Clinical neuroimaging markers of response to treatment in mood disorders

Association of BDNF risk variant and dorsolateral cortical thickness with long-term treatment response to valproate in type I bipolar disorder: An exploratory study

Valproate is among the most prescribed drugs for bipolar disorder; however, 87% of patients do not report full long-term treatment response (LTTR) to this medication. One of valproate's suggested mechanisms of action involves the brain-derived neurotrophic factor (BDNF), expressed in the brain areas regulating emotions, such as the prefrontal cortex. Nonetheless, data about the role of BDNF in LTTR and its implications in the structure of the dorsolateral prefrontal cortex (dlPFC) is scarce. We explore the association of BDNF variants and dorsolateral cortical thickness (CT) with LTTR to valproate in bipolar disorder type I (BDI). Twenty-eight BDI patients were genotyped for BDNF polymorphisms rs1519480, rs6265, and rs7124442, and T1-weighted 3D brain scans were acquired. LTTR to valproate was evaluated with Alda's scale. A logistic regression analysis was conducted to evaluate LTTR according to BDNF genotypes and CT. We evaluated CT differences by genotypes with analysis of covariance. LTTR was associated with BDNF rs1519480 and right dlPFC thickness. Insufficient responders with the CC genotype had thicker right dlPFC than TC and TT genotypes. Full responders reported thicker right dlPFC in TC and TT genotypes. In conclusion, different patterns of CT related to BDNF genotypes were identified, suggesting a potential biomarker of LTTR to valproate in our population.

Molecular imaging findings for treatment resistant depression

Approximately 40% of patients with major depressive disorder (MDD) had limited response to conventional antidepressant treatments, resulting in treatment-resistant depression (TRD), a debilitating subtype that yielded a significant disease burden worldwide. Molecular imaging techniques, such as positron emission tomography (PET) and single photon emission tomography (SPECT), can measure targeted macromolecules or biological processes in vivo. These imaging tools provide a unique possibility to explore the pathophysiology and treatment mechanisms underlying TRD. This work reviewed and summarized prior PET and SPECT studies to examine the neurobiology and treatment-induced changes of TRD. A total of 51 articles were included with supplementary information from studies for MDD and healthy controls (HC). We found that there were altered regional blood flow or metabolic activity in several brain regions, such as the anterior cingulate cortex, prefrontal cortex, insula, hippocampus, amygdala, parahippocampus, and striatum. These regions have been suggested to engage in the pathophysiology or treatment resistance of depression. There was also limited data to demonstrate the changes in the markers of serotonin, dopamine, amyloid, and microglia over some regions in TRD. Moreover, several observed abnormal imaging indices were linked to treatment outcomes, supporting their specificity and clinical relevance. To address the limitations of the included studies, we proposed that future studies needed longitudinal designs, multimodal approaches, and radioligands targeting specific neural substrates for TRD to evaluate their baseline and treatment-related alterations in TRD. Adequate data sharing and reproducible data analysis can facilitate advances in this field.

Wilson disease tissue classification and characterization using seven artificial intelligence models embedded with 3D optimization paradigm on a weak training brain magnetic resonance imaging datasets: a supercomputer application

Wilson's disease (WD) is caused by copper accumulation in the brain and liver, and if not treated early, can lead to severe disability and death. WD has shown white matter hyperintensity (WMH) in the brain magnetic resonance scans (MRI) scans, but the diagnosis is challenging due to (i) subtle intensity changes and (ii) weak training MRI when using artificial intelligence (AI). Design and validate seven types of high-performing AI-based computer-aided design (CADx) systems consisting of 3D optimized classification, and characterization of WD against controls. We propose a "conventional deep convolution neural network" (cDCNN) and an "improved DCNN" (iDCNN) where rectified linear unit (ReLU) activation function was modified ensuring "differentiable at zero." Three-dimensional optimization was achieved by recording accuracy while changing the CNN layers and augmentation by several folds. WD was characterized using (i) CNN-based feature map strength and (ii) Bispectrum strengths of pixels having higher probabilities of WD. We further computed the (a) area under the curve (AUC), (b) diagnostic odds ratio (DOR), (c) reliability, and (d) stability and (e) benchmarking. Optimal results were achieved using 9 layers of CNN, with 4-fold augmentation. iDCNN yields superior performance compared to cDCNN with accuracy and AUC of 98.28 ± 1.55, 0.99 (p < 0.0001), and 97.19 ± 2.53%, 0.984 (p < 0.0001), respectively. DOR of iDCNN outperformed cDCNN fourfold. iDCNN also outperformed (a) transfer learning-based "Inception V3" paradigm by 11.92% and (b) four types of "conventional machine learning-based systems": k-NN, decision tree, support vector machine, and random forest by 55.13%, 28.36%, 15.35%, and 14.11%, respectively. The AI-based systems can potentially be useful in the early WD diagnosis. Graphical Abstract.

Imaging-Based Subtyping for Psychiatric Syndromes

Despite considerable research evidence demonstrating significant neurobiological alterations in psychiatric disorders, incorporating neuroimaging approaches into clinical practice remains challenging. There is an urgent need for biologically validated psychiatric disease constructs that can inform diagnostic algorithms and targeted treatment development. In this article, we present a conceptual review of the most robust and impactful findings from studies that use neuroimaging methods in efforts to define distinct disease subtypes, while emphasizing cross-diagnostic and dimensional approaches. In addition, we discuss current challenges in psychoradiology and outline potential future strategies for clinically applicable translation.