A situational awareness Bayesian network approach for accurate and credible personalized adaptive radiotherapy outcomes prediction in lung cancer patients.

PURPOSE: A situational awareness Bayesian network (SA-BN) approach is developed to improve physicians' trust in the prediction of radiation outcomes and evaluate its performance for personalized adaptive radiotherapy (pART). METHODS: 118 non-small-cell lung cancer patients with their biophysical features were employed for discovery (n = 68) and validation (n = 50) of radiation outcomes prediction modeling. Patients' important characteristics identified by radiation experts to predict individual's tumor local control (LC) or radiation pneumonitis with grade ≥ 2 (RP2) were incorporated as expert knowledge (EK). Besides generating an EK-based naïve BN (EK-NBN), an SA-BN was developed by incorporating the EK features into pure data-driven BN (PD-BN) methods to improve the credibility of LC or / and RP2 prediction. After using area under the free-response receiver operating characteristics curve (AU-FROC) to assess the joint prediction of these outcomes, their prediction performances were compared with a regression approach based on the expert yielded estimates (EYE) penalty and its variants. RESULTS: In addition to improving the credibility of radiation outcomes prediction, the SA-BN approach outperformed the EYE penalty and its variants in terms of the joint prediction of LC and RP2. The value of AU-FROC improves from 0.70 (95% CI: 0.54-0.76) using EK-NBN, to 0.75 (0.65-0.82) using a variant of EYE penalty, to 0.83 (0.75-0.93) using PD-BN and 0.83 (0.77-0.90) using SA-BN; with similar trends in the validation cohort. CONCLUSIONS: The SA-BN approach can provide an accurate and credible human-machine interface to gain physicians' trust in clinical decision-making, which has the potential to be an important component of pART.

Dual-Modality X-Ray-Induced Radiation Acoustic and Ultrasound Imaging for Real-Time Monitoring of Radiotherapy.

Objective. The goal is to increase the precision of radiation delivery during radiotherapy by tracking the movements of the tumor and other surrounding normal tissues due to respiratory and other body motions. Introduction. This work presents the recent advancement of X-ray-induced radiation acoustic imaging (xRAI) technology and the evaluation of its feasibility for real-time monitoring of geometric and morphological misalignments of the X-ray field with respect to the target tissue by combining xRAI with established ultrasound (US) imaging, thereby improving radiotherapy tumor eradication and limiting treatment side effects. Methods. An integrated xRAI and B-mode US dual-modality system was established based on a clinic-ready research US platform. The performance of this dual-modality imaging system was evaluated via experiments on phantoms and ex vivo and in vivo rabbit liver models. Results. This system can alternatively switch between the xRAI and the US modes, with spatial resolutions of 1.1 mm and 0.37 mm, respectively. 300 times signal averaging was required for xRAI to reach a satisfactory signal-to-noise ratio, and a frame rate of 1.1 Hz was achieved with a clinical linear accelerator. The US imaging frame rate was 22 Hz, which is sufficient for real-time monitoring of the displacement of the target due to internal body motion. Conclusion. Our developed xRAI, in combination with US imaging, allows for mapping of the dose deposition in biological samples in vivo, in real-time, during radiotherapy. Impact Statement. The US-based image-guided radiotherapy system presented in this work holds great potential for personalized cancer treatment and better outcomes.