Dataset Information

Early Diagnosis of Autism Disease by Multi-channel CNNs.

ABSTRACT: Currently there are still no early biomarkers to detect infants with risk of autism spectrum disorder (ASD), which is mainly diagnosed based on behavior observations at three or four years old. Since intervention efforts may miss a critical developmental window after 2 years old, it is significant to identify imaging-based biomarkers for early diagnosis of ASD. Although some methods using magnetic resonance imaging (MRI) for brain disease prediction have been proposed in the last decade, few of them were developed for predicting ASD in early age. Inspired by deep multi-instance learning, in this paper, we propose a patch-level data-expanding strategy for multi-channel convolutional neural networks to automatically identify infants with risk of ASD in early age. Experiments were conducted on the National Database for Autism Research (NDAR), with results showing that our proposed method can significantly improve the performance of early diagnosis of ASD.

SUBMITTER: Li G

PROVIDER: S-EPMC6235442 | biostudies-other | 2018 Sep

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Early Diagnosis of Autism Disease by Multi-channel CNNs.

Li Guannan G Liu Mingxia M Sun Quansen Q Shen Dinggang D Wang Li L

Machine learning in medical imaging. MLMI (Workshop) 20180915

Currently there are still no early biomarkers to detect infants with risk of autism spectrum disorder (ASD), which is mainly diagnosed based on behavior observations at three or four years old. Since intervention efforts may miss a critical developmental window after 2 years old, it is significant to identify imaging-based biomarkers for early diagnosis of ASD. Although some methods using magnetic resonance imaging (MRI) for brain disease prediction have been proposed in the last decade, few of ...[more]

PMID: 30450494

Similar Datasets

Project description:BackgroundEarly and accurate diagnosis of Alzheimer's disease (AD) is essential for disease management and therapeutic choices that can delay disease progression. Machine learning (ML) approaches have been extensively used in attempts to develop algorithms for reliable early diagnosis of AD, although clinical usefulness, interpretability, and generalizability of the classifiers across datasets and MRI protocols remain limited.MethodsWe report a multi-diagnostic and generalizable approach for mild cognitive impairment (MCI) and AD diagnosis using structural MRI and ML. Classifiers were trained and tested using subjects from the AD Neuroimaging Initiative (ADNI) database (n = 570) and the Open Access Series of Imaging Studies (OASIS) project database (n = 531). Several classifiers are compared and combined using voting for a decision. Additionally, we report tests of generalizability across datasets and protocols (IR-SPGR and MPRAGE), the impact of using graph theory measures on diagnostic classification performance, the relative importance of different brain regions on classification for better interpretability, and an evaluation of the potential for clinical applicability of the classifier.ResultsOur "healthy controls (HC) vs. AD" classifier trained and tested on the combination of ADNI and OASIS datasets obtained a balanced accuracy (BAC) of 90.6% and a Matthew's correlation coefficient (MCC) of 0.811. Our "HC vs. MCI vs. AD" classifier trained and tested on the ADNI dataset obtained a 62.1% BAC (33.3% being the by-chance cut-off) and 0.438 MCC. Hippocampal features were the strongest contributors to the classification decisions (approx. 25-45%), followed by temporal (approx. 13%), cingulate, and frontal regions (approx. 8-13% each), which is consistent with our current understanding of AD and its progression. Classifiers generalized well across both datasets and protocols. Finally, using graph theory measures did not improve classification performance.ConclusionsIn sum, we present a diagnostic tool for MCI and AD trained using baseline scans and a follow-up diagnosis regardless of progression, which is multi-diagnostic, generalizable across independent data sources and acquisition protocols, and with transparently reported performance. Rated as potentially clinically applicable, our tool may be clinically useful to inform diagnostic decisions in dementia, if successful in real-world prospective clinical trials.

Project description:Some individuals can flexibly adapt to life's changing demands while others, in particular those with Autism Spectrum Disorder (ASD), find it challenging. The origin of early individual differences in cognitive abilities, the putative tools with which to navigate novel information in life, including in infants later diagnosed with ASD remains unexplored. Moreover, the role of intelligence quotient (IQ) vis-à-vis core features of autism remains debated. We systematically investigate the contribution of early IQ in future autism outcomes in an extremely large, population-based study of 8000 newborns, infants, and toddlers from the US between 2 and 68 months with over 15,000 cross-sectional and longitudinal assessments, and for whom autism outcomes are ascertained or ruled out by about 2-4 years. This population is representative of subjects involved in the National Institutes of Health (NIH)-funded research, mainly on atypical development, in the US. Analyses using predetermined age bins showed that IQ scores are consistently lower in ASD relative to typically developing (TD) children at all ages (p < 0.001), and IQ significantly correlates with social, non-social, and total Calibrated Severity Scores (CSS) on the Autism Diagnostic Observation Schedule (ADOS) (p<0.01). Lower IQ is associated with greater autistic impairments. Note, verbal IQ (VIQ) is no better than the full-scale IQ to predict ASD cases. These findings raise new, compelling questions about potential atypical brain circuitry affecting performance in both verbal and nonverbal abilities and preceding an ASD diagnosis. This study is the first to establish prospectively that low early IQ is a major feature of ASD in early childhood. LAY SUMMARY: The role of IQ scores in autism remains debated. We systematically investigate the contribution of early IQ in an extremely large study of 8,000 children between 2 and 68 months with autism outcomes by about 2-4 years. We show that IQ scores are consistently lower in ASD relative to TD children. This study is the first to establish prospectively that low early IQ is a predictor for ASD diagnosis in early childhood.

Dataset Information

Early Diagnosis of Autism Disease by Multi-channel CNNs.

Publications

Early Diagnosis of Autism Disease by Multi-channel CNNs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets