Advancing diagnostic performance and clinical applicability of deep learning-driven generative adversarial networks for Alzheimer’s disease

Alzheimer’s disease(AD)is a neurodegenerative disease that severely affects the activities of daily living in aged individuals,which typically needs to be diagnosed at an early stage.Generative adversarial networks(GANs)provide a new deep learning method that show good performance in image processing,while it remains to be verified whether a GAN brings benefit in AD diagnosis.The purpose of this research is to systematically review psychoradiological studies on the application of a GAN in the diagnosis of AD from the aspects of classification of AD state and AD-related image processing compared with other methods.In addition,we evaluated the research methodology and provided suggestions from the perspective of clinical application.Compared with othermethods,a GAN has higher accuracy in the classification of AD state and better performance in AD-related image processing(e.g.image denoising and segmentation).Most studies used data from public databases but lacked clinical validation,and the process of quantitative assessment and comparison in these studies lacked clinicians’participation,which may have an impact on the improvement of generation effect and generalization ability of the GAN model.The application value of GANs in the classification of AD state and AD-related image processing has been confirmed in reviewed studies.Improvement methods toward better GAN architecture were also discussed in this paper.In sum,the present study demonstrated advancing diagnostic performance and clinical applicability of GAN for AD,and suggested that the future researchers should consider recruiting clinicians to compare the algorithm with clinician manual methods and evaluate the clinical effect of the algorithm.

Altered cortical morphology in major depression disorder patients with suicidality

Background:Major depressive disorder(MDD)is associated with high risk of suicide,but the biological under-pinnings of suicidality in MDD patients are far from conclusive.Previous neuroimaging studies using voxel-based morphometry(VBM)demonstrated that depressed individuals with suicidal thoughts or behaviors exhibit specific cortical structure alterations.To complement VBM findings,surface-based morphometry(SBM)can pro-vide more details into gray matter structure,including the cortical complexity,cortical thickness and sulcal depth for brain images.Objective:This study aims to use SBM to investigate cortical morphology alterations to obtain evidence for neuroanatomical alterations in depressed patients with suicidality.Methods:Here,3D T1-weighted MR images of brain from 39 healthy controls,40 depressed patients without suicidality(patient controls),and 39 with suicidality(suicidal groups)were analyzed based on SBM to estimate the fractal dimension,gyrification index,sulcal depth,and cortical thickness using the Computational Anatomy Toolbox.Correlation analyses were performed between clinical data and cortical surface measurements from patients.Results:Surface-based morphometry showed decreased sulcal depth in the parietal,frontal,limbic,occipital and temporal regions and decreased fractal dimension in the frontal regions in depressed patients with sui-cidality compared to both healthy and patient controls.Additionally,in patients with depression,the sulcal depth of the left caudal anterior cingulate cortex was negatively correlated with Hamilton Depression Rating Scale scores.Conclusions:Depressed patients with suicidality had abnormal cortical morphology in some brain regions within the default mode network,frontolimbic circuitry and temporal regions.These structural deficits may be associated with the dysfunction of emotional processing and impulsivity control.This study provides insights into the underlying neurobiology of the suicidal brain.