Diagnostic and interventional paediatric bronchoscopy in low and middle-income countries.

Objectives: To investigate the role of both diagnostic and interventional paediatric bronchoscopy in the management of respiratory diseases in children in low- and middle-income countries (LMICs).

Design: A review of published English literature from January 2014 to February 2024.

Results: Indications for bronchoscopy in LMICs will vary depending on the burden of infectious diseases like tuberculosis (TB) and HIV, and the expertise and equipment available.

Prostate brachytherapy boost: Long-term results of protocol-based treatment of patients with non-metastatic prostate cancer.

Purpose: To evaluate the efficacy and toxicity of interstitial temporary brachytherapy boost for prostate cancer patients using real-world data.

Material And Methods: Between 2008 and 2016, 115 patients treated with external beam radiotherapy (EBRT) followed by a brachytherapy boost (BT boost) were eligible for this retrospective analysis. Patients received either interstitial high-dose-rate brachytherapy (HDR-BT) with 2 x 9-9.

Fine-tuning a local LLaMA-3 large language model for automated privacy-preserving physician letter generation in radiation oncology.

Introduction: Generating physician letters is a time-consuming task in daily clinical practice.

Methods: This study investigates local fine-tuning of large language models (LLMs), specifically LLaMA models, for physician letter generation in a privacy-preserving manner within the field of radiation oncology.

Results: Our findings demonstrate that base LLaMA models, without fine-tuning, are inadequate for effectively generating physician letters.

Safety and Efficacy of Brachytherapy in Inoperable Endometrial Cancer.

: Radiotherapy represents the only treatment option for patients with inoperable endometrial cancer (EC). The aim of our study was to evaluate the efficacy and safety of brachytherapy (BT) in this selected patient population. : Between 1990 and 2019, 18 patients with inoperable EC in stage FIGO I-IV were treated with intracavitary brachytherapy using the "Heyman Packing technique".

The Segment Anything foundation model achieves favorable brain tumor auto-segmentation accuracy in MRI to support radiotherapy treatment planning.

Background: Promptable foundation auto-segmentation models like Segment Anything (SA, Meta AI, New York, USA) represent a novel class of universal deep learning auto-segmentation models that could be employed for interactive tumor auto-contouring in RT treatment planning.

Methods: Segment Anything was evaluated in an interactive point-to-mask auto-segmentation task for glioma brain tumor auto-contouring in 16,744 transverse slices from 369 MRI datasets (BraTS 2020 dataset). Up to nine interactive point prompts were automatically placed per slice.