Endocuff Vision-Assisted Colonoscopy Significantly Improves Adenoma Detection In A Shorter Withdrawal Time Compared With Standard Colonoscopy: A Randomized Controlled Trial.

Introduction: Although several studies in Western countries have shown that Endocuff Vision-assisted colonoscopy (EC) can improve the colorectal adenoma detection rate (ADR), such evidence in Asia is still scarce. This study aimed to evaluate the performance of EC in detecting colorectal adenomas in Vietnamese patients.

Methods: This was a randomized controlled trial conducted at a tertiary hospital in Vietnam.

A phase II double-blind multicentre, placebo-controlled trial to assess the efficacy and safety of alpelisib (BYL719) in paediatric and adult patients with Megalencephaly-CApillary malformation Polymicrogyria syndrome (MCAP): the SESAM study protocol.

Introduction: The megalencephaly capillary malformation polymicrogyria (MCAP syndrome) results from mosaic gain-of-function variants. The main clinical features are macrocephaly, somatic overgrowth, neurodevelopmental delay and brain anomalies. Alpelisib (Vijoice) is a recently FDA-approved PI3Kα-specific inhibitor for patients with PIK3CA-related overgrowth spectrum (PROS).

Patient preferences for life expectancy cutoffs for aggressive treatment in clinically localized prostate cancer.

Background: Guidelines for prostate cancer treatment in men with limited life expectancy are based on expert opinion. Patient preferences for when to defer treatment based on longevity are unknown. We sought to define life expectancy thresholds at which men are more likely to choose conservative management in the context of varying risks of cancer death and treatment-related side effects.

Reconfigurable nanomaterials folded from multicomponent chains of DNA origami voxels.

In cells, proteins rapidly self-assemble into sophisticated nanomachines. Bioinspired self-assembly approaches, such as DNA origami, have been used to achieve complex three-dimensional (3D) nanostructures and devices. However, current synthetic systems are limited by low yields in hierarchical assembly and challenges in rapid and efficient reconfiguration between diverse structures.

Transfer Learning Approaches for Brain Metastases Screenings.

Background: In this study, we examined the effectiveness of transfer learning in improving automatic segmentation of brain metastases on magnetic resonance imaging scans, with potential applications in preventive exams and remote diagnostics.

Methods: We trained three deep learning models on a public dataset from the ASNR-MICCAI Brain Metastasis Challenge 2024, fine-tuned them on a small private dataset, and compared their performance to models trained from scratch.

Results: Results showed that models using transfer learning performed better than scratch-trained models, though the improvement was not statistically substantial.