetated targets. A detailed treatment is given to the mixture problem resulting from the contribution of multiple materials within the instantaneous field of view (IFOV) of a given sensor. Because multiple applications can benefit from the increased explanation power provided by a large number of spectral bands, hyperspectral data processing is also presented and discussed. Further, the chapter addresses the benefits and challenges involved in combining datasets acquired by different systems (Data Fusion). Image classification addresses multiple strategies involved in assigning classes to images (e.g., Support Vector Machine, and Decision Trees); and includes advances in Object-Based Image Analysis (OBIA), particularly those related to image segmentation in preparation for classification. Given the increasing length of remotely-sensed data time series, particular attention is given to preparing sequences of images and data, including multiple techniques for smoothing, spike removal and the retrieval of metrics associated with temporal variations of targets. The chapter also brings multiple examples of use of products derived from processing remotely-sensed data as input to a variety of workflows, including modeling and analysis efforts. Finally, very current topics involving recent advances in image acquisition and availability, are presented for generating 3D surfaces from multiple images using Structure from Motion (SfM); processing of very large datasets (Big Data); and processing of images in the cloud are presented.

Retinal image analysis: concepts, applications and potential

The rise of the digital imaging is remarkable, and the methods and techniques of image processing and analysis of the digital one must also accompany this technological evolution. In a line of research on the moments theory associated with digital imaging, values are extracted from digital images for the needs of classifications or even of reconstruction, as unique descriptors of an image, our work fits. In this paper, we propose a new method, fast and efficient, for calculating orthogonal moments on the discrete 3D image. We opted for the orthogonal polynomials of Meixner and for a new representation of the 3D image by cuboids having same gray levels called image cuboid representation. Based on this representation, we calculate the moments on each cuboid before summing all cuboids in order to obtain the global moments of a 3D image. Through a set of simulations, we prove that our method allows to reduce the time required for the calculation of moment on a 3D image of any size and any order, but not only, this method makes it possible to improve the quality of 3D image reconstruction from low-order moment.

The book puts special stress on the contemporary techniques for reasoning-based image processing and analysis: learning based image representation and advanced video coding; intelligent image processing and analysis in medical vision systems; similarity learning models for image reconstruction; visual perception for mobile robot motion control, simulation of human brain activity in the analysis of video sequences; shape-based invariant features extraction; essential of paraconsistent neural networks, creativity and intelligent representation in computational systems.KeywordsVideo CodecAdvanced Video CodeVisual Attention ModelPublic Service BroadcasterIntelligent RepresentationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.