Brachytherapy Workflow Practices: Analysis of Different Workflow Scenarios in Patients With Cervical Cancer and Impact on IGBT Implementation-An IAEA Study.

PURPOSE: The workflow of brachytherapy (BT) is an essential aspect of treatment to consider in image-guided brachytherapy (IGBT). It has an overarching effect influencing patient throughput and the number of cancer treatments that can be performed as it occupies equipment, space, and personnel. There is limited research addressing this issue. Under the International Atomic Energy Agency's Coordinated Research Activity titled IGBT for cervix cancer: An implementation study, our study analyzes various scenarios in the clinical workflow of BT delivery for cervical cancer. It aims to determine the extent to which these scenarios allow the routine implementation of IGBT. With this information, current barriers and individualized adaptations to efficient workflows can be identified to enhance the global application of IGBT, leading to better cervical cancer treatment. MATERIALS AND METHODS: A web-based poll of questions regarding practices in BT workflow was presented to 62 participants from low-, lower middle-, upper middle-, and high-income countries (19 countries). RESULTS: This study highlighted diversity in BT practices across countries, income levels, and regions. It identified variations in workflow, patient throughput, and resource availability, which can have implications for the efficiency and quality of BT treatments. Scenario A, utilizing multiple locations for the steps of the BT procedure, was the most commonly used. The availability of resources, such as imaging devices and trained personnel, varied among the participating centers and remained challenging for IGBT implementation and sustainability. CONCLUSION: The design of the BT facility plays a vital role in improving efficiency, with a dedicated BT suite contributing to an efficient workflow but limiting patient throughput, especially for high-volume centers. Although IGBT is effective, its implementation requires consideration of various logistical challenges and should be individualized.

Radiation therapy dose prediction for left-sided breast cancers using two-dimensional and three-dimensional deep learning models.

PURPOSE: To develop a deep learning model capable of producing clinically acceptable dose distributions for left-sided breast cancers for 3D-CRT while exploring the use of two-dimensional versus three-dimensional anatomical data. METHODS: Two deep learning models, a two-dimensional and three-dimensional model, based on U-net architecture were trained to predict dose distribution given anatomical information and dose prescription. The input consists of 6 channels including the patient CT along with binary masks for four OARs and one covering the volume receiving 95% dose (based on the clinical plan). A training set of 120 patients was compiled and used with 5-fold cross validation. The best performing model from the 5 folds was analyzed with a test set of 25 patients using cumulative DVH, mean differences in mean dose to OARs represented by box plots, and V20 of the left lung. RESULTS: We have shown that both models are capable of producing clinically acceptable dose distributions, with the 3D outperforming the 2D model. The average dose difference for mean dose is within 0.02% of the dose prescription for both models. The V20 from the predicted dose distributions are comparable with the V20 from clinical plans, where predictions tend to be slightly under. CONCLUSIONS: Based on the results, the models could be implemented clinically to produce dose distributions that can be used as a reference to ensure the most ideal plan is used. Each prediction is patient-specific while requiring minimal time and information creating a new standard in plan quality without hindering the planning process.