Detecting IDH and TERTp mutations in diffuse gliomas using H-MRS with attention deep-shallow networks.

Background: Preoperative and noninvasive detection of isocitrate dehydrogenase (IDH) and telomerase reverse transcriptase gene promoter (TERTp) mutations in glioma is critical for prognosis and treatment planning. This study aims to develop deep learning classifiers to identify IDH and TERTp mutations using proton magnetic resonance spectroscopy (H-MRS) and a one-dimensional convolutional neural network (1D-CNN) architecture.

Methods: This study included H-MRS data from 225 adult patients with hemispheric diffuse glioma (117 IDH mutants and 108 IDH wild-type; 99 TERTp mutants and 100 TERTp wild-type).

Decoding brain structure to stage Alzheimer's disease pathology in Down syndrome.

Introduction: Alzheimer's disease (AD) in Down syndrome (DS) is associated with changes in brain structure. It is unknown if thickness and volumetric changes can identify AD stages and if they are similar to other genetic forms of AD.

Methods: Magnetic resonance imaging scans were collected for 178 DS adults (106 nonclinical, 45 preclinical, and 27 symptomatic).

Predicting the need for medial augmentation for primary total knee arthroplasty with varus deformity.

Objectives: This study aims to compare the radiographic results with and without postoperative metal augmentation in varus knee patients with primary total knee arthroplasty (TKA) with a hip-knee-ankle (HKA) angle >10° and to determine a cut-off value using radiographic parameters to predict the need for metal augmentation.

Patients And Methods: Between October 2022 and April 2024, a total of 87 knees (51 right and 36 left) of 82 patients (11 males, 71 females; mean age: 68.7±8 years; range, 53 to 86 years) who underwent primary TKA were retrospectively analyzed.

Deep profiling of gene expression across 18 human cancers.

Clinical and biological information in large datasets of gene expression across cancers could be tapped with unsupervised deep learning. However, difficulties associated with biological interpretability and methodological robustness have made this impractical. Here we describe an unsupervised deep-learning framework for the generation of low-dimensional latent spaces for gene-expression data from 50,211 transcriptomes across 18 human cancers.

Impact of Specimen Extraction Site and Gallstone Size on Early Postoperative Pain Following Laparoscopic Cholecystectomy: A Prospective Randomized Controlled Study.

Background: Laparoscopic cholecystectomy (LC) is widely performed with generally favorable outcomes, but postoperative pain remains a significant issue, influenced by various factors including the specimen extraction site and gallstone size.

Methods: A prospective randomized controlled study was conducted on 100 patients undergoing LC. Participants were randomized to have the specimen removed through either the epigastric or umbilical trocar.