This study aimed to develop a large language model (LLM) chatbot for radiation therapy education and compare the performance of portable document format (PDF)- and webpage-based question-and-answer (Q&A) chatbots. An LLM chatbot was created using the EmbedChain framework, OpenAI GPT-3.5-Turbo API, and Gradio UI. The performance of both chatbots was evaluated based on 10 questions and their corresponding answers, using the parameters of accuracy, semantic similarity, consistency, and response time. The accuracy scores were 0.672 and 0.675 for the PDF- and webpage-based Q&A chatbots, respectively. The semantic similarity between the two chatbots was 0.928 (92.8%). The consistency score was one for both chatbots. The average response time was 3.3 s and 2.38 s for the PDF- and webpage-based chatbots, respectively. The LLM chatbot developed in this study demonstrates the potential to provide reliable responses for radiation therapy education. However, its reliability and efficiency must be further optimized to be effectively utilized as an educational tool.

It is very important to use effective parameters in the treatment plan of breast cancer patients in TomoDirect (TD)-three-dimensional conformal radiation therapy (TD-3DCRT). The objective of this study was to compare the radiation treatment plans to the parameters (jaw width and jaw mode) of TD-3DCRT for left-breast cancer. This study was conducted using the phantom, the jaw mode (fixed and dynamic) and field width (2.5 cm and 5.0 cm) were controlled to compare the TD-3DCRT treatment plans. There was small difference in the conformity index (CI) and homogeneity index (HI) values for target according to the jaw mode for each field width. As a result of observation in terms of dose, treatment time and unnecessary damage to surrounding normal organs could be minimized when dynamic jaw with a field width of 5.0 cm was used. In conclusion, we verified that the use of dynamic jaws and 5.0 cm field width was effective in left-breast cancer radiotherapy plan using TD-3DCRT.

Background and Objectives: The axillary lateral vessel thoracic junction (ALTJ) is a key lymphatic drainage pathway for the arm and a potential structure to spare during regional nodal irradiation (RNI) to reduce lymphedema risk in breast cancer patients. This study aims to demonstrate the feasibility of ALTJ-sparing radiation therapy (RT) planning using Tomotherapy. Materials and Methods: Ten breast cancer patients who had undergone axillary lymph node dissection and whose dissected axillary levels were excluded from the RNI target volume were included. A TomoDirect intensity-modulated RT plan was generated at a dose of 50 Gy in 25 fractions. The dissected axilla was not designated as an organ at risk (OAR) in the original treatment plan. For this study, the axillary lymph node level I (AXL1) and the ALTJ were delineated retrospectively, with the ALTJ considered an OAR in the newly generated study plan. A total of 20 RT plans (10 per group) were statistically compared using various dose-volume parameters. Results: Compared to the original plans, the study plans with ALTJ as an OAR significantly reduced the incidental dose to both the ALTJ (mean: 41.7 ± 3.4 Gy vs. 27.2 ± 1.3 Gy; p = 0.005) and the AXL1 (mean: 43.9 ± 2.0 Gy vs. 37.7 ± 1.9 Gy; p = 0.005). All other dosimetric parameters (V25Gy, V35Gy, V40Gy, Dmin, Dmax) for the ALTJ were also significantly lower in the study plans. This ALTJ sparing was achieved while maintaining all required dose-volume constraints for target volumes and standard OARs such as the lung and heart. Conclusions: This study demonstrates that simply excluding the dissected axilla from the target volume without designating it as an OAR still results in a substantial incidental dose to this region. Our findings also show the feasibility of using Tomotherapy to selectively spare the axilla, particularly the ALTJ subregion of AXL1, which is critical for lymphedema risk in breast cancer patients.

Background and Objectives: The axillary lateral vessel thoracic junction (ALTJ) is a key lymphatic drainage pathway for the arm and a potential structure to spare during regional nodal irradiation (RNI) to reduce lymphedema risk in breast cancer patients. This study aims to demonstrate the feasibility of ALTJ-sparing radiation therapy (RT) planning using Tomotherapy. Materials and Methods: Ten breast cancer patients who had undergone axillary lymph node dissection and whose dissected axillary levels were excluded from the RNI target volume were included. A TomoDirect intensity-modulated RT plan was generated at a dose of 50 Gy in 25 fractions. The dissected axilla was not designated as an organ at risk (OAR) in the original treatment plan. For this study, the axillary lymph node level I (AXL1) and the ALTJ were delineated retrospectively, with the ALTJ considered an OAR in the newly generated study plan. A total of 20 RT plans (10 per group) were statistically compared using various dose-volume parameters. Results: Compared to the original plans, the study plans with ALTJ as an OAR significantly reduced the incidental dose to both the ALTJ (mean: 41.7 ± 3.4 Gy vs. 27.2 ± 1.3 Gy; p=0.005) and the AXL1 (mean: 43.9 ± 2.0 Gy vs. 37.7 ± 1.9 Gy; p=0.005). All other dosimetric parameters (V25Gy, V35Gy, V40Gy, Dmin, Dmax) for the ALTJ were also significantly lower in the study plans. This ALTJ sparing was achieved while maintaining all required dose-volume constraints for target volumes and standard OARs such as the lung and heart. Conclusions: This study demonstrates that simply excluding the dissected axilla from the target volume without designating it as an OAR still results in a substantial incidental dose to this region. Our findings also show the feasibility of using Tomotherapy to selectively spare the axilla, particularly the ALTJ subregion of AXL1, which is critical for lymphedema risk in breast cancer patients.