Figure - uploaded by Olayinka Ayodele Jongbo
Content may be subject to copyright.
Source publication
Accurate medical image processing plays a crucial role in several clinical diagnoses by assisting physicians in timely treatment of wounds and mishaps. Medical doctors in the hospitals generally rely on examining bone x-ray images based on their expertise, knowledge and past experiences in determining whether a fracture exist in bone or not. Nevert...
Citations
... Image segmentation is a prerequisite for X-ray image-based scoliosis severity calculation, serving to mitigate image noise and focus on the image area. Despite its critical importance, image segmentation represents one of the most complex and time-consuming pre-processing steps [7]. Radiologists traditionally rely on subjective standards in image segmentation, although recent research encompasses edge detection, thresholding, region growth, and deformable models, in addition to more conventional image segmentation techniques [8]. ...
... Usually, these values vary in normal and abnormal regions of an image. The detection will be more accurate as the size of sub areas becomes smaller [16,17]. ...
Osteoporosis causes harmful influences on both men and women of all races. Bone mass, also referred to as “bone density,” is frequently used to assess the health of bone. Humans frequently experience bone fractures as a result of trauma, accidents, metabolic bone diseases, and disorders of bone strength, which are typically led by changes in mineral composition and result in conditions like osteoporosis, osteoarthritis, osteopenia, etc. Artificial intelligence holds a lot of promise for the healthcare system. Data collection and preprocessing seem to be more essential for analysis, so bone images from different modalities, such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI), are taken into consideration that help to recognize, classify, and evaluate the patterns in clinical images. This research presents a comprehensive overview of the performance of various image processing techniques and deep learning approaches used to predict osteoporosis through image segmentation, classification, and fault detection. This survey outlined the proposed domain-based deep learning model for image classification in addition to the initial findings. The outcome identifies the flaws in the existing literature's methodology and lays the way for future work in the deep learning-based image analysis model.
Healthcare information management has received an enormous deal of attention in recent times due to enormous potential for delivering more precise and cost-effective patient care. The Blockchain network could be used in the healthcare to exchange user data among hospitals, diagnostic laboratories, and pharmaceutical enterprises. Nowadays securing images is a big provocation to maintain confidentiality and integrity. The developed technology in the health industry might be misused by the public network and give chance to unauthorized access. The Blockchain network could be used in the healthcare to exchange user data among hospitals, diagnostic laboratories, and pharmaceutical enterprises. To put it another way, blockchain provides a public record of peer-to-peer transactions so that everyone can view them. This technology helps medical organizations in obtaining insight and enhancing the analysis of medical records. Blockchain technology provides a robust and secure framework for storing and sharing data throughout the healthcare business. In the health sector, the image-based diagnostic is an essential process. This proposed research in blockchain technology allows sharing of patient records in a secured way for telemedicine applications. These images will be shared geographically because these medical images will be passed through public networks, so the security issues like integrity and authentication may occur. These images will be encrypted using cover image and final steganography image is created. Steganography is used as major tool to improve the security of one’s data. This proposed system will have two layers in medical security by using LSB (Least Significant Bit) method with encryption. The medical image should be inserted into a cover image by LSB this is also known as the Stego image. Encryption will be provided in integrity which is a piece of cryptography. The medical image will be secured in the steganography process. The entire process can be executed by using MATLAB 2021 version. The simulation results show that the medical images are secured from various attacks. The extracted image shows minimum mean square error of 0.5.KeywordsEncryptionBlockchain technologySteganographyTelemedicineMedical image encryption
Deep neural networks reached high accuracy in the wide range of task, like computer vision, detection and natural language processing. This became possible due to increase of the amount of the neural network layers, by adding the special purpose blocks, such as Convolutions for computer vision tasks, GRU/LSTM – for NLP. However, the price for high accuracy is the increase in hardware requirements for DNN systems. That is why, specialized neural network accelerators TPU, VPU, NPU become widely used. These accelerators consist of special computation block Tensor Cores, which designed for certain layers of DNN. The main limitation of these accelerators is related with the necessity to adapt and convert the neural network model in the format supported by the accelerator. To solve this problem, multilayer hierarchical methodology of deep neural networks optimization for edge computing accelerators with specialized architecture is proposed in this paper. To study the effective performance of DNN accelerator in the practical use case, the testing application for x-ray lung abnormally diagnostic was developed.KeywordsEdge computingTPUDeep learningHealth careLung abnormality detection
