Pulmonary hypertension (PH) is a fatal pulmonary vascular disease. The standard diagnosis of PH heavily relies on an invasive technique, i.e., right heart catheterization, which leads to a delay in diagnosis and serious consequences. Noninvasive approaches are crucial for detecting PH as early as possible; however, it remains a challenge, especially in detecting mild PH patients. To address this issue, we present a new fully automated framework, hereinafter referred to as PHNet, for noninvasively detecting PH patients, especially improving the detection accuracy of mild PH patients, based on cine cardiac magnetic resonance (CMR) images. The PHNet framework employs a hybrid strategy of adaptive triplet and binary cross-entropy losses (HSATBCL) to enhance discriminative feature learning for classifying PH and non-PH. Triplet pairs in HSATBCL are created using a semi-hard negative mining strategy which maintains the stability of the training process. Experiments show that the detection error rate of PHNet for mild PH is reduced by 24.5% on average compared to state-of-the-art PH detection models. The hybrid strategy can effectively improve the model's ability to detect PH, making PHNet achieve an average area under the curve (AUC) of 0.964, an accuracy of 0.912, and an F1-score of 0.884 in the internal validation dataset. In the external testing dataset, PHNet achieves an average AUC value of 0.828. Thus, PHNet has great potential for noninvasively detecting PH based on cine CMR images in clinical practice. Future research could explore more clinical information and refine feature extraction to further enhance the network performance.

Graph Neural Networks (GNNs) play a pivotal role in learning representations of brain networks for estimating brain age. However, the over-squashing impedes interactions between long-range nodes, hindering the ability of message-passing mechanism-based GNNs to learn the topological structure of brain networks. Graph rewiring methods and curvature GNNs have been proposed to alleviate over-squashing. However, most graph rewiring methods overlook node features and curvature GNNs neglect the geometric properties of signed curvature. In this study, a Signed Curvature GNN (SCGNN) was proposed to rewire the graph based on node features and curvature, and learn the representation of signed curvature. First, a Mutual Information Ollivier-Ricci Flow (MORF) was proposed to add connections in the neighborhood of edge with the minimal negative curvature based on the maximum mutual information between node features, improving the efficiency of information interaction between nodes. Then, a Signed Curvature Convolution (SCC) was proposed to aggregate node features based on positive and negative curvature, facilitating the model's ability to capture the complex topological structures of brain networks. Additionally, an Ollivier-Ricci Gradient Pooling (ORG-Pooling) was proposed to select the key nodes and topology structures by curvature gradient and attention mechanism, accurately obtaining the global representation for brain age estimation. Experiments conducted on six public datasets with structural magnetic resonance imaging (sMRI), spanning ages from 18 to 91 years, validate that our method achieves promising performance compared with existing methods. Furthermore, we employed the gaps between brain age and chronological age for identifying Alzheimer's Disease (AD), yielding the best classification performance.

To quantitatively determining the temporal ordering of abnormal age onsets (AAO) among various biomarkers for Alzheimer's disease (AD), we introduced a computational Monte-Carlo simulation (CMCS) to statistically examine such ordering of an AAO pair or over all AAOs. The CMCS 1) simulates longitudinal data, estimates AAO for each iteration, and finally assesses the type-I error of an AAO pair or all AAO ordering. Using hippocampus volume (VHC), cerebral glucose hypometabolic convergence index (HCI), plasma neurofilament light (NfL), mini-mental state exam (MMSE), the auditory verbal learning test-long term memory (AVLT-LTM), short term memory (AVLT-STM) and clinical-dementia rating sum of box scale (CDR-SOB) from 382 mild cognitive impairment converters and non-converters, the CMCS estimated type-I error for the earlier AAO of VHC, AVLT_STM and AVLT_LTM each than MMSE was significant (pHC≤ AVLT_STM ≤ AVLT_LTM < HCI ≤ MMSE ≤ CDR-SOB ≤ NfL was p = 0.012. These findings showed that our CMCS is capable of providing statistical inferences for quantifying AAO ordering which has important implications in advancing our understanding of AD.

With the development of deep learning in medical image analysis, decoding brain states from functional magnetic resonance imaging (fMRI) signals has made significant progress. Previous studies often utilized deep neural networks to automatically classify brain activity patterns related to diverse cognitive states. However, due to the individual differences between subjects and the variation in acquisition parameters across devices, the inconsistency in data distributions degrades the performance of cross-subject decoding. Besides, most current networks were trained in a supervised way, which is not suitable for the actual scenarios in which massive amounts of data are unlabeled. To address these problems, we proposed the deep cross-subject adaptation decoding (DCAD) framework to decipher the brain states. The proposed volume-based 3D feature extraction architecture can automatically learn the common spatiotemporal features of labeled source data to generate a distinct descriptor. Then, the distance between the source and target distributions is minimized via an unsupervised domain adaptation (UDA) method, which can help to accurately decode the cognitive states across subjects. The performance of the DCAD was evaluated on task-fMRI (tfMRI) dataset from the Human Connectome Project (HCP). Experimental results showed that the proposed method achieved the state-of-the-art decoding performance with mean 81.9% and 84.9% accuracies under two conditions (4 brain states and 9 brain states respectively) of working memory task. Our findings also demonstrated that UDA can mitigate the impact of the data distribution shift, thereby providing a superior choice for increasing the performance of cross-subject decoding without depending on annotations.