AI/ML-Readiness for Neuroimaging of Language

语言神经影像的 AI/ML 准备

• 批准号: 10412576
• 负责人: Rutvik H Desai
• 金额: $ 28.74万
• 依托单位: UNIVERSITY OF SOUTH CAROLINA AT COLUMBIA
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-05-15 至 2025-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10412576
• 关键词: Affect; Anatomy; Anterior; Aphasia; Artificial Intelligence; Behavioral; Brain; Code; Cognitive; Communication; Communities; Complex; Crude Extracts; Data; Data Set; Decision Making; Dementia; Dimensions; Distributed Systems; Electrophysiology (science); FAIR principles; Functional Magnetic Resonance Imaging; Goals; Impairment; Individual; Inferior; Knowledge; Language; Language Disorders; Lesion; Life; Light; Machine Learning; Measures; Mental disorders; Metadata; Methodology; Methods; Modernization; Motor; Motor Cortex; Nature; Noise; Parietal Lobe; Participant; Patients; Pattern; Process; Property; Psycholinguistics; Quality of life; Readiness; Recovery; Research; Rest; Role; Scanning; Schizophrenia; Semantic memory; Semantics; Sensory; Series; Social Interaction; Stimulus; Stroke; Structure; Structure of middle temporal gyrus; Symptoms; System; Techniques; Temporal Lobe; Temporal Lobe Epilepsy; Time; United States National Institutes of Health; Variant; angular gyrus; autism spectrum disorder; deep learning; feature selection; frontal lobe; insight; language comprehension; language processing; learning strategy; lexical; machine learning method; nervous system disorder; neuroimaging; neuropathology; neurotransmission; open data; parent grant; phrases; rehabilitation strategy; relating to nervous system; repository; segregation; semantic processing; social cognition; stroke recovery; stroke survivor; support vector machine; treatment strategy

Project Summary/Abstract Conceptual or semantic knowledge refers to information about objects, actions, relations, self, culture, and includes meanings of words and phrases. The use of this knowledge is pervasive and automatic in daily life. Everyday activities such as communication, recognition and use of objects, social interactions, and decision making are crucially reliant on conceptual knowledge. Impairment of this complex and widely distributed system has serious consequences for quality of life. Several neurological and psychiatric disorders are associated with the impairment of this system, including stroke with aphasia, dementias, temporal lobe epilepsy, schizophrenia, and autism. Understanding the structure and organization of this system, and the specific ways it is disrupted in these individuals, is critical for developing better treatments and rehabilitation strategies. The goal of this research is to understand the structure and use of this information, its neural basis, and the ways in which it can be impaired by neuropathology. This project pertains to three neuroimaging datasets — two functional MRI and one from stroke survivors — that speak to the neural basis of concepts and language processing in the brain. We aim to transform these data and associated metadata to a “machine learning ready” format and make them easily accessible. This will enable application of powerful modern machine learning techniques, such as Deep Learning, for their analysis. We expect that these analyses will shed new light on the organization and function of this core semantic region in the healthy and impaired brain.

项目总结/摘要 概念或语义知识是指关于对象、动作、关系、自我、文化和 包括单词和短语的含义。这种知识的使用在日常生活中是普遍和自动的。 日常活动，如沟通，识别和使用对象，社会交往和决策 关键在于概念知识。这种复杂而广泛分布的 系统对生活质量有严重影响。几种神经和精神疾病是 与该系统受损相关，包括中风失语症、痴呆、颞叶 癫痫精神分裂症和自闭症了解这个系统的结构和组织， 在这些个体中，它被破坏的具体方式对于开发更好的治疗和康复至关重要 战略布局这项研究的目的是了解这些信息的结构和使用，它的神经基础， 以及它如何被神经病理学损害。该项目涉及三种神经成像 数据集-两个功能性MRI和一个来自中风幸存者-这些数据集涉及概念的神经基础， 大脑中的语言处理我们的目标是将这些数据和相关的元数据转换为“机器 学习准备”的格式，并使它们易于访问。这将使强大的现代应用 机器学习技术，如深度学习，用于分析。我们预计，这些分析将 揭示了健康和受损大脑中这一核心语义区域的组织和功能。