China
Africa
Explore chapters and articles related to this topic
Reliable Biomedical Applications Using AI Models
Published in Punit Gupta, Dinesh Kumar Saini, Rohit Verma, Healthcare Solutions Using Machine Learning and Informatics, 2023
Shambhavi Mishra, Tanveer Ahmed, Vipul Mishra
In radiology, skilled clinicians visually examine medical images to detect, monitor, and report disease findings. The reliability of these evaluations depends on experience, and they can be subjective at times. When AI is integrated into the clinical process as a tool to assist clinicians, more accurate and reproducible radiological assessments can be made. Examples in the field of radiology include thoracic imaging, mammography, brain imaging, and radiation oncology. According to researchers, [79], artificial intelligence systems that use continuous learning and retrain themselves are less error prone. Radiology departments are working together to co-develop and test AI algorithms, provide continuous data feeds, and integrate more diversified data sources in order to execute continuous learning AI. Another study looked at how AI monitoring tools could assist radiologists in prioritizing their patient lists by detecting suspicious or positive cases that need to be reviewed immediately. Current constraints in technical competence and even processing capacity will be alleviated with time, and remote access technologies will be able to help [80].
Thermometry and medical imaging
Published in Riadh Habash, BioElectroMagnetics, 2020
MRI is a medical imaging technique used in radiology to picture internal structures. It is a relatively new imaging technique that offers several advantages. It produces no ionizing radiation and provides superior tissue discrimination, lesion definition, an improved anatomic context for surrounding vessels and nerves, and excellent spatial resolution at close to or in real time. MRI also provides the capability of characterizing functional and physiological parameters of tissues, including diffusion, perfusion, flow, and temperature. However, high costs are associated with MRI and it also requires a special environment that can hinder patient accessibility [1].
Healthcare Delivery Systems
Published in A. Ravi Ravindran , Paul M. Griffin , Vittaldas V. Prabhu , Service Systems Engineering and Management, 2018
A. Ravi Ravindran , Paul M. Griffin , Vittaldas V. Prabhu
Diagnostic Services—these are made up primarily of radiology and laboratories. Radiology consists of various imaging equipment including x-rays, computed tomography (CT) scans, MRI, ultrasound, and positron emission tomography scans. These resources can, in some cases, be quite expensive. Laboratories are where tests are done on clinical specimens such as blood or urine.
Efficient Machine Learning-based Approach for Brain Tumor Detection Using the CAD System
Published in IETE Journal of Research, 2023
Mohamed Amine Guerroudji, Zineb Hadjadj, Mohamed Lichouri, Kahina Amara, Nadia Zenati
The field of medical imaging research has long been considered one of the most active areas of image processing. Radiologists utilize diagnostic and therapeutic radiology devices to aid in disease detection, particularly for diseases such as tumors and cancers. While Magnetic Resonance Imaging (MRI) was first developed in the 1930s, the majority of publications in this area have been dated to the last two decades, with numerous strategies proposed in recent years. This high level of attention is due to the critical role medical imaging plays in public health [1,2]. In response, researchers have focused their R&D efforts on the evolution of Computer Assisted Diagnosis (CAD) systems, which can aid in clinical trials [3,4] and provide more transparent operations. This paper proposes a CAD system for detecting brain tumor pathologies using a statistical classification approach. The suggested method involves three stages: first, recovering regions of interest using mathematical morphology approaches and Gradient Vector Flow (GVF) Snake models; second, characterizing these regions through morphological and textural methods; and finally, inputting this description into a Bayesian network to distinguish between benign and malignant cancer types. The rest of the paper is organized as follows: section 2 provides an overview of related literature, section 3 explains the proposed CAD system in detail, and section 4 discusses the experimental results obtained from each sub-step, including a comparison with other classification methods. Some discussions are given in section 5. The paper concludes with section 6 providing overall conclusions.
Biomechanical performance design of joint prosthesis for medical rehabilitation via generative structure optimization
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2020
Jinghua Xu, Kang Wang, Mingyu Gao, Zhengxin Tu, Shuyou Zhang, Jianrong Tan
Magnetic resonance imaging (MRI) is a medical imaging technique used in radiology to form pictures of the anatomy and the physiological processes of the body. MRI scanners use stronger magnetic fields, magnetic field gradients, and radio waves to generate recognizable images of the organs with wide-range densities in the body. MRI does not involve X-rays or the use of ionizing radiation, which distinguishes it from CT or CAT scans and PET (Positron Emission Tomography) scans. The human knee cartilage (right) from MR Images (MRI) is shown in Figure 3. The pixel spacing is hereby used to obtain the scale bar of the MRI.