Autism classified by magnetic resonance imaging: A pilot study of a potential diagnostic tool

Sarovic, Darko; Hadjikhani, Nouchine; Schneiderman, Justin F.; Lundström, Staffan; Gillberg, Christopher

doi:10.1002/mpr.1846

Cited by 10 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Approximately half of the models (258 of 555 [46.48%; 95% CI, 42.3%- 50.6%]) were assessed for poor reporting quality in the technique domain across 3 signaling questions. 25 , 28 , 29 , 33 , 34 , 35 , 44 , 45 , 47 , 48 , 49 , 51 , 53 , 54 , 56 , 59 , 60 , 62 , 66 , 73 , 75 , 78 , 79 , 81 , 83 , 84 , 95 , 99 , 100 , 107 , 114 , 117 , 122 , 124 , 126 , 128 , 129 , 130 , 131 , 133 , 135 , 137 , 142 , 144 , 145 , 146 , 147 , 148 , 151 , 153 , 155 , 159 , 161 , 163 , 165 , 166 , 167 , 169 , …”

Section: Resultsmentioning

confidence: 99%

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

et al. 2023

View full text Add to dashboard Cite

ImportanceNeuroimaging-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.ObjectiveTo systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.Evidence ReviewPubMed 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.FindingsA 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 RelevanceThis 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.

show abstract

Section: Resultsmentioning

confidence: 99%

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Other studies reported both increase and decrease in CT in different brain regions [12,24,32,38,40,41] in ASD subjects. Cortical development trajectories in ASD subjects report an early hyperplasia in the first years of life [9,10], followed by nearly normalization in successive stages [24]; this confirms the hypothesis of early brain overgrowth, followed by volume plateau and decline, could be considered a biologic hallmark of this disease.…”

Section: Discussionmentioning

confidence: 92%

Brain volumetric and white matter structural connectivity alterations in autistic children: case–control study

Shehata

Ibrahim

El-Kammash

et al. 2023

Egypt J Radiol Nucl Med

View full text Add to dashboard Cite

Background Autism spectrum disorder (ASD) is a neurodevelopmental disorder that includes a large heterogeneous constellation of disorders with overlapping symptoms and clinical features. The diagnosis is based mainly on clinical symptoms meeting DSM-5 criteria with no radiologic or laboratory diagnostic investigations available yet. The specific neuropathologic aberrations occurring in ASD are still under investigation. This study aimed at providing a preliminary database for better understanding of the neuropathologic aspects of ASD, regarding both macrostructure and microstructure of the brain using magnetic resonance imaging. This case–control study included total of 40 children, 20 cases (diagnosed with ASD) and 20 control (Typically Developing Children, TDC) aged 2–18 years. 3D-T1 and Diffusion Tensor Images (DTI) were acquired. 3D-T1 images were uploaded to Volbrain and brain segmentation was done using Volbrain 2.0 pipeline. DTI data were analyzed using FSL where Tract-Based Spatial Statistics analysis was carried out and mean fractional anisotropy values obtained. Independent samples t test was used to compare means of both groups. Results ASD group displayed statistically significant larger intracranial cavity, brain, white matter, grey matter and cerebrospinal fluid volumes (p < 0.001 for all except CSF volume p = 0.01) with the white matter occupying higher percentage of intracranial volume in ASD compared to TDC group (p < 0.001). The cortical thickness showed statistically significant larger volume in entorhinal cortex in ASD group compared to TDC group at both sides (p < 0.001 at right side, p = 0.003 at left side). Widespread statistically significant (p < 0.001) higher mean FA value was observed at multiple white matter tracts. Conclusion These findings suggest that the main pathology of ASD is within the white matter. It also supports the hypothesis that autistic brain undergoes period of precocious growth in early years of life. Further studies with age and clinical severity stratification are needed to investigate temporal changes and severity related macrostructure and microstructure changes in autistic brains.

show abstract

“…Superior Temporal Gyrus is found to be possess a greater gray matter volume in ASD subjects who show drive to assess or construct rule-based systems [ 83 ], a diminished functional connectivity between cerebellum in ASD subjects of ABIDE I dataset [ 84 ], other functional connectivity differences, occurred in superior temporal gyrus, between ASD and TD subjects in three age cohorts <12, 12–19, and >20 years old [ 85 ], more different morphological alterations have been reported for superior temporal gyrus in different studies [ 79 , 86 , 87 , 88 ]. Banks of Superior Temporal Sulcus are found to demonstrate less developmental trajectory of the surface area [ 89 ], and an increased thickness of the right Banks of Superior Temporal Sulcus [ 90 ].…”

Section: Discussionmentioning

confidence: 99%

“…Banks of Superior Temporal Sulcus was found to demonstrate less developmental trajectory of the surface area [ 89 ] and an increased thickness of the right Banks of Superior Temporal Sulcus [ 90 ].…”

Section: Discussionmentioning

confidence: 99%

The Role of Structure MRI in Diagnosing Autism

et al. 2022

View full text Add to dashboard Cite

This study proposes a Computer-Aided Diagnostic (CAD) system to diagnose subjects with autism spectrum disorder (ASD). The CAD system identifies morphological anomalies within the brain regions of ASD subjects. Cortical features are scored according to their contribution in diagnosing a subject to be ASD or typically developed (TD) based on a trained machine-learning (ML) model. This approach opens the hope for developing a new CAD system for early personalized diagnosis of ASD. We propose a framework to extract the cerebral cortex from structural MRI as well as identifying the altered areas in the cerebral cortex. This framework consists of the following five main steps: (i) extraction of cerebral cortex from structural MRI; (ii) cortical parcellation to a standard atlas; (iii) identifying ASD associated cortical markers; (iv) adjusting feature values according to sex and age; (v) building tailored neuro-atlases to identify ASD; and (vi) artificial neural networks (NN) are trained to classify ASD. The system is tested on the Autism Brain Imaging Data Exchange (ABIDE I) sites achieving an average balanced accuracy score of 97±2%. This paper demonstrates the ability to develop an objective CAD system using structure MRI and tailored neuro-atlases describing specific developmental patterns of the brain in autism.

show abstract

Autism classified by magnetic resonance imaging: A pilot study of a potential diagnostic tool

Cited by 10 publications

References 54 publications

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

Brain volumetric and white matter structural connectivity alterations in autistic children: case–control study

The Role of Structure MRI in Diagnosing Autism

Contact Info

Product

Resources

About