Utilizing domain knowledge to improve the classification of intravenous contrast phase of CT scans.

Multiple intravenous contrast phases of CT scans are commonly used in clinical practice to facilitate disease diagnosis. However, contrast phase information is commonly missing or incorrect due to discrepancies in CT series descriptions and imaging practices. This work aims to develop a classification algorithm to automatically determine the contrast phase of a CT scan.

Using Rigidity and Conjugation of Subunits to Modulate Supramolecular Topologies Constructed by Half-Sandwich Fragments.

The synthesis of supramolecular compounds with a high degree of controllability and the targeted modulation of their topological transitions pose significant challenges in situ. In this study, we have successfully constructed an array of discrete structures based on a series of bidentate pyridyl ligands (L1, L2, and L3), which were subsequently ligated with half-sandwiched (Cp*Ir fragments) building blocks. Our further investigations elucidate a strategy for coordinating the relative lengths of the bidentate ligands with the building blocks, achieving specific concentrations that drive the transformation of tetranuclear metal macrocycles into Borromean rings.

A New Benchmark: Clinical Uncertainty and Severity Aware Labeled Chest X-Ray Images with Multi-Relationship Graph Learning.

Chest radiography, commonly known as CXR, is frequently utilized in clinical settings to detect cardiopulmonary conditions. However, even seasoned radiologists might offer different evaluations regarding the seriousness and uncertainty associated with observed abnormalities. Previous research has attempted to utilize clinical notes to extract abnormal labels for training deep-learning models in CXR image diagnosis.

Interpretable medical image Visual Question Answering via multi-modal relationship graph learning.

Medical Visual Question Answering (VQA) is an important task in medical multi-modal Large Language Models (LLMs), aiming to answer clinically relevant questions regarding input medical images. This technique has the potential to improve the efficiency of medical professionals while relieving the burden on the public health system, particularly in resource-poor countries. However, existing medical VQA datasets are small and only contain simple questions (equivalent to classification tasks), which lack semantic reasoning and clinical knowledge.

Frequency Information Disentanglement Network for Video-Based Person Re-Identification.

Recently, most video-based person re-identification (Re-ID) methods adopt complex model or multi-scaled information to explore more discriminative spatio-temporal clues, thus achieving better retrieval accuracy. However, we witness that these approaches involve significant higher computation costs but only improve limited performances. Therefore, the overarching goal at this stage is to solve video Re-ID on the trade-off between accuracy and efficiency, thereby boosting the application in real scenarios.

Hepatic paraoxonase 1 ameliorates dysfunctional high-density lipoprotein and atherosclerosis in scavenger receptor class B type I deficient mice.

Background: High-density lipoprotein (HDL) plays an antiatherogenic role by mediating reverse cholesterol transport (RCT), antioxidation, anti-inflammation, and endothelial cell protection. Recently, series of evidence have shown that HDL can also convert to proatherogenic HDL under certain circumstances. Plasma paraoxonase 1 (PON1) as an HDL-bound esterase, is responsible for most of the antioxidant properties of HDL.

A Two-Stream Dynamic Pyramid Representation Model for Video-Based Person Re-Identification.

Video-based person re-identification (Re-ID) leverages rich spatio-temporal information embedded in sequence data to further improve the retrieval accuracy comparing with single image Re-ID. However, it also brings new difficulties. 1) Both spatial and temporal information should be considered simultaneously.

Multi-Modal Joint Clustering With Application for Unsupervised Attribute Discovery.

Utilizing multiple descriptions/views of an object is often useful in image clustering tasks. Despite many works that have been proposed to effectively cluster multi-view data, there are still unaddressed problems such as the errors introduced by the traditional spectral-based clustering methods due to the two disjoint stages: 1) eigendecomposition and 2) the discretization of new representations. In this paper, we propose a unified clustering framework which jointly learns the two stages together as well as utilizing multiple descriptions of the data.

A human apolipoprotein E mimetic peptide reduces atherosclerosis in aged apolipoprotein E null mice.

Apolipoprotein E (apoE) is well known as an antiatherogenic protein via regulating lipid metabolism and inflammation. We previously reported that a human apoE mimetic peptide, EpK, reduced atherosclerosis in apoE null (apoE(-/-)) mice through reducing inflammation without affecting plasma lipid levels. Here, we construct another human apoE mimetic peptide, named hEp, and investigate whether expression of hEp can reduce atherosclerotic lesion development in aged female apoE(-/-) mice with pre-existing lesions.