Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: This study aimed to evaluate the clinical outcomes and prognostic implications of regional nodal irradiation (RNI) after neoadjuvant chemotherapy (NAC) in patients with residual triple-negative breast cancer (TNBC). Materials and Methods: We analyzed 152 patients with residual TNBC who underwent breast-conserving surgery after NAC between December 2008 and December 2017. Most patients (n = 133; 87.5%) received taxane-based chemotherapy. Adjuvant radiotherapy (RT) was administered at a total dose of 45–65 Gy in 15–30 fractions to the whole breast, with some patients also receiving RT to regional nodes. Survival was calculated using the Kaplan–Meier method, and prognostic factors influencing survival were analyzed using the Cox proportional-hazards model. Results: During a median follow-up of 66 months (range, 9 to 179 months), the 5-year disease-free survival (DFS) rate was 68.0%. The 5-year locoregional recurrence-free survival, distant metastasis-free survival, and overall survival rates were 83.6%, 72.6%, and 78.7%, respectively. In the univariate analysis, the cN stage, ypT stage, ypN stage, axillary operation type, and RT field were associated with DFS. Multivariate analysis revealed that higher ypT stage (hazard ratio [HR] = 2.0; 95% confidence interval [CI] 1.00–3.82; p = 0.049) and ypN stage (HR = 4.7; 95% CI 1.57–14.24; p = 0.006) were associated with inferior DFS. Among clinically node-positive patients, those who received RT to the breast only had a 5-year DFS of 73.7%, whereas those who received RNI achieved a DFS of 59.6% (p = 0.164). There were no differences between the DFS and RNI. Conclusion In patients with residual TNBC, higher ypT and ypN stages were associated with poorer outcomes after NAC. RNI did not appear to improve DFS. More intensive treatments incorporating systemic therapy and RT should be considered for these patients.

Background: Islet transplantation holds promise for treating selected type 1 diabetes mellitus patients, yet the scarcity of human donor organs impedes widespread adoption. Porcine islets, deemed a viable alternative, recently demonstrated successful longterm survival without zoonotic risks in a clinically relevant pig-to-non-human primate islet transplantation model. This success prompted the development of a clinical trial protocol for porcine islet xenotransplantation in humans. Methods: A single-center, open-label clinical trial initiated by the sponsor will assess the safety and efficacy of porcine islet transplantation for diabetes patients at Gachon Hospital. The protocol received approval from the Gachon Hospital Institutional Review Board (IRB) and the Korean Ministry of Food and Drug Safety (MFDS) under the Investigational New Drug (IND) process. Two diabetic patients, experiencing inadequate glycemic control despite intensive insulin treatment and frequent hypoglycemic unawareness, will be enrolled. Participants and their family members will engage in deliberation before xenotransplantation during the screening period. Each patient will receive islets isolated from designated pathogen-free pigs. Immunosuppressants and systemic infection prophylaxis will follow the program schedule. The primary endpoint is to confirm the safety of porcine islets in patients, and the secondary endpoint is to assess whether porcine islets can reduce insulin dose and the frequency of hypoglycemic unawareness. Conclusion A clinical trial protocol adhering to global consensus guidelines for porcine islet xenotransplantation is presented, facilitating streamlined implementation of comparable human trials worldwide.

Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: This study aimed to evaluate the clinical outcomes and prognostic implications of regional nodal irradiation (RNI) after neoadjuvant chemotherapy (NAC) in patients with residual triple-negative breast cancer (TNBC). Materials and Methods: We analyzed 152 patients with residual TNBC who underwent breast-conserving surgery after NAC between December 2008 and December 2017. Most patients (n = 133; 87.5%) received taxane-based chemotherapy. Adjuvant radiotherapy (RT) was administered at a total dose of 45–65 Gy in 15–30 fractions to the whole breast, with some patients also receiving RT to regional nodes. Survival was calculated using the Kaplan–Meier method, and prognostic factors influencing survival were analyzed using the Cox proportional-hazards model. Results: During a median follow-up of 66 months (range, 9 to 179 months), the 5-year disease-free survival (DFS) rate was 68.0%. The 5-year locoregional recurrence-free survival, distant metastasis-free survival, and overall survival rates were 83.6%, 72.6%, and 78.7%, respectively. In the univariate analysis, the cN stage, ypT stage, ypN stage, axillary operation type, and RT field were associated with DFS. Multivariate analysis revealed that higher ypT stage (hazard ratio [HR] = 2.0; 95% confidence interval [CI] 1.00–3.82; p = 0.049) and ypN stage (HR = 4.7; 95% CI 1.57–14.24; p = 0.006) were associated with inferior DFS. Among clinically node-positive patients, those who received RT to the breast only had a 5-year DFS of 73.7%, whereas those who received RNI achieved a DFS of 59.6% (p = 0.164). There were no differences between the DFS and RNI. Conclusion In patients with residual TNBC, higher ypT and ypN stages were associated with poorer outcomes after NAC. RNI did not appear to improve DFS. More intensive treatments incorporating systemic therapy and RT should be considered for these patients.

Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: This study aimed to evaluate the clinical outcomes and prognostic implications of regional nodal irradiation (RNI) after neoadjuvant chemotherapy (NAC) in patients with residual triple-negative breast cancer (TNBC). Materials and Methods: We analyzed 152 patients with residual TNBC who underwent breast-conserving surgery after NAC between December 2008 and December 2017. Most patients (n = 133; 87.5%) received taxane-based chemotherapy. Adjuvant radiotherapy (RT) was administered at a total dose of 45–65 Gy in 15–30 fractions to the whole breast, with some patients also receiving RT to regional nodes. Survival was calculated using the Kaplan–Meier method, and prognostic factors influencing survival were analyzed using the Cox proportional-hazards model. Results: During a median follow-up of 66 months (range, 9 to 179 months), the 5-year disease-free survival (DFS) rate was 68.0%. The 5-year locoregional recurrence-free survival, distant metastasis-free survival, and overall survival rates were 83.6%, 72.6%, and 78.7%, respectively. In the univariate analysis, the cN stage, ypT stage, ypN stage, axillary operation type, and RT field were associated with DFS. Multivariate analysis revealed that higher ypT stage (hazard ratio [HR] = 2.0; 95% confidence interval [CI] 1.00–3.82; p = 0.049) and ypN stage (HR = 4.7; 95% CI 1.57–14.24; p = 0.006) were associated with inferior DFS. Among clinically node-positive patients, those who received RT to the breast only had a 5-year DFS of 73.7%, whereas those who received RNI achieved a DFS of 59.6% (p = 0.164). There were no differences between the DFS and RNI. Conclusion In patients with residual TNBC, higher ypT and ypN stages were associated with poorer outcomes after NAC. RNI did not appear to improve DFS. More intensive treatments incorporating systemic therapy and RT should be considered for these patients.

Background: Islet transplantation holds promise for treating selected type 1 diabetes mellitus patients, yet the scarcity of human donor organs impedes widespread adoption. Porcine islets, deemed a viable alternative, recently demonstrated successful longterm survival without zoonotic risks in a clinically relevant pig-to-non-human primate islet transplantation model. This success prompted the development of a clinical trial protocol for porcine islet xenotransplantation in humans. Methods: A single-center, open-label clinical trial initiated by the sponsor will assess the safety and efficacy of porcine islet transplantation for diabetes patients at Gachon Hospital. The protocol received approval from the Gachon Hospital Institutional Review Board (IRB) and the Korean Ministry of Food and Drug Safety (MFDS) under the Investigational New Drug (IND) process. Two diabetic patients, experiencing inadequate glycemic control despite intensive insulin treatment and frequent hypoglycemic unawareness, will be enrolled. Participants and their family members will engage in deliberation before xenotransplantation during the screening period. Each patient will receive islets isolated from designated pathogen-free pigs. Immunosuppressants and systemic infection prophylaxis will follow the program schedule. The primary endpoint is to confirm the safety of porcine islets in patients, and the secondary endpoint is to assess whether porcine islets can reduce insulin dose and the frequency of hypoglycemic unawareness. Conclusion A clinical trial protocol adhering to global consensus guidelines for porcine islet xenotransplantation is presented, facilitating streamlined implementation of comparable human trials worldwide.

Background: Islet transplantation holds promise for treating selected type 1 diabetes mellitus patients, yet the scarcity of human donor organs impedes widespread adoption. Porcine islets, deemed a viable alternative, recently demonstrated successful longterm survival without zoonotic risks in a clinically relevant pig-to-non-human primate islet transplantation model. This success prompted the development of a clinical trial protocol for porcine islet xenotransplantation in humans. Methods: A single-center, open-label clinical trial initiated by the sponsor will assess the safety and efficacy of porcine islet transplantation for diabetes patients at Gachon Hospital. The protocol received approval from the Gachon Hospital Institutional Review Board (IRB) and the Korean Ministry of Food and Drug Safety (MFDS) under the Investigational New Drug (IND) process. Two diabetic patients, experiencing inadequate glycemic control despite intensive insulin treatment and frequent hypoglycemic unawareness, will be enrolled. Participants and their family members will engage in deliberation before xenotransplantation during the screening period. Each patient will receive islets isolated from designated pathogen-free pigs. Immunosuppressants and systemic infection prophylaxis will follow the program schedule. The primary endpoint is to confirm the safety of porcine islets in patients, and the secondary endpoint is to assess whether porcine islets can reduce insulin dose and the frequency of hypoglycemic unawareness. Conclusion A clinical trial protocol adhering to global consensus guidelines for porcine islet xenotransplantation is presented, facilitating streamlined implementation of comparable human trials worldwide.

Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.