Deep learning plays a crucial role in healthcare decision making especially in medical imaging. Medical image analysis portrays a vital role in detection, diagnosis, prognosis, and care field. The formation of Artificial Intelligence in healthcare is an important research area which possesses potential to offer several societal benefits in the medical realm. Despite the popular application of these techniques in a wide range of medical image applications, there is still a lack of theoretical and practical understanding of their learning characteristics and decision-making behaviour when applied to medical images. Further, there is still a need to advance real-world modelling in medical image applications by proposing efficient solutions for current challenges and introducing new frameworks/techniques.
The aim of this Research Topic is to publish the recent research contributions related to advancement in machine learning and deep learning algorithms for medical imaging for neurogenerative diseases. Progressive brain disorders with a high prevalence in the general population include Parkinson's disease, Alzheimer's disease and other types of dementia, Huntington's disease, and motor neuron disease. Worldwide, it is estimated that 33 million people have Alzheimer's disease, and 10 million people have Parkinson's disease. The global health economy is significantly impacted by these disorders, which affect both the patient and the caregivers. For differential diagnoses, a variety of diagnostic techniques are used, such as brain imaging, EEG analysis, molecular analysis, and cognitive, psychological, and physical examination.
The primary objective of this Research Topic is to allow researchers to communicate their high-quality and original ideas by presenting and publishing innovative advances in the field of computer vision, Artificial Intelligence theories/tools, Deep learning methods/techniques and their applications in medical imaging for neurogenerative diseases. The goal of the Research Topic is to develop effective treatments, enhance patient quality of life, and extend life expectancy. It focuses on novel artificial intelligence approaches to clarify the pathogenesis of neurodegenerative disorders and provide early diagnosis.
Few suggested subtopics(not limited to):
• Deep Learning for neurodegenerative disorders
• Interpretable and explainable machine learning for neurodegenerative diseases
• Responsible AI for medical image processing for neurodegenerative diseases
• Texture analysis of medical images for neurodegenerative diseases
• Explainable AI (XAI) and predictive data analytics for neurodegenerative
diseases
• Innovative approaches to connecting AI, ML, and Big Data in the
neurodegenerative medical image analysis
• Medical Image Learning with limited and noisy data for neurodegenerative
diseases
• Approaches for automated medical image annotation/labelling for
neurodegenerative diseases
• Approaches for medical image augmentation/synthesis for neurodegenerative
diseases
• Transfer learning strategies and modality-specific representation for
neurodegenerative diseases
• Approaches for learning noise invariant features
• Advanced techniques in deep learning for neuroimaging analysis and
diagnostics.
Deep learning plays a crucial role in healthcare decision making especially in medical imaging. Medical image analysis portrays a vital role in detection, diagnosis, prognosis, and care field. The formation of Artificial Intelligence in healthcare is an important research area which possesses potential to offer several societal benefits in the medical realm. Despite the popular application of these techniques in a wide range of medical image applications, there is still a lack of theoretical and practical understanding of their learning characteristics and decision-making behaviour when applied to medical images. Further, there is still a need to advance real-world modelling in medical image applications by proposing efficient solutions for current challenges and introducing new frameworks/techniques.
The aim of this Research Topic is to publish the recent research contributions related to advancement in machine learning and deep learning algorithms for medical imaging for neurogenerative diseases. Progressive brain disorders with a high prevalence in the general population include Parkinson's disease, Alzheimer's disease and other types of dementia, Huntington's disease, and motor neuron disease. Worldwide, it is estimated that 33 million people have Alzheimer's disease, and 10 million people have Parkinson's disease. The global health economy is significantly impacted by these disorders, which affect both the patient and the caregivers. For differential diagnoses, a variety of diagnostic techniques are used, such as brain imaging, EEG analysis, molecular analysis, and cognitive, psychological, and physical examination.
The primary objective of this Research Topic is to allow researchers to communicate their high-quality and original ideas by presenting and publishing innovative advances in the field of computer vision, Artificial Intelligence theories/tools, Deep learning methods/techniques and their applications in medical imaging for neurogenerative diseases. The goal of the Research Topic is to develop effective treatments, enhance patient quality of life, and extend life expectancy. It focuses on novel artificial intelligence approaches to clarify the pathogenesis of neurodegenerative disorders and provide early diagnosis.
Few suggested subtopics(not limited to):
• Deep Learning for neurodegenerative disorders
• Interpretable and explainable machine learning for neurodegenerative diseases
• Responsible AI for medical image processing for neurodegenerative diseases
• Texture analysis of medical images for neurodegenerative diseases
• Explainable AI (XAI) and predictive data analytics for neurodegenerative
diseases
• Innovative approaches to connecting AI, ML, and Big Data in the
neurodegenerative medical image analysis
• Medical Image Learning with limited and noisy data for neurodegenerative
diseases
• Approaches for automated medical image annotation/labelling for
neurodegenerative diseases
• Approaches for medical image augmentation/synthesis for neurodegenerative
diseases
• Transfer learning strategies and modality-specific representation for
neurodegenerative diseases
• Approaches for learning noise invariant features
• Advanced techniques in deep learning for neuroimaging analysis and
diagnostics.
