yasui keisuke

Abstract Large language models (LLMs) have recently gained attention for their potential. However, concerns remain regarding their reliability due to limitations such as hallucinations and insufficient domain-specific knowledge. Retrieval-augmented generation (RAG) has emerged as a promising approach, enabling LLMs to reference external knowledge sources and generate accurate outputs. We aimed to clarify the potential of RAG-enhanced LLMs with Japanese input in the field of radiotherapy. This was assessed by evaluating performance on three certification examinations in Japan: the Japanese Medical Physicist Examination, the Japanese Board Examination for Radiologists, and the Japanese Board Examination for Radiation Oncologists. In this study, we constructed a RAG system named Rad-Hub, consisting of a Japanese Radiotherapy Knowledge Database (JRKD) and a retrieval framework built on Microsoft Azure. The JRKD was populated with 32 Japanese radiotherapy textbooks and clinical guidelines. We assessed its utility by inputting all multiple-choice questions from the three examinations into ChatGPT-4o, both with and without Rad-Hub, and recording the answers. They were then compared with reference answers determined by experienced medical physicists and radiation oncologists. Rad-Hub improved accuracy across all examinations. Accuracy increased from 77.0% ± 2.6% to 84.6% ± 1.5% in the Medical Physicist examination, from 74.9% ± 2.0% to 82.1% ± 1.1% in the Radiologist examination, and from 55.6% ± 4.4% to 71.7% ± 4.5% in the Radiation Oncologist examination. Performance gains ranged from 7.2% to 16.1%. These findings highlight the potential of RAG-enhanced LLMs, particularly ChatGPT-4o with Rad-Hub, for integration into radiotherapy applications, such as educational and clinical decision assistance.

ABSTRACT The patient setup using the surface‐guided radiation therapy (SGRT) system differs from conventional surface marker procedures. Owing to the abundance of three‐dimensional information, there may be operator variability in where to focus during the patient setup. This study aimed to clarify the differences between expert and novice operators in SGRT positioning for head and neck cases by tracking their eye movements, thereby providing data for developing efficient patient setup procedures. Six radiation therapists set up a simulated patient on the SGRT system while recording eye movements on the screen using the QG‐PLUS eye‐tracking system. The positioning time and number of gaze fixations on the screen were analysed, and the relationship between years of experience with SGRT, positioning time and number of gaze fixations was evaluated. No significant correlation was found between SGRT experience and positioning time ( r  = −0.67, p  = 0.15). However, more experienced radiation therapists exhibited fewer gaze fixations per positioning session ( r  = −0.81, p  < 0.05), indicating that they efficiently identified key positioning points. Additionally, experienced radiation therapists focused more intently on a specific screen during the latter half of positioning, suggesting a refined approach for final patient alignment verification. More experienced radiation therapists showed fewer gaze fixations and demonstrated increased attention to a specific screen during the latter half of the patient setup process, suggesting that eye‐tracking technology may provide useful data for standardising patient setup procedures in SGRT patient setups.

BACKGROUND: Accurate absolute dosimetry is essential for achieving high-precision proton beam therapy. Consequently, a comprehensive characterization of the ionization chamber's response properties is necessary. PURPOSE: This study aimed to evaluate the average f Q using Monte Carlo (MC) code PHITS to assess uncertainties among different MC simulation tools. Additionally, P Q values for PTW 30013, NACP-02, and PTW 31013 ionization chambers are calculated using PHITS to provide new reference data for P Q . Furthermore, a new k Q factor for PTW 31013 chamber is established using MC method, contributing to advancements in proton beam dosimetry protocols. METHODS: Monoenergetic proton beams were employed to calculate f Q , k Q , and P Q for Farmer, Semiflex, and plane-parallel chambers. The absorbed dose deposited within the sensitive volume of each chamber was determined via simulations employing PHITS, thereby providing the basis for the estimation of these factors. Computed f Q values were compared with previous reports, while k Q and P Q were benchmarked against literature and Technical Reports Series No. 398 (TRS-398) Rev.1 guideline. RESULTS: Incorporating PHITS-derived f Q values reduced the uncertainty of f ¯ Q P H I T S compared to previous findings. The k Q factor for PTW 31013 followed trends observed in cylindrical chambers with varying sensitive volumes; notably, this study represents the first MC estimation of k Q for this chamber. P Q values for values deviated by up to 1.7% from unity. CONCLUSION: The data generated in this study provide important insights for refining proton beam dosimetry, contributing to the improvement of treatment precision.