1
|
Zhang X, Gao Y, Zhang Y, Li F, Li H, Lei F. Identification of Autism Spectrum Disorder Using Topological Data Analysis. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:1023-1037. [PMID: 38351222 PMCID: PMC11169318 DOI: 10.1007/s10278-024-01002-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Revised: 10/30/2023] [Accepted: 11/21/2023] [Indexed: 06/13/2024]
Abstract
Autism spectrum disorder (ASD) is a pervasive brain development disease. Recently, the incidence rate of ASD has increased year by year and posed a great threat to the lives and families of individuals with ASD. Therefore, the study of ASD has become very important. A suitable feature representation that preserves the data intrinsic information and also reduces data complexity is very vital to the performance of established models. Topological data analysis (TDA) is an emerging and powerful mathematical tool for characterizing shapes and describing intrinsic information in complex data. In TDA, persistence barcodes or diagrams are usually regarded as visual representations of topological features of data. In this paper, the Regional Homogeneity (ReHo) data of subjects obtained from Autism Brain Imaging Data Exchange (ABIDE) database were used to extract features by using TDA. The average accuracy of cross validation on ABIDE I database was 95.6% that was higher than any other existing methods (the highest accuracy among existing methods was 93.59%). The average accuracy for sampling with the same resolutions with the ABIDE I on the ABIDE II database was 96.5% that was also higher than any other existing methods (the highest accuracy among existing methods was 75.17%).
Collapse
Affiliation(s)
- Xudong Zhang
- School of Mathematical Sciences, Dalian University of Technology, Dalian, 116024, China
| | - Yaru Gao
- School of Mathematical Sciences, Dalian University of Technology, Dalian, 116024, China
| | - Yunge Zhang
- School of Biomedical Engineering, Dalian University of Technology, Dalian, 116024, China
| | - Fengling Li
- School of Mathematical Sciences, Dalian University of Technology, Dalian, 116024, China.
| | - Huanjie Li
- School of Biomedical Engineering, Dalian University of Technology, Dalian, 116024, China
| | - Fengchun Lei
- School of Mathematical Sciences, Dalian University of Technology, Dalian, 116024, China
| |
Collapse
|
2
|
Zhang S, Jiang L, Hu Z, Liu W, Yu H, Chu Y, Wang J, Chen Y. T1w/T2w ratio maps identify children with autism spectrum disorder and the relationships between myelin-related changes and symptoms. Prog Neuropsychopharmacol Biol Psychiatry 2024; 134:111040. [PMID: 38806093 DOI: 10.1016/j.pnpbp.2024.111040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Revised: 05/14/2024] [Accepted: 05/23/2024] [Indexed: 05/30/2024]
Abstract
BACKGROUND Modern neuroimaging methods have revealed that autistic symptoms are associated with abnormalities in brain morphology, connectivity, and activity patterns. However, the changes in brain microstructure underlying the neurobiological and behavioral deficits of autism remain largely unknown. METHODS we characterized the associated abnormalities in intracortical myelination pattern by constructing cortical T1-weighted/T2-weighted ratio maps. Voxel-wise comparisons of cortical myelination were conducted between 150 children with autism spectrum disorder (ASD) and 139 typically developing (TD) children. Group differences in cortical T1-weighted/T2-weighted ratio and gray matter volume were then examined for associations with autistic symptoms. A convolutional neural network (CNN) model was also constructed to examine the utility of these regional abnormalities in cortical myelination for ASD diagnosis. RESULTS Compared to TD children, the ASD group exhibited widespread reductions in cortical myelination within regions related to default mode, salience, and executive control networks such as the inferior frontal gyrus, bilateral insula, left fusiform gyrus, bilateral hippocampus, right calcarine sulcus, bilateral precentral, and left posterior cingulate gyrus. Moreover, greater myelination deficits in most of these regions were associated with more severe autistic symptoms. In addition, children with ASD exhibited reduced myelination in regions with greater gray matter volume, including left insula, left cerebellum_4_5, left posterior cingulate gyrus, and right calcarine sulcus. Notably, the CNN model based on brain regions with abnormal myelination demonstrated high diagnostic efficacy for ASD. CONCLUSIONS Our findings suggest that microstructural abnormalities in myelination contribute to autistic symptoms and so are potentially promising therapeutic targets as well as biomarkers for ASD diagnosis.
Collapse
Affiliation(s)
- Shujun Zhang
- Department of Radiology, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China
| | - Liping Jiang
- Department of Pharmacy, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China
| | - Zhe Hu
- Department of Radiology, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China
| | - Wenjing Liu
- Children Rehabilitation Center, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China
| | - Hao Yu
- Department of Radiology, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China
| | - Yao Chu
- Department of Radiology, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China
| | - Jiehuan Wang
- Department of Radiology, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China.
| | - Yueqin Chen
- Department of Radiology, Affiliated Hospital of Jining Medical University, Jining 272000, Shandong Province, China.
| |
Collapse
|
3
|
Yu Z, Pang H, Yang Y, Luo D, Zheng H, Huang Z, Zhang M, Ren K. Microglia dysfunction drives disrupted hippocampal amplitude of low frequency after acute kidney injury. CNS Neurosci Ther 2024; 30:e14363. [PMID: 37469216 PMCID: PMC10848109 DOI: 10.1111/cns.14363] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Revised: 06/20/2023] [Accepted: 06/24/2023] [Indexed: 07/21/2023] Open
Abstract
AIMS Acute kidney injury (AKI) has been associated with a variety of neurological problems, while the neurobiological mechanism remains unclear. In the present study, we utilized resting-state functional magnetic resonance imaging (rs-fMRI) to detect brain injury at an early stage and investigated the impact of microglia on the neuropathological mechanism of AKI. METHODS Rs-fMRI data were collected from AKI rats and the control group with a 9.4-Tesla scanner at 24, 48, and 72 h post administration of contrast medium or saline. The amplitude of low-frequency fluctuations (ALFF) was then compared across the groups at each time course. Additionally, flow cytometry and SMART-seq2 were employed to evaluate microglia. Furthermore, pathological staining and Western blot were used to analyze the samples. RESULTS MRI results revealed that AKI led to a decreased ALFF in the hippocampus, particularly in the 48 h and 72 h groups. Additionally, western blot suggested that AKI-induced the neuronal apoptosis at 48 h and 72 h. Flow cytometry and confocal microscopy images demonstrated that AKI activated the aggregation of microglia into neurons at 24 h, with a strong upregulation of M1 polarization at 48 h and peaking at 72 h, accompanying with the release of proinflammatory cytokines. The ALFF value was strongly correlated with the proportion of microglia (|r| > 0.80, p < 0.001). CONCLUSIONS Our study demonstrated that microglia aggregation and inflammatory factor upregulation are significant mechanisms of AKI-induced neuronal apoptosis. We used fMRI to detect the alterations in hippocampal function, which may provide a noninvasive method for the early detection of brain injury after AKI.
Collapse
Affiliation(s)
- Ziyang Yu
- School of MedicineXiamen UniversityXiamenChina
| | - Huize Pang
- Department of RadiologyThe First Hospital of China Medical UniversityShenyangChina
| | - Yifan Yang
- School of MedicineXiamen UniversityXiamenChina
| | - Doudou Luo
- School of MedicineXiamen UniversityXiamenChina
| | - Haiping Zheng
- State Key Laboratory of Cellular Stress Biology, Innovation Center for Cell Signaling Network, School of Life SciencesXiamen UniversityXiamenChina
| | - Zicheng Huang
- State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics and Center for Molecular Imaging and Translational Medicine, School of Public HealthXiamen UniversityXiamenChina
| | - Mingxia Zhang
- State Key Laboratory of Cellular Stress Biology, Innovation Center for Cell Signaling Network, School of Life SciencesXiamen UniversityXiamenChina
| | - Ke Ren
- School of MedicineXiamen UniversityXiamenChina
- Department of RadiologyThe First Hospital of China Medical UniversityShenyangChina
| |
Collapse
|
4
|
Kolasa K, Admassu B, Hołownia-Voloskova M, Kędzior KJ, Poirrier JE, Perni S. Systematic reviews of machine learning in healthcare: a literature review. Expert Rev Pharmacoecon Outcomes Res 2024; 24:63-115. [PMID: 37955147 DOI: 10.1080/14737167.2023.2279107] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Accepted: 10/31/2023] [Indexed: 11/14/2023]
Abstract
INTRODUCTION The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery. METHODS A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted. RESULTS In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively). EXPERT OPINION The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.
Collapse
Affiliation(s)
- Katarzyna Kolasa
- Division of Health Economics and Healthcare Management, Kozminski University, Warsaw, Poland
| | - Bisrat Admassu
- Division of Health Economics and Healthcare Management, Kozminski University, Warsaw, Poland
| | | | | | | | | |
Collapse
|
5
|
Chen Z, Hu B, Liu X, Becker B, Eickhoff SB, Miao K, Gu X, Tang Y, Dai X, Li C, Leonov A, Xiao Z, Feng Z, Chen J, Chuan-Peng H. Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry. BMC Med 2023; 21:241. [PMID: 37400814 DOI: 10.1186/s12916-023-02941-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Accepted: 06/13/2023] [Indexed: 07/05/2023] Open
Abstract
BACKGROUND The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation. METHODS Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses. RESULTS A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β = - 2.75, p < .001, R2adj = 0.40; r = - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF10 > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance. CONCLUSIONS Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.
Collapse
Affiliation(s)
- Zhiyi Chen
- Experimental Research Center for Medical and Psychological Science (ERC-MPS), School of Psychology, Third Military Medical University, Chongqing, China.
- Faculty of Psychology, Southwest University, Chongqing, China.
| | - Bowen Hu
- Faculty of Psychology, Southwest University, Chongqing, China
| | - Xuerong Liu
- Experimental Research Center for Medical and Psychological Science (ERC-MPS), School of Psychology, Third Military Medical University, Chongqing, China
| | - Benjamin Becker
- The Center of Psychosomatic Medicine, Sichuan Provincial Center for Mental Health, Sichuan Provincial People's Hospital, Chengdu, China
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
| | - Simon B Eickhoff
- Institute of Systems Neuroscience, Heinrich Heine University Düsseldorf, Düsseldorf, Germany
| | - Kuan Miao
- Experimental Research Center for Medical and Psychological Science (ERC-MPS), School of Psychology, Third Military Medical University, Chongqing, China
| | - Xingmei Gu
- Experimental Research Center for Medical and Psychological Science (ERC-MPS), School of Psychology, Third Military Medical University, Chongqing, China
| | - Yancheng Tang
- School of Business and Management, Shanghai International Studies University, Shanghai, China
| | - Xin Dai
- Faculty of Psychology, Southwest University, Chongqing, China
| | - Chao Li
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangdong, China
| | - Artemiy Leonov
- School of Psychology, Clark University, Worcester, MA, USA
| | - Zhibing Xiao
- State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China
| | - Zhengzhi Feng
- Experimental Research Center for Medical and Psychological Science (ERC-MPS), School of Psychology, Third Military Medical University, Chongqing, China
| | - Ji Chen
- Department of Psychology and Behavioral Sciences, Zhejiang University, Hangzhou, China.
- Department of Psychiatry, The Fourth Affiliated Hospital, Zhejiang University School of Medicine, Yiwu, Zhejiang, China.
| | - Hu Chuan-Peng
- School of Psychology, Nanjing Normal University, Nanjing, China
| |
Collapse
|
6
|
Mishra M, Pati UC. A classification framework for Autism Spectrum Disorder detection using sMRI: Optimizer based ensemble of deep convolution neural network with on-the-fly data augmentation. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104686] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/26/2023]
|
7
|
Helmy E, Elnakib A, ElNakieb Y, Khudri M, Abdelrahim M, Yousaf J, Ghazal M, Contractor S, Barnes GN, El-Baz A. Role of Artificial Intelligence for Autism Diagnosis Using DTI and fMRI: A Survey. Biomedicines 2023; 11:1858. [PMID: 37509498 PMCID: PMC10376963 DOI: 10.3390/biomedicines11071858] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Revised: 06/22/2023] [Accepted: 06/27/2023] [Indexed: 07/30/2023] Open
Abstract
Autism spectrum disorder (ASD) is a wide range of diseases characterized by difficulties with social skills, repetitive activities, speech, and nonverbal communication. The Centers for Disease Control (CDC) estimates that 1 in 44 American children currently suffer from ASD. The current gold standard for ASD diagnosis is based on behavior observational tests by clinicians, which suffer from being subjective and time-consuming and afford only late detection (a child must have a mental age of at least two to apply for an observation report). Alternatively, brain imaging-more specifically, magnetic resonance imaging (MRI)-has proven its ability to assist in fast, objective, and early ASD diagnosis and detection. With the recent advances in artificial intelligence (AI) and machine learning (ML) techniques, sufficient tools have been developed for both automated ASD diagnosis and early detection. More recently, the development of deep learning (DL), a young subfield of AI based on artificial neural networks (ANNs), has successfully enabled the processing of brain MRI data with improved ASD diagnostic abilities. This survey focuses on the role of AI in autism diagnostics and detection based on two basic MRI modalities: diffusion tensor imaging (DTI) and functional MRI (fMRI). In addition, the survey outlines the basic findings of DTI and fMRI in autism. Furthermore, recent techniques for ASD detection using DTI and fMRI are summarized and discussed. Finally, emerging tendencies are described. The results of this study show how useful AI is for early, subjective ASD detection and diagnosis. More AI solutions that have the potential to be used in healthcare settings will be introduced in the future.
Collapse
Affiliation(s)
- Eman Helmy
- Department of Diagnostic Radiology, Faculty of Medicine, Mansoura University, Elgomheryia Street, Mansoura 3512, Egypt;
| | - Ahmed Elnakib
- Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (A.E.); (Y.E.); (M.K.); (M.A.)
| | - Yaser ElNakieb
- Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (A.E.); (Y.E.); (M.K.); (M.A.)
| | - Mohamed Khudri
- Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (A.E.); (Y.E.); (M.K.); (M.A.)
| | - Mostafa Abdelrahim
- Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (A.E.); (Y.E.); (M.K.); (M.A.)
| | - Jawad Yousaf
- Electrical, Computer, and Biomedical Engineering Department, Abu Dhabi University, Abu Dhabi 59911, United Arab Emirates; (J.Y.); (M.G.)
| | - Mohammed Ghazal
- Electrical, Computer, and Biomedical Engineering Department, Abu Dhabi University, Abu Dhabi 59911, United Arab Emirates; (J.Y.); (M.G.)
| | - Sohail Contractor
- Department of Radiology, University of Louisville, Louisville, KY 40202, USA;
| | - Gregory Neal Barnes
- Department of Neurology, Pediatric Research Institute, University of Louisville, Louisville, KY 40202, USA;
| | - Ayman El-Baz
- Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (A.E.); (Y.E.); (M.K.); (M.A.)
| |
Collapse
|
8
|
Chen Z, Liu X, Yang Q, Wang YJ, Miao K, Gong Z, Yu Y, Leonov A, Liu C, Feng Z, Chuan-Peng H. Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review. JAMA Netw Open 2023; 6:e231671. [PMID: 36877519 PMCID: PMC9989906 DOI: 10.1001/jamanetworkopen.2023.1671] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/07/2023] Open
Abstract
IMPORTANCE Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated. OBJECTIVE To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis. EVIDENCE REVIEW PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality. FINDINGS A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%). CONCLUSIONS AND RELEVANCE This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.
Collapse
Affiliation(s)
- Zhiyi Chen
- School of Psychology, Third Military Medical University, Chongqing, China
- Experimental Research Center for Medical and Psychological Science, Third Military Medical University, Chongqing, China
| | - Xuerong Liu
- School of Psychology, Third Military Medical University, Chongqing, China
- Experimental Research Center for Medical and Psychological Science, Third Military Medical University, Chongqing, China
| | - Qingwu Yang
- Department of Neurology, Daping Hospital, Third Military Medical University, Chongqing, China
| | - Yan-Jiang Wang
- Department of Neurology, Daping Hospital, Third Military Medical University, Chongqing, China
| | - Kuan Miao
- School of Psychology, Third Military Medical University, Chongqing, China
- Experimental Research Center for Medical and Psychological Science, Third Military Medical University, Chongqing, China
| | - Zheng Gong
- School of Psychology, Third Military Medical University, Chongqing, China
- Experimental Research Center for Medical and Psychological Science, Third Military Medical University, Chongqing, China
| | - Yang Yu
- School of Psychology, Third Military Medical University, Chongqing, China
| | - Artemiy Leonov
- Department of Psychology, Clark University, Worcester, Massachusetts
| | - Chunlei Liu
- School of Psychology, Qufu Normal University, Qufu, China
| | - Zhengzhi Feng
- School of Psychology, Third Military Medical University, Chongqing, China
- Experimental Research Center for Medical and Psychological Science, Third Military Medical University, Chongqing, China
| | - Hu Chuan-Peng
- School of Psychology, Nanjing Normal University, Nanjing, China
| |
Collapse
|
9
|
Atasever S, Azginoglu N, Terzi DS, Terzi R. A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning. Clin Imaging 2023; 94:18-41. [PMID: 36462229 DOI: 10.1016/j.clinimag.2022.11.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 10/17/2022] [Accepted: 11/01/2022] [Indexed: 11/13/2022]
Abstract
This survey aims to identify commonly used methods, datasets, future trends, knowledge gaps, constraints, and limitations in the field to provide an overview of current solutions used in medical image analysis in parallel with the rapid developments in transfer learning (TL). Unlike previous studies, this survey grouped the last five years of current studies for the period between January 2017 and February 2021 according to different anatomical regions and detailed the modality, medical task, TL method, source data, target data, and public or private datasets used in medical imaging. Also, it provides readers with detailed information on technical challenges, opportunities, and future research trends. In this way, an overview of recent developments is provided to help researchers to select the most effective and efficient methods and access widely used and publicly available medical datasets, research gaps, and limitations of the available literature.
Collapse
Affiliation(s)
- Sema Atasever
- Computer Engineering Department, Nevsehir Hacı Bektas Veli University, Nevsehir, Turkey.
| | - Nuh Azginoglu
- Computer Engineering Department, Kayseri University, Kayseri, Turkey.
| | | | - Ramazan Terzi
- Computer Engineering Department, Amasya University, Amasya, Turkey.
| |
Collapse
|
10
|
Deng X, Zhang J, Liu R, Liu K. Classifying ASD based on time-series fMRI using spatial-temporal transformer. Comput Biol Med 2022; 151:106320. [PMID: 36442277 DOI: 10.1016/j.compbiomed.2022.106320] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2022] [Revised: 10/11/2022] [Accepted: 11/14/2022] [Indexed: 11/18/2022]
Abstract
As the prevalence of autism spectrum disorder (ASD) increases globally, more and more patients need to receive timely diagnosis and treatment to alleviate their suffering. However, the current diagnosis method of ASD still adopts the subjective symptom-based criteria through clinical observation, which is time-consuming and costly. In recent years, functional magnetic resonance imaging (fMRI) neuroimaging techniques have emerged to facilitate the identification of potential biomarkers for diagnosing ASD. In this study, we developed a deep learning framework named spatial-temporal Transformer (ST-Transformer) to distinguish ASD subjects from typical controls based on fMRI data. Specifically, a linear spatial-temporal multi-headed attention unit is proposed to obtain the spatial and temporal representation of fMRI data. Moreover, a Gaussian GAN-based data balancing method is introduced to solve the data unbalance problem in real-world ASD datasets for subtype ASD diagnosis. Our proposed ST-Transformer is evaluated on a large cohort of subjects from two independent datasets (ABIDE I and ABIDE II) and achieves robust accuracies of 71.0% and 70.6%, respectively. Compared with state-of-the-art methods, our results demonstrate competitive performance in ASD diagnosis.
Collapse
Affiliation(s)
- Xin Deng
- The Key Laboratory of Data Engineering and Visual Computing, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
| | - Jiahao Zhang
- The Key Laboratory of Data Engineering and Visual Computing, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
| | - Rui Liu
- Department of Computer Science, City University of Hong Kong, 999077, Hong Kong, China.
| | - Ke Liu
- The Key Laboratory of Data Engineering and Visual Computing, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
| |
Collapse
|
11
|
Supekar K, Ryali S, Yuan R, Kumar D, de Los Angeles C, Menon V. Robust, Generalizable, and Interpretable Artificial Intelligence-Derived Brain Fingerprints of Autism and Social Communication Symptom Severity. Biol Psychiatry 2022; 92:643-653. [PMID: 35382930 PMCID: PMC9378793 DOI: 10.1016/j.biopsych.2022.02.005] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/01/2021] [Revised: 02/04/2022] [Accepted: 02/04/2022] [Indexed: 12/29/2022]
Abstract
BACKGROUND Autism spectrum disorder (ASD) is among the most pervasive neurodevelopmental disorders, yet the neurobiology of ASD is still poorly understood because inconsistent findings from underpowered individual studies preclude the identification of robust and interpretable neurobiological markers and predictors of clinical symptoms. METHODS We leverage multiple brain imaging cohorts and exciting recent advances in explainable artificial intelligence to develop a novel spatiotemporal deep neural network (stDNN) model, which identifies robust and interpretable dynamic brain markers that distinguish ASD from neurotypical control subjects and predict clinical symptom severity. RESULTS stDNN achieved consistently high classification accuracies in cross-validation analysis of data from the multisite ABIDE (Autism Brain Imaging Data Exchange) cohort (n = 834). Crucially, stDNN also accurately classified data from independent Stanford (n = 202) and GENDAAR (Gender Exploration of Neurogenetics and Development to Advanced Autism Research) (n = 90) cohorts without additional training. stDNN could not distinguish attention-deficit/hyperactivity disorder from neurotypical control subjects, highlighting the model's specificity. Explainable artificial intelligence revealed that brain features associated with the posterior cingulate cortex and precuneus, dorsolateral and ventrolateral prefrontal cortex, and superior temporal sulcus, which anchor the default mode network, cognitive control, and human voice processing systems, respectively, most clearly distinguished ASD from neurotypical control subjects in the three cohorts. Furthermore, features associated with the posterior cingulate cortex and precuneus nodes of the default mode network emerged as robust predictors of the severity of core social and communication deficits but not restricted/repetitive behaviors in ASD. CONCLUSIONS Our findings, replicated across independent cohorts, reveal robust individualized functional brain fingerprints of ASD psychopathology, which could lead to more objective and precise phenotypic characterization and targeted treatments.
Collapse
Affiliation(s)
- Kaustubh Supekar
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California.
| | - Srikanth Ryali
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California
| | - Rui Yuan
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California
| | - Devinder Kumar
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California
| | - Carlo de Los Angeles
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California
| | - Vinod Menon
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California; Department of Neurology & Neurological Sciences, Stanford University School of Medicine, Stanford, California; Stanford Neurosciences Institute, Stanford University School of Medicine, Stanford, California.
| |
Collapse
|
12
|
Moridian P, Ghassemi N, Jafari M, Salloum-Asfar S, Sadeghi D, Khodatars M, Shoeibi A, Khosravi A, Ling SH, Subasi A, Alizadehsani R, Gorriz JM, Abdulla SA, Acharya UR. Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review. Front Mol Neurosci 2022; 15:999605. [PMID: 36267703 PMCID: PMC9577321 DOI: 10.3389/fnmol.2022.999605] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2022] [Accepted: 08/09/2022] [Indexed: 12/04/2022] Open
Abstract
Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.
Collapse
Affiliation(s)
- Parisa Moridian
- Faculty of Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
| | - Navid Ghassemi
- Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
| | - Mahboobeh Jafari
- Faculty of Electrical and Computer Engineering, Semnan University, Semnan, Iran
| | - Salam Salloum-Asfar
- Neurological Disorders Research Center, Qatar Biomedical Research Institute, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar
| | - Delaram Sadeghi
- Department of Medical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
| | - Marjane Khodatars
- Department of Medical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
| | - Afshin Shoeibi
- Data Science and Computational Intelligence Institute, University of Granada, Granada, Spain
| | - Abbas Khosravi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, VIC, Australia
| | - Sai Ho Ling
- Faculty of Engineering and IT, University of Technology Sydney (UTS), Ultimo, NSW, Australia
| | - Abdulhamit Subasi
- Faculty of Medicine, Institute of Biomedicine, University of Turku, Turku, Finland
- Department of Computer Science, College of Engineering, Effat University, Jeddah, Saudi Arabia
| | - Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, VIC, Australia
| | - Juan M. Gorriz
- Data Science and Computational Intelligence Institute, University of Granada, Granada, Spain
| | - Sara A. Abdulla
- Neurological Disorders Research Center, Qatar Biomedical Research Institute, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar
| | - U. Rajendra Acharya
- Ngee Ann Polytechnic, Singapore, Singapore
- Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung, Taiwan
- Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore, Singapore
| |
Collapse
|
13
|
Xie J, Wang L, Webster P, Yao Y, Sun J, Wang S, Zhou H. Identifying Visual Attention Features Accurately Discerning Between Autism and Typically Developing: a Deep Learning Framework. Interdiscip Sci 2022; 14:639-651. [PMID: 35415827 DOI: 10.1007/s12539-022-00510-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2021] [Revised: 03/10/2022] [Accepted: 03/15/2022] [Indexed: 06/14/2023]
Abstract
Atypical visual attention is a hallmark of autism spectrum disorder (ASD). Identifying the attention features accurately discerning between people with ASD and typically developing (TD) at the individual level remains a challenge. In this study, we developed a new systematic framework combining high accuracy deep learning classification, deep learning segmentation, image ablation and a direct measurement of classification ability to identify the discriminative features for autism identification. Our two-stream model achieved the state-of-the-art performance with a classification accuracy of 0.95. Using this framework, two new categories of features, Food & drink and Outdoor-objects, were identified as discriminative attention features, in addition to the previously reported features including Center-object and Human-faces, etc. Altered attention to the new categories helps to understand related atypical behaviors in ASD. Importantly, the area under curve (AUC) based on the combined top-9 features identified in this study was 0.92, allowing an accurate classification at the individual level. We also obtained a small but informative dataset of 12 images with an AUC of 0.86, suggesting a potentially efficient approach for the clinical diagnosis of ASD. Together, our deep learning framework based on VGG-16 provides a novel and powerful tool to recognize and understand abnormal visual attention in ASD, which will, in turn, facilitate the identification of biomarkers for ASD.
Collapse
Affiliation(s)
- Jin Xie
- The Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Longfei Wang
- The Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
| | - Paula Webster
- Department of Chemical and Biomedical Engineering and Rockefeller Neuroscience Institute, West Virginia University, Morgantown, WV, 26506, USA
| | - Yang Yao
- The Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
| | - Jiayao Sun
- The Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Shuo Wang
- Department of Radiology, Washington University in St. Louis, St. Louis, MO, 63130, USA.
| | - Huihui Zhou
- The Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China.
- The Research Center for Artificial Intelligence, Peng Cheng Laboratory, No. 2 Xingke First Street, Nanshan District, Shenzhen, 518000, China.
| |
Collapse
|
14
|
rs-fMRI and machine learning for ASD diagnosis: a systematic review and meta-analysis. Sci Rep 2022; 12:6030. [PMID: 35411059 PMCID: PMC9001715 DOI: 10.1038/s41598-022-09821-6] [Citation(s) in RCA: 27] [Impact Index Per Article: 13.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2021] [Accepted: 03/23/2022] [Indexed: 02/08/2023] Open
Abstract
AbstractAutism Spectrum Disorder (ASD) diagnosis is still based on behavioral criteria through a lengthy and time-consuming process. Much effort is being made to identify brain imaging biomarkers and develop tools that could facilitate its diagnosis. In particular, using Machine Learning classifiers based on resting-state fMRI (rs-fMRI) data is promising, but there is an ongoing need for further research on their accuracy and reliability. Therefore, we conducted a systematic review and meta-analysis to summarize the available evidence in the literature so far. A bivariate random-effects meta-analytic model was implemented to investigate the sensitivity and specificity across the 55 studies that offered sufficient information for quantitative analysis. Our results indicated overall summary sensitivity and specificity estimates of 73.8% and 74.8%, respectively. SVM stood out as the most used classifier, presenting summary estimates above 76%. Studies with bigger samples tended to obtain worse accuracies, except in the subgroup analysis for ANN classifiers. The use of other brain imaging or phenotypic data to complement rs-fMRI information seems promising, achieving higher sensitivities when compared to rs-fMRI data alone (84.7% versus 72.8%). Finally, our analysis showed AUC values between acceptable and excellent. Still, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of those classification algorithms to clinical settings.
Collapse
|
15
|
Chen Y, Liu A, Fu X, Wen J, Chen X. An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification. Front Neurosci 2022; 15:828512. [PMID: 35185454 PMCID: PMC8854990 DOI: 10.3389/fnins.2021.828512] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2021] [Accepted: 12/23/2021] [Indexed: 12/23/2022] Open
Abstract
Autism Spectrum Disorder (ASD) is one common developmental disorder with great variations in symptoms and severity, making the diagnosis of ASD a challenging task. Existing deep learning models using brain connectivity features to classify ASD still suffer from degraded performance for multi-center data due to limited feature representation ability and insufficient interpretability. Given that Graph Convolutional Network (GCN) has demonstrated superiority in learning discriminative representations of brain connectivity networks, in this paper, we propose an invertible dynamic GCN model to identify ASD and investigate the alterations of connectivity patterns associated with the disease. In order to select explainable features from the model, invertible blocks are introduced in the whole network, and we are able to reconstruct the input dynamic features from the network's output. A pre-screening of connectivity features is adopted to reduce the redundancy of the input information, and a fully-connected layer is added to perform classification. The experimental results on 867 subjects show that our proposed method achieves superior disease classification performance. It provides an interpretable deep learning model for brain connectivity analysis and is of great potential in studying brain-related disorders.
Collapse
Affiliation(s)
- Yueying Chen
- School of Information Science and Technology, University of Science and Technology of China, Hefei, China
- USTC IAT-Huami Joint Laboratory for Brain-Machine Intelligence, Institute of Advanced Technology, University of Science and Technology of China, Hefei, China
| | - Aiping Liu
- School of Information Science and Technology, University of Science and Technology of China, Hefei, China
- USTC IAT-Huami Joint Laboratory for Brain-Machine Intelligence, Institute of Advanced Technology, University of Science and Technology of China, Hefei, China
- *Correspondence: Aiping Liu
| | - Xueyang Fu
- School of Information Science and Technology, University of Science and Technology of China, Hefei, China
- USTC IAT-Huami Joint Laboratory for Brain-Machine Intelligence, Institute of Advanced Technology, University of Science and Technology of China, Hefei, China
| | - Jie Wen
- Division of Life Sciences and Medicine, Department of Radiology, The First Affiliated Hospital of USTC (Anhui Provincial Hospital), University of Science and Technology of China, Hefei, China
| | - Xun Chen
- School of Information Science and Technology, University of Science and Technology of China, Hefei, China
- USTC IAT-Huami Joint Laboratory for Brain-Machine Intelligence, Institute of Advanced Technology, University of Science and Technology of China, Hefei, China
| |
Collapse
|
16
|
Wang Y, Huang YW, Ablikim D, Lu Q, Zhang AJ, Dong YQ, Zeng FC, Xu JH, Wang W, Hu ZH. Efficacy of acupuncture at ghost points combined with fluoxetine in treating depression: A randomized study. World J Clin Cases 2022; 10:929-938. [PMID: 35127907 PMCID: PMC8790430 DOI: 10.12998/wjcc.v10.i3.929] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Revised: 12/11/2021] [Accepted: 12/25/2021] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND Depression affects more than 350 million people worldwide. In China, 4.2% (54 million people) of the total population suffers from depression. Psychotherapy has been shown to change cognition, improve personality, and enhance the ability to cope with difficulties and setbacks. While pharmacotherapy can reduce symptoms, it is also associated with adverse reactions and relapse after drug withdrawal. Therefore, there has been an increasing emphasis placed on the use of non-pharmacological therapies for depression. The hypothesis of this study was that acupuncture at ghost points combined with fluoxetine would be more effective than fluoxetine alone for the treatment of depression.
AIM To investigate the efficacy of acupuncture at ghost points combined with fluoxetine for the treatment of patients with depression.
METHODS This randomized controlled trial included patients with mild to moderate depression (n = 160). Patients received either acupuncture at ghost points combined with fluoxetine (n = 80) or fluoxetine alone (control group, n = 80). Needles were retained in place for 30 min, 5 times a week; three treatment cycles were administered. The Mann–Whitney U test was used to compare functional magnet resonance imaging parameters, Hamilton depression rating scale (HAMD) scores, and self-rating depression scale (SDS) scores between the acupuncture group and control group.
RESULTS There were no significant differences in HAMD or SDS scores between the acupuncture group and control group, before or after 4 wk of treatment. The acupuncture group exhibited significantly lower HAMD and SDS scores than the control group after 8 wk of treatment (P < 0.05). The acupuncture group had significantly lower fractional Amplitude of Low Frequency Fluctuations values for the left anterior wedge leaf, left posterior cingulate gyrus, left middle occipital gyrus, and left inferior occipital gyrus after 8 wk. The acupuncture group also had significantly higher values for the right inferior frontal gyrus, right insula, and right hippocampus (P < 0.05). After 8 wk of treatment, the effective rates of the acupuncture and control groups were 51.25% and 36.25%, respectively (P < 0.05).
CONCLUSION The study results suggest that acupuncture at ghost points combined with fluoxetine is more effective than fluoxetine alone for the treatment of patients with mild to moderate depression.
Collapse
Affiliation(s)
- Yi Wang
- Department of Acupuncture and Moxibustion, Shanghai TCM-Integrated Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai 200082, China
| | - Yu-Wei Huang
- Department of Acupuncture and Moxibustion, Shanghai TCM-Integrated Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai 200082, China
| | - Dilnur Ablikim
- Department of Acupuncture and Moxibustion, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China
| | - Qun Lu
- Department of Clinical Laboratory, Shanghai TCM-Integrated Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai 200082, China
| | - Ai-Jia Zhang
- Department of Acupuncture and Moxibustion, Shanghai TCM-Integrated Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai 200082, China
| | - Ye-Qing Dong
- Department of Traditional Chinese Medicine, Jiangwan Hospital, Shanghai 200081, China
| | - Fei-Cui Zeng
- Department of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai 200081, China
| | - Jing-Hua Xu
- Department of Acupuncture and Moxibustion, Shanghai TCM-Integrated Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai 200082, China
| | - Wen Wang
- Department of Acupuncture and Moxibustion, Shanghai TCM-Integrated Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai 200082, China
| | - Zhi-Hai Hu
- Department of Acupuncture and Moxibustion, Shanghai TCM-Integrated Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai 200082, China
| |
Collapse
|
17
|
Khodatars M, Shoeibi A, Sadeghi D, Ghaasemi N, Jafari M, Moridian P, Khadem A, Alizadehsani R, Zare A, Kong Y, Khosravi A, Nahavandi S, Hussain S, Acharya UR, Berk M. Deep learning for neuroimaging-based diagnosis and rehabilitation of Autism Spectrum Disorder: A review. Comput Biol Med 2021; 139:104949. [PMID: 34737139 DOI: 10.1016/j.compbiomed.2021.104949] [Citation(s) in RCA: 80] [Impact Index Per Article: 26.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 10/02/2021] [Accepted: 10/13/2021] [Indexed: 01/23/2023]
Abstract
Accurate diagnosis of Autism Spectrum Disorder (ASD) followed by effective rehabilitation is essential for the management of this disorder. Artificial intelligence (AI) techniques can aid physicians to apply automatic diagnosis and rehabilitation procedures. AI techniques comprise traditional machine learning (ML) approaches and deep learning (DL) techniques. Conventional ML methods employ various feature extraction and classification techniques, but in DL, the process of feature extraction and classification is accomplished intelligently and integrally. DL methods for diagnosis of ASD have been focused on neuroimaging-based approaches. Neuroimaging techniques are non-invasive disease markers potentially useful for ASD diagnosis. Structural and functional neuroimaging techniques provide physicians substantial information about the structure (anatomy and structural connectivity) and function (activity and functional connectivity) of the brain. Due to the intricate structure and function of the brain, proposing optimum procedures for ASD diagnosis with neuroimaging data without exploiting powerful AI techniques like DL may be challenging. In this paper, studies conducted with the aid of DL networks to distinguish ASD are investigated. Rehabilitation tools provided for supporting ASD patients utilizing DL networks are also assessed. Finally, we will present important challenges in the automated detection and rehabilitation of ASD and propose some future works.
Collapse
Affiliation(s)
- Marjane Khodatars
- Dept. of Medical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
| | - Afshin Shoeibi
- Faculty of Electrical Engineering, FPGA Lab, K. N. Toosi University of Technology, Tehran, Iran; Computer Engineering Department, Ferdowsi University of Mashhad, Mashhad, Iran.
| | - Delaram Sadeghi
- Dept. of Medical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
| | - Navid Ghaasemi
- Faculty of Electrical Engineering, FPGA Lab, K. N. Toosi University of Technology, Tehran, Iran; Computer Engineering Department, Ferdowsi University of Mashhad, Mashhad, Iran
| | - Mahboobeh Jafari
- Electrical and Computer Engineering Faculty, Semnan University, Semnan, Iran
| | - Parisa Moridian
- Faculty of Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
| | - Ali Khadem
- Department of Biomedical Engineering, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran.
| | - Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Victoria, 3217, Australia
| | - Assef Zare
- Faculty of Electrical Engineering, Gonabad Branch, Islamic Azad University, Gonabad, Iran
| | - Yinan Kong
- School of Engineering, Macquarie University, Sydney, 2109, Australia
| | - Abbas Khosravi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Victoria, 3217, Australia
| | - Saeid Nahavandi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Victoria, 3217, Australia
| | | | - U Rajendra Acharya
- Ngee Ann Polytechnic, Singapore, 599489, Singapore; Dept. of Biomedical Informatics and Medical Engineering, Asia University, Taichung, Taiwan; Dept. of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore
| | - Michael Berk
- Deakin University, IMPACT - the Institute for Mental and Physical Health and Clinical Translation, School of Medicine, Barwon Health, Geelong, Australia; Orygen, The National Centre of Excellence in Youth Mental Health, Centre for Youth Mental Health, Florey Institute for Neuroscience and Mental Health and the Department of Psychiatry, The University of Melbourne, Melbourne, Australia
| |
Collapse
|
18
|
Guo X, Wang J, Wang X, Liu W, Yu H, Xu L, Li H, Wu J, Dong M, Tan W, Chen W, Yang Y, Chen Y. Diagnosing autism spectrum disorder in children using conventional MRI and apparent diffusion coefficient based deep learning algorithms. Eur Radiol 2021; 32:761-770. [PMID: 34482428 DOI: 10.1007/s00330-021-08239-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2021] [Revised: 07/19/2021] [Accepted: 08/02/2021] [Indexed: 10/20/2022]
Abstract
OBJECTIVE To develop and validate deep learning (DL) methods for diagnosing autism spectrum disorder (ASD) based on conventional MRI (cMRI) and apparent diffusion coefficient (ADC) images. METHODS A total of 151 ASD children and 151 age-matched typically developing (TD) controls were included in this study. The data from these subjects were assigned to training and validation datasets. An additional 20 ASD children and 25 TD controls were acquired, whose data were utilized in an independent test set. All subjects underwent cMRI and diffusion-weighted imaging examination of the brain. We developed a series of DL models to separate ASD from TD based on the cMRI and ADC data. The seven models used include five single-sequence models (SSMs), one dominant-sequence model (DSM), and one all-sequence model (ASM). To enhance the feature detection of the models, we embed an attention mechanism module. RESULTS The highest AUC (0.824 ~ 0.850) was achieved when applying the SSM based on either FLAIR or ADC to the validation and independent test sets. A DSM using the combination of FLAIR and ADC showed an improved AUC in the validation (0.873) and independent test sets (0.876). The ASM also showed better diagnostic value in the validation (AUC = 0.838) and independent test sets (AUC = 0.836) compared to the SSMs. Among the models with attention mechanism, the DSM achieved the highest diagnostic performance with an AUC, accuracy, sensitivity, and specificity of 0.898, 84.4%, 85.0%, and 84.0% respectively. CONCLUSIONS This study established the potential of DL models to distinguish ASD cases from TD controls based on cMRI and ADC images. KEY POINTS • Deep learning models based on conventional MRI and ADC can be used to diagnose ASD. • The model (DSM) based on the FLAIR and ADC sequence achieved the best diagnostic performance with an AUC of 0.836 in the independent test sets. • The attention mechanism further improved the diagnostic performance of the models.
Collapse
Affiliation(s)
- Xiang Guo
- Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China
| | - Jiehuan Wang
- Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China
| | - Xiaoqiang Wang
- Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China
| | - Wenjing Liu
- Children Rehabilitation Center, the Affiliated Hospital of Jining Medical University, Jining, China
| | - Hao Yu
- Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China
| | - Li Xu
- Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China
| | - Hengyan Li
- Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China
| | | | | | | | - Weijian Chen
- Department of Medical Imaging, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Yunjun Yang
- Department of Medical Imaging, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Yueqin Chen
- Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China.
| |
Collapse
|
19
|
Hashimoto Y, Ogata Y, Honda M, Yamashita Y. Deep Feature Extraction for Resting-State Functional MRI by Self-Supervised Learning and Application to Schizophrenia Diagnosis. Front Neurosci 2021; 15:696853. [PMID: 34512240 PMCID: PMC8429808 DOI: 10.3389/fnins.2021.696853] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2021] [Accepted: 07/20/2021] [Indexed: 01/21/2023] Open
Abstract
In this study, we propose a deep-learning technique for functional MRI analysis. We introduced a novel self-supervised learning scheme that is particularly useful for functional MRI wherein the subject identity is used as the teacher signal of a neural network. The neural network is trained solely based on functional MRI-scans, and the training does not require any explicit labels. The proposed method demonstrated that each temporal volume of resting state functional MRI contains enough information to identify the subject. The network learned a feature space in which the features were clustered per subject for the test data as well as for the training data; this is unlike the features extracted by conventional methods including region of interests (ROIs) pooling signals and principal component analysis. In addition, applying a simple linear classifier to the per-subject mean of the features (namely "identity feature"), we demonstrated that the extracted features could contribute to schizophrenia diagnosis. The classification accuracy of our identity features was comparable to that of the conventional functional connectivity. Our results suggested that our proposed training scheme of the neural network captured brain functioning related to the diagnosis of psychiatric disorders as well as the identity of the subject. Our results together highlight the validity of our proposed technique as a design for self-supervised learning.
Collapse
Affiliation(s)
- Yuki Hashimoto
- Department of Information Medicine, National Center of Neurology and Psychiatry, National Institute of Neuroscience, Kodaira, Japan
| | - Yousuke Ogata
- Institute of Innovative Research, Tokyo Institute of Technology, Yokohama, Japan
| | - Manabu Honda
- Department of Information Medicine, National Center of Neurology and Psychiatry, National Institute of Neuroscience, Kodaira, Japan
| | - Yuichi Yamashita
- Department of Information Medicine, National Center of Neurology and Psychiatry, National Institute of Neuroscience, Kodaira, Japan
| |
Collapse
|
20
|
Yamaguchi H, Hashimoto Y, Sugihara G, Miyata J, Murai T, Takahashi H, Honda M, Hishimoto A, Yamashita Y. Three-Dimensional Convolutional Autoencoder Extracts Features of Structural Brain Images With a "Diagnostic Label-Free" Approach: Application to Schizophrenia Datasets. Front Neurosci 2021; 15:652987. [PMID: 34305514 PMCID: PMC8294943 DOI: 10.3389/fnins.2021.652987] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2021] [Accepted: 06/07/2021] [Indexed: 01/17/2023] Open
Abstract
There has been increasing interest in performing psychiatric brain imaging studies using deep learning. However, most studies in this field disregard three-dimensional (3D) spatial information and targeted disease discrimination, without considering the genetic and clinical heterogeneity of psychiatric disorders. The purpose of this study was to investigate the efficacy of a 3D convolutional autoencoder (3D-CAE) for extracting features related to psychiatric disorders without diagnostic labels. The network was trained using a Kyoto University dataset including 82 patients with schizophrenia (SZ) and 90 healthy subjects (HS) and was evaluated using Center for Biomedical Research Excellence (COBRE) datasets, including 71 SZ patients and 71 HS. We created 16 3D-CAE models with different channels and convolutions to explore the effective range of hyperparameters for psychiatric brain imaging. The number of blocks containing two convolutional layers and one pooling layer was set, ranging from 1 block to 4 blocks. The number of channels in the extraction layer varied from 1, 4, 16, and 32 channels. The proposed 3D-CAEs were successfully reproduced into 3D structural magnetic resonance imaging (MRI) scans with sufficiently low errors. In addition, the features extracted using 3D-CAE retained the relation to clinical information. We explored the appropriate hyperparameter range of 3D-CAE, and it was suggested that a model with 3 blocks may be related to extracting features for predicting the dose of medication and symptom severity in schizophrenia.
Collapse
Affiliation(s)
- Hiroyuki Yamaguchi
- Department of Information Medicine, National Center of Neurology and Psychiatry, National Institute of Neuroscience, Tokyo, Japan.,Department of Psychiatry, School of Medicine, Yokohama City University, Yokohama, Japan
| | - Yuki Hashimoto
- Department of Information Medicine, National Center of Neurology and Psychiatry, National Institute of Neuroscience, Tokyo, Japan
| | - Genichi Sugihara
- Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
| | - Jun Miyata
- Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Toshiya Murai
- Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Hidehiko Takahashi
- Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
| | - Manabu Honda
- Department of Information Medicine, National Center of Neurology and Psychiatry, National Institute of Neuroscience, Tokyo, Japan
| | - Akitoyo Hishimoto
- Department of Psychiatry, School of Medicine, Yokohama City University, Yokohama, Japan
| | - Yuichi Yamashita
- Department of Information Medicine, National Center of Neurology and Psychiatry, National Institute of Neuroscience, Tokyo, Japan
| |
Collapse
|
21
|
Xu M, Calhoun V, Jiang R, Yan W, Sui J. Brain imaging-based machine learning in autism spectrum disorder: methods and applications. J Neurosci Methods 2021; 361:109271. [PMID: 34174282 DOI: 10.1016/j.jneumeth.2021.109271] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2021] [Revised: 05/25/2021] [Accepted: 06/19/2021] [Indexed: 01/09/2023]
Abstract
Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.
Collapse
Affiliation(s)
- Ming Xu
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China 100190; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 100049
| | - Vince Calhoun
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, GA, USA 30303
| | - Rongtao Jiang
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China 100190
| | - Weizheng Yan
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, GA, USA 30303
| | - Jing Sui
- State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China 100088.
| |
Collapse
|
22
|
Estimating Gender and Age from Brain Structural MRI of Children and Adolescents: A 3D Convolutional Neural Network Multitask Learning Model. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2021; 2021:5550914. [PMID: 34122531 PMCID: PMC8172319 DOI: 10.1155/2021/5550914] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Revised: 04/01/2021] [Accepted: 04/24/2021] [Indexed: 01/10/2023]
Abstract
Despite recent advances, assessing biological measurements for neuropsychiatric disorders is still a challenge, where confounding variables such as gender and age (as a proxy for neurodevelopment) play an important role. This study explores brain structural magnetic resonance imaging (sMRI) from two public data sets (ABIDE-II and ADHD-200) with healthy control (HC, N = 894), autism spectrum disorder (ASD, N = 251), and attention deficit hyperactivity disorder (ADHD, N = 357) individuals. We used gray and white matter preprocessed via voxel-based morphometry (VBM) to train a 3D convolutional neural network with a multitask learning strategy to estimate gender, age, and mental health status from structural brain differences. Gradient-based methods were employed to generate attention maps, providing clinically relevant identification of most representative brain regions for models' decision-making. This approach resulted in satisfactory predictions for gender and age. ADHD-200-trained models, evaluated in 10-fold cross-validation procedures on test set, obtained a mean absolute error (MAE) of 1.43 years (±0.22 SD) for age prediction and an area under the curve (AUC) of 0.85 (±0.04 SD) for gender classification. In out-of-sample validation, the best-performing ADHD-200 models satisfactorily predicted age (MAE = 1.57 years) and gender (AUC = 0.89) in the ABIDE-II data set. The models' accuracy was in line with the current state-of-the-art machine learning applications in neuroimaging. Key regions for models' accuracy were presented as a meaningful graphical output. New implementations, such as the use of VBM along with a 3D convolutional neural network multitask learning model and a brain imaging graphical output, reinforce the relevance of the proposed workflow.
Collapse
|
23
|
Quaak M, van de Mortel L, Thomas RM, van Wingen G. Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis. Neuroimage Clin 2021; 30:102584. [PMID: 33677240 PMCID: PMC8209481 DOI: 10.1016/j.nicl.2021.102584] [Citation(s) in RCA: 31] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2020] [Revised: 01/18/2021] [Accepted: 01/29/2021] [Indexed: 12/20/2022]
Abstract
Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n = 22), schizophrenia (SZ; n = 22) and attention-deficit/hyperactivity disorder (ADHD; n = 9). Thirty-two of the thirty-five studies that directly compared DL to SML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and SML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. Our results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. However, it is not yet used to its full potential: most studies use pre-engineered features, whereas one of the main advantages of DL is its ability to learn representations of minimally processed data. Our current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets. To truly uncover the added value of DL, we need carefully designed comparisons of SML and DL models which are yet rarely performed.
Collapse
Affiliation(s)
- Mirjam Quaak
- Amsterdam UMC, University of Amsterdam, Department of Psychiatry, Meibergdreef 5, 1105 AZ Amsterdam, The Netherlands
| | - Laurens van de Mortel
- Amsterdam UMC, University of Amsterdam, Department of Psychiatry, Meibergdreef 5, 1105 AZ Amsterdam, The Netherlands
| | - Rajat Mani Thomas
- Amsterdam UMC, University of Amsterdam, Department of Psychiatry, Meibergdreef 5, 1105 AZ Amsterdam, The Netherlands
| | - Guido van Wingen
- Amsterdam UMC, University of Amsterdam, Department of Psychiatry, Meibergdreef 5, 1105 AZ Amsterdam, The Netherlands.
| |
Collapse
|
24
|
Pandey B, Kumar Pandey D, Pratap Mishra B, Rhmann W. A comprehensive survey of deep learning in the field of medical imaging and medical natural language processing: Challenges and research directions. JOURNAL OF KING SAUD UNIVERSITY - COMPUTER AND INFORMATION SCIENCES 2021. [DOI: 10.1016/j.jksuci.2021.01.007] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
25
|
Song JW, Yoon NR, Jang SM, Lee GY, Kim BN. Neuroimaging-Based Deep Learning in Autism Spectrum Disorder and Attention-Deficit/Hyperactivity Disorder. Soa Chongsonyon Chongsin Uihak 2020; 31:97-104. [PMID: 32665754 PMCID: PMC7350542 DOI: 10.5765/jkacap.200021] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Revised: 06/08/2020] [Accepted: 06/11/2020] [Indexed: 12/22/2022] Open
Abstract
Deep learning (DL) is a kind of machine learning technique that uses artificial intelligence to identify the characteristics of given data and efficiently analyze large amounts of information to perform tasks such as classification and prediction. In the field of neuroimaging of neurodevelopmental disorders, various biomarkers for diagnosis, classification, prognosis prediction, and treatment response prediction have been examined; however, they have not been efficiently combined to produce meaningful results. DL can be applied to overcome these limitations and produce clinically helpful results. Here, we review studies that combine neurodevelopmental disorder neuroimaging and DL techniques to explore the strengths, limitations, and future directions of this research area.
Collapse
Affiliation(s)
- Jae-Won Song
- Department of Child and Adolescent Psychiatry, Seoul National University Hospital, Seoul, Korea
| | - Na-Rae Yoon
- Department of Child and Adolescent Psychiatry, Seoul National University Hospital, Seoul, Korea
| | - Soo-Min Jang
- Department of Child and Adolescent Psychiatry, Seoul National University Hospital, Seoul, Korea
| | - Ga-Young Lee
- Seoul National University Hospital, Autism and Developmental Disorder Center, Seoul, Korea
| | - Bung-Nyun Kim
- Department of Child and Adolescent Psychiatry, Seoul National University Hospital, Seoul, Korea
| |
Collapse
|