Pain is defined as “an unpleasant sensory and emotional experience associated with actual or potential tissue damage, or described in terms of such damage” by the International Association for the Study of Pain. The classification of pain is multi-dimensional in clinical practice, covering anatomic features, etiologic and pathophysiological factors, intensity, duration, and other types that are not easily classifiable (e.g. idiopathic pain, cancer pain, fibromyalgia, and etc.). In addition, psychological, cognitive, affective and behavioral factors should also be taken into consideration in the measurement and classification of pain.
Pain is a complex process and numerous studies have demonstrated that central nervous system (CNS) is involved in the development, maintenance, and experience of pain. However, our understanding of how pain is processed within the CNS is still a work in progress. A variety of neuroimaging methods, most commonly structural and functional magnetic resonance imaging (MRI) has become increasingly popular to unravel the secrets of human brain, including the neuro-mechanisms underlying pain. For instance, MRI techniques exhibited a great potential in providing multiple perspectives on the pain-related aberrations of brain function, structure, and their connectivity maps at the group level. MRI also captures the differences of brain aberrations across various forms of pain.
In recent years we have seen growing interest in applying machine learning techniques in neuroimaging research. Machine learning is the core subdomain of artificial intelligence, focusing on prediction by using sophisticated algorithms to identify useful patterns in the large-scaled, heterogeneous data sets. In the neuroscience research field machine learning can be used to identify specific neural signatures derived from neuroimages and to establish models to classify neuropsychiatric diseases, which empowers us to investigate the connection between brain neuroimaging patterns and human behavior at individual subject level. Previous studies have also shown that the functional and structural brain signatures can predict one’s pain sensitivity and distinguish individuals with pain from healthy human individuals. Machine learning, although still at its early stage shows a promising prospect with great potential for translation into clinical diagnosis or prognosis for patients suffering pain.
This Research Topic aims to provide an update on research exploring the mechanism of pain, how pain is processed by and within CNS, as well as how the perception of pain is influenced by emotion, experience and expectation, from the perspective of neuroimaging. More specifically, this collection of articles is intended to emphasize on the validation of machine learning models on measuring pain, distinguishing physical pain from emotional pain, classifying subtypes of pain, predicting responses to the currently available treatments and identifying any specific areas to be further explored for novel interventions.
We welcome submissions that focus on the applications of neuroimaging approaches under the following conditions:
1. Neuroimaging mechanisms of pain and analgesia;
2. Neuroimaging mechanisms of interactions between pain and emotion, memory or other subdomains of cognition;
3. Prediction of the pain intensity and response to analgesic treatments;
4. Classification for the subtypes of pain;
5. Machine learning analyses combining neuroimaging and genetics, biochemical indicators, or clinical features.
Pain is defined as “an unpleasant sensory and emotional experience associated with actual or potential tissue damage, or described in terms of such damage” by the International Association for the Study of Pain. The classification of pain is multi-dimensional in clinical practice, covering anatomic features, etiologic and pathophysiological factors, intensity, duration, and other types that are not easily classifiable (e.g. idiopathic pain, cancer pain, fibromyalgia, and etc.). In addition, psychological, cognitive, affective and behavioral factors should also be taken into consideration in the measurement and classification of pain.
Pain is a complex process and numerous studies have demonstrated that central nervous system (CNS) is involved in the development, maintenance, and experience of pain. However, our understanding of how pain is processed within the CNS is still a work in progress. A variety of neuroimaging methods, most commonly structural and functional magnetic resonance imaging (MRI) has become increasingly popular to unravel the secrets of human brain, including the neuro-mechanisms underlying pain. For instance, MRI techniques exhibited a great potential in providing multiple perspectives on the pain-related aberrations of brain function, structure, and their connectivity maps at the group level. MRI also captures the differences of brain aberrations across various forms of pain.
In recent years we have seen growing interest in applying machine learning techniques in neuroimaging research. Machine learning is the core subdomain of artificial intelligence, focusing on prediction by using sophisticated algorithms to identify useful patterns in the large-scaled, heterogeneous data sets. In the neuroscience research field machine learning can be used to identify specific neural signatures derived from neuroimages and to establish models to classify neuropsychiatric diseases, which empowers us to investigate the connection between brain neuroimaging patterns and human behavior at individual subject level. Previous studies have also shown that the functional and structural brain signatures can predict one’s pain sensitivity and distinguish individuals with pain from healthy human individuals. Machine learning, although still at its early stage shows a promising prospect with great potential for translation into clinical diagnosis or prognosis for patients suffering pain.
This Research Topic aims to provide an update on research exploring the mechanism of pain, how pain is processed by and within CNS, as well as how the perception of pain is influenced by emotion, experience and expectation, from the perspective of neuroimaging. More specifically, this collection of articles is intended to emphasize on the validation of machine learning models on measuring pain, distinguishing physical pain from emotional pain, classifying subtypes of pain, predicting responses to the currently available treatments and identifying any specific areas to be further explored for novel interventions.
We welcome submissions that focus on the applications of neuroimaging approaches under the following conditions:
1. Neuroimaging mechanisms of pain and analgesia;
2. Neuroimaging mechanisms of interactions between pain and emotion, memory or other subdomains of cognition;
3. Prediction of the pain intensity and response to analgesic treatments;
4. Classification for the subtypes of pain;
5. Machine learning analyses combining neuroimaging and genetics, biochemical indicators, or clinical features.