China 
Africa 
Explore chapters and articles related to this topic
Biomedical Engineering and Informatics Using Artificial Intelligence
Published in Saravanan Krishnan, Ramesh Kesavan, B. Surendiran, G. S. Mahalakshmi, Handbook of Artificial Intelligence in Biomedical Engineering, 2021
Medical imaging is a collection of techniques that are used to create visual representations of a body interior for clinical analysis and medical intervention. Medical imaging plays an important role in medical diagnosis, treatment, and medical applications, which seeks to reveal internal structures hidden by the skin and bones for diagnosing and treating disease. In medicine, AI is used to identify diagnosis and give therapy recommendations. In medical diagnosis, artificial neural networks (ANNs) is used to get the result of the diagnosis. ANN provides an extraordinary level of achievement in the medical field. ANN has been applied to various areas in medicine like disease diagnosis, biochemical analysis, image analysis, etc. In recent years, medical image processing uses ANNs for analyzing medical images. The main components of medical image processing that heavily depend on ANNs are medical image object detection and recognition, medical image segmentation, and medical image preprocessing. The various AI imaging technologies help to examine various factors of the human body using radiography, MRI, nuclear medicine, ultrasound imaging, tomography, cardiograph, and so on (Smita et al., 2012).
Detection and Description of Tissue Disease: Advances in the Use of Nanomedicine for Medical Imaging
Published in Dan Peer, Handbook of Harnessing Biomaterials in Nanomedicine, 2021
Jason L. J. Dearling, Alan B. Packard
The increasing personalization of medicine and its increasing ability to specifically target appropriate medicines to ever-smaller populations of patients demands a corresponding improvement in our ability to more precisely characterize and describe disease. Medical imaging offers the opportunity to detect, describe, and, in some cases, treat disease, as well as the ability to monitor the response of diseased tissue to therapy. Here we have briefly considered some aspects of the development of contrast agents for both computed tomography and ultrasound imaging. Both modalities have advantages as well as limitations, depending on the specific application. Through the appropriate use of biomaterials within the field of nanotechnology, these challenges are gradually being addressed.
Automatic Detection of Brain Tumor using NSR Filter and K-means Clustering
Published in P. C. Thomas, Vishal John Mathai, Geevarghese Titus, Emerging Technologies for Sustainability, 2020
P. Athira, Therese Yamuna Mahesh
Medical Imaging techniques such as Computed Tomography (CT), Single-Photon Emission Computed Tomography (SPECT), Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) are all used for diagnosing the brain tumor. These techniques provide valuable information about shape, size, location and metabolism of brain tumors, assisting in diagnosis. While these modalities are used in combination to provide the highest detailed information about the brain tumors, due to the property of good soft tissue contrast and wide availability, MRI is considered as the standard technique. MRI is a non-invasive method in vivo imaging technique that uses radio frequency signals to excite target tissues to produce their internal images under the influence of a very powerful magnetic field. Images of different MRI sequences are generated by altering excitation and repetition times during image acquisition. These different MRI modalities produce different types of tissue contrast images, thus providing valuable structural information and enabling diagnosis that aids in segmentation of tumors along with their sub regions.
Texture-driven super-resolution of ultrasound images using optimized deep learning model
Published in The Imaging Science Journal, 2023
Due to insufficient lighting, medical images lack the fine details required for accurate classification. When a clinical diagnosis is made, a difficult task is set [3]. Magnetic resonance imaging (MRI), chest X-rays, computerized tomography (CT) scans, and others are examples of several sorts of medical images. Object boundary information and pixel intensity variations across various regions are important factors in categorization [4]. To improve the overall quality of the medical image for feature visibility and clinical measurement, contrast enhancement is a key consideration in any subjective assessment of image quality. Due to its low cost and non-invasive calculations, ultrasound images have started to play a larger role in recent years in terms of medical diagnostic evaluations. However, it cannot be employed in many real-time applications due to its image quality restrictions [5]. Medical images of relatively low resolutions (LR) were created due to technical constraints, and these images did not transmit enough information to evaluate aberrant entities. When compared to all other medical imaging modalities, such as computed tomography (CT), magnetic resonance imaging (MRI), and X-ray, ultrasound images show low-resolution (LR) findings [6].
An efficient stacked ensemble model for the detection of COVID-19 and skin cancer using fused feature of transfer learning and handcrafted methods
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
Over the years, many computer-aided systems have been developed to diagnose and detect human disease by using medical images. The most recent imaging modalities rely on high-resolution imaging to provide radiologists with multi-oriented representations, which helps them with a clinical diagnosis and perform accurate predictions and treatment for a patient. Ultrasound, magnetic resonance imaging (MRI), x-ray computed tomography and endoscopy are some of the most common modalities for medical imaging (Chowdhary and Acharjya 2020; Houssein et al. 2021c). Due to the fast development of medical imaging technologies, the field of digital pathology, which concentrates on the analysis and management of image information produced by these technologies, is expanding quickly (Mormont et al. 2018). Digital pathology with machine learning and deep learning technologies holds considerable potential for medical practices (diagnostic medicine and disease prediction) and research studies related to biomedical (Foucart et al. 2019; Fan et al. 2021; Houssein et al. 2022b).
Automated segmentation of standard scanning planes to measure biometric parameters in foetal ultrasound images – a survey
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
U. B. Balagalla, J.V.D. Jayasooriya, C. de Alwis, A. Subasinghe
Medical imaging modalities visualise the interior anatomy of the body structures. These modalities include Ultrasound (US), Magnetic Resonance Imaging (MRI), X-ray, Computed Tomography (CT), Positron Emission Tomography (PET), and Endoscopy (Hermawati et al. 2019). (Table 1 presents a list of important acronyms given in the paper). The generated medical images are observed to make diagnoses and treatments in a large clinical scope such as cancers, bone fractures, and pregnancy by observing the clinically important areas in the medical image (Sobhaninia et al. 2019). Medical US images are produced using the time of flight of the echo pulses. Therefore, US imaging is comparatively safe because of its non-invasive and non-ionising nature. It is also a low-cost, real-time medical imaging modality that does not require pre-preparation (Rawat et al. 2018; Meiburger et al. 2018; Kumar and Prakash 2020). Considering these advantages of medical US imaging, it is recommended for routine scans of the expectant mothers.