NRG Oncology Assessment of Artificial Intelligence Deep Learning-Based Auto-segmentation for Radiation Therapy: Current Developments, Clinical Considerations, and Future Directions.

Deep learning neural networks (DLNN) in Artificial intelligence (AI) have been extensively explored for automatic segmentation in radiotherapy (RT). In contrast to traditional model-based methods, data-driven AI-based models for auto-segmentation have shown high accuracy in early studies in research settings and controlled environment (single institution). Vendor-provided commercial AI models are made available as part of the integrated treatment planning system (TPS) or as a stand-alone tool that provides streamlined workflow interacting with the main TPS. These commercial tools have drawn clinics' attention thanks to their significant benefit in reducing the workload from manual contouring and shortening the duration of treatment planning. However, challenges occur when applying these commercial AI-based segmentation models to diverse clinical scenarios, particularly in uncontrolled environments. Contouring nomenclature and guideline standardization has been the main task undertaken by the NRG Oncology. AI auto-segmentation holds the potential clinical trial participants to reduce interobserver variations, nomenclature non-compliance, and contouring guideline deviations. Meanwhile, trial reviewers could use AI tools to verify contour accuracy and compliance of those submitted datasets. In recognizing the growing clinical utilization and potential of these commercial AI auto-segmentation tools, NRG Oncology has formed a working group to evaluate the clinical utilization and potential of commercial AI auto-segmentation tools. The group will assess in-house and commercially available AI models, evaluation metrics, clinical challenges, and limitations, as well as future developments in addressing these challenges. General recommendations are made in terms of the implementation of these commercial AI models, as well as precautions in recognizing the challenges and limitations.

Moving Forward in the Next Decade: Radiation Oncology Sciences for Patient-Centered Cancer Care.

In a time of rapid advances in science and technology, the opportunities for radiation oncology are undergoing transformational change. The linkage between and understanding of the physical dose and induced biological perturbations are opening entirely new areas of application. The ability to define anatomic extent of disease and the elucidation of the biology of metastases has brought a key role for radiation oncology for treating metastatic disease. That radiation can stimulate and suppress subpopulations of the immune response makes radiation a key participant in cancer immunotherapy. Targeted radiopharmaceutical therapy delivers radiation systemically with radionuclides and carrier molecules selected for their physical, chemical, and biochemical properties. Radiation oncology usage of "big data" and machine learning and artificial intelligence adds the opportunity to markedly change the workflow for clinical practice while physically targeting and adapting radiation fields in real time. Future precision targeting requires multidimensional understanding of the imaging, underlying biology, and anatomical relationship among tissues for radiation as spatial and temporal "focused biology." Other means of energy delivery are available as are agents that can be activated by radiation with increasing ability to target treatments. With broad applicability of radiation in cancer treatment, radiation therapy is a necessity for effective cancer care, opening a career path for global health serving the medically underserved in geographically isolated populations as a substantial societal contribution addressing health disparities. Understanding risk and mitigation of radiation injury make it an important discipline for and beyond cancer care including energy policy, space exploration, national security, and global partnerships.

Advancing Targeted Radionuclide Therapy Through the National Cancer Institute's Small Business Innovation Research Pathway.

The Small Business Innovation Research (SBIR) and Small Business Technology Transfer (STTR) programs of the National Cancer Institute (NCI) are congressionally mandated set-aside programs that provide research funding to for-profit small businesses for the development of innovative technologies and treatments that serve the public good. These two programs have an annual budget of $159 million (in 2017) and serve as the NCI's main engine of innovation for developing and commercializing cancer technologies. In collaboration with the NCI's Radiation Research Program, the NCI SBIR Development Center published in 2015-2017 three separate requests for proposals from small businesses for the development of systemic targeted radionuclide therapy (TRT) technologies to treat cancer. TRT combines a cytotoxic radioactive isotope with a molecularly targeted agent to produce an anticancer therapy capable of treating local or systemic disease. This article summarizes the NCI SBIR funding solicitations for the development of TRTs and the research proposals funded through them.

Rapid RBE-Weighted Proton Radiation Dosimetry Risk Assessment.

Proton therapy dose is affected by relative biological effectiveness differently than X-ray therapies. The current clinically accepted weighting factor is 1.1 at all positions along the depth-dose profile. However, the relative biological effectiveness correlates with the linear energy transfer, cell or tissue type, and the dose per fraction causing variation of relative biological effectiveness along the depth-dose profile. In this article, we present a simple relative biological effectiveness-weighted treatment planning risk assessment algorithm in 2-dimensions and compare the results with those derived using the standard relative biological effectiveness of 1.1. The isodose distribution profiles for beams were accomplished using matrices that represent coplanar intersecting beams. These matrices were combined and contoured using MATLAB to achieve the distribution of dose. There are some important differences in dose distribution between the dose profiles resulting from the use of relative biological effectiveness = 1.1 and the empirically derived depth-dependent values of relative biological effectiveness. Significant hot spots of up to twice the intended dose are indicated in some beam configurations. This simple and rapid risk analysis could quickly evaluate the safety of various dose delivery schema.