Search

Quality assessment (QA) of magnetic resonance imaging (MRI) encompasses several factors such as noise, contrast, homogeneity, and imaging artifacts. Quality evaluation is often not standardized and relies on the expertise, and vigilance of the personnel, posing limitations especially with large datasets. Machine learning based on convolutional neural networks (CNNs) is a promising approach to address these challenges by performing automated inspection of MR images. In this study, a CNN for the detection of random head motion artifacts (RHM) in T1-weighted MRI as one aspect of image quality is proposed. A two-step approach aimed to first identify images exhibiting pronounced motion artifacts, and second to evaluate the feasibility of a more detailed three-class classification. The utilized dataset consisted of 420 T1-weighted whole-brain image volumes with isotropic resolution. Human experts assigned each volume to one of three classes of artifact prominence. Results demonstrate an accuracy of 95% for the identification of images with pronounced artifact load. The addition of an intermediate class retained an accuracy of 76%. The findings highlight the potential of CNN-based approaches to increase the efficiency of post-hoc QAs in large datasets by flagging images with potentially relevant artifact loads for closer inspection. [ABSTRACT FROM AUTHOR]

The mismatch negativity is a cortical response to auditory changes and its reduction is a consistent finding in schizophrenia. Recent evidence revealed that the human brain detects auditory changes already at subcortical stages of the auditory pathway. This finding, however, raises the question where in the auditory hierarchy the schizophrenic deficit first evolves and whether the well-known cortical deficit may be a consequence of dysfunction at lower hierarchical levels. Finally, it should be resolved whether mismatch profiles differ between schizophrenia and affective disorders which exhibit auditory processing deficits as well. We used functional magnetic resonance imaging to assess auditory mismatch processing in 29 patients with schizophrenia, 27 patients with major depression, and 31 healthy control subjects. Analysis included whole-brain activation, region of interest, path and connectivity analysis. In schizophrenia, mismatch deficits emerged at all stages of the auditory pathway including the inferior colliculus, thalamus, auditory, and prefrontal cortex. In depression, deficits were observed in the prefrontal cortex only. Path analysis revealed that activation deficits propagated from subcortical to cortical nodes in a feed-forward mechanism. Finally, both patient groups exhibited reduced connectivity along this processing stream. Auditory mismatch impairments in schizophrenia already manifest at the subcortical level. Moreover, subcortical deficits contribute to the well-known cortical deficits and show specificity for schizophrenia. In contrast, depression is associated with cortical dysfunction only. Hence, schizophrenia and major depression exhibit different neural profiles of sensory processing deficits. Our findings add to a converging body of evidence for brainstem and thalamic dysfunction as a hallmark of schizophrenia. [ABSTRACT FROM AUTHOR]