Artificial Intelligence Medical Compendium

UNLABELLED: Hematopoietic stem cell (HSC) mobilization is a critical step in bone marrow transplantation for treating hematological malignancies and other disorders. Since poor mobilization affects 10–20% of patients, it can cause failure of the tran... read more 

OBJECTIVES: This research aimed to investigate how different image processing techniques influence the performance of a deep learning model in classifying cervical vertebral maturation (CVM) stages. METHODS: A dataset of 799 cephalometric radiographs... read more 

OBJECTIVES: Lupus nephritis (LN) is one of the most common complications of systemic lupus erythematosus. This study aimed to identify key autophagy-related genes and to provide a novel approach for the diagnosis and treatment of LN. METHODS: Gene ex... read more 

OBJECTIVE: Accurate classification of salivary gland tumors is critical to guiding appropriate management. This study evaluates the diagnostic performance of artificial intelligence models in classifying salivary gland tumors on ultrasound. DATA SOUR... read more 

read more 

OBJECTIVE: To evaluate the performance of convolutional neural network (CNN)-based models for predicting fetal rabbit lung development: unimodal models using B-mode and shear wave elastography (SWE) and a multimodal model combining B-mode and SWE. ME... read more 

PURPOSE: To develop and validate a rapid, fully automated method for shimming of the lung. METHODS: For field mapping of the lung, a custom 2D RF spoiled gradient echo sequence was used offering sub-millisecond echo times. At 3T, four echo-shifted co... read more 

Accurate antioxidant detection remains crucial for biomedical and food applications, although conventional methods face persistent challenges including structural similarity interference, instrument dependency, and unreliable detection outcomes. To a... read more 

Fast intraoperative histopathology is critical for optimal surgery in ovarian, endometrial and cervical cancers, yet frozen-section pathology is slow and resource-intensive. We obtained 4750 Raman spectra from 85 human gynecological tissue specimens ... read more 

The majority of machine learning scoring functions used in drug discovery for predicting protein-ligand binding poses and affinities have been trained on the PDBBind data set. However, it is unclear whether these new scoring functions are actually an... read more