A-GCL: Adversarial graph contrastive learning for fMRI analysis to diagnose neurodevelopmental disorders.

Accurate diagnosis of neurodevelopmental disorders is a challenging task due to the time-consuming cognitive tests and potential human bias in clinics. To address this challenge, we propose a novel adversarial self-supervised graph neural network (GNN) based on graph contrastive learning, named A-GCL, for diagnosing neurodevelopmental disorders using functional magnetic resonance imaging (fMRI) data. Taking advantage of the success of GNNs in psychiatric disease diagnosis using fMRI, our proposed A-GCL model is expected to improve the performance of diagnosis and provide more robust results. A-GCL takes graphs constructed from the fMRI images as input and uses contrastive learning to extract features for classification. The graphs are constructed with 3 bands of the amplitude of low-frequency fluctuation (ALFF) as node features and Pearson's correlation coefficients (PCC) of the average fMRI time series in different brain regions as edge weights. The contrastive learning creates an edge-dropped graph from a trainable Bernoulli mask to extract features that are invariant to small variations of the graph. Experiment results on three datasets - Autism Brain Imaging Data Exchange (ABIDE) I, ABIDE II, and attention deficit hyperactivity disorder (ADHD) - with 3 atlases - AAL1, AAL3, Shen268 - demonstrate the superiority and generalizability of A-GCL compared to the other GNN-based models. Extensive ablation studies verify the robustness of the proposed approach to atlas selection and model variation. Explanatory results reveal key functional connections and brain regions associated with neurodevelopmental disorders.

TW-Net: Transformer Weighted Network for Neonatal Brain MRI Segmentation.

Accurate neonatal brain MRI segmentation is valuable for investigating brain growth patterns and tracking the progression of neurodevelopmental disorders. However, it is a challenging task to use intensity-based methods to segment neonatal brain structures because of small contrast differences between brain regions caused by the inherent myelination process. Although convolutional neural networks offer the potential to segment brain structures in an intensity-independent manner, they suffer from lack of in-plane long-range dependency which is essential for the segmentation. To solve this problem, we propose a novel Transformer-Weighted network (TW-Net) to incorporate in-plane long-range dependency information. TW-Net employs a conventional encoder-decoder architecture with a Transformer module in the middle. The Transformer module uses a rotate-and-flip layer to better calculate the similarity between two patches in a slice to leverage similar patterns of geometrical and texture features within brain structures. In addition, a deep supervision module and squeeze-and-excitation blocks are introduced to incorporate boundary information of brain structures. Compared with state-of-the-art deep learning algorithms, TW-Net outperforms these methods for multiple-label tasks in 2D and 2.5D configurations on two independent public datasets, demonstrating that TW-Net is a promising method for neonatal brain MRI segmentation.

TRIM65 determines the fate of a novel subtype of pituitary neuroendocrine tumors via ubiquitination and degradation of TPIT.

BACKGROUND: Pituitary neuroendocrine tumors (PitNETs) are common intracranial tumors that are classified into seven histological subtypes, including lactotroph, somatotroph, corticotroph, thyrotroph, gonadotroph, null cell, and plurihormonal PitNETs. However, the molecular characteristics of these types of PitNETs are not completely clear. METHODS: A total of 180 consecutive cases of PitNETs were collected to perform RNA sequencing. All subtypes of PitNETs were distinguished by unsupervised clustering analysis. We investigated the regulation of TPIT by TRIM65 and its effects on ACTH production and secretion in ACTH-secreting pituitary cell lines, as well as in murine models using biochemical analyses, confocal microscopy, and luciferase reporter assays. RESULTS: A novel subtype of PitNETs derived from TPIT lineage cells was identified as with normal TPIT transcription but with lowered protein expression. Furthermore, for the first time, TRIM65 was identified as the E3 ubiquitin ligase of TPIT. Depending on the RING domain, TRIM65 ubiquitinated and degraded the TPIT protein at multiple Lys sites. In addition, TRIM65-mediated ubiquitination of TPIT inhibited POMC transcription and ACTH production to determine the fate of the novel subtype of PitNETs in vitro and in vivo. CONCLUSION: Our studies provided a novel classification of PitNETs and revealed that the TRIM65-TPIT complex controlled the fate of the novel subtype of PitNETs, which provides a potential therapy target for Cushing's disease.

The long noncoding RNA-H19/miRNA-93a/ATG7 axis regulates the sensitivity of pituitary adenomas to dopamine agonists.

Dopamine agonists (DAs), such as cabergoline and bromocriptine, are the first-line clinical treatment for prolactinomas. Our previous study demonstrated that long noncoding RNA H19 expression is frequently downregulated in human primary pituitary adenomas and is negatively correlated with tumor progression. However, the significance and mechanism of H19 in the DA treatment of prolactinomas are still unknown. In this study, we reported that H19 had a synergistic effect with DA treatment on prolactinomas in vitro and in vivo. Mechanistically, H19 promoted ATG7 expression in pituitary tumor cells by inhibiting miR-93a expression. In addition, a potential binding site between miR-93 and H19 was confirmed, and low expression of miR-93 was previously found in DA-resistant prolactinomas. Furthermore, we showed that miR-93a regulates ATG7 expression by targeting ATG7 mRNA. In conclusion, our study has identified the role of the H19-miR-93-ATG7 axis in DA treatment of prolactinomas, which may be a potential therapeutic target for human prolactinomas.