Late rectal bleeding after 3D-CRT for prostate cancer: development of a neural-network-based predictive model

Utilization of machine learning methods for prediction of acute and late rectal toxicity due to curative prostate radiotherapy

OBJECTIVE

Rectal toxicity is one of the primary dose-limiting side effects of prostate cancer radiotherapy, and consequential impairment on quality of life in these patients with long survival is an important problem. In this study, we aimed to evaluate the possibility of predicting rectal toxicity with artificial intelligence model which was including certain dosimetric parameters.

MATERIALS AND METHODS

One hundred and thirty-seven patients with a diagnosis of prostate cancer who received curative radiotherapy for prostate +/- pelvic lymphatics were included in the study. The association of the clinical data and dosimetric data between early and late rectal toxicity reported during follow-up was evaluated. The sample size was increased to 274 patients by synthetic data generation method. To determine suitable models, 15 models were studied with machine learning algorithms using Python 2.3, Pycaret library. Random forest classifier was used with to detect active variables.

RESULTS

The area under the curve and accuracy were found to be 0.89-0.97 and 95%-99%, respectively, with machine learning algorithms. The sensitivity values for acute and toxicity were found to be 0.95 and 0.99, respectively.

CONCLUSION

Early or late rectal toxicity can be predicted with a high probability via dosimetric and physical data and machine learning algorithms of patients who underwent prostate +/- pelvic radiotherapy. The fact that rectal toxicity can be predicted before treatment, which may result in limiting the dose and duration of treatment, makes us think that artificial intelligence can enter our daily practice in a short time in this sense.

Embedding machine learning based toxicity models within radiotherapy treatment plan optimization

Objective.This study addresses radiation-induced toxicity (RIT) challenges in radiotherapy (RT) by developing a personalized treatment planning framework. It leverages patient-specific data and dosimetric information to create an optimization model that limits adverse side effects using constraints learned from historical data.Approach.The study uses the optimization with constraint learning (OCL) framework, incorporating patient-specific factors into the optimization process. It consists of three steps: optimizing the baseline treatment plan using population-wide dosimetric constraints; training a machine learning (ML) model to estimate the patient's RIT for the baseline plan; and adapting the treatment plan to minimize RIT using ML-learned patient-specific constraints. Various predictive models, including classification trees, ensembles of trees, and neural networks, are applied to predict the probability of grade 2+ radiation pneumonitis (RP2+) for non-small cell lung (NSCLC) cancer patients three months post-RT. The methodology is assessed with four high RP2+ risk NSCLC patients, with the goal of optimizing the dose distribution to constrain the RP2+ outcome below a pre-specified threshold. Conventional and OCL-enhanced plans are compared based on dosimetric parameters and predicted RP2+ risk. Sensitivity analysis on risk thresholds and data uncertainty is performed using a toy NSCLC case.Main results.Experiments show the methodology's capacity to directly incorporate all predictive models into RT treatment planning. In the four patients studied, mean lung dose and V20 were reduced by an average of 1.78 Gy and 3.66%, resulting in an average RP2+ risk reduction from 95% to 42%. Notably, this reduction maintains tumor coverage, although in two cases, sparing the lung slightly increased spinal cord max-dose (0.23 and 0.79 Gy).Significance.By integrating patient-specific information into learned constraints, the study significantly reduces adverse side effects like RP2+ without compromising target coverage. This unified framework bridges the gap between predicting toxicities and optimizing treatment plans in personalized RT decision-making.

Machine-learning with region-level radiomic and dosimetric features for predicting radiotherapy-induced rectal toxicities in prostate cancer patients

BACKGROUND AND PURPOSE

This study aims to build machine learning models to predict radiation-induced rectal toxicities for three clinical endpoints and explore whether the inclusion of radiomic features calculated on radiotherapy planning computerised tomography (CT) scans combined with dosimetric features can enhance the prediction performance.

MATERIALS AND METHODS

183 patients recruited to the VoxTox study (UK-CRN-ID-13716) were included. Toxicity scores were prospectively collected after 2 years with grade ≥ 1 proctitis, haemorrhage (CTCAEv4.03); and gastrointestinal (GI) toxicity (RTOG) recorded as the endpoints of interest. The rectal wall on each slice was divided into 4 regions according to the centroid, and all slices were divided into 4 sections to calculate region-level radiomic and dosimetric features. The patients were split into a training set (75%, N = 137) and a test set (25%, N = 46). Highly correlated features were removed using four feature selection methods. Individual radiomic or dosimetric or combined (radiomic + dosimetric) features were subsequently classified using three machine learning classifiers to explore their association with these radiation-induced rectal toxicities.

RESULTS

The test set area under the curve (AUC) values were 0.549, 0.741 and 0.669 for proctitis, haemorrhage and GI toxicity prediction using radiomic combined with dosimetric features. The AUC value reached 0.747 for the ensembled radiomic-dosimetric model for haemorrhage.

CONCLUSIONS

Our preliminary results show that region-level pre-treatment planning CT radiomic features have the potential to predict radiation-induced rectal toxicities for prostate cancer. Moreover, when combined with region-level dosimetric features and using ensemble learning, the model prediction performance slightly improved.

Spatial descriptions of radiotherapy dose: normal tissue complication models and statistical associations

For decades, dose-volume information for segmented anatomy has provided the essential data for correlating radiotherapy dosimetry with treatment-induced complications. Dose-volume information has formed the basis for modelling those associations via normal tissue complication probability (NTCP) models and for driving treatment planning. Limitations to this approach have been identified. Many studies have emerged demonstrating that the incorporation of information describing the spatial nature of the dose distribution, and potentially its correlation with anatomy, can provide more robust associations with toxicity and seed more general NTCP models. Such approaches are culminating in the application of computationally intensive processes such as machine learning and the application of neural networks. The opportunities these approaches have for individualising treatment, predicting toxicity and expanding the solution space for radiation therapy are substantial and have clearly widespread and disruptive potential. Impediments to reaching that potential include issues associated with data collection, model generalisation and validation. This review examines the role of spatial models of complication and summarises relevant published studies. Sources of data for these studies, appropriate statistical methodology frameworks for processing spatial dose information and extracting relevant features are described. Spatial complication modelling is consolidated as a pathway to guiding future developments towards effective, complication-free radiotherapy treatment.

A review of deep learning based methods for medical image multi-organ segmentation

Deep learning has revolutionized image processing and achieved the-state-of-art performance in many medical image segmentation tasks. Many deep learning-based methods have been published to segment different parts of the body for different medical applications. It is necessary to summarize the current state of development for deep learning in the field of medical image segmentation. In this paper, we aim to provide a comprehensive review with a focus on multi-organ image segmentation, which is crucial for radiotherapy where the tumor and organs-at-risk need to be contoured for treatment planning. We grouped the surveyed methods into two broad categories which are 'pixel-wise classification' and 'end-to-end segmentation'. Each category was divided into subgroups according to their network design. For each type, we listed the surveyed works, highlighted important contributions and identified specific challenges. Following the detailed review, we discussed the achievements, shortcomings and future potentials of each category. To enable direct comparison, we listed the performance of the surveyed works that used thoracic and head-and-neck benchmark datasets.

Artificial intelligence in rectal cancer

Accurate and rapid diagnosis is essential for correct treatment in rectal cancer. Determining the optimal treatment plan for a patient with rectal cancer is a complex process, and the oncological results and toxicity are not the same in every patient with the same treatment at the same stage. In recent years, the increasing interest in artificial intelligence in all fields of science has also led to the development of innovative tools in oncology. Artificial intelligence studies have increased in many steps from diagnosis to follow-up in rectal cancer. It is thought that artificial intelligence will provide convenience in many ways from personalized treatment to reducing the workload of the physician. Prediction algorithms can be standardized by sharing data between centers, diversifying data, and creating big data.

Ethical evaluation of artificial intelligence applications in radiotherapy using the Four Topics Approach

Artificial Intelligence is the capability of a machine to imitate intelligent human behavior. An important impact can be expected from Artificial Intelligence throughout the workflow of radiotherapy (such as automated organ segmentation, treatment planning, prediction of outcome and quality assurance). However, ethical concerns regarding the binding agreement between the patient and the physician have followed the introduction of artificial intelligence. Through the recording of personal and social moral values in addition to the usual demographics and the implementation of these as distinctive inputs to matching algorithms, ethical concerns such as consistency, applicability and relevance can be solved. In the meantime, physicians' awareness of the ethical dimension in their decision-making should be challenged, so that they prioritize treating their patients and not diseases, remain vigilant to preserve patient safety, avoid unintended harm and establish institutional policies on these issues.

External Validation of a Predictive Model for Acute Skin Radiation Toxicity in the REQUITE Breast Cohort

Background: Acute skin toxicity is a common and usually transient side-effect of breast radiotherapy although, if sufficiently severe, it can affect breast cosmesis, aftercare costs and the patient's quality-of-life. The aim of this study was to develop predictive models for acute skin toxicity using published risk factors and externally validate the models in patients recruited into the prospective multi-center REQUITE (validating pREdictive models and biomarkers of radiotherapy toxicity to reduce side-effects and improve QUalITy of lifE in cancer survivors) study.

Methods: Patient and treatment-related risk factors significantly associated with acute breast radiation toxicity on multivariate analysis were identified in the literature. These predictors were used to develop risk models for acute erythema and acute desquamation (skin loss) in three Radiogenomics Consortium cohorts of patients treated by breast-conserving surgery and whole breast external beam radiotherapy (n = 2,031). The models were externally validated in the REQUITE breast cancer cohort (n = 2,057).

Results: The final risk model for acute erythema included BMI, breast size, hypo-fractionation, boost, tamoxifen use and smoking status. This model was validated in REQUITE with moderate discrimination (AUC 0.65), calibration and agreement between predicted and observed toxicity (Brier score 0.17). The risk model for acute desquamation, excluding the predictor tamoxifen use, failed to validate in the REQUITE cohort.

Conclusions: While most published prediction research in the field has focused on model development, this study reports successful external validation of a predictive model using clinical risk factors for acute erythema following radiotherapy after breast-conserving surgery. This model retained discriminatory power but will benefit from further re-calibration. A similar model to predict acute desquamation failed to validate in the REQUITE cohort. Future improvements and more accurate predictions are expected through the addition of genetic markers and application of other modeling and machine learning techniques.

Modelling and optimisation of treatment parameters in high-dose-rate mono brachytherapy for localised prostate carcinoma using a multilayer artificial neural network and a genetic algorithm: Pilot study

BACKGROUND

High-dose-rate mono brachytherapy (HDR-MB) is employed in the treatment of prostate carcinoma (CaP). As an ideal plan of CaP brachytherapy cannot be created, it is necessary to identify a reliable tool to optimise the parameters of HDR-MB. This paper applies a multilayer artificial neural network (MANN) and a genetic algorithm (GA) to optimise brachytherapy parameters based on an individual dose-volumetric analysis.

METHODS

Patients with localised CaP of various risks were treated with HDR-MB. Consecutive levels of the biochemical control parameter (prostate specific antigen (PSA) nadir) have been collected after completion of HDR-MB in the range 2-9 years. The Kaplan-Meier regression analysis of biochemical-free survival (BFS) was applied. The clinical risk of recurrent CaP (RCaP), the therapy dose (TD), TD coverage index (CI_100%) and PSA nadir were modelled using the MANN and GA.

RESULTS

In the low-risk group, BFS was achieved in 100% of treated patients, while in the group of patients with high risk, BFS was achieved in 95.8% of treated patients. The MANN-GA model optimises a TD of 47.3 Gy and CI_100% of 1.14 as well as a TD of 50.4 Gy and CI_100% of 1.6 for the low-risk group and high-risk group, respectively, of localised CaP. The optimised PSA nadir was 0.047 and 0.25 ng cm^-3 for low-risk group and high-risk group, respectively.

CONCLUSIONS

The developed MANN-GA model presents a method for optimising the treatment parameters in radiation therapy, which could be a valuable tool in planning of the HDR-MB.

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.

Prediction of perioperative transfusions using an artificial neural network

BACKGROUND

Accurate prediction of operative transfusions is essential for resource allocation and identifying patients at risk of postoperative adverse events. This research examines the efficacy of using artificial neural networks (ANNs) to predict transfusions for all inpatient operations.

METHODS

Over 1.6 million surgical cases over a two year period from the NSQIP-PUF database are used. Data from 2014 (750937 records) are used for model development and data from 2015 (885502 records) are used for model validation. ANN and regression models are developed to predict perioperative transfusions for surgical patients.

RESULTS

Various ANN models and logistic regression, using four variable sets, are compared. The best performing ANN models with respect to both sensitivity and area under the receiver operator characteristic curve outperformed all of the regression models (p < .001) and achieved a performance of 70-80% specificity with a corresponding 75-62% sensitivity.

CONCLUSION

ANNs can predict >75% of the patients who will require transfusion and 70% of those who will not. Increasing specificity to 80% still enables a sensitivity of almost 67%. The unique contribution of this research is the utilization of a single ANN model to predict transfusions across a broad range of surgical procedures.

Deep Learning: A Review for the Radiation Oncologist

Introduction: Deep Learning (DL) is a machine learning technique that uses deep neural networks to create a model. The application areas of deep learning in radiation oncology include image segmentation and detection, image phenotyping, and radiomic signature discovery, clinical outcome prediction, image dose quantification, dose-response modeling, radiation adaptation, and image generation. In this review, we explain the methods used in DL and perform a literature review using the Medline database to identify studies using deep learning in radiation oncology. The search was conducted in April 2018, and identified studies published between 1997 and 2018, strongly skewed toward 2015 and later. Methods: A literature review was performed using PubMed/Medline in order to identify important recent publications to be synthesized into a review of the current status of Deep Learning in radiation oncology, directed at a clinically-oriented reader. The search strategy included the search terms "radiotherapy" and "deep learning." In addition, reference lists of selected articles were hand searched for further potential hits of relevance to this review. The search was conducted in April 2018, and identified studies published between 1997 and 2018, strongly skewed toward 2015 and later. Results: Studies using DL for image segmentation were identified in Brain (n = 2), Head and Neck (n = 3), Lung (n = 6), Abdominal (n = 2), and Pelvic (n = 6) cancers. Use of Deep Learning has also been reported for outcome prediction, such as toxicity modeling (n = 3), treatment response and survival (n = 2), or treatment planning (n = 5). Conclusion: Over the past few years, there has been a significant number of studies assessing the performance of DL techniques in radiation oncology. They demonstrate how DL-based systems can aid clinicians in their daily work, be it by reducing the time required for or the variability in segmentation, or by helping to predict treatment outcomes and toxicities. It still remains to be seen when these techniques will be employed in routine clinical practice.

Dosimetry and Gastrointestinal Toxicity Relationships in a Phase II Trial of Pelvic Lymph Node Radiotherapy in Advanced Localised Prostate Cancer

AIMS

Pelvic lymph node (PLN) radiotherapy for high-risk prostate cancer is limited by late gastrointestinal toxicity. Application of rectal and bowel constraints may reduce risks of side-effects. We evaluated associations between intensity-modulated radiotherapy (IMRT) dose-volume data and long-term gastrointestinal toxicity.

MATERIALS AND METHODS

Data from a single-centre dose-escalation trial of PLN-IMRT were analysed, including conventionally fractionated (CFRT) and hypofractionated (HFRT) radiotherapy schedules. Associations between volumes of rectum and bowel receiving specified doses and clinician- and patient-reported toxicity outcomes were investigated independently. A metric, δ median (δM), was defined as the difference in the medians of a volume between groups with and without toxicity at a specified dose and was used to test for statistically significant differences.

RESULTS

Constraints were respected in most patients and, when exceeded, led to higher rates of gastrointestinal toxicity. Biologically relevant associations between rectum dose-points and toxicity were more numerous with both mild and moderate toxicity thresholds, but statistical significance was limited after correction for false discovery rate. Rectal V50Gy (CFRT) associated with grade 2+ bleeding; bowel V43Gy and V47 (HFRT/4 days/week schedule) associated with patient-reported loose stools and diarrhoea, respectively. Further investigation showed that CFRT patients with rectal bleeding had a mean rectal V50Gy above the treatment planning constraint.

CONCLUSIONS

When dose-volume parameters are kept below tight constraints, toxicity is low. Residual dosimetry loses much of its predictive power for gastrointestinal toxicity in the setting of PLN-IMRT for prostate cancer. We have benchmarked dose-volume constraints for safely delivering PLN-IMRT using CFRT or HFRT.

Development of a Ready-to-Use Graphical Tool Based on Artificial Neural Network Classification: Application for the Prediction of Late Fecal Incontinence After Prostate Cancer Radiation Therapy

PURPOSE

This study was designed to apply artificial neural network (ANN) classification methods for the prediction of late fecal incontinence (LFI) after high-dose prostate cancer radiation therapy and to develop a ready-to-use graphical tool.

MATERIALS AND METHODS

In this study, 598 men recruited in 2 national multicenter trials were analyzed. Information was recorded on comorbidity, previous abdominal surgery, use of drugs, and dose distribution. Fecal incontinence was prospectively evaluated through self-reported questionnaires. To develop the ANN, the study population was randomly split into training (n = 300), validation (n = 149), and test (n = 149) sets. Mean grade of longitudinal LFI (ie, expressed as the average incontinence grade over the first 3 years after radiation therapy) ≥1 was considered the endpoint. A suitable subset of variables able to better predict LFI was selected by simulating 100,000 ANN configurations. The search for the definitive ANN was then performed by varying the number of inputs and hidden neurons from 4 to 5 and from 1 to 9, respectively. A final classification model was established as the average of the best 5 among 500 ANNs with the same architecture. An ANN-based graphical method to compute LFI prediction was developed to include one continuous and n dichotomous variables.

RESULTS

An ANN architecture was selected, with 5 input variables (mean dose, previous abdominal surgery, use of anticoagulants, use of antihypertensive drugs, and use of neoadjuvant and adjuvant hormone therapy) and 4 hidden neurons. The developed classification model correctly identified patients with LFI with 80.8% sensitivity and 63.7% ± 1.0% specificity and an area under the curve of 0.78. The developed graphical tool may efficiently classify patients in low, intermediate, and high LFI risk classes.

CONCLUSIONS

An ANN-based model was developed to predict LFI. The model was translated in a ready-to-use graphical tool for LFI risk classification, with direct interpretation of the role of the predictors.

Independent component analysis for rectal bleeding prediction following prostate cancer radiotherapy

BACKGROUND AND PURPOSE

To evaluate the benefit of independent component analysis (ICA)-based models for predicting rectal bleeding (RB) following prostate cancer radiotherapy.

MATERIALS AND METHODS

A total of 593 irradiated prostate cancer patients were prospectively analyzed for Grade ≥2 RB. ICA was used to extract two informative subspaces (presenting RB or not) from the rectal DVHs, enabling a set of new pICA parameters to be estimated. These DVH-based parameters, along with others from the principal component analysis (PCA) and functional PCA, were compared to "standard" features (patient/treatment characteristics and DVH bins) using the Cox proportional hazards model for RB prediction. The whole cohort was divided into: (i) training (N = 339) for ICA-based subspace identification and Cox regression model identification and (ii) validation (N = 254) for RB prediction capability evaluation using the C-index and the area under the receiving operating curve (AUC), by comparing predicted and observed toxicity probabilities.

RESULTS

In the training cohort, multivariate Cox analysis retained pICA and PC as significant parameters of RB with 0.65 C-index. For the validation cohort, the C-index increased from 0.64 when pICA was not included in the Cox model to 0.78 when including pICA parameters. When pICA was not included, the AUC for 3-, 5-, and 8-year RB prediction were 0.68, 0.66, and 0.64, respectively. When included, the AUC increased to 0.83, 0.80, and 0.78, respectively.

CONCLUSION

Among the many various extracted or calculated features, ICA parameters improved RB prediction following prostate cancer radiotherapy.

Radiogenomics and radiotherapy response modeling

Advances in patient-specific information and biotechnology have contributed to a new era of computational medicine. Radiogenomics has emerged as a new field that investigates the role of genetics in treatment response to radiation therapy. Radiation oncology is currently attempting to embrace these recent advances and add to its rich history by maintaining its prominent role as a quantitative leader in oncologic response modeling. Here, we provide an overview of radiogenomics starting with genotyping, data aggregation, and application of different modeling approaches based on modifying traditional radiobiological methods or application of advanced machine learning techniques. We highlight the current status and potential for this new field to reshape the landscape of outcome modeling in radiotherapy and drive future advances in computational oncology.

Spatial features of dose-surface maps from deformably-registered plans correlate with late gastrointestinal complications

This study investigates the associations between spatial distribution of dose to the rectal surface and observed gastrointestinal toxicities after deformably registering each phase of a combined external beam radiotherapy (EBRT)/high-dose-rate brachytherapy (HDRBT) prostate cancer treatment. The study contains data for 118 patients where the HDRBT CT was deformably-registered to the EBRT CT. The EBRT and registered HDRBT TG43 dose distributions in a reference 2 Gy/fraction were 3D-summed. Rectum dose-surface maps (DSMs) were obtained by virtually unfolding the rectum surface slice-by-slice. Associations with late peak gastrointestinal toxicities were investigated using voxel-wise DSM analysis as well as parameterised spatial patterns. The latter were obtained by thresholding DSMs from 1-80 Gy (increment  =  1) and extracting inferior-superior extent, left-right extent, area, perimeter, compactness, circularity and ellipse fit parameters. Logistic regressions and Mann-Whitney U-tests were used to correlate features with toxicities. Rectal bleeding, stool frequency, diarrhoea and urgency/tenesmus were associated with greater lateral and/or longitudinal spread of the high doses near the anterior rectal surface. Rectal bleeding and stool frequency were also influenced by greater low-intermediate doses to the most inferior 20% of the rectum and greater low-intermediate-high doses to 40-80% of the rectum length respectively. Greater low-intermediate doses to the superior 20% and inferior 20% of the rectum length were associated with anorectal pain and urgency/tenesmus respectively. Diarrhoea, completeness of evacuation and proctitis were also related to greater low doses to the posterior side of the rectum. Spatial features for the intermediate-high dose regions such as area, perimeter, compactness, circularity, ellipse eccentricity and confinement to ellipse fits were strongly associated with toxicities other than anorectal pain. Consequently, toxicity is related to the shape of isodoses as well as dose coverage. The findings indicate spatial constraints on doses to certain sections of the rectum may be important for reducing toxicities and optimising dose.

Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods

PURPOSE

Given the paucity of available data concerning radiotherapy-induced urinary toxicity, it is important to ensure derivation of the most robust models with superior predictive performance. This work explores multiple statistical-learning strategies for prediction of urinary symptoms following external beam radiotherapy of the prostate.

METHODS

The performance of logistic regression, elastic-net, support-vector machine, random forest, neural network, and multivariate adaptive regression splines (MARS) to predict urinary symptoms was analyzed using data from 754 participants accrued by TROG03.04-RADAR. Predictive features included dose-surface data, comorbidities, and medication-intake. Four symptoms were analyzed: dysuria, haematuria, incontinence, and frequency, each with three definitions (grade ≥ 1, grade ≥ 2 and longitudinal) with event rate between 2.3% and 76.1%. Repeated cross-validations producing matched models were implemented. A synthetic minority oversampling technique was utilized in endpoints with rare events. Parameter optimization was performed on the training data. Area under the receiver operating characteristic curve (AUROC) was used to compare performance using sample size to detect differences of ≥0.05 at the 95% confidence level.

RESULTS

Logistic regression, elastic-net, random forest, MARS, and support-vector machine were the highest-performing statistical-learning strategies in 3, 3, 3, 2, and 1 endpoints, respectively. Logistic regression, MARS, elastic-net, random forest, neural network, and support-vector machine were the best, or were not significantly worse than the best, in 7, 7, 5, 5, 3, and 1 endpoints. The best-performing statistical model was for dysuria grade ≥ 1 with AUROC ± standard deviation of 0.649 ± 0.074 using MARS. For longitudinal frequency and dysuria grade ≥ 1, all strategies produced AUROC>0.6 while all haematuria endpoints and longitudinal incontinence models produced AUROC<0.6.

CONCLUSIONS

Logistic regression and MARS were most likely to be the best-performing strategy for the prediction of urinary symptoms with elastic-net and random forest producing competitive results. The predictive power of the models was modest and endpoint-dependent. New features, including spatial dose maps, may be necessary to achieve better models.

Perspectives on making big data analytics work for oncology

Oncology, with its unique combination of clinical, physical, technological, and biological data provides an ideal case study for applying big data analytics to improve cancer treatment safety and outcomes. An oncology treatment course such as chemoradiotherapy can generate a large pool of information carrying the 5Vs hallmarks of big data. This data is comprised of a heterogeneous mixture of patient demographics, radiation/chemo dosimetry, multimodality imaging features, and biological markers generated over a treatment period that can span few days to several weeks. Efforts using commercial and in-house tools are underway to facilitate data aggregation, ontology creation, sharing, visualization and varying analytics in a secure environment. However, open questions related to proper data structure representation and effective analytics tools to support oncology decision-making need to be addressed. It is recognized that oncology data constitutes a mix of structured (tabulated) and unstructured (electronic documents) that need to be processed to facilitate searching and subsequent knowledge discovery from relational or NoSQL databases. In this context, methods based on advanced analytics and image feature extraction for oncology applications will be discussed. On the other hand, the classical p (variables)≫n (samples) inference problem of statistical learning is challenged in the Big data realm and this is particularly true for oncology applications where p-omics is witnessing exponential growth while the number of cancer incidences has generally plateaued over the past 5-years leading to a quasi-linear growth in samples per patient. Within the Big data paradigm, this kind of phenomenon may yield undesirable effects such as echo chamber anomalies, Yule-Simpson reversal paradox, or misleading ghost analytics. In this work, we will present these effects as they pertain to oncology and engage small thinking methodologies to counter these effects ranging from incorporating prior knowledge, using information-theoretic techniques to modern ensemble machine learning approaches or combination of these. We will particularly discuss the pros and cons of different approaches to improve mining of big data in oncology.

Pitfalls in Prediction Modeling for Normal Tissue Toxicity in Radiation Therapy: An Illustration With the Individual Radiation Sensitivity and Mammary Carcinoma Risk Factor Investigation Cohorts

PURPOSE

To identify the main causes underlying the failure of prediction models for radiation therapy toxicity to replicate.

METHODS AND MATERIALS

Data were used from two German cohorts, Individual Radiation Sensitivity (ISE) (n=418) and Mammary Carcinoma Risk Factor Investigation (MARIE) (n=409), of breast cancer patients with similar characteristics and radiation therapy treatments. The toxicity endpoint chosen was telangiectasia. The LASSO (least absolute shrinkage and selection operator) logistic regression method was used to build a predictive model for a dichotomized endpoint (Radiation Therapy Oncology Group/European Organization for the Research and Treatment of Cancer score 0, 1, or ≥2). Internal areas under the receiver operating characteristic curve (inAUCs) were calculated by a naïve approach whereby the training data (ISE) were also used for calculating the AUC. Cross-validation was also applied to calculate the AUC within the same cohort, a second type of inAUC. Internal AUCs from cross-validation were calculated within ISE and MARIE separately. Models trained on one dataset (ISE) were applied to a test dataset (MARIE) and AUCs calculated (exAUCs).

RESULTS

Internal AUCs from the naïve approach were generally larger than inAUCs from cross-validation owing to overfitting the training data. Internal AUCs from cross-validation were also generally larger than the exAUCs, reflecting heterogeneity in the predictors between cohorts. The best models with largest inAUCs from cross-validation within both cohorts had a number of common predictors: hypertension, normalized total boost, and presence of estrogen receptors. Surprisingly, the effect (coefficient in the prediction model) of hypertension on telangiectasia incidence was positive in ISE and negative in MARIE. Other predictors were also not common between the 2 cohorts, illustrating that overcoming overfitting does not solve the problem of replication failure of prediction models completely.

CONCLUSIONS

Overfitting and cohort heterogeneity are the 2 main causes of replication failure of prediction models across cohorts. Cross-validation and similar techniques (eg, bootstrapping) cope with overfitting, but the development of validated predictive models for radiation therapy toxicity requires strategies that deal with cohort heterogeneity.

Big Data Analytics for Prostate Radiotherapy

Radiation therapy is a first-line treatment option for localized prostate cancer and radiation-induced normal tissue damage are often the main limiting factor for modern radiotherapy regimens. Conversely, under-dosing of target volumes in an attempt to spare adjacent healthy tissues limits the likelihood of achieving local, long-term control. Thus, the ability to generate personalized data-driven risk profiles for radiotherapy outcomes would provide valuable prognostic information to help guide both clinicians and patients alike. Big data applied to radiation oncology promises to deliver better understanding of outcomes by harvesting and integrating heterogeneous data types, including patient-specific clinical parameters, treatment-related dose-volume metrics, and biological risk factors. When taken together, such variables make up the basis for a multi-dimensional space (the "RadoncSpace") in which the presented modeling techniques search in order to identify significant predictors. Herein, we review outcome modeling and big data-mining techniques for both tumor control and radiotherapy-induced normal tissue effects. We apply many of the presented modeling approaches onto a cohort of hypofractionated prostate cancer patients taking into account different data types and a large heterogeneous mix of physical and biological parameters. Cross-validation techniques are also reviewed for the refinement of the proposed framework architecture and checking individual model performance. We conclude by considering advanced modeling techniques that borrow concepts from big data analytics, such as machine learning and artificial intelligence, before discussing the potential future impact of systems radiobiology approaches.

Big Data and machine learning in radiation oncology: State of the art and future prospects

Precision medicine relies on an increasing amount of heterogeneous data. Advances in radiation oncology, through the use of CT Scan, dosimetry and imaging performed before each fraction, have generated a considerable flow of data that needs to be integrated. In the same time, Electronic Health Records now provide phenotypic profiles of large cohorts of patients that could be correlated to this information. In this review, we describe methods that could be used to create integrative predictive models in radiation oncology. Potential uses of machine learning methods such as support vector machine, artificial neural networks, and deep learning are also discussed.

Normal tissue complication probability (NTCP) models for late rectal bleeding, stool frequency and fecal incontinence after radiotherapy in prostate cancer patients

BACKGROUND AND PURPOSE

Curative radiotherapy for prostate cancer may lead to anorectal side effects, including rectal bleeding, fecal incontinence, increased stool frequency and rectal pain. The main objective of this study was to develop multivariable NTCP models for these side effects.

MATERIAL AND METHODS

The study sample was composed of 262 patients with localized or locally advanced prostate cancer (stage T1-3). Anorectal toxicity was prospectively assessed using a standardized follow-up program. Different anatomical subregions within and around the anorectum were delineated. A LASSO logistic regression analysis was used to analyze dose volume effects on toxicity.

RESULTS

In the univariable analysis, rectal bleeding, increase in stool frequency and fecal incontinence were significantly associated with a large number of dosimetric parameters. The collinearity between these predictors was high (VIF>5). In the multivariable model, rectal bleeding was associated with the anorectum (V70) and anticoagulant use, fecal incontinence was associated with the external sphincter (V15) and the iliococcygeal muscle (V55). Finally, increase in stool frequency was associated with the iliococcygeal muscle (V45) and the levator ani (V40). No significant associations were found for rectal pain.

CONCLUSIONS

Different anorectal side effects are associated with different anatomical substructures within and around the anorectum. The dosimetric variables associated with these side effects can be used to optimize radiotherapy treatment planning aiming at prevention of specific side effects and to estimate the benefit of new radiation technologies.

Predicting toxicity in radiotherapy for prostate cancer

This comprehensive review addresses most organs at risk involved in planning optimization for prostate cancer. It can be considered an update of a previous educational review that was published in 2009 (Fiorino et al., 2009). The literature was reviewed based on PubMed and MEDLINE database searches (from January 2009 up to September 2015), including papers in press; for each section/subsection, key title words were used and possibly combined with other more general key-words (such as radiotherapy, dose-volume effects, NTCP, DVH, and predictive model). Publications generally dealing with toxicity without any association with dose-volume effects or correlations with clinical risk factors were disregarded, being outside the aim of the review. A focus was on external beam radiotherapy, including post-prostatectomy, with conventional fractionation or moderate hypofractionation (<4Gy/fraction); extreme hypofractionation is the topic of another paper in this special issue. Gastrointestinal and urinary toxicity are the most investigated endpoints, with quantitative data published in the last 5years suggesting both a dose-response relationship and the existence of a number of clinical/patient related risk factors acting as dose-response modifiers. Some results on erectile dysfunction, bowel toxicity and hematological toxicity are also presented.

Outcome modeling techniques for prostate cancer radiotherapy: Data, models, and validation

Prostate cancer is a frequently diagnosed malignancy worldwide and radiation therapy is a first-line approach in treating localized as well as locally advanced cases. The limiting factor in modern radiotherapy regimens is dose to normal structures, an excess of which can lead to aberrant radiation-induced toxicities. Conversely, dose reduction to spare adjacent normal structures risks underdosing target volumes and compromising local control. As a result, efforts aimed at predicting the effects of radiotherapy could invaluably optimize patient treatments by mitigating such toxicities and simultaneously maximizing biochemical control. In this work, we review the types of data, frameworks and techniques used for prostate radiotherapy outcome modeling. Consideration is given to clinical and dose-volume metrics, such as those amassed by the QUANTEC initiative, and also to newer methods for the integration of biological and genetic factors to improve prediction performance. We furthermore highlight trends in machine learning that may help to elucidate the complex pathophysiological mechanisms of tumor control and radiation-induced normal tissue side effects.

Recent advancements in toxicity prediction following prostate cancer radiotherapy

In external beam radiotherapy for prostate cancer limiting toxicities for dose escalation are bladder and rectum toxicities. Normal tissue complication probability models aim at quantifying the risk of developping adverse events following radiotherapy. These models, originally proposed in the context of uniform irradiation, have evolved to implementations based on the state-of-the-art classification methods which are trained using empirical data. Recently, the use of image processing techniques combined with population analysis methods has led to a new generation of models to understand the risk of normal tissue complications following radiotherapy. This paper overviews those methods in the case of prostate cancer radiation therapy and propose some lines of future research.

Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician's Perspective

Radiation oncology has always been deeply rooted in modeling, from the early days of isoeffect curves to the contemporary Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) initiative. In recent years, medical modeling for both prognostic and therapeutic purposes has exploded thanks to increasing availability of electronic data and genomics. One promising direction that medical modeling is moving toward is adopting the same machine learning methods used by companies such as Google and Facebook to combat disease. Broadly defined, machine learning is a branch of computer science that deals with making predictions from complex data through statistical models. These methods serve to uncover patterns in data and are actively used in areas such as speech recognition, handwriting recognition, face recognition, "spam" filtering (junk email), and targeted advertising. Although multiple radiation oncology research groups have shown the value of applied machine learning (ML), clinical adoption has been slow due to the high barrier to understanding these complex models by clinicians. Here, we present a review of the use of ML to predict radiation therapy outcomes from the clinician's point of view with the hope that it lowers the "barrier to entry" for those without formal training in ML. We begin by describing 7 principles that one should consider when evaluating (or creating) an ML model in radiation oncology. We next introduce 3 popular ML methods--logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN)--and critique 3 seminal papers in the context of these principles. Although current studies are in exploratory stages, the overall methodology has progressively matured, and the field is ready for larger-scale further investigation.

Random forests to predict rectal toxicity following prostate cancer radiation therapy

PURPOSE

To propose a random forest normal tissue complication probability (RF-NTCP) model to predict late rectal toxicity following prostate cancer radiation therapy, and to compare its performance to that of classic NTCP models.

METHODS AND MATERIALS

Clinical data and dose-volume histograms (DVH) were collected from 261 patients who received 3-dimensional conformal radiation therapy for prostate cancer with at least 5 years of follow-up. The series was split 1000 times into training and validation cohorts. A RF was trained to predict the risk of 5-year overall rectal toxicity and bleeding. Parameters of the Lyman-Kutcher-Burman (LKB) model were identified and a logistic regression model was fit. The performance of all the models was assessed by computing the area under the receiving operating characteristic curve (AUC).

RESULTS

The 5-year grade ≥2 overall rectal toxicity and grade ≥1 and grade ≥2 rectal bleeding rates were 16%, 25%, and 10%, respectively. Predictive capabilities were obtained using the RF-NTCP model for all 3 toxicity endpoints, including both the training and validation cohorts. The age and use of anticoagulants were found to be predictors of rectal bleeding. The AUC for RF-NTCP ranged from 0.66 to 0.76, depending on the toxicity endpoint. The AUC values for the LKB-NTCP were statistically significantly inferior, ranging from 0.62 to 0.69.

CONCLUSIONS

The RF-NTCP model may be a useful new tool in predicting late rectal toxicity, including variables other than DVH, and thus appears as a strong competitor to classic NTCP models.

Reducing rectal injury during external beam radiotherapy for prostate cancer

Rectal bleeding and faecal incontinence are serious injuries that men with prostate cancer who receive radiotherapy can experience. Although technical advances--including the use of intensity-modulated radiotherapy coupled with image-guided radiotherapy--have enabled the delivery of dose distributions that conform to the shape of the tumour target with steep dose gradients that reduce the dose given to surrounding tissues, radiotherapy-associated toxicity can not be avoided completely. Many large-scale prospective studies have analysed the correlations of patient-related and treatment-related parameters with acute and late toxicity to optimize patient selection and treatment planning. The careful application of dose-volume constraints and the tuning of these constraints to the individual patient's characteristics are now considered the most effective ways of reducing rectal morbidity. Additionally, the use of endorectal balloons (to reduce the margins between the clinical target volume and planning target volume) and the insertion of tissue spacers into the region between the prostate and anterior rectal wall have been investigated as means to further reduce late rectal injury. Finally, some drugs and other compounds are also being considered to help protect healthy tissue. Overall, a number of approaches exist that must be fully explored in large prospective trials to address the important issue of rectal toxicity in prostate cancer radiotherapy.