RESUMO
It is well-established that brain size is associated with intelligence. But the relationship between cortical morphometric measures and intelligence is unclear. Studies have produced conflicting results or no significant relations between intelligence and cortical morphometric measures such as cortical thickness and peri-cortical contrast. This discrepancy may be due to multicollinearity amongst the independent variables in a multivariate regression analysis, or a failure to fully account for the relationship between brain size and intelligence in some other way. Our study shows that neither cortical thickness nor peri-cortical contrast reliably improves IQ prediction accuracy beyond what is achieved with brain volume alone. We show this in multiple datasets, with child data, developmental data, and with adult data; we show this with data acquired either at multiple sites, or at a single site; we show this with data acquired with different MRI scanner manufacturers, or with all data acquired on a single scanner; and we show this with fluid intelligence, full-scale IQ, performance IQ, and verbal IQ. But our point is not really even about IQ; rather we proffer a methodological caveat and potential explanation of the discrepancies in previous results, and which applies broadly.
Assuntos
Córtex Cerebral , Inteligência , Imageamento por Ressonância Magnética , Humanos , Inteligência/fisiologia , Córtex Cerebral/diagnóstico por imagem , Córtex Cerebral/anatomia & histologia , Feminino , Masculino , Adulto , Criança , Testes de Inteligência , Adolescente , Adulto Jovem , Encéfalo/anatomia & histologia , Encéfalo/diagnóstico por imagemRESUMO
BACKGROUND AND OBJECTIVE: Machine learning techniques typically used in dementia assessment are not able to learn multiple tasks jointly and deal with time-dependent heterogeneous data containing missing values. In this paper, we reformulate SSHIBA, a recently introduced Bayesian multi-view latent variable model, for jointly learning diagnosis, ventricle volume, and ADAS score in dementia on longitudinal data with missing values. METHODS: We propose a novel Bayesian Variational inference framework capable of simultaneously imputing missing values and combining information from several views. This way, we can combine different data views from different time-points in a common latent space and learn the relationships between each time-point, using the semi-supervised formulation to fully exploit the temporal structure of the data and handle missing values. In turn, the model can combine all the available information to simultaneously model and predict multiple output variables. RESULTS: We applied the proposed model to jointly predict diagnosis, ventricle volume, and ADAS score in dementia. The comparison of imputation strategies demonstrated the superior performance of the semi-supervised formulation of the model, improving the best baseline methods. Moreover, the performance in simultaneous prediction of diagnosis, ventricle volume, and ADAS score led to an improved prediction performance over the best baseline method. CONCLUSIONS: The results demonstrate that the proposed SSHIBA framework can learn an excellent imputation of the missing values and outperforming the baselines while simultaneously predicting three different tasks.
Assuntos
Doença de Alzheimer , Humanos , Doença de Alzheimer/diagnóstico por imagem , Teorema de Bayes , Aprendizado de Máquina , Projetos de PesquisaRESUMO
(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.