1,721,049 research outputs found
DTD 5 ARTICLE IN PRESS Expert Systems with Applications xx (2004) 1–11
No full textwww.elsevier.com/locate/eswa Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients Abdulhamit Subasi
Breast cancer detection from mammograms using artificial intelligence
No full textBreast cancer is one of the fastest-growing forms of cancer in the world today. Breast cancer is primarily found in women, and its frequency has been gaining significantly in the last few years. The key to tackle the rising cases of breast cancer is early detection. Many studies have shown that early detection significantly reduces the mortality rate of those affected. Machine learning and deep learning techniques have been adopted in the present scenario to help detect breast cancer in an early stage. Deep learning models such as the convolutional neural networks (CNNs) are suited explicitly to image data and overcome the drawbacks of machine learning models. To improve upon conventional approaches, we apply deep CNNs for automatic feature extraction and classifier building. In this chapter, we have demonstrated thoroughly the use of deep learning models through transfer learning, deep feature extraction, and machine learning models. Computer-aided detection or diagnosis systems have recently been developed to help health-care professionals increase diagnosis accuracy. This chapter presents early breast cancer detection from mammograms using artificial intelligence (AI). Various models have been presented along with an in-depth comparative analysis of the different state-of-the-art architectures, custom CNN networks, and classifiers trained on features extracted from pretrained networks. Our findings have indicated that deep learning models can achieve training accuracies of up to 99%, while both validation and test accuracies up to 96%. We conclude by suggesting various improvements that could be made to existing architectures and how AI techniques could help further improve and help in the early detection of breast cancer
Introduction to artificial intelligence techniques for medical image analysis
No full textAs the main goal of artificial intelligence (AI) is to provide inference from a sample, it employs statistics theory to develop mathematical models. When a model is constructed, its description and algorithmic solution for understanding must be competent. In some cases, the AI algorithm’s competency may be just as crucial as its classification accuracy. AI is applied in a variety of domains, such as anomaly detection, forecasting, medical signal/image analysis as a decision support component, and so on. The goal of this chapter is to assist scientists in selecting an acceptable AI approach and then guiding them in determining the best strategy by utilizing medical imaging. Furthermore, to introduce readers with the fundamentals of AI before digging into tackling real-world issues with AI methodologies. Machine learning, deep learning, and transfer learning are examples of basic ideas discussed. Topics relating to the various AI methodologies, such as supervised and unsupervised learning, will be covered. As a result, the key AI algorithms are discussed briefly in this chapter. Relevant PYTHON programming codes and routines are provided in each section
Digital twins in healthcare and biomedicine
No full textA digital twin (DT) is a three-part idea, which includes a virtual counterpart, a physical model, and the interaction between the two. This intersection of medicine and computer science represents a new area with numerous possible applications. DT technology can evaluate the correlations between a physical cancer patient and a comparable digital counterpart to isolate predictors of disease. DT can be created in healthcare for both patients and the disease risk assessment and therapy process, and they can be used to inform quantitatively adaptive risk assessment, diagnosis, and therapy decision-making, as well as personalization and optimization of health outcomes, prediction and prevention of adverse events, and intervention planning. In an ideal world, the DT concept may be used to patients to enhance diagnoses and therapy. The goal is to (1) create an unlimited number of replicas of network models of all phenotypic, molecular, and environmental factors related to disease mechanisms in individual patients; (2) computationally treat those DTs with thousands of drugs to find the best-performing drug; and (3) treat the patient with this drug and observe the side effects. To address multistage risk assessment and therapy selection models, which include both related disease and side-effect considerations in which a digital replica or DT of a physical process or entity is virtually recreated, with similar elements and dynamics, to achieve real-time optimization and testing, is used. This chapter presents the notion that data science may supplement clinical expertise to scientifically guide disease diagnosis, treatment planning, and prognosis. In particular, digital twins could forecast disease obstacles by using them in precision medicine, disease care and treatment modeling, machine learning, and predictive analytics and combining distinct scales of clinician viewpoints
Understanding dyslexia and the potential of artificial intelligence in detecting neurocognitive impairment in dyslexia
Get PDFDyslexia is a specific learning disorder that affects reading and writing abilities. Children with dyslexia are typically diagnosed during their primary school years, typically between the ages of 5 and 8, when their academic performance lags behind their peers. However, the diagnostic process can be lengthy, and due to the diverse range of characteristics exhibited by individuals with dyslexia, misdiagnosis as other learning disabilities is not uncommon. This delay in diagnosis can result in delayed intervention, further exacerbating their learning challenges. This chapter aims to provide an understanding of the clinical procedures involved in diagnosing dyslexia alongside current interventions, followed by a discussion of electrophysiological processing differences between children with dyslexia and typically developing children. This involves identifying significant abnormalities in neurocognitive processing activity in brain signals provided by electroencephalography (EEG) during the resting state and event-related potential (ERP) during different task stimulations. Taking significant abnormalities existing between dyslexia and healthy children into account, the current technology of artificial intelligence and machine learning as tools for diagnosing and intervening in dyslexia using multimodel of brain signals is considered beneficial to enable the development of methods for early diagnosis and tailored interventions for children with dyslexia as young as possible
- …
