Background: Hypofractionated whole-breast irradiation is a standard adjuvant therapy for early-stage breast cancer. This study evaluates the plan quality and efficacy of an in-house-developed automated radiotherapy treatment planning algorithm for hypofractionated whole-breast radiotherapy. Methods: A cohort of 99 node-negative left-sided breast cancer patients completed hypofractionated whole-breast irradiation with six-field IMRT for 42.56 Gy in 16 daily fractions from year 2016 to 2018 at a tertiary center were re-planned with an in-house-developed algorithm. The automated plan-generating C#-based program is developed in a Varian ESAPI research mode. The dose-volume histogram (DVH) and other dosimetric parameters of the automated and manual plans were directly compared. Results: The average time for generating an autoplan was 5 to 6 min, while the manual planning time ranged from 1 to 1.5 h. There was only a small difference in both the gantry angles and the collimator angles between the autoplans and the manual plans (ranging from 2.2 to 5.3 degrees). Autoplans and manual plans performed similarly well in hotspot volume and PTV coverage, with the autoplans performing slightly better in the ipsilateral-lung-sparing dose parameters but were inferior in contralateral-breast-sparing. The autoplan dosimetric quality did not vary with different breast sizes, but for manual plans, there was worse ipsilateral-lung-sparing (V_4Gy) in larger or medium-sized breasts than in smaller breasts. Autoplans were generally superior than manual plans in CI (1.24 ± 0.06 vs. 1.30 ± 0.09, p < 0.01) and MU (1010 ± 46 vs. 1205 ± 187, p < 0.01). Conclusions: Our study presents a well-designed standardized fully automated planning algorithm for optimized whole-breast radiotherapy treatment plan generation. A large cohort of 99 patients were re-planned and retrospectively analyzed. The automated plans demonstrated similar or even better dosimetric quality and efficacy in comparison with the manual plans. Our result suggested that the autoplanning algorithm has great clinical applicability potential.

To determine whether radiotherapy (RT) can increase pelvic fracture risk in rectal cancer survivors. Rectal cancer patients who underwent curative surgery between 1996 and 2011 in Taiwan were retrospectively studied using the National Health Insurance Research Database (NHIRD) of Taiwan. ICD‐9 Codes 808, 805.4‐805.7, 806.4‐806.7, and 820 (including pelvic, sacrum, lumbar, and femoral neck fracture) were defined as pelvic fracture. Propensity scores for RT, age, and sex were used to perform one‐to‐one matches between the RT and non‐RT group. Risks of pelvic and arm fractures were compared by multivariable Cox regression. Of the 32 689 patients, 7807 (23.9%) received RT, and 1616 suffered from a pelvic fracture (incidence rate: 1.17/100 person‐years). The median time to pelvic fracture was 2.47 years. After matching, 6952 patients each in the RT and non‐RT groups were analyzed. RT was associated with an increased risk of pelvic fractures in the multivariable Cox model (hazard ratio (HR): 1.246, 95% confidence interval (CI): 1.037‐1.495, P = 0.019) but not with arm fractures (HR: 1.013, 95% CI: 0.814‐1.259, P = 0.911). Subgroup analyses revealed that RT was associated with a higher pelvic fracture rate in women (HR: 1.431, 95% CI: 1.117‐1.834) but not in men, and the interaction between sex and RT was significant (P = 0.03). The HR of pelvic fracture increased 2‐4 years after RT (HR: 1.707, 95% CI: 1.150‐2.534, P = 0.008). An increased risk of pelvic fracture is noted in rectal cancer survivors, especially women, who receive RT.

The dosimetric leaf gap (DLG) and multileaf collimator (MLC) transmission are two important systematic parameters used to model the rounded MLC leaf ends effect when commissioning an Eclipse treatment planning system (TPS). Determining the optimal DLG is a time consuming process. This study develops a simple and reliable method for determining the DLG using the cross-field dose width. A Varian TrueBeam linac with 6 MV, 10 MV, 6 MV flattening filter free (FFF) and 10 MV FFF photon beams and equipped with the 120 Millennium MLC and the Eclipse™ TPS was used in this study. Integral sliding fields and static slit MLC field doses with different gap widths were measured with an ionization chamber and GAFCHROMIC EBT3 films, respectively. Measurements were performed for different beam energies and at depths of 5 and 10 cm. DLGs were derived from a linear extrapolation to zero dose and intercepting at the gap width axis. In the ion chamber measurements method, the average MLC leaf transmission to the gap reading for each gap (RgT) were calculated with nominal and cross-field dose widths, respectively. The cross-field dose widths were determined according to the dose profile measured with EBT3 films. Additionally, the optimal DLG values were determined using plan dose measurements, as the value that produced the closest agreement between the planned and measured doses. DLGs derived from the nominal and cross-field dose width, the film measurements, and the optimal process, were obtained and compared. The DLG values are insensitive to the variations in depth (within 0.07 mm). DLGs derived from nominal gap widths showed a significantly lower values (with difference about 0.5 mm) than that from cross-field dose widths and from film measurements and from plan optimal values. The method in deriving DLGs by correcting the nominal gap widths to the cross-field dose widths has shown good agreements to the plan optimal values (with difference within 0.21 mm). The DLG values derived from the cross-field dose width method were consistent with the values derived from film measurements and from the plan optimal process. A simple and reliable method to determine DLG for rounded leaf-end MLC systems was established. This method provides a referable DLG value required during TPS commissioning.

The COVID-19 pandemic has caused a high rate of infection, and thus effective epidemic prevention measures of avoiding the second spread of COVID-19 in hospitals are major challenges for healthcare workers. Hospitals, where medicines are collected, are vulnerable to the rapid spread of COVID-19. Using the remote health monitoring technology of the Internet of Things (IoT) to automatically monitor and record the basic medical information of patients, reduce the workload of healthcare workers, and avoid direct contact with healthcare workers to cause secondary infections is an important research topic. This research proposes a new artificial intelligence solution based on the IoT, replacing existing medicine stations and recognizing medicine bags through the state-of-the-art optical character recognition (OCR) model and PP-OCR v2. The use of OCR in identification of medicine bags can replace healthcare workers in data recording. In addition, this research proposes an administrator management and monitoring system to monitor the equipment and provide a mobile application for patients to check the latest status of medicine bags in real time, and record their medication times. The results of the experiments indicate that the recognition model works very well in different conditions (up to 80.76% in PP-OCR v2 and 94.22% in PGNet), which supports both Chinese and English languages.