Modeling Radiotherapy Induced Normal Tissue Complications: An Overview beyond Phenomenological Models

Heterogeneity of absorbed dose distribution in kidney tissues and dose-response modelling of nephrotoxicity in radiopharmaceutical therapy with beta-particle emitters: A review

Absorbed dose heterogeneity in kidney tissues is an important issue in radiopharmaceutical therapy. The effect of absorbed dose heterogeneity in nephrotoxicity is, however, not fully understood yet, which hampers the implementation of treatment optimization by obscuring the interpretation of clinical response data and the selection of optimal treatment options. Although some dosimetry methods have been developed for kidney dosimetry to the level of microscopic renal substructures, the clinical assessment of the microscopic distribution of radiopharmaceuticals in kidney tissues currently remains a challenge. This restricts the anatomical resolution of clinical dosimetry, which hinders a thorough clinical investigation of the impact of absorbed dose heterogeneity. The potential of absorbed dose-response modelling to support individual treatment optimization in radiopharmaceutical therapy is recognized and gaining attraction. However, biophysical modelling is currently underexplored for the kidney, where particular modelling challenges arise from the convolution of a complex functional organization of renal tissues with the function-mediated dose distribution of radiopharmaceuticals. This article reviews and discusses the heterogeneity of absorbed dose distribution in kidney tissues and the absorbed dose-response modelling of nephrotoxicity in radiopharmaceutical therapy. The review focuses mainly on the peptide receptor radionuclide therapy with beta-particle emitting somatostatin analogues, for which the scientific literature reflects over two decades of clinical experience. Additionally, detailed research perspectives are proposed to address various identified challenges to progress in this field.

AAPM Task Group Report 267: A joint AAPM GEC-ESTRO report on biophysical models and tools for the planning and evaluation of brachytherapy

Brachytherapy utilizes a multitude of radioactive sources and treatment techniques that often exhibit widely different spatial and temporal dose delivery patterns. Biophysical models, capable of modeling the key interacting effects of dose delivery patterns with the underlying cellular processes of the irradiated tissues, can be a potentially useful tool for elucidating the radiobiological effects of complex brachytherapy dose delivery patterns and for comparing their relative clinical effectiveness. While the biophysical models have been used largely in research settings by experts, it has also been used increasingly by clinical medical physicists over the last two decades. A good understanding of the potentials and limitations of the biophysical models and their intended use is critically important in the widespread use of these models. To facilitate meaningful and consistent use of biophysical models in brachytherapy, Task Group 267 (TG-267) was formed jointly with the American Association of Physics in Medicine (AAPM) and The Groupe Européen de Curiethérapie and the European Society for Radiotherapy & Oncology (GEC-ESTRO) to review the existing biophysical models, model parameters, and their use in selected brachytherapy modalities and to develop practice guidelines for clinical medical physicists regarding the selection, use, and interpretation of biophysical models. The report provides an overview of the clinical background and the rationale for the development of biophysical models in radiation oncology and, particularly, in brachytherapy; a summary of the results of literature review of the existing biophysical models that have been used in brachytherapy; a focused discussion of the applications of relevant biophysical models for five selected brachytherapy modalities; and the task group recommendations on the use, reporting, and implementation of biophysical models for brachytherapy treatment planning and evaluation. The report concludes with discussions on the challenges and opportunities in using biophysical models for brachytherapy and with an outlook for future developments.

Extending the relative seriality formalism for interpretable deep learning of normal tissue complication probability models

We formally demonstrate that the relative seriality (RS) model of normal tissue complication probability (NTCP) can be recast as a simple neural network with one convolutional and one pooling layer. This approach enables us to systematically construct deep relative seriality networks (DRSNs), a new class of mechanistic generalizations of the RS model with radiobiologically interpretable parameters amenable to deep learning. To demonstrate the utility of this formulation, we analyze a simplified example of xerostomia due to irradiation of the parotid gland during alpha radiopharmaceutical therapy. Using a combination of analytical calculations and numerical simulations, we show for both the RS and DRSN cases that the ability of the neural network to generalize without overfitting is tied to ‘stiff’ and ‘sloppy’ directions in the parameter space of the mechanistic model. These results serve as proof-of-concept for radiobiologically interpretable deep learning of NTCP, while simultaneously yielding insight into how such techniques can robustly generalize beyond the training set despite uncertainty in individual parameters.

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

In order to limit radiotherapy (RT)-related side effects, effective toxicity prediction and assessment schemes are essential. In recent years, the growing interest toward artificial intelligence and machine learning (ML) within the science community has led to the implementation of innovative tools in RT. Several researchers have demonstrated the high performance of ML-based models in predicting toxicity, but the application of these approaches in clinics is still lagging, partly due to their low interpretability. Therefore, an overview of contemporary research is needed in order to familiarize practitioners with common methods and strategies. Here, we present a review of ML-based models for predicting and classifying RT-induced complications from both a methodological and a clinical standpoint, focusing on the type of features considered, the ML methods used, and the main results achieved. Our work overviews published research in multiple cancer sites, including brain, breast, esophagus, gynecological, head and neck, liver, lung, and prostate cancers. The aim is to define the current state of the art and main achievements within the field for both researchers and clinicians.

First-passage times and normal tissue complication probabilities in the limit of large populations

The time of a stochastic process first passing through a boundary is important to many diverse applications. However, we can rarely compute the analytical distribution of these first-passage times. We develop an approximation to the first and second moments of a general first-passage time problem in the limit of large, but finite, populations using Kramers–Moyal expansion techniques. We demonstrate these results by application to a stochastic birth-death model for a population of cells in order to develop several approximations to the normal tissue complication probability (NTCP): a problem arising in the radiation treatment of cancers. We specifically allow for interaction between cells, via a nonlinear logistic growth model, and our approximations capture the effects of intrinsic noise on NTCP. We consider examples of NTCP in both a simple model of normal cells and in a model of normal and damaged cells. Our analytical approximation of NTCP could help optimise radiotherapy planning, for example by estimating the probability of complication-free tumour under different treatment protocols.