Artificial intelligence (AI) is rapidly transforming various medical fields, including radiation oncology.This review explores the integration of AI into radiation oncology, highlighting both challenges and opportunities. AI can improve the precision, efficiency, and outcomes of radiation therapy by optimizing treatment planning, enhancing image analysis, facilitating adaptive radiation therapy, and enabling predictive analytics. Through the analysis of large datasets to identify optimal treatment parameters, AI can automate complex tasks, reduce planning time, and improve accuracy. In image analysis, AI-driven techniques enhance tumor detection and segmentation by processing data from CT, MRI, and PET scans to enable precise tumor delineation. In adaptive radiation therapy, AI is beneficial because it allows real-time adjustments to treatment plans based on changes in patient anatomy and tumor size, thereby improving treatment accuracy and effectiveness. Predictive analytics using historical patient data can predict treatment outcomes and potential complications, guiding clinical decision-making and enabling more personalized treatment strategies. Challenges to AI adoption in radiation oncology include ensuring data quality and quantity, achieving interoperability and standardization, addressing regulatory and ethical considerations, and overcoming resistance to clinical implementation. Collaboration among researchers, clinicians, data scientists, and industry stakeholders is crucial to overcoming these obstacles. By addressing these challenges, AI can drive advancements in radiation therapy, improving patient care and operational efficiencies. This review presents an overview of the current state of AI integration in radiation oncology and insights into future directions for research and clinical practice.

Artificial intelligence (AI) is rapidly transforming various medical fields, including radiation oncology.This review explores the integration of AI into radiation oncology, highlighting both challenges and opportunities. AI can improve the precision, efficiency, and outcomes of radiation therapy by optimizing treatment planning, enhancing image analysis, facilitating adaptive radiation therapy, and enabling predictive analytics. Through the analysis of large datasets to identify optimal treatment parameters, AI can automate complex tasks, reduce planning time, and improve accuracy. In image analysis, AI-driven techniques enhance tumor detection and segmentation by processing data from CT, MRI, and PET scans to enable precise tumor delineation. In adaptive radiation therapy, AI is beneficial because it allows real-time adjustments to treatment plans based on changes in patient anatomy and tumor size, thereby improving treatment accuracy and effectiveness. Predictive analytics using historical patient data can predict treatment outcomes and potential complications, guiding clinical decision-making and enabling more personalized treatment strategies. Challenges to AI adoption in radiation oncology include ensuring data quality and quantity, achieving interoperability and standardization, addressing regulatory and ethical considerations, and overcoming resistance to clinical implementation. Collaboration among researchers, clinicians, data scientists, and industry stakeholders is crucial to overcoming these obstacles. By addressing these challenges, AI can drive advancements in radiation therapy, improving patient care and operational efficiencies. This review presents an overview of the current state of AI integration in radiation oncology and insights into future directions for research and clinical practice.

Artificial intelligence (AI) is rapidly transforming various medical fields, including radiation oncology.This review explores the integration of AI into radiation oncology, highlighting both challenges and opportunities. AI can improve the precision, efficiency, and outcomes of radiation therapy by optimizing treatment planning, enhancing image analysis, facilitating adaptive radiation therapy, and enabling predictive analytics. Through the analysis of large datasets to identify optimal treatment parameters, AI can automate complex tasks, reduce planning time, and improve accuracy. In image analysis, AI-driven techniques enhance tumor detection and segmentation by processing data from CT, MRI, and PET scans to enable precise tumor delineation. In adaptive radiation therapy, AI is beneficial because it allows real-time adjustments to treatment plans based on changes in patient anatomy and tumor size, thereby improving treatment accuracy and effectiveness. Predictive analytics using historical patient data can predict treatment outcomes and potential complications, guiding clinical decision-making and enabling more personalized treatment strategies. Challenges to AI adoption in radiation oncology include ensuring data quality and quantity, achieving interoperability and standardization, addressing regulatory and ethical considerations, and overcoming resistance to clinical implementation. Collaboration among researchers, clinicians, data scientists, and industry stakeholders is crucial to overcoming these obstacles. By addressing these challenges, AI can drive advancements in radiation therapy, improving patient care and operational efficiencies. This review presents an overview of the current state of AI integration in radiation oncology and insights into future directions for research and clinical practice.

Artificial intelligence (AI) is rapidly transforming various medical fields, including radiation oncology.This review explores the integration of AI into radiation oncology, highlighting both challenges and opportunities. AI can improve the precision, efficiency, and outcomes of radiation therapy by optimizing treatment planning, enhancing image analysis, facilitating adaptive radiation therapy, and enabling predictive analytics. Through the analysis of large datasets to identify optimal treatment parameters, AI can automate complex tasks, reduce planning time, and improve accuracy. In image analysis, AI-driven techniques enhance tumor detection and segmentation by processing data from CT, MRI, and PET scans to enable precise tumor delineation. In adaptive radiation therapy, AI is beneficial because it allows real-time adjustments to treatment plans based on changes in patient anatomy and tumor size, thereby improving treatment accuracy and effectiveness. Predictive analytics using historical patient data can predict treatment outcomes and potential complications, guiding clinical decision-making and enabling more personalized treatment strategies. Challenges to AI adoption in radiation oncology include ensuring data quality and quantity, achieving interoperability and standardization, addressing regulatory and ethical considerations, and overcoming resistance to clinical implementation. Collaboration among researchers, clinicians, data scientists, and industry stakeholders is crucial to overcoming these obstacles. By addressing these challenges, AI can drive advancements in radiation therapy, improving patient care and operational efficiencies. This review presents an overview of the current state of AI integration in radiation oncology and insights into future directions for research and clinical practice.

Artificial intelligence (AI) is rapidly transforming various medical fields, including radiation oncology.This review explores the integration of AI into radiation oncology, highlighting both challenges and opportunities. AI can improve the precision, efficiency, and outcomes of radiation therapy by optimizing treatment planning, enhancing image analysis, facilitating adaptive radiation therapy, and enabling predictive analytics. Through the analysis of large datasets to identify optimal treatment parameters, AI can automate complex tasks, reduce planning time, and improve accuracy. In image analysis, AI-driven techniques enhance tumor detection and segmentation by processing data from CT, MRI, and PET scans to enable precise tumor delineation. In adaptive radiation therapy, AI is beneficial because it allows real-time adjustments to treatment plans based on changes in patient anatomy and tumor size, thereby improving treatment accuracy and effectiveness. Predictive analytics using historical patient data can predict treatment outcomes and potential complications, guiding clinical decision-making and enabling more personalized treatment strategies. Challenges to AI adoption in radiation oncology include ensuring data quality and quantity, achieving interoperability and standardization, addressing regulatory and ethical considerations, and overcoming resistance to clinical implementation. Collaboration among researchers, clinicians, data scientists, and industry stakeholders is crucial to overcoming these obstacles. By addressing these challenges, AI can drive advancements in radiation therapy, improving patient care and operational efficiencies. This review presents an overview of the current state of AI integration in radiation oncology and insights into future directions for research and clinical practice.

PURPOSE: Toxicity of mucosa is one of the major concerns of radiotherapy (RT), when a target tumor is located near a mucosal lined organ. Energy of photon RT is transferred primarily by secondary electrons. If these secondary electrons could be removed in an internal cavity of mucosal lined organ, the mucosa will be spared without compromising the target tumor dose. The purpose of this study was to present a RT dose reduction in near target inner-surface (NTIS) of internal cavity, using Lorentz force of magnetic field. MATERIALS AND METHODS: Tissue equivalent phantoms, composed with a cylinder shaped internal cavity, and adjacent a target tumor part, were developed. The phantoms were irradiated using 6 MV photon beam, with or without 0.3 T of perpendicular magnetic field. Two experimental models were developed: single beam model (SBM) to analyze central axis dose distributions and multiple beam model (MBM) to simulate a clinical case of prostate cancer with rectum. RT dose of NTIS of internal cavity and target tumor area (TTA) were measured. RESULTS: With magnetic field applied, bending effect of dose distribution was visualized. The depth dose distribution of SBM showed 28.1% dose reduction of NTIS and little difference in dose of TTA with magnetic field. In MBM, cross-sectional dose of NTIS was reduced by 33.1% with magnetic field, while TTA dose were the same, irrespective of magnetic field. CONCLUSION: RT dose of mucosal lined organ, located near treatment target, could be modulated by perpendicular magnetic field.
Axis, Cervical Vertebra ; Magnetic Fields* ; Models, Theoretical ; Mucous Membrane ; Prostatic Neoplasms ; Radiation Injuries ; Radiotherapy* ; Rectum

We studied a Monte Carlo simulation of the proton beam delivery system at the National Cancer Center (NCC) using the Geant4 Monte Carlo toolkit and tested its feasibility as a dose verification framework. The Monte Carlo technique for dose calculation methodology has been recognized as the most accurate way for understanding the dose distribution in given materials. In order to take advantage of this methodology for application to externalbeam radiotherapy, a precise modeling of the nozzle elements along with the beam delivery path and correct initial beam characteristics are mandatory. Among three different treatment modes, double/single.scattering, uniform scanning and pencil beam scanning, we have modeled and simulated the double.scattering mode for the nozzle elements, including all components and varying the time and space with the Geant4.8.2 Monte Carlo code. We have obtained simulation data that showed an excellent correlation to the measured dose distributions at a specific treatment depth. We successfully set up the Monte Carlo simulation platform for the NCC proton therapy facility. It can be adapted to the precise dosimetry for therapeutic proton beam use at the NCC. Additional Monte Carlo work for the full proton beam energy range can be performed.
Proton Therapy ; Protons* ; Radiotherapy

This study examined the dosimetric influence of implanted gold markers in proton therapy and the effects of their positions in the spread-out Bragg peak (SOBP) proton beam. The implanted cylindrical gold markers were 3 mm long and 1.2 mm in diameter. The dosimetric influence of the gold markers was determined with markers at various locations in a proton-beam field. Spatial dose distributions were measured using a three-dimensional moving water phantom and a stereotactic diode detector with an effective diameter of 0.5 mm. Also, a film dosimetry was performed using Gafchromic External Beam Treatment (EBT) film. The GEANT4 simulation toolkit was used for Monte-Carlo simulations to confirm the measurements and to construct the dose-volume histogram with implanting markers. Motion data were obtained from the portal images of 10 patients to investigate the effect of organ motions on the dosimetric influence of markers in the presence of a rectal balloon. The underdosed volume due to a single gold marker, in which the dose was less than 95% of a prescribed amount, was 0.15 cc. The underdosed volume due to the presence of a gold marker is much smaller than the target volume. However, the underdosed volume is inside the gross tumor volume and is not smeared out due to translational prostate motions. The positions of gold markers and the conditions of the proton-beam field give different impacts on the dose distribution of a target with implanted gold markers, and should be considered in all clinical proton-based therapies.
Film Dosimetry ; Humans ; Prostate ; Prostatic Neoplasms ; Proton Therapy ; Protons ; Tumor Burden ; Water

PURPOSE: To evaluate the treatment results in early stage non-small cell lung cancer patients who have undergone fiducial-less CyberKnife radiosurgery (CKRS). MATERIALS AND METHODS: From June 2011 to November 2013, 58 patients underwent CKRS at Asan Medical Center for stage I lung cancer. After excluding 14 patients, we retrospectively reviewed the records of the remaining 44 patients. All analyses were performed using SPSS ver. 21. RESULTS: The median age at diagnosis was 75 years. Most patients had inoperable primary lung cancer with a poor pulmonary function test with comorbidity or old age. The clinical stage was IA in 30 patients (68.2%), IB in 14 (31.8%). The mean tumor size was 2.6 cm (range, 1.2 to 4.8 cm), and the tumor was smaller than 2 cm in 12 patients (27.3%). The radiation dose given was 48-60 Gy in 3-4 fractions. In a median follow-up of 23.1 months, local recurrence occurred in three patients (2-year local recurrence-free survival rate, 90.4%) and distant metastasis occurred in 13 patients. All patients tolerated the radiosurgery well, only two patients developing grade 3 dyspnea. The most common complications were radiation-induced fibrosis and pneumonitis. Eight patients died due to cancer progression. CONCLUSION: The results showed that fiducial-less CKRS shows comparable local tumor control and survival rates to those of LINAC-based SABR or CKRS with a fiducial marker. Thus, fiducial-less CKRS using Xsight lung tracking system can be effectively and safely performed for patients with medically inoperable stage I non-small cell lung cancer without any risk of procedure-related complication.
Carcinoma, Non-Small-Cell Lung* ; Chungcheongnam-do ; Comorbidity ; Diagnosis ; Dyspnea ; Fibrosis ; Fiducial Markers ; Follow-Up Studies ; Humans ; Lung ; Lung Neoplasms ; Neoplasm Metastasis ; Pneumonia ; Radiosurgery* ; Recurrence ; Respiratory Function Tests ; Retrospective Studies ; Survival Rate

PURPOSE: To evaluate the treatment results in early stage non-small cell lung cancer patients who have undergone fiducial-less CyberKnife radiosurgery (CKRS). MATERIALS AND METHODS: From June 2011 to November 2013, 58 patients underwent CKRS at Asan Medical Center for stage I lung cancer. After excluding 14 patients, we retrospectively reviewed the records of the remaining 44 patients. All analyses were performed using SPSS ver. 21. RESULTS: The median age at diagnosis was 75 years. Most patients had inoperable primary lung cancer with a poor pulmonary function test with comorbidity or old age. The clinical stage was IA in 30 patients (68.2%), IB in 14 (31.8%). The mean tumor size was 2.6 cm (range, 1.2 to 4.8 cm), and the tumor was smaller than 2 cm in 12 patients (27.3%). The radiation dose given was 48-60 Gy in 3-4 fractions. In a median follow-up of 23.1 months, local recurrence occurred in three patients (2-year local recurrence-free survival rate, 90.4%) and distant metastasis occurred in 13 patients. All patients tolerated the radiosurgery well, only two patients developing grade 3 dyspnea. The most common complications were radiation-induced fibrosis and pneumonitis. Eight patients died due to cancer progression. CONCLUSION: The results showed that fiducial-less CKRS shows comparable local tumor control and survival rates to those of LINAC-based SABR or CKRS with a fiducial marker. Thus, fiducial-less CKRS using Xsight lung tracking system can be effectively and safely performed for patients with medically inoperable stage I non-small cell lung cancer without any risk of procedure-related complication.
Carcinoma, Non-Small-Cell Lung* ; Chungcheongnam-do ; Comorbidity ; Diagnosis ; Dyspnea ; Fibrosis ; Fiducial Markers ; Follow-Up Studies ; Humans ; Lung ; Lung Neoplasms ; Neoplasm Metastasis ; Pneumonia ; Radiosurgery* ; Recurrence ; Respiratory Function Tests ; Retrospective Studies ; Survival Rate