Cancer risk assessment in modern radiotherapy workflow with medical big data.

Modern radiotherapy (RT) is being enriched by big digital data and intensive technology. Multimodality image registration, intelligence-guided planning, real-time tracking, image-guided RT (IGRT), and automatic follow-up surveys are the products of the digital era. Enormous digital data are created in the process of treatment, including benefits and risks. Generally, decision making in RT tries to balance these two aspects, which is based on the archival and retrieving of data from various platforms. However, modern risk-based analysis shows that many errors that occur in radiation oncology are due to failures in workflow. These errors can lead to imbalance between benefits and risks. In addition, the exact mechanism and dose-response relationship for radiation-induced malignancy are not well understood. The cancer risk in modern RT workflow continues to be a problem. Therefore, in this review, we develop risk assessments based on our current knowledge of IGRT and provide strategies for cancer risk reduction. Artificial intelligence (AI) such as machine learning is also discussed because big data are transforming RT via AI.

A parameterized model for mean urinary inflow rate and its preliminary application in radiotherapy for cervical cancer.

Forty-nine patients with stage IIb cervical cancer were included to investigate the changes in bladder volume in response to different approaches to maintaining consistent bladder filling. The impacts of age (P age), water consumption (P wat ), and body mass index (BMI, P bmi ) on the mean urinary inflow rate (v tot ) were analysed. The bladder volume (BV) increased linearly over time. A large variation in v tot among individuals was observed, ranging from 0.19 to 5.13 ml/min. The v tot was correlated with P age (R = -0.53, p = 0.01) and P wat (R = 0.84, p = 0.00), and no correlation between v tot and P bmi was found (p > 0.05). Therefore, v tot could be parameterized using two methods: multivariable linear regression and iterative fitting. There was no statistically significant difference between the two methods. The model accuracy was successfully assessed with several validation tests for patients with good compliance (79.2% of all patients), and the proportion of radiotherapy (RT) fractions with zero wait time (one ultrasound (US) scan) increased from 6.5% to 41.2%. The optimal US scanning number and RT time could be provided using this model. This adaptive RT approach could reduce patient discomfort caused by holding onto urine and reduce technician labour as well as cost.