Adaptive Mathematical Model of Tumor Response to Radiotherapy Based on CBCT Data

A reinforcement learning approach for finding optimal policy of adaptive radiation therapy considering uncertain tumor biological response

Recent studies have shown that a tumor's biological response to radiation varies over time and has a dynamic nature. Dynamic biological features of tumor cells underscore the importance of using fractionation and adapting the treatment plan to tumor volume changes in radiation therapy treatment. Adaptive radiation therapy (ART) is an iterative process to adjust the dose of radiation in response to potential changes during the treatment. One of the key challenges in ART is how to determine the optimal timing of adaptations corresponding to tumor response to radiation. This paper aims to develop an automated treatment planning framework incorporating the biological uncertainties to find the optimal adaptation points to achieve a more effective treatment plan. First, a dynamic tumor-response model is proposed to predict weekly tumor volume regression during the period of radiation therapy treatment based on biological factors. Second, a Reinforcement Learning (RL) framework is developed to find the optimal adaptation points for ART considering the uncertainty in biological factors with the goal of achieving maximum final tumor control while minimizing or maintaining the toxicity level of the organs at risk (OARs) per the decision-maker's preference. Third, a beamlet intensity optimization model is solved using the predicted tumor volume at each adaptation point. The performance of the proposed RT treatment planning framework is tested using a clinical non-small cell lung cancer (NSCLC) case. The results are compared with the conventional fractionation schedule (i.e., equal dose fractionation) as a reference plan. The results show that the proposed approach performed well in achieving a robust optimal ART treatment plan under high uncertainty in the biological parameters. The ART plan outperformed the reference plan by increasing the mean biological effective dose (BED) value of the tumor by 2.01%, while maintaining the OAR BED within +0.5% and reducing the variability, in terms of the interquartile range (IQR) of tumor BED, by 25%.

Deep Reinforcement Learning for Fractionated Radiotherapy in Non-Small Cell Lung Carcinoma

Lung cancer is by far the leading cause of cancer death among both men and women. Radiation therapy is one of the main approaches to lung cancer treatment, and its planning is crucial for the therapy outcome. However, the current practice that uniformly delivers the dose does not take into account the patient-specific tumour features that may affect treatment success. Since radiation therapy is by its very nature a sequential procedure, Deep Reinforcement Learning (DRL) is a well-suited methodology to overcome this limitation. In this respect, in this work we present a DRL controller optimizing the daily dose fraction delivered to the patient on the basis of CT scans collected over time during the therapy, offering a personalized treatment not only for volume adaptation, as currently intended, but also for daily fractionation. Furthermore, this contribution introduces a virtual radiotherapy environment based on a set of ordinary differential equations modelling the tissue radiosensitivity by combining both the effect of the radiotherapy treatment and cell growth. Their parameters are estimated from CT scans routinely collected using the Particle Swarm Optimization algorithm. This permits the DRL to learn the optimal behaviour through an iterative trial and error process with the environment. We performed several experiments considering three rewards functions modelling treatment strategies with different tissue aggressiveness and two exploration strategies for the exploration-exploitation dilemma. The results show that our DRL approach can adapt to radiation therapy treatment, optimizing its behaviour according to the different reward functions and outperforming the current clinical practice.

IMRT and brachytherapy comparison in gynaecological cancer treatment: thinking over dosimetry and radiobiology

Background

The role of radiotherapy and brachytherapy in the management of locally advanced cervical and endometrial cancer is well established. However, in some cases, intracavitary brachytherapy (ICBRT) is not recommended or cannot be carried out. We aimed to investigate whether external-beam irradiation delivered by means of intensity-modulated radiation therapy (IMRT) might replace ICBRT in gynaecological cancer when the standard ICBRT boost delivering cannot be administered for technical or clinical reasons.

Materials and methods

Fifteen already delivered treatments for gynaecological cancer patients were analysed. The treatments were performed through 3-dimensional conformal radiotherapy (3D-CRT) to the whole-pelvis up to the dose of 45–50.4 Gy followed by a boost dose administered with ICBRT in high-dose-rate or pulsed-dose-rate modality. For each patient, IMRT plans were elaborated to mimic the ICBRT. We analysed the ICBRT boost versus IMRT boost in terms of dosimetric and radiobiological aspects.

Results

Mean conformity index value calculated on boost volume was 0.73 for ICBRT and 0.97 for IMRT. Mean conformation number was 0.24 for ICBRT boost and 0.78 for IMRT boost. Mean normal tissue complication probability (NTCP) values for 3D-CRT plus ICBRT and for IMRT (pelvis plus boost) were, respectively, 28% and 5% for rectum; 1.5% and 0.1% for urinary bladder and 8.9% and 6.1% for bowel.

Conclusions

Our findings suggest that IMRT may represent a viable alternative in delivering the boost in patients diagnosed with gynaecological cancer not amenable to ICBRT.

A Review of Mathematical Models for Tumor Dynamics and Treatment Resistance Evolution of Solid Tumors

Increasing knowledge of intertumor heterogeneity, intratumor heterogeneity, and cancer evolution has improved the understanding of anticancer treatment resistance. A better characterization of cancer evolution and subsequent use of this knowledge for personalized treatment would increase the chance to overcome cancer treatment resistance. Model‐based approaches may help achieve this goal. In this review, we comprehensively summarized mathematical models of tumor dynamics for solid tumors and of drug resistance evolution. Models displayed by ordinary differential equations, algebraic equations, and partial differential equations for characterizing tumor burden dynamics are introduced and discussed. As for tumor resistance evolution, stochastic and deterministic models are introduced and discussed. The results may facilitate a novel model‐based analysis on anticancer treatment response and the occurrence of resistance, which incorporates both tumor dynamics and resistance evolution. The opportunities of a model‐based approach as discussed in this review can be of great benefit for future optimizing and personalizing anticancer treatment.

Model-Supported Radiotherapy Personalization: In silico Test of Hyper- and Hypo-Fractionation Effects

The need for radiotherapy personalization is now widely recognized, however, it would require considerations not only on the probability of control and survival of the tumor, but also on the possible toxic effects, on the quality of the expected life and the economic efficiency of the treatment. In this paper, we propose a simulation tool that can be integrated into a decision support system that allows selection of the most suitable irradiation regimen. We used a macroscale mathematical model, which includes active and necrotic tumor dynamics and the role of oxygenation to simulate the effects of different hypo-/hyper-fractional regimens using retrospective data of seven virtual patients from as many cervical cancer patients used for its training in a previous study. The results confirmed the heterogeneous response across the patients as a function of treatment regimen and suggested the tumor growth rate as a main factor in the final tumor regression. In addition to the maximum regression, another criterion was suggested to select the most suitable regimen (minimum number of fractions to achieve a regression of 80%) minimizing the toxicity and maximizing the cost-effectiveness ratio. Despite the lack of direct validation, the simulation results are in agreement with the literature findings that suggest the need for hypo-fractionated regimens in case of aggressive tumor phenotypes. Finally, the paper suggests a possible exploitation of the model within a tool to support clinical decisions.