Artificial Intelligence Medical Compendium

BACKGROUND: Hepatocellular carcinoma (HCC) remains a therapeutic challenge due to high post-resection recurrence rates and heterogeneous outcomes. We developed and validated a digital pathology-based prognostic model combining pathomics signatures wi... read more 

Resting-state functional MRI (rs-fMRI) is widely used for diagnosing and analyzing brain disorders. However, existing fMRI studies have shown that learning-based approaches depend heavily on labeled training data, which is difficult to obtain due to ... read more 

BACKGROUND: ICU patients often suffer from critical and complex condition, and multiple potential risks should be monitored to provide them comprehensive care. However, no study proposes continual learning (CL) model that can effectively solve multip... read more 

Unsupervised domain adaptive object detection (UDAOD) aims to effectively apply the detector trained on a labeled (source domain) and an unlabeled (target domain) dataset to the target domain. The mean teacher framework has demonstrated good applicab... read more 

Lung cancer's metastatic propensity and recurrence prevalence necessitate innovative immunotherapy strategies beyond conventional single-mode regulation. We engineered low-capacity turmeric-derived extracellular vesicles (TEVs) that integrated with z... read more 

CS₂ and SO₂ are typical characteristic gases for evaluating the insulation status of gas-insulated switchgear. Their significant absorption peaks in the ultraviolet band make ultraviolet differential optical absorption spectroscopy (UV-DOAS) an ideal... read more 

The complex physical and chemical interactions between desert mineral aerosol, industrial pollutants, and lake water during drought periods pose significant challenges for accurately assessing lake water quality. This study analyzes Spectral Water Qu... read more 

BACKGROUND: The identification of anomalies in physiological time-series data, specifically ECG and EEG spectra, is a key part of the diagnostic process for patients who may be experiencing cardiac arrest or epileptic seizures. The application of mac... read more 

Cross-domain recommendation (CDR) aims to improve recommendation accuracy in sparse domains by transferring knowledge from data-rich domains. However, existing CDR approaches often assume that user-item interaction data across domains is publicly ava... read more 

This study investigated the microbially driven spoilage mechanism of sturgeon (Acipenser baerii) under refrigerated (4 °C) aerobic storage. High-throughput sequencing analysis revealed that Pseudomonas and Shewanella dominated late-stage spoilage, wh... read more