Current status and future developments in predicting outcomes in radiation oncology.

Advancements in data-driven technologies and the inclusion of information-rich multiomics features have significantly improved the performance of outcomes modeling in radiation oncology. For this current trend to be sustainable, challenges related to robust data modeling such as small sample size, low size to feature ratio, noisy data, as well as issues related to algorithmic modeling such as complexity, uncertainty, and interpretability, need to be mitigated if not resolved. Emerging computational technologies and new paradigms such as federated learning, human-in-the-loop, quantum computing, and novel interpretability methods show great potential in overcoming these challenges and bridging the gap towards precision outcome modeling in radiotherapy. Examples of these promising technologies will be presented and their potential role in improving outcome modeling will be discussed.

Management of Motion and Anatomical Variations in Charged Particle Therapy: Past, Present, and Into the Future.

The major aim of radiation therapy is to provide curative or palliative treatment to cancerous malignancies while minimizing damage to healthy tissues. Charged particle radiotherapy utilizing carbon ions or protons is uniquely suited for this task due to its ability to achieve highly conformal dose distributions around the tumor volume. For these treatment modalities, uncertainties in the localization of patient anatomy due to inter- and intra-fractional motion present a heightened risk of undesired dose delivery. A diverse range of mitigation strategies have been developed and clinically implemented in various disease sites to monitor and correct for patient motion, but much work remains. This review provides an overview of current clinical practices for inter and intra-fractional motion management in charged particle therapy, including motion control, current imaging and motion tracking modalities, as well as treatment planning and delivery techniques. We also cover progress to date on emerging technologies including particle-based radiography imaging, novel treatment delivery methods such as tumor tracking and FLASH, and artificial intelligence and discuss their potential impact towards improving or increasing the challenge of motion mitigation in charged particle therapy.

Imaging response assessment for predicting outcomes after bioselection chemotherapy in larynx cancer: A secondary analysis of two prospective trials.

BACKGROUND AND PURPOSE: Bioselection with induction chemotherapy in larynx cancer is associated with excellent larynx preservation and disease-specific survival but requires visual inspection of the primary tumor. We retrospectively compare clinical and imaging response in bioselected patients to develop predictive models of surgeon-assessed response (SR), laryngectomy-free survival (LFS), and overall survival (OS) in bioselected patients. MATERIALS AND METHODS: In a secondary analysis of patients on two single-institution bioselection trials, model building used a regularized regression model (elastic-net) and applied nested cross-validation. Logistic regression-based model was used to predict SR and Cox proportional hazard-based models were used to predict LFS and OS. RESULTS: In 115 patients with a median age of 57 years, most patients had supraglottic tumors (73.0%) and T3/T4 disease (94.8%). Definitive treatment was chemoradiation in 76.5% and laryngectomy in 23.5%. Change in primary tumor (OR = 5.78, p < 0.001) and N-classification (OR = 1.64, p = 0.003) predicted SR (AUC 0.847). Change in tumor volume (HR = 0.58, p < 0.001) predicted LFS (c-index 0.724). N-classification (HR = 1.48, p = 0.04) and pre-chemotherapy tumor volume (HR = 1.30, p = 0.174) predicted OS (c-index 0.552). CONCLUSIONS: Imaging offers a non-invasive opportunity to evaluate response to induction chemotherapy, complementary to surgeon assessment. Further evaluation of approaches to bioselection that optimize generalizability of this paradigm are needed, and clinical trials utilizing imaging to predict outcomes including LFS are warranted.

Dynamic stochastic deep learning approaches for predicting geometric changes in head and neck cancer.

Objective.Modern radiotherapy stands to benefit from the ability to efficiently adapt plans during treatment in response to setup and geometric variations such as those caused by internal organ deformation or tumor shrinkage. A promising strategy is to develop a framework, which given an initial state defined by patient-attributes, can predict future states based on pre-learned patterns from a well-defined patient population.Approach.Here, we investigate the feasibility of predicting patient anatomical changes, defined as a joint state of volume and daily setup changes, across a fractionated treatment schedule using two approaches. The first is based on a new joint framework employing quantum mechanics in combination with deep recurrent neural networks, denoted QRNN. The second approach is developed based on a classical framework, which models patient changes as a Markov process, denoted MRNN. We evaluated the performance characteristics of these two approaches on a dataset of 125 head and neck cancer patients, which was supplemented by synthetic data generated using a generative adversarial network. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) scores.Main results.The MRNN framework had slightly better performance than the QRNN framework, with MRNN (QRNN) validation AUC scores of 0.742±0.021 (0.675±0.036), 0.709±0.026 (0.656±0.021), 0.724±0.036 (0.652±0.044), and 0.698±0.016 (0.605±0.035) for system state vector sizes of 4, 6, 8, and 10, respectively. Of these, only the results from the two higher order states had statistically significant differences(p<0.05).A similar trend was also observed when the models were applied to an external testing dataset of 20 patients, yielding MRNN (QRNN) AUC scores of 0.707 (0.623), 0.687 (0.608), 0.723 (0.669), and 0.697 (0.609) for states vectors sizes of 4, 6, 8, and 10, respectively.Significance.These results suggest that both stochastic models have potential value in predicting patient changes during the course of adaptive radiotherapy.

Needle-compatible miniaturized optoelectronic sensor for pancreatic cancer detection.

Pancreatic cancer is one of the deadliest cancers, with a 5-year survival rate of <10%. The current approach to confirming a tissue diagnosis, endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA), requires a time-consuming, qualitative cytology analysis and may be limited because of sampling error. We designed and engineered a miniaturized optoelectronic sensor to assist in situ, real-time, and objective evaluation of human pancreatic tissues during EUS-FNA. A proof-of-concept prototype sensor, compatible with a 19-gauge hollow-needle commercially available for EUS-FNA, was constructed using microsized optoelectronic chips and microfabrication techniques to perform multisite tissue optical sensing. In our bench-top verification and pilot validation during surgery on freshly excised human pancreatic tissues (four patients), the fabricated sensors showed a comparable performance to our previous fiber-based system. The flexibility in source-detector configuration using microsized chips potentially allows for various light-based sensing techniques inside a confined channel such as a hollow needle or endoscopy.

Introduction to machine and deep learning for medical physicists.

Recent years have witnessed tremendous growth in the application of machine learning (ML) and deep learning (DL) techniques in medical physics. Embracing the current big data era, medical physicists equipped with these state-of-the-art tools should be able to solve pressing problems in modern radiation oncology. Here, a review of the basic aspects involved in ML/DL model building, including data processing, model training, and validation for medical physics applications is presented and discussed. Machine learning can be categorized based on the underlying task into supervised learning, unsupervised learning, or reinforcement learning; each of these categories has its own input/output dataset characteristics and aims to solve different classes of problems in medical physics ranging from automation of processes to predictive analytics. It is recognized that data size requirements may vary depending on the specific medical physics application and the nature of the algorithms applied. Data processing, which is a crucial step for model stability and precision, should be performed before training the model. Deep learning as a subset of ML is able to learn multilevel representations from raw input data, eliminating the necessity for hand crafted features in classical ML. It can be thought of as an extension of the classical linear models but with multilayer (deep) structures and nonlinear activation functions. The logic of going "deeper" is related to learning complex data structures and its realization has been aided by recent advancements in parallel computing architectures and the development of more robust optimization methods for efficient training of these algorithms. Model validation is an essential part of ML/DL model building. Without it, the model being developed cannot be easily trusted to generalize to unseen data. Whenever applying ML/DL, one should keep in mind, according to Amara's law, that humans may tend to overestimate the ability of a technology in the short term and underestimate its capability in the long term. To establish ML/DL role into standard clinical workflow, models considering balance between accuracy and interpretability should be developed. Machine learning/DL algorithms have potential in numerous radiation oncology applications, including automatizing mundane procedures, improving efficiency and safety of auto-contouring, treatment planning, quality assurance, motion management, and outcome predictions. Medical physicists have been at the frontiers of technology translation into medicine and they ought to be prepared to embrace the inevitable role of ML/DL in the practice of radiation oncology and lead its clinical implementation.

Quantum-inspired algorithm for radiotherapy planning optimization.

PURPOSE: Modern inverse radiotherapy treatment planning requires nonconvex, large-scale optimizations that must be solved within a clinically feasible timeframe. We have developed and tested a quantum-inspired, stochastic algorithm for intensity-modulated radiotherapy (IMRT): quantum tunnel annealing (QTA). By modeling the likelihood probability of accepting a higher energy solution after a particle tunneling through a potential energy barrier, QTA features an additional degree of freedom (the barrier width, w) not shared by traditional stochastic optimization methods such as Simulated Annealing (SA). This additional degree of freedom can improve convergence rates and achieve a more efficient and, potentially, effective treatment planning process. METHODS: To analyze the character of the proposed QTA algorithm, we chose two stereotactic body radiation therapy (SBRT) liver cases of variable complexity. The "easy" first case was used to confirm functionality, while the second case, with a more challenging geometry, was used to characterize and evaluate the QTA algorithm performance. Plan quality was assessed using dose-volume histogram-based objectives and dose distributions. Due to the stochastic nature of the solution search space, extensive tests were also conducted to determine the optimal smoothing technique, ensuring balance between plan deliverability and the resulting plan quality. QTA convergence rates were investigated in relation to the chosen barrier width function, and QTA and SA performances were compared regarding sensitivity to the choice of solution initializations, annealing schedules, and complexity of the dose-volume constraints. Finally, we investigated the extension from beamlet intensity optimization to direct aperture optimization (DAO). Influence matrices were calculated using the Eclipse scripting application program interface (API), and the optimizations were run on the University of Michigan's high-performance computing cluster, Flux. RESULTS: Our results indicate that QTA's barrier-width function can be tuned to achieve faster convergence rates. The QTA algorithm reached convergence up to 46.6% faster than SA for beamlet intensity optimization and up to 26.8% faster for DAO. QTA and SA were ultimately found to be equally insensitive to the initialization process, but the convergence rate of QTA was found to be more sensitive to the complexity of the dose-volume constraints. The optimal smoothing technique was found to be a combination of a Laplace-of-Gaussian (LOG) edge-finding filter implemented as a penalty within the objective function and a two-dimensional Savitzky-Golay filter applied to the final iteration; this achieved total monitor units more than 20% smaller than plans optimized by commercial treatment planning software. CONCLUSIONS: We have characterized the performance of a stochastic, quantum-inspired optimization algorithm, QTA, for radiotherapy treatment planning. This proof of concept study suggests that QTA can be tuned to achieve faster convergence than SA; therefore, QTA may be a good candidate for future knowledge-based or adaptive radiation therapy applications.

Compact dual-mode diffuse optical system for blood perfusion monitoring in a porcine model of microvascular tissue flaps.

In reconstructive surgery, the ability to detect blood flow interruptions to grafted tissue represents a critical step in preventing postsurgical complications. We have developed and pilot tested a compact, fiber-based device that combines two complimentary modalities-diffuse correlation spectroscopy (DCS) and diffuse reflectance spectroscopy-to quantitatively monitor blood perfusion. We present a proof-of-concept study on an in vivo porcine model (n=8). With a controllable arterial blood flow supply, occlusion studies (n=4) were performed on surgically isolated free flaps while the device simultaneously monitored blood flow through the supplying artery as well as flap perfusion from three orientations: the distal side of the flap and two transdermal channels. Further studies featuring long-term monitoring, arterial failure simulations, and venous failure simulations were performed on flaps that had undergone an anastomosis procedure (n=4). Additionally, benchtop verification of the DCS system was performed on liquid flow phantoms. Data revealed relationships between diffuse optical measures and state of occlusion as well as the ability to detect arterial and venous compromise. The compact construction of the device, along with its noninvasive and quantitative nature, would make this technology suitable for clinical translation.

Design verification of a compact system for detecting tissue perfusion using bimodal diffuse optical technologies.

It is essential to monitor tissue perfusion during and after reconstructive surgery, as restricted blood flow can result in graft failures. Current clinical procedures are insufficient to monitor tissue perfusion, as they are intermittent and often subjective. To address this unmet clinical need, a compact, low-cost, multimodal diffuse correlation spectroscopy and diffuse reflectance spectroscopy system was developed. We verified system performance via tissue phantoms and experimental protocols for rigorous bench testing. Quantitative data analysis methods were employed and tested to enable the extraction of tissue perfusion parameters. This design verification study assures data integrity in future in vivo studies.

Novel diffuse optics system for continuous tissue viability monitoring - extended recovery in vivo testing in a porcine flap model.

In reconstructive surgery, tissue perfusion/vessel patency is critical to the success of microvascular free tissue flaps. Early detection of flap failure secondary to compromise of vascular perfusion would significantly increase the chances of flap salvage. We have developed a compact, clinically-compatible monitoring system to enable automated, minimally-invasive, continuous, and quantitative assessment of flap viability/perfusion. We tested the system's continuous monitoring capability during extended non-recovery surgery using an in vivo porcine free flap model. Initial results indicated that the system could assess flap viability/perfusion in a quantitative and continuous manner. With proven performance, the compact form constructed with cost-effective components would make this system suitable for clinical translation.

In vivo preclinical verification of a multimodal diffuse reflectance and correlation spectroscopy system for sensing tissue perfusion.

In reconstructive surgery, impeded blood flow in microvascular free flaps due to a compromise in arterial or venous patency secondary to blood clots or vessel spasms can rapidly result in flap failures. Thus, the ability to detect changes in microvascular free flaps is critical. In this paper, we report progress on in vivo pre-clinical testing of a compact, multimodal, fiber-based diffuse correlation and reflectance spectroscopy system designed to quantitatively monitor tissue perfusion in a porcine model's surgically-grafted free flap. We also describe the device's sensitivity to incremental blood flow changes and discuss the prospects for continuous perfusion monitoring in future clinical translational studies.