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.

In this paper, we review the use of hypofractionated radiotherapy for gastrointestinal malignancies, focusing on primary and metastatic liver cancer, and recurrent rectal cancer. Technological advancements in radiotherapy have facilitated the direct delivery of high-dose radiation to tumors, while limiting normal tissue exposure, supporting the use of hypofractionation. Hypofractionated radiotherapy is particularly effective for primary and metastatic liver cancer where high-dose irradiation is crucial to achieve effective local control. For recurrent rectal cancer, the use of stereotactic body radiotherapy offers a promising approach for re-irradiation, balancing efficacy and safety in patients who have been administered previous pelvic radiotherapy and in whom salvage surgery is not applicable. Nevertheless, the potential for radiation-induced liver disease and gastrointestinal complications presents challenges when applying hypofractionation to gastrointestinal organs. Given the lack of universal consensus on hypofractionation regimens and the dose constraints for primary and metastatic liver cancer, as well as for recurrent rectal cancer, this review aims to facilitate clinical decision-making by pointing to potential regimens and dose constraints, underpinned by a comprehensive review of existing clinical studies and guidelines.

Hypofractionated radiotherapy (RT) has become a trend in the modern era, as advances in RT techniques, including intensity-modulated RT and image-guided RT, enable the precise and safe delivery of high-dose radiation. Hypofractionated RT offers convenience and can reduce the financial burden on patients by decreasing the number of fractions. Furthermore, hypofractionated RT is potentially more beneficial for tumors with a low α/β ratio compared with conventional fractionation RT. Therefore, hypofractionated RT has been investigated for various primary cancers and has gained status as a standard treatment recommended in the guidelines. In genitourinary (GU) cancer, especially prostate cancer, the efficacy, and safety of various hypofractionated dose schemes have been evaluated in numerous prospective clinical studies, establishing the standard hypofractionated RT regimen. Hypofractionated RT has also been explored for gynecological (GY) cancer, yielding relevant evidence in recent years. In this review, we aimed to summarize the representative evidence and current trends in clinical studies on hypofractionated RT for GU and GY cancers addressing several key questions. In addition, the objective is to offer suggestions for the available dose regimens for hypofractionated RT by reviewing protocols from previous clinical studies.

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.

In this paper, we review the use of hypofractionated radiotherapy for gastrointestinal malignancies, focusing on primary and metastatic liver cancer, and recurrent rectal cancer. Technological advancements in radiotherapy have facilitated the direct delivery of high-dose radiation to tumors, while limiting normal tissue exposure, supporting the use of hypofractionation. Hypofractionated radiotherapy is particularly effective for primary and metastatic liver cancer where high-dose irradiation is crucial to achieve effective local control. For recurrent rectal cancer, the use of stereotactic body radiotherapy offers a promising approach for re-irradiation, balancing efficacy and safety in patients who have been administered previous pelvic radiotherapy and in whom salvage surgery is not applicable. Nevertheless, the potential for radiation-induced liver disease and gastrointestinal complications presents challenges when applying hypofractionation to gastrointestinal organs. Given the lack of universal consensus on hypofractionation regimens and the dose constraints for primary and metastatic liver cancer, as well as for recurrent rectal cancer, this review aims to facilitate clinical decision-making by pointing to potential regimens and dose constraints, underpinned by a comprehensive review of existing clinical studies and guidelines.

Hypofractionated radiotherapy (RT) has become a trend in the modern era, as advances in RT techniques, including intensity-modulated RT and image-guided RT, enable the precise and safe delivery of high-dose radiation. Hypofractionated RT offers convenience and can reduce the financial burden on patients by decreasing the number of fractions. Furthermore, hypofractionated RT is potentially more beneficial for tumors with a low α/β ratio compared with conventional fractionation RT. Therefore, hypofractionated RT has been investigated for various primary cancers and has gained status as a standard treatment recommended in the guidelines. In genitourinary (GU) cancer, especially prostate cancer, the efficacy, and safety of various hypofractionated dose schemes have been evaluated in numerous prospective clinical studies, establishing the standard hypofractionated RT regimen. Hypofractionated RT has also been explored for gynecological (GY) cancer, yielding relevant evidence in recent years. In this review, we aimed to summarize the representative evidence and current trends in clinical studies on hypofractionated RT for GU and GY cancers addressing several key questions. In addition, the objective is to offer suggestions for the available dose regimens for hypofractionated RT by reviewing protocols from previous clinical studies.

Background: Although symptomatic local recurrence (SLR) of spinal metastasis is relatively common after aggressive surgery, there have been few studies on SLR according to the extent of tumor removal. This study aimed to evaluate the incidence of SLR after surgery in spinal metastasis and analyze the risk factors of SLR. Methods: This study included patients with spinal metastasis to all 3 vertebral columns. SLR was defined as the occurrence of new symptoms, confirmed by radiologic regrowth of tumor. The extent of tumor removal was classified into 3 types (corpectomy, separation surgery, and only posterior column removal). The Kaplan-Meier method was used to analyze the SLR rate after surgery.The presumed risk factors of SLR were evaluated using log-rank test and Cox regression analysis. Results: This study included 102 patients with a mean follow-up period of 17.7 months (range, 3–84 months). After surgical treatment, SLR was confirmed in 35 patients (34.3%). Kaplan-Meier analysis predicted that the incidence of SLR was 4.4% at 6 months, 21.5% at 12 months, 34.0% at 18 months, and 42.7% at 24 months. In the univariate analysis, the primary malignancy site, number of vertebral metastases, and surgery for progressed tumor after previous radiation therapy were significant (p = 0.042, p = 0.048, and p = 0.008, respectively). No significant differences were observed in the extent of tumor removal (p = 0.536). In the multivariate analysis, the significant risk factors of SLR included only previous radiation therapy (p = 0.012). The risk of SLR was 2.8 times higher in patients who received surgery for progressed tumor after previous radiation therapy than in those without it. Conclusions The SLR of spinal metastasis was predicted in 21.5% of patients at 1 year after surgical treatment. The extent of tumor removal did not seem to affect SLR. Surgery for progressed tumor after previous radiation therapy was confirmed as the only substantial risk factor. Therefore, the tumor's response to preoperative radiation therapy is the most important factor in determining SLR.

Background: Although symptomatic local recurrence (SLR) of spinal metastasis is relatively common after aggressive surgery, there have been few studies on SLR according to the extent of tumor removal. This study aimed to evaluate the incidence of SLR after surgery in spinal metastasis and analyze the risk factors of SLR. Methods: This study included patients with spinal metastasis to all 3 vertebral columns. SLR was defined as the occurrence of new symptoms, confirmed by radiologic regrowth of tumor. The extent of tumor removal was classified into 3 types (corpectomy, separation surgery, and only posterior column removal). The Kaplan-Meier method was used to analyze the SLR rate after surgery.The presumed risk factors of SLR were evaluated using log-rank test and Cox regression analysis. Results: This study included 102 patients with a mean follow-up period of 17.7 months (range, 3–84 months). After surgical treatment, SLR was confirmed in 35 patients (34.3%). Kaplan-Meier analysis predicted that the incidence of SLR was 4.4% at 6 months, 21.5% at 12 months, 34.0% at 18 months, and 42.7% at 24 months. In the univariate analysis, the primary malignancy site, number of vertebral metastases, and surgery for progressed tumor after previous radiation therapy were significant (p = 0.042, p = 0.048, and p = 0.008, respectively). No significant differences were observed in the extent of tumor removal (p = 0.536). In the multivariate analysis, the significant risk factors of SLR included only previous radiation therapy (p = 0.012). The risk of SLR was 2.8 times higher in patients who received surgery for progressed tumor after previous radiation therapy than in those without it. Conclusions The SLR of spinal metastasis was predicted in 21.5% of patients at 1 year after surgical treatment. The extent of tumor removal did not seem to affect SLR. Surgery for progressed tumor after previous radiation therapy was confirmed as the only substantial risk factor. Therefore, the tumor's response to preoperative radiation therapy is the most important factor in determining SLR.

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.

In this paper, we review the use of hypofractionated radiotherapy for gastrointestinal malignancies, focusing on primary and metastatic liver cancer, and recurrent rectal cancer. Technological advancements in radiotherapy have facilitated the direct delivery of high-dose radiation to tumors, while limiting normal tissue exposure, supporting the use of hypofractionation. Hypofractionated radiotherapy is particularly effective for primary and metastatic liver cancer where high-dose irradiation is crucial to achieve effective local control. For recurrent rectal cancer, the use of stereotactic body radiotherapy offers a promising approach for re-irradiation, balancing efficacy and safety in patients who have been administered previous pelvic radiotherapy and in whom salvage surgery is not applicable. Nevertheless, the potential for radiation-induced liver disease and gastrointestinal complications presents challenges when applying hypofractionation to gastrointestinal organs. Given the lack of universal consensus on hypofractionation regimens and the dose constraints for primary and metastatic liver cancer, as well as for recurrent rectal cancer, this review aims to facilitate clinical decision-making by pointing to potential regimens and dose constraints, underpinned by a comprehensive review of existing clinical studies and guidelines.