Triplet-constrained deep hashing for chest X-ray image retrieval in COVID-19 assessment.

Radiology images of the chest, such as computer tomography scans and X-rays, have been prominently used in computer-aided COVID-19 analysis. Learning-based radiology image retrieval has attracted increasing attention recently, which generally involves image feature extraction and finding matches in extensive image databases based on query images. Many deep hashing methods have been developed for chest radiology image search due to the high efficiency of retrieval using hash codes. However, they often overlook the complex triple associations between images; that is, images belonging to the same category tend to share similar characteristics and vice versa. To this end, we develop a triplet-constrained deep hashing (TCDH) framework for chest radiology image retrieval to facilitate automated analysis of COVID-19. The TCDH consists of two phases, including (a) feature extraction and (b) image retrieval. For feature extraction, we have introduced a triplet constraint and an image reconstruction task to enhance discriminative ability of learned features, and these features are then converted into binary hash codes to capture semantic information. Specifically, the triplet constraint is designed to pull closer samples within the same category and push apart samples from different categories. Additionally, an auxiliary image reconstruction task is employed during feature extraction to help effectively capture anatomical structures of images. For image retrieval, we utilize learned hash codes to conduct searches for medical images. Extensive experiments on 30,386 chest X-ray images demonstrate the superiority of the proposed method over several state-of-the-art approaches in automated image search. The code is now available online.

Multi-Scale Dynamic Graph Learning for Brain Disorder Detection With Functional MRI.

Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used in the detection of brain disorders such as autism spectrum disorder based on various machine/deep learning techniques. Learning-based methods typically rely on functional connectivity networks (FCNs) derived from blood-oxygen-level-dependent time series of rs-fMRI data to capture interactions between brain regions-of-interest (ROIs). Graph neural networks have been recently used to extract fMRI features from graph-structured FCNs, but cannot effectively characterize spatiotemporal dynamics of FCNs, e.g., the functional connectivity of brain ROIs is dynamically changing in a short period of time. Also, many studies usually focus on single-scale topology of FCN, thereby ignoring the potential complementary topological information of FCN at different spatial resolutions. To this end, in this paper, we propose a multi-scale dynamic graph learning (MDGL) framework to capture multi-scale spatiotemporal dynamic representations of rs-fMRI data for automated brain disorder diagnosis. The MDGL framework consists of three major components: 1) multi-scale dynamic FCN construction using multiple brain atlases to model multi-scale topological information, 2) multi-scale dynamic graph representation learning to capture spatiotemporal information conveyed in fMRI data, and 3) multi-scale feature fusion and classification. Experimental results on two datasets show that MDGL outperforms several state-of-the-art methods.

Learning to Fuse Multiple Brain Functional Networks for Automated Autism Identification.

Functional connectivity network (FCN) has become a popular tool to identify potential biomarkers for brain dysfunction, such as autism spectrum disorder (ASD). Due to its importance, researchers have proposed many methods to estimate FCNs from resting-state functional MRI (rs-fMRI) data. However, the existing FCN estimation methods usually only capture a single relationship between brain regions of interest (ROIs), e.g., linear correlation, nonlinear correlation, or higher-order correlation, thus failing to model the complex interaction among ROIs in the brain. Additionally, such traditional methods estimate FCNs in an unsupervised way, and the estimation process is independent of the downstream tasks, which makes it difficult to guarantee the optimal performance for ASD identification. To address these issues, in this paper, we propose a multi-FCN fusion framework for rs-fMRI-based ASD classification. Specifically, for each subject, we first estimate multiple FCNs using different methods to encode rich interactions among ROIs from different perspectives. Then, we use the label information (ASD vs. healthy control (HC)) to learn a set of fusion weights for measuring the importance/discrimination of those estimated FCNs. Finally, we apply the adaptively weighted fused FCN on the ABIDE dataset to identify subjects with ASD from HCs. The proposed FCN fusion framework is straightforward to implement and can significantly improve diagnostic accuracy compared to traditional and state-of-the-art methods.

[Anticoagulant efficacy and safety of argatroban for patients undergoing elective percutaneous coronary intervention].

OBJECTIVE: To investigate the anticoagulant efficacy and safety of argatroban for patients undergoing elective percutaneous coronary intervention (PCI). METHODS: A total of 300 consecutive patients with coronary heart disease undergoing elective PCI were enrolled and randomized into heparin group (100 U/kg via artery sheaths, n = 150) and argatroban group (200 µg/kg bolus, followed by 350 µg·kg(-1)·h(-1) i.v. infusion, n = 150). The primary efficacy endpoint was the activated clotting time (ACT) results (10 min and 60 min after anticoagulant administration and at the point at the end of PCI). The additional dosage of heparin or argatroban was given if the ACT value during PCI procedure < 250 s. Activated partial thromboplastin time (APTT) was also measured at pre-procedure, 10 min after anticoagulant injection and 60 min after PCI. The primary safety endpoint was thrombosis and hemorrhagic events during PCI procedure and hospital stay. RESULTS: All patients in the two groups attained the target ACT ( ≥ 250 s), and ACT in heparin group was significantly prolonged [(343.32 ± 44.70) s vs. (289.60 ± 20.88) s, P < 0.01], at 10 min after anticoagulation injection. ACT was similar between the two groups at 60 min after anticoagulation injection [(291.26 ± 46.79) s vs. (288.40 ± 21.61) s, P > 0.05]. The ACT value in argatroban group was similar at 10 min and 60 min after injection (P > 0.05). Supplemental anticoagulant was needed for 13 (8.7%) patients in heparin group and 2 (1.3%) patients in argatroban group because of ACT under 250 s (P < 0.05) . At the end of PCI procedure, ACT in heparin group was significantly shorter than in argatroban group [(247.16 ± 41.38)s vs. (278.65 ± 20.51) s, P < 0.01]. APTT in heparin group was significantly prolonged than in argatroban group not only at 10 min point [(182.16 ± 4.37) s vs. (81.69 ± 21.49) s, P < 0.01] after anticoagulant injection but also at the point of 60 min after PCI procedure[(169.13 ± 6.35)s vs. (56.21 ± 15.68) s, P < 0.01]. There was no thrombus event in two groups and no bleeding event in argatroban group, and there was three bleeding events in heparin group [2.0% (3/150) vs.0, P > 0.05]. CONCLUSION: Argatroban is an effective and safe anticoagulation agent during elective PCI procedure, anticoagulant efficacy and risk of bleeding side effects of argatroban are similar to heparin.