A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Zhang, Li; Wang, Mingliang; Liu, Mingxia; Zhang, Daoqiang

doi:10.3389/fnins.2020.00779

Cited by 141 publications

(99 citation statements)

References 129 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We seek to explain the fundamental reasons why GNNs are worth investigating for this domain, and highlight the emerging medical analytics challenges that GNNs are well placed to address. Although some papers have surveyed medical image analysis using deep learning techniques and have introduced the concept of GNNs for the assessment of neurological disorders [ 14 ], to the best of our knowledge, no systematic review exists that introduces and discusses the current applications of GNNs to unstructured medical data.…”

Section: Introductionmentioning

confidence: 99%

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Ahmedt-Aristizabal

Armin

Denman

et al. 2021

Sensors

130

View full text Add to dashboard Cite

With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled. It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data. A major limitation of existing methods has been the focus on grid-like data; however, the structure of physiological recordings are often irregular and unordered, which makes it difficult to conceptualise them as a matrix. As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interacting nodes connected by edges whose weights can be determined by either temporal associations or anatomical junctions. In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare. We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure, and electrical-based analysis. We also outline the limitations of existing techniques and discuss potential directions for future research.

show abstract

Section: Introductionmentioning

confidence: 99%

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Ahmedt-Aristizabal

Armin

Denman

et al. 2021

Sensors

130

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning (DL) models have attracted significant attention for their ability to learn reliable and robust features directly from the high-dimensional data in diverse neuroimaging applications [13][14][15][16][17] in addition to their highly discriminative capabilities. More recently, Abrol et al (2021) 18 demonstrated the advantages of DL models trained on raw data over SML models trained on pre-engineered features in structural magnetic resonance imaging (sMRI).…”

Section: Introductionmentioning

confidence: 99%

Interpreting models interpreting brain dynamics

Rahman

Mahmood

Lewis

et al. 2021

Preprint

View full text Add to dashboard Cite

Brain dynamics are highly complex and yet hold the key to understanding brain function and dysfunction. The dynamics captured by resting-state functional magnetic resonance imaging data are noisy, high-dimensional, and not readily interpretable. The typical approach of reducing this data to low-dimensional features and focusing on the most predictive features comes with strong assumptions and can miss essential aspects of the underlying dynamics. In contrast, introspection of discriminatively trained deep learning models may uncover disorder-relevant elements of the signal at the level of individual time points and spatial locations. Yet, the difficulty of reliable training on high-dimensional low sample size datasets and the unclear relevance of the resulting predictive markers prevent the widespread use of deep learning in functional neuroimaging. In this work, we introduce a deep learning framework to learn from high-dimensional dynamical data while maintaining stable, ecologically valid interpretations. Results successfully demonstrate that the proposed framework enables learning the dynamics of resting-state fMRI directly from small data and capturing compact, stable interpretations of features predictive of function and dysfunction.

show abstract

“…Since its conception, deep learning methods have been used in medical data analysis; for an overview of deep learning applications in medical data analysis, we recommend readers to go through the review papers by Jang and Cho (7) while Zhang et al (8). In the past decade, deep learning has been employed in classification, segmentation, and identification tasks in assisted or fully automated diagnosis of brain-related disorders.…”

Section: Discussionmentioning

confidence: 99%