Clinical integration of machine learning for curative-intent radiation treatment of patients with prostate cancer

Advances in Automated Treatment Planning

Treatment planning in radiation therapy has progressed enormously over the past several decades. Such advancements came in the form of innovative hardware and algorithms, giving rise to modalities such as intensity-modulated radiation therapy and volume modulated arc therapy, greatly improving patient outcome and quality of life. While these developments have improved the overall plan quality, they have also given rise to higher treatment planning complexity. This has resulted in increased treatment planning time and higher variability in the final approved plan quality. Radiation oncology, as an already technologically advanced field, has much research and implementation involving the use of AI. The field has begun to show the efficacy of using such technologies in many of its sub-areas, such as in diagnosis, imaging, segmentation, treatment planning, quality assurance, treatment delivery, and follow-up. Some AI technologies have already been clinically implemented by commercial systems. In this article, we will provide an overview to methods involved with treatment planning in radiation therapy. In particular, we will review the recent research and literature related to automation of the treatment planning process, leading to potentially higher efficiency and higher quality plans. We will then present the current and future challenges, as well as some future perspectives.

Prospective clinical research of radiomics and deep learning in oncology: A translational review

Radiomics and deep learning (DL) hold transformative promise and substantial and significant advances in oncology; however, most methods have been tested in retrospective or simulated settings. There is considerable interest in the biomarker validation, clinical utility, and methodological robustness of these studies and their deployment in real-world settings. This review summarizes the characteristics of studies, the level of prospective validation, and the overview of research on different clinical endpoints. The discussion of methodological robustness shows the potential for independent external replication of prospectively reported results. These in-depth analyses further describe the barriers limiting the translation of radiomics and DL into primary care options and provide specific recommendations regarding clinical deployment. Finally, we propose solutions for integrating novel approaches into the treatment environment to unravel the critical process of translating AI models into the clinical routine and explore strategies to improve personalized medicine.

OpenKBP-Opt: an international and reproducible evaluation of 76 knowledge-based planning pipelines

Objective.To establish an open framework for developing plan optimization models for knowledge-based planning (KBP).Approach.Our framework includes radiotherapy treatment data (i.e. reference plans) for 100 patients with head-and-neck cancer who were treated with intensity-modulated radiotherapy. That data also includes high-quality dose predictions from 19 KBP models that were developed by different research groups using out-of-sample data during the OpenKBP Grand Challenge. The dose predictions were input to four fluence-based dose mimicking models to form 76 unique KBP pipelines that generated 7600 plans (76 pipelines × 100 patients). The predictions and KBP-generated plans were compared to the reference plans via: the dose score, which is the average mean absolute voxel-by-voxel difference in dose; the deviation in dose-volume histogram (DVH) points; and the frequency of clinical planning criteria satisfaction. We also performed a theoretical investigation to justify our dose mimicking models.Main results.The range in rank order correlation of the dose score between predictions and their KBP pipelines was 0.50-0.62, which indicates that the quality of the predictions was generally positively correlated with the quality of the plans. Additionally, compared to the input predictions, the KBP-generated plans performed significantly better (P< 0.05; one-sided Wilcoxon test) on 18 of 23 DVH points. Similarly, each optimization model generated plans that satisfied a higher percentage of criteria than the reference plans, which satisfied 3.5% more criteria than the set of all dose predictions. Lastly, our theoretical investigation demonstrated that the dose mimicking models generated plans that are also optimal for an inverse planning model.Significance.This was the largest international effort to date for evaluating the combination of KBP prediction and optimization models. We found that the best performing models significantly outperformed the reference dose and dose predictions. In the interest of reproducibility, our data and code is freely available.

[Clinical research in radiation oncology: how to move from the laboratory to the patient?]

Translational research in radiation oncology is undergoing intense development. An increasingly rapid transfer is taking place from the laboratory to the patients, both in the selection of patients who can benefit from radiotherapy and in the development of innovative irradiation strategies or the development of combinations with drugs. Accelerating the passage of discoveries from the laboratory to the clinic represents the ideal of any translational research program but requires taking into account the multiple obstacles that can slow this progress. The ambition of the RadioTransNet network, a project to structure preclinical research in radiation oncology in France, is precisely to promote scientific and clinical interactions at the interface of radiotherapy and radiobiology, in its preclinical positioning, in order to identify priorities for strategic research dedicated to innovation in radiotherapy. The multidisciplinary radiotherapy teams with experts in biology, medicine, medical physics, mathematics and engineering sciences are able to meet these new challenges which will allow these advances to be made available to patients as quickly as possible.

Integrated MRI-guided radiotherapy - opportunities and challenges

MRI can help to categorize tissues as malignant or non-malignant both anatomically and functionally, with a high level of spatial and temporal resolution. This non-invasive imaging modality has been integrated with radiotherapy in devices that can differentially target the most aggressive and resistant regions of tumours. The past decade has seen the clinical deployment of treatment devices that combine imaging with targeted irradiation, making the aspiration of integrated MRI-guided radiotherapy (MRIgRT) a reality. The two main clinical drivers for the adoption of MRIgRT are the ability to image anatomical changes that occur before and during treatment in order to adapt the treatment approach, and to image and target the biological features of each tumour. Using motion management and biological targeting, the radiation dose delivered to the tumour can be adjusted during treatment to improve the probability of tumour control, while simultaneously reducing the radiation delivered to non-malignant tissues, thereby reducing the risk of treatment-related toxicities. The benefits of this approach are expected to increase survival and quality of life. In this Review, we describe the current state of MRIgRT, and the opportunities and challenges of this new radiotherapy approach.

Domain adaptation of automated treatment planning from computed tomography to magnetic resonance

Objective. Machine learning (ML) based radiation treatment planning addresses the iterative and time-consuming nature of conventional inverse planning. Given the rising importance of magnetic resonance (MR) only treatment planning workflows, we sought to determine if an ML based treatment planning model, trained on computed tomography (CT) imaging, could be applied to MR through domain adaptation. Methods. In this study, MR and CT imaging was collected from 55 prostate cancer patients treated on an MR linear accelerator. ML based plans were generated for each patient on both CT and MR imaging using a commercially available model in RayStation 8B. The dose distributions and acceptance rates of MR and CT based plans were compared using institutional dose-volume evaluation criteria. The dosimetric differences between MR and CT plans were further decomposed into setup, cohort, and imaging domain components. Results. MR plans were highly acceptable, meeting 93.1% of all evaluation criteria compared to 96.3% of CT plans, with dose equivalence for all evaluation criteria except for the bladder wall, penile bulb, small and large bowel, and one rectum wall criteria (p < 0.05). Changing the input imaging modality (domain component) only accounted for about half of the dosimetric differences observed between MR and CT plans. Anatomical differences between the ML training set and the MR linac cohort (cohort component) were also a significant contributor. Significance. We were able to create highly acceptable MR based treatment plans using a CT-trained ML model for treatment planning, although clinically significant dose deviations from the CT based plans were observed. Future work should focus on combining this framework with atlas selection metrics to create an interpretable quality assurance QA framework for ML based treatment planning.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI

A growing number of artificial intelligence (AI)-based clinical decision support systems are showing promising performance in preclinical, in silico evaluation, but few have yet demonstrated real benefit to patient care. Early-stage clinical evaluation is important to assess an AI system's actual clinical performance at small scale, ensure its safety, evaluate the human factors surrounding its use and pave the way to further large-scale trials. However, the reporting of these early studies remains inadequate. The present statement provides a multi-stakeholder, consensus-based reporting guideline for the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI). We conducted a two-round, modified Delphi process to collect and analyze expert opinion on the reporting of early clinical evaluation of AI systems. Experts were recruited from 20 pre-defined stakeholder categories. The final composition and wording of the guideline was determined at a virtual consensus meeting. The checklist and the Explanation & Elaboration (E&E) sections were refined based on feedback from a qualitative evaluation process. In total, 123 experts participated in the first round of Delphi, 138 in the second round, 16 in the consensus meeting and 16 in the qualitative evaluation. The DECIDE-AI reporting guideline comprises 17 AI-specific reporting items (made of 28 subitems) and ten generic reporting items, with an E&E paragraph provided for each. Through consultation and consensus with a range of stakeholders, we developed a guideline comprising key items that should be reported in early-stage clinical studies of AI-based decision support systems in healthcare. By providing an actionable checklist of minimal reporting items, the DECIDE-AI guideline will facilitate the appraisal of these studies and replicability of their findings.

Toward automatic beam angle selection for pencil-beam scanning proton liver Treatments: A deep learning-based approach

BACKGROUND

Dose deposition characteristics of proton radiation can be advantageous over photons. Proton treatment planning however poses additional challenges for the planners. Proton therapy is usually delivered with only a small number of beam angles, and the quality of a proton treatment plan is largely determined by the beam angles employed. Finding the optimal beam angles for a proton treatment plan requires time and experience, motivating the investigation of automatic beam angle selection methods.

PURPOSE

A deep learning-based approach to automatic beam angle selection is proposed for proton pencil-beam scanning treatment planning of liver lesions.

METHODS

We cast beam-angle selection as a multi-label classification problem. To account for angular boundary discontinuity, the underlying convolution neural network is trained with the proposed Circular Earth Mover's Distance based regularization and multi-label circular-smooth label technique. Furthermore, an analytical algorithm emulating proton treatment planners' clinical practice is employed in post-processing to improve the output of the model. Forty-nine patients that received proton liver treatments between 2017 and 2020 were randomly divided into training (n = 31), validation (n = 7), and test sets (n = 11). AI-selected beam angles were compared with those angles selected by human planners, and the dosimetric outcome was investigated by creating plans using knowledge-based treatment planning.

RESULTS

For 7 of the 11 cases in the test set, AI-selected beam angles agreed with those chosen by human planners to within 20 degrees (median angle difference = 10°; mean = 18.6°). Moreover, out of the total 22 beam angles predicted by the model, 15 (68%) were within 10 degrees of the human-selected angles. The high correlation in beam angles resulted in comparable dosimetric statistics between proton treatment plans generated using AI- and human-selected angles. For the cases with beam angle differences exceeding 20°, the dosimetric analysis showed similar plan quality although with different emphases on organ-at-risk sparing.

CONCLUSIONS

This pilot study demonstrated the feasibility of a novel deep learning-based beam angle selection technique. Testing on liver cancer patients showed that the resulting plans were clinically viable with comparable dosimetric quality to those using human-selected beam angles. In tandem with auto-contouring and knowledge-based treatment planning tools, the proposed model could represent a pathway for nearly fully automated treatment planning in proton therapy. This article is protected by copyright. All rights reserved.

Identification of clinical and molecular features of recurrent serous borderline ovarian tumour

BACKGROUND

Serous borderline ovarian tumour (SBOT) is the most common type of BOT. Fertility sparing surgery (FSS) is an option for patients with SBOT, though it may increase the risk of recurrence. The clinical and molecular features of its recurrence are important and need to be investigated in detail.

METHODS

An internal cohort of 319 patients with SBOT was collected from Aug 1, 2009 to July 31, 2019 from the Obstetrics and Gynecology Hospital of Fudan University in China. An external cohort of 100 patients with SBOT was collected from Aug 1, 2009 to Nov 30, 2019 from the Shandong Provincial Hospital in China. The risk factors for the recurrence were identified by multivariate cox analysis. Several computational methods were tested to establish a prediction tool for recurrence. Whole genome sequencing, RNA-seq, metabolomics and lipidomics were used to understand the molecular characteristics of the recurrence of SBOT.

FINDINGS

Five factors were significantly correlated with SBOT recurrence in a Han population: micropapillary pattern, advanced stage, FSS, microinvasion, and lymph node invasion. A random forest-based online recurrence prediction tool was established and validated using an internal cohort and an independent external cohort for patients with SBOT. The multi-omics analysis on the original SBOT samples revealed that recurrence is related to metabolic regulation of immunological suppression.

INTERPRETATION

Our study identified several important clinical and molecular features of recurrent SBOT. The prediction tool we established could help physicians to estimate the prognosis of patients with SBOT. These findings will contribute to the development of personalised and targeted therapies to improve prognosis.

FUNDING

JL was funded by MOST 2020YFA0803600, 2018YFA0801300, NSFC 32071138, and SKLGE-2118 to Jin Li; JY was funded by the Initial Project for Young and Middle-aged Medical Talents of Wuhan City, Hubei Province ([2014] 41); HH was funded by MOST 2019YFA0801900 and 2020YF1402600 to He Huang; JS was funded by NSFC 22,104,080; CG was funded by Natural Science Foundation of Shanghai 20ZR1408800 and NSFC82171633; BL was funded by Natural Science Foundation of Shanghai 19ZR1406800.

Challenges of Utilizing Medical Big Data in Reproductive Health Research

In the background of the “Three-Child Policy” introduced by the Chinese government, reproductive health has become one of the most important public health issues. With the promotion of digitization management of medical care institutions for women and children in the country, there will be chances to acquire medical big data of obstetrics and pediatrics. Here the authors are presenting their opinions on the challenges of the management and utilization of reproductive big data.

Stereotactic Body Radiation Therapy in Patients with Oligometastatic Disease: Clinical State of the Art and Perspectives

Stereotactic body radiation therapy (SBRT) is a form of radiation therapy (RT) in which a small number of high doses of radiation are delivered to a target volume using highly sophisticated equipment. Stereotactic body radiation therapy is crucial in two cancer stages: early primary cancer and oligometastatic disease, with the goal of inducing complete cancer remission in both. This treatment method is commonly used to treat a variety of disease types. Over the years, a growing body of clinical evidence on the use of SBRT for the treatment of primary and metastatic tumors has accumulated, with efficacy and safety demonstrated in randomized clinical trials. This article will review the technical and clinical aspects of SBRT according to disease type and clinical indication.

Clinical evaluation of two AI models for automated breast cancer plan generation

Background

Artificial intelligence (AI) shows great potential to streamline the treatment planning process. However, its clinical adoption is slow due to the limited number of clinical evaluation studies and because often, the translation of the predicted dose distribution to a deliverable plan is lacking. This study evaluates two different, deliverable AI plans in terms of their clinical acceptability based on quantitative parameters and qualitative evaluation by four radiation oncologists.

Methods

For 20 left-sided node-negative breast cancer patients, treated with a prescribed dose of 40.05 Gy, using tangential beam intensity modulated radiotherapy, two model-based treatment plans were evaluated against the corresponding manual plan. The two models used were an in-house developed U-net model and a vendor-developed contextual atlas regression forest model (cARF). Radiation oncologists evaluated the clinical acceptability of each blinded plan and ranked plans according to preference. Furthermore, a comparison with the manual plan was made based on dose volume histogram parameters, clinical evaluation criteria and preparation time.

Results

The U-net model resulted in a higher average and maximum dose to the PTV (median difference 0.37 Gy and 0.47 Gy respectively) and a slightly higher mean heart dose (MHD) (0.01 Gy). The cARF model led to higher average and maximum doses to the PTV (0.30 and 0.39 Gy respectively) and a slightly higher MHD (0.02 Gy) and mean lung dose (MLD, 0.04 Gy). The maximum MHD/MLD difference was ≤ 0.5 Gy for both AI plans. Regardless of these dose differences, 90–95% of the AI plans were considered clinically acceptable versus 90% of the manual plans. Preferences varied between the radiation oncologists. Plan preparation time was comparable between the U-net model and the manual plan (287 s vs 253 s) while the cARF model took longer (471 s). When only considering user interaction, plan generation time was 121 s for the cARF model and 137 s for the U-net model.

Conclusions

Two AI models were used to generate deliverable plans for breast cancer patients, in a time-efficient manner, requiring minimal user interaction. Although the AI plans resulted in slightly higher doses overall, radiation oncologists considered 90–95% of the AI plans clinically acceptable.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-022-01993-9.

Probabilistic Pareto plan generation for semiautomated multicriteria radiation therapy treatment planning

Objective.We propose a semiautomatic pipeline for radiation therapy treatment planning, combining ideas from machine learning-automated planning and multicriteria optimization (MCO).Approach.Using knowledge extracted from historically delivered plans, prediction models for spatial dose and dose statistics are trained and furthermore systematically modified to simulate changes in tradeoff priorities, creating a set of differently biased predictions. Based on the predictions, an MCO problem is subsequently constructed using previously developed dose mimicking functions, designed in such a way that its Pareto surface spans the range of clinically acceptable yet realistically achievable plans as exactly as possible. The result is an algorithm outputting a set of Pareto optimal plans, either fluence-based or machine parameter-based, which the user can navigate between in real time to make adjustments before a final deliverable plan is created.Main results.Numerical experiments performed on a dataset of prostate cancer patients show that one may often navigate to a better plan than one produced by a single-plan-output algorithm.Significance.We demonstrate the potential of merging MCO and a data-driven workflow to automate labor-intensive parts of the treatment planning process while maintaining a certain extent of manual control for the user.

Deep learning-based GTV contouring modeling inter- and intra- observer variability in sarcomas

BACKGROUND AND PURPOSE

The delineation of the gross tumor volume (GTV) is a critical step for radiation therapy treatment planning. The delineation procedure is typically performed manually which exposes two major issues: cost and reproducibility. Delineation is a time-consuming process that is subject to inter- and intra-observer variability. While methods have been proposed to predict GTV contours, typical approaches ignore variability and therefore fail to utilize the valuable confidence information offered by multiple contours.

MATERIALS AND METHODS

In this work we propose an automatic GTV contouring method for soft-tissue sarcomas from X-ray computed tomography (CT) images, using deep learning by integrating inter- and intra-observer variability in the learned model. Sixty-eight patients with soft tissue and bone sarcomas were considered in this evaluation, all underwent pre-operative CT imaging used to perform GTV delineation. Four radiation oncologists and radiologists performed three contouring trials each for all patients. We quantify variability by defining confidence levels based on the frequency of inclusion of a given voxel into the GTV and use a deep convolutional neural network to learn GTV confidence maps.

RESULTS

Results were compared to confidence maps from the four readers as well as ground-truth consensus contours established jointly by all readers. The resulting continuous Dice score between predicted and true confidence maps was 87% and the Hausdorff distance was 14 mm.

CONCLUSION

Results demonstrate the ability of the proposed method to predict accurate contours while utilizing variability and as such it can be used to improve clinical workflow.

Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients

Glioblastoma is an aggressive brain tumor with a low survival rate. Understanding tumor behavior by predicting prognosis outcomes is a crucial factor in deciding a proper treatment plan. In this paper, an automatic overall survival time prediction system (OST) for glioblastoma patients is developed on the basis of radiomic features and machine learning (ML). This system is designed to predict prognosis outcomes by classifying a glioblastoma patient into one of three survival groups: short-term, mid-term, and long-term. To develop the prediction system, a medical dataset based on imaging information from magnetic resonance imaging (MRI) and non-imaging information is used. A novel radiomic feature extraction method is proposed and developed on the basis of volumetric and location information of brain tumor subregions extracted from MRI scans. This method is based on calculating the volumetric features from two brain sub-volumes obtained from the whole brain volume in MRI images using brain sectional planes (sagittal, coronal, and horizontal). Many experiments are conducted on the basis of various ML methods and combinations of feature extraction methods to develop the best OST system. In addition, the feature fusions of both radiomic and non-imaging features are examined to improve the accuracy of the prediction system. The best performance was achieved by the neural network and feature fusions.

Cancer Needs a Robust "Metadata Supply Chain" to Realize the Promise of Artificial Intelligence

Profound advances in computational methods, including artificial intelligence (AI), present the opportunity to use the exponentially growing volume and complexity of available cancer measurements toward data-driven personalized care. While exciting, this opportunity has highlighted the disconnect between the promise of compute and the supply of high-quality data. The current paradigm of ad-hoc aggregation and curation of data needs to be replaced with a "metadata supply chain" that provides robust data in context with known provenance, that is, lineage and comprehensive data governance that will allow the promise of AI technology to be realized to its full potential in clinical practice.

Outcome-based multiobjective optimization of lymphoma radiation therapy plans

At its core, radiation therapy (RT) requires balancing therapeutic effects against risk of adverse events in cancer survivors. The radiation oncologist weighs numerous disease and patient-level factors when considering the expected risk-benefit ratio of combined treatment modalities. As part of this, RT plan optimization software is used to find a clinically acceptable RT plan delivering a prescribed dose to the target volume while respecting pre-defined radiation dose-volume constraints for selected organs at risk. The obvious limitation to the current approach is that it is virtually impossible to ensure the selected treatment plan could not be bettered by an alternative plan providing improved disease control and/or reduced risk of adverse events in this individual. Outcome-based optimization refers to a strategy where all planning objectives are defined by modeled estimates of a specific outcome's probability. Noting that various adverse events and disease control are generally incommensurable, leads to the concept of a Pareto-optimal plan: a plan where no single objective can be improved without degrading one or more of the remaining objectives. Further benefits of outcome-based multiobjective optimization are that quantitative estimates of risks and benefit are obtained as are the effects of choosing a different trade-off between competing objectives. Furthermore, patient-level risk factors and combined treatment modalities may be integrated directly into plan optimization. Here, we present this approach in the clinical setting of multimodality therapy for malignant lymphoma, a malignancy with marked heterogeneity in biology, target localization, and patient characteristics. We discuss future research priorities including the potential of artificial intelligence.

An atlas-guided automatic planning approach for rectal cancer intensity-modulated radiotherapy

We try to develop an atlas-guided automatic planning (AGAP) approach and evaluate its feasibility and performance in rectal cancer intensity-modulated radiotherapy. The developed AGAP approach consisted of four independent modules: patient atlas, similar patient retrieval, beam morphing (BM), and plan fine-tuning (PFT) modules. The atlas was setup using anatomy and plan data from Pinnacle auto-planning (P-auto) plans. Given a new patient, the retrieval function searched the top similar patient by a generic Fourier descriptor algorithm and retrieved its plan information. The BM function generated an initial plan for the new patient by morphing the beam aperture from the top similar patient plan. The beam aperture and calculated dose of the initial plan were used to guide the new plan optimization in the PFT function. The AGAP approach was tested on 96 patients by the leave-one-out validation and plan quality was compared with the P-auto plans. The AGAP and P-auto plans had no statistical difference for target coverage and dose homogeneity in terms ofV_100%(p = 0.76) and homogeneity index (p = 0.073), respectively. The CI index showed they had a statistically significant difference. But the ΔCI was both 0.02 compared to the perfect CI index of 1. The AGAP approach reduced the bladder mean dose by 152.1 cGy (p < 0.05) andV₅₀by 0.9% (p < 0.05), and slightly increased the left and right femoral head mean dose by 70.1 cGy (p < 0.05) and 69.7 cGy (p < 0.05), respectively. This work developed an efficient and automatic approach that could fully automate the IMRT planning process in rectal cancer radiotherapy. It reduced the plan quality dependence on the planner experience and maintained the comparable plan quality with P-auto plans.