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

Performance Comparison of 10 State-of-the-Art Machine Learning Algorithms for Outcome Prediction Modeling of Radiation-Induced Toxicity

Purpose

To evaluate the efficacy of prominent machine learning algorithms in predicting normal tissue complication probability using clinical data obtained from 2 distinct disease sites and to create a software tool that facilitates the automatic determination of the optimal algorithm to model any given labeled data set.

Methods and Materials

We obtained 3 sets of radiation toxicity data (478 patients) from our clinic: gastrointestinal toxicity, radiation pneumonitis, and radiation esophagitis. These data comprised clinicopathological and dosimetric information for patients diagnosed with non-small cell lung cancer and anal squamous cell carcinoma. Each data set was modeled using 11 commonly employed machine learning algorithms (elastic net, least absolute shrinkage and selection operator [LASSO], random forest, random forest regression, support vector machine, extreme gradient boosting, light gradient boosting machine, k-nearest neighbors, neural network, Bayesian-LASSO, and Bayesian neural network) by randomly dividing the data set into a training and test set. The training set was used to create and tune the model, and the test set served to assess it by calculating performance metrics. This process was repeated 100 times by each algorithm for each data set. Figures were generated to visually compare the performance of the algorithms. A graphical user interface was developed to automate this whole process.

Results

LASSO achieved the highest area under the precision-recall curve (0.807 ± 0.067) for radiation esophagitis, random forest for gastrointestinal toxicity (0.726 ± 0.096), and the neural network for radiation pneumonitis (0.878 ± 0.060). The area under the curve was 0.754 ± 0.069, 0.889 ± 0.043, and 0.905 ± 0.045, respectively. The graphical user interface was used to compare all algorithms for each data set automatically. When averaging the area under the precision-recall curve across all toxicities, Bayesian-LASSO was the best model.

Conclusions

Our results show that there is no best algorithm for all data sets. Therefore, it is important to compare multiple algorithms when training an outcome prediction model on a new data set. The graphical user interface created for this study automatically compares the performance of these 11 algorithms for any data set.

Radiomics model based on computed tomography images for prediction of radiation-induced optic neuropathy following radiotherapy of brain and head and neck tumors

Purpose

We aimed to build a machine learning-based model to predict radiation-induced optic neuropathy in patients who had treated head and neck cancers with radiotherapy.

Materials and methods

To measure radiation-induced optic neuropathy, the visual evoked potential values were obtained in both case and control groups and compared. Radiomics features were extracted from the area segmented which included the right and left optic nerves and chiasm. We integrated CT image features with dosimetric and clinical data subsequently, ranked 5 supervised ML models Bernoulli Naive Bayes, Decision Tree, Gradient Boosting Decision Trees, K-Nearest Neighbor, and Random Forest on 4 input datasets to predict radiation-induced visual complications classifiers by implementing 5-fold cross-validation. The F1 score, accuracy, sensitivity, specificity, and area under the ROC curve were compared to access prediction capability.

Results

radiation-induced optic neuropathy affected 31 % of the patients. 856 radiomic characteristics were extracted and selected from each segmented area. Decision Tree and Random Forest with the highest AUC (97 % and 95 % respectively) among the five classifiers were the most powerful algorithms to predict radiation-induced optic neuropathy. Chiasm with higher sensitivity and precision was able to predict radiation-induced optic neuropathy better than right or left optic nerve or combination of all radiomic features.

Conclusion

We found that combination of radiomic, dosimetric, and clinical factors can predict radiation-induced optic neuropathy after radiation treatment with high accuracy. To acquire more reliable results, it is recommended to conduct visual evoked potential tests before and after radiation therapy, with multiple follow-up courses and more patients.

Machine learning prediction model for oral mucositis risk in head and neck radiotherapy: a preliminary study

PURPOSE

Oral mucositis (OM) reflects a complex interplay of several risk factors. Machine learning (ML) is a promising frontier in science, capable of processing dense information. This study aims to assess the performance of ML in predicting OM risk in patients undergoing head and neck radiotherapy.

METHODS

Clinical data were collected from 157 patients with oral and oropharyngeal squamous cell carcinoma submitted to radiotherapy. Grade 2 OM or higher was considered (NCI). Two dataset versions were used; in the first version, all data were considered, and in the second version, a feature selection was added. Age, smoking status, surgery, radiotherapy prescription dose, treatment modality, histopathological differentiation, tumor stage, presence of oral cancer lesion, and tumor location were selected as key features. The training process used a fivefold cross-validation strategy with 10 repetitions. A total of 4 algorithms and 3 scaling methods were trained (12 models), without using data augmentation.

RESULTS

A comparative assessment was performed. Accuracy greater than 55% was considered. No relevant results were achieved with the first version, closest performance was Decision Trees with 52% of accuracy, 42% of sensitivity, and 60% of specificity. For the second version, relevant results were achieved, K-Nearest Neighbors outperformed with 64% accuracy, 58% sensitivity, and 68% specificity.

CONCLUSION

ML demonstrated promising results in OM risk prediction. Model improvement was observed after feature selection. Best result was achieved with the KNN model. This is the first study to test ML for OM risk prediction using clinical data.

NRG Oncology White Paper on the Relative Biological Effectiveness in Proton Therapy

This position paper, led by the NRG Oncology Particle Therapy Work Group, focuses on the concept of relative biologic effect (RBE) in clinical proton therapy (PT), with the goal of providing recommendations for the next-generation clinical trials with PT on the best practice of investigating and using RBE, which could deviate from the current standard proton RBE value of 1.1 relative to photons. In part 1, current clinical utilization and practice are reviewed, giving the context and history of RBE. Evidence for variation in RBE is presented along with the concept of linear energy transfer (LET). The intertwined nature of tumor radiobiology, normal tissue constraints, and treatment planning with LET and RBE considerations is then reviewed. Part 2 summarizes current and past clinical data and then suggests the next steps to explore and employ tools for improved dynamic models for RBE. In part 3, approaches and methods for the next generation of prospective clinical trials are explored, with the goal of optimizing RBE to be both more reflective of clinical reality and also deployable in trials to allow clinical validation and interpatient comparisons. These concepts provide the foundation for personalized biologic treatments reviewed in part 4. Finally, we conclude with a summary including short- and long-term scientific focus points for clinical PT. The practicalities and capacity to use RBE in treatment planning are reviewed and considered with more biological data in hand. The intermediate step of LET optimization is summarized and proposed as a potential bridge to the ultimate goal of case-specific RBE planning that can be achieved as a hypothesis-generating tool in near-term proton trials.

Study of late toxicity biomarkers of locally advanced head and neck cancer patients treated with radiotherapy plus cisplatin or cetuximab points to the relevance of skin macrophages (TOX-TTCC-2015-01)

PURPOSE

Radiotherapy (RT) with concomitant cisplatin (CRT) or cetuximab (ERT) are accepted treatment options for locally advanced squamous cell carcinoma of the head and neck (LA-SCCHN). Long-term adverse events (AEs) have a vast impact on patients' quality of life. This study explored tissue biomarkers which could help predict late toxicity.

METHODS/PATIENTS

Single-institution prospective study including patients aged ≥ 18 with histologically confirmed newly diagnosed LA-SCCHN treated with RT and either concomitant cisplatin q3w or weekly cetuximab, according to institutional protocols. All patients underwent pre- and post-treatment skin biopsies of neck regions included in the clinical target volume. Angiogenesis, macrophages, and extracellular matrix (ECM) markers were evaluated by immunohistochemistry (IHC).

RESULTS

From April 15, 2016, to December 11, 2017; 31 patients were evaluated [CRT = 12 (38.7%) and ERT = 19 (61.3%)]. 27 patients (87%) had received induction chemotherapy. All patients finished RT as planned. IHC expression of vasculature (CD34) and collagen (Masson's Trichrome) did not differ significantly between and within CRT and ERT arms. Conversely, an increased CD68 and CD163 macrophage infiltration expression was observed after treatment, without significant impact of treatment modality. Patients with higher late toxicity showed lower expression of macrophage markers in pre-treatment samples compared with those with lower late toxicity, with statistically significant differences for CD68.

CONCLUSIONS

Angiogenesis and ECM biomarkers did not differ significantly between CRT and ERT. Macrophage markers increased after both treatments and deserve further investigation as predictors of late toxicity in LA-SCCHN patients. [Protocol code: TOX-TTCC-2015-01/Spanish registry of clinical studies (REec): 2015-003012-21/Date of registration: 27/01/2016].

Breast cancer radiobiology: The renaissance of whole breast radiation fractionation (Review)

Breast cancer radiotherapy has evolved significantly, driven by decades of research into fractionation schedules aimed at optimizing treatment efficacy and minimizing toxicity. Initial trials such as NSABP B-06 and EBCTCG meta-analyses established the benefits of adjuvant whole-breast irradiation in reducing local recurrence and improving survival rates. The linear-quadratic (LQ) model provided a framework to understand tissue response to radiation, highlighting the importance of the α/β ratio in determining fractionation sensitivity. The present scoping review aimed to identify and describe hypofractionation regimens for whole breast radiotherapy and evaluate dose differences using the LQ model across proposed α/β ratios. A comprehensive PubMed search for clinical trials published since 2010 on hypo-fractionated regimens was performed. Studies discussing α/β ratios for breast cancer have been also searched. Data on dose, fractions and α/β ratios were collected, and biologically effective dose (BED) and equivalent dose in 2 Gy fractions were calculated. The coefficient of variation for BED varied with α/β ratios, showing the lowest variability for an α/β ratio of ~3 without tumor repopulation and increased with repopulation (BED-kT; k is a constant that depends on the repopulation rate of the tumor, and T is the total treatment time in days). Significant differences in BED variances were observed across α/β ratios (F-statistic 219.6, P<0.0001). START trials (P, A, and B) established α/β ratios of 3-4 Gy for breast cancer and normal tissues, confirming that hypofractionation is as effective as standard fractionation with potentially fewer late toxicities. Subsequent trials, such as FAST and FAST-Forward, demonstrated that ultra-hypofractionation is equivalent in tumor compared with conventional regimens. Further research is needed to gain a stronger understanding of radiobiological properties of breast cancer cells. Advances in radiotherapy technologies and the integration of biomarkers, radiomics and genomics are transforming treatment, moving towards precision medicine.

Predicting radiation pneumonitis in lung cancer using machine learning and multimodal features: a systematic review and meta-analysis of diagnostic accuracy

OBJECTIVES

To evaluate the diagnostic accuracy of machine learning models incorporating multimodal features for predicting radiation pneumonitis in lung cancer through a systematic review and meta-analysis.

METHODS

Relevant studies were identified through a systematic search of PubMed, Web of Science, Embase, and the Cochrane Library from October 2003 to December 2023. Additional studies were located by reviewing bibliographies and relevant websites. Two independent researchers screened titles, abstracts, and full-text articles according to predefined inclusion and exclusion criteria. Data extraction was performed using standardized forms, and study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. The primary outcomes, including combined sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC), were calculated using STATA MP-64 software(Stata Corporation LLC, College Station, USA) with a random-effects model. Meta-analysis was conducted to synthesize diagnostic accuracy measures, and analyses of heterogeneity and publication bias were performed.

RESULTS

A total of 1,406 patients with primary lung cancer were included in this systematic review, drawing data from 9 studies. The pooled analysis revealed a sensitivity of 0.74 [0.58-0.85] and a specificity of 0.91 [0.87-0.95] for machine learning models in diagnosing radiation pneumonitis. The positive likelihood ratio (PLR) was 8.69 [5.21-14.50], the negative likelihood ratio (NLR) was 0.28 [0.16-0.49], and the diagnostic odds ratio (DOR) was 30.73 [11.96-78.97]. The area under the curve (AUC) was 0.93 [0.90-0.95], indicating excellent diagnostic performance. Meta-regression analysis identified that the number of machine learning models, year of publication, and study design contributed to heterogeneity among studies. No evidence of publication bias was found. Overall, machine learning models incorporating multimodal characteristics demonstrated 75% accuracy in predicting moderate to severe radiation pneumonitis.

CONCLUSION

In conclusion, by integrating the current machine learning (ML) algorithm's ability in big data mining, a predictive model can be constructed by combining multi-modal features such as genetics, imaging, and cell factors. By selecting multiple machine learning algorithm frameworks and competing for the best combination model based on research goals, the reliability and accuracy of the radiation pneumonitis prediction model can be greatly improved.

TRIAL REGISTRATION

PROSPERO (CRD42024497599).

CT-based radiomics for predicting breast cancer radiotherapy side effects

Skin inflammation with the potential sequel of moist epitheliolysis and edema constitute the most frequent breast radiotherapy (RT) acute side effects. The aim of this study was to compare the predictive value of tissue-derived radiomics features to the total breast volume (TBV) for the moist cells epitheliolysis as a surrogate for skin inflammation, and edema. Radiomics features were extracted from computed tomography (CT) scans of 252 breast cancer patients from two volumes of interest: TBV and glandular tissue (GT). Machine learning classifiers were trained on radiomics and clinical features, which were evaluated for both side effects. The best radiomics model was a least absolute shrinkage and selection operator (LASSO) classifier, using TBV features, predicting moist cells epitheliolysis, achieving an area under the receiver operating characteristic (AUROC) of 0.74. This was comparable to TBV breast volume (AUROC of 0.75). Combined models of radiomics and clinical features did not improve performance. Exclusion of volume-correlated features slightly reduced the predictive performance (AUROC 0.71). We could demonstrate the general propensity of planning CT-based radiomics models to predict breast RT-dependent side effects. Mammary tissue was more predictive than glandular tissue. The radiomics features performance was influenced by their high correlation to TBV volume.

The Role of Artificial Intelligence on Tumor Boards: Perspectives from Surgeons, Medical Oncologists and Radiation Oncologists

The integration of multidisciplinary tumor boards (MTBs) is fundamental in delivering state-of-the-art cancer treatment, facilitating collaborative diagnosis and management by a diverse team of specialists. Despite the clear benefits in personalized patient care and improved outcomes, the increasing burden on MTBs due to rising cancer incidence and financial constraints necessitates innovative solutions. The advent of artificial intelligence (AI) in the medical field offers a promising avenue to support clinical decision-making. This review explores the perspectives of clinicians dedicated to the care of cancer patients-surgeons, medical oncologists, and radiation oncologists-on the application of AI within MTBs. Additionally, it examines the role of AI across various clinical specialties involved in cancer diagnosis and treatment. By analyzing both the potential and the challenges, this study underscores how AI can enhance multidisciplinary discussions and optimize treatment plans. The findings highlight the transformative role that AI may play in refining oncology care and sustaining the efficacy of MTBs amidst growing clinical demands.

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.

Imaging Analytics using Artificial Intelligence in Oncology: A Comprehensive Review

The present era has seen a surge in artificial intelligence-related research in oncology, mainly using deep learning, because of powerful computer hardware, improved algorithms and the availability of large amounts of data from open-source domains and the use of transfer learning. Here we discuss the multifaceted role of deep learning in cancer care, ranging from risk stratification, the screening and diagnosis of cancer, to the prediction of genomic mutations, treatment response and survival outcome prediction, through the use of convolutional neural networks. Another role of artificial intelligence is in the generation of automated radiology reports, which is a boon in high-volume centres to minimise report turnaround time. Although a validated and deployable deep-learning model for clinical use is still in its infancy, there is ongoing research to overcome the barriers for its universal implementation and we also delve into this aspect. We also briefly describe the role of radiomics in oncoimaging. Artificial intelligence can provide answers pertaining to cancer management at baseline imaging, saving cost and time. Imaging biobanks, which are repositories of anonymised images, are also briefly described. We also discuss the commercialisation and ethical issues pertaining to artificial intelligence. The latest generation generalist artificial intelligence model is also briefly described at the end of the article. We believe this article will not only enrich knowledge, but also promote research acumen in the minds of readers to take oncoimaging to another level using artificial intelligence and also work towards clinical translation of such research.

Metabolomics in Radiotherapy-Induced Early Adverse Skin Reactions of Breast Cancer Patients

Background

Early adverse skin reactions (EASRs) are common side effects of radiotherapy (RT) that impact the quality of life of breast cancer patients. This study used global metabolomics profiles of breast cancer populations to identify metabolic pathways and biomarkers significantly associated with RT-induced EASRs to identify potential targets for precision interventions.

Methods

We used a frequency-matched study design to identify pre-RT urine samples from 60 female breast cancer patients (30 with high and 30 with low EASRs) for metabolomic analysis by Metabolon Inc. using UPLC-MS/MS and GC-MS. Using MetaboAnalyst, we performed metabolomic data analysis and visualization on 84 candidate metabolites from 478 total compounds. We used the Oncology Nursing Society (ONS) Skin Toxicity Criteria (0-6) for EASRs assessment.

Results

Seven metabolic pathways were significantly associated with RT-induced EASRs, including alanine, aspartate, and glutamate metabolism (p = 0.0028), caffeine metabolism (p = 0.0360), pentose and glucuronate interconversions (p = 0.0028), glycine, serine, and threonine metabolism (p = 0.0360), beta-alanine metabolism (p = 0.0210), pantothenate and CoA biosynthesis (p = 0.0028), and glutathione metabolism (p = 0.0490). The alanine, aspartate, and glutamate metabolic pathway had the lowest false discovery rate (FDR)-adjusted p-value and the highest impact value of 0.60. Thirteen metabolite biomarkers were significantly associated with RT-induced EASRs.

Conclusion

Our data show that the alanine, aspartate, and glutamate metabolism pathways had the highest impact value on RT-induced EASRs. Future larger studies are warranted to validate our findings and facilitate targeted interventions for preventing or mitigating RT-induced EASRs, offering a promising direction for further research and clinical applications.

Dosimetric and toxicity comparison between Syed-Neblett and Fletcher-Suit-Delclos Tandem and Ovoid applicators in high dose rate cervix cancer brachytherapy

PURPOSE

To compare patient and tumor characteristics, dosimetry, and toxicities between interstitial Syed-Neblett and intracavitary Fletcher-Suit-Delclos Tandem and Ovoid (T&O) applicators in high dose rate (HDR) cervical cancer brachytherapy.

METHODS

A retrospective analysis was performed for cervical cancer patients treated with 3D-based HDR brachytherapy from 2011 to 2023 at a single institution. Dosimetric parameters for high-risk clinical target volume and organs at risk were obtained. Toxicities were evaluated using the Common Terminology Criteria for Adverse Events version 5.0.

RESULTS

A total of 115 and 58 patients underwent Syed and T&O brachytherapy, respectively. Patients treated with Syed brachytherapy were more likely to have larger tumors and FIGO stage III or IV disease. The median D2cc values to the bladder, small bowel, and sigmoid colon were significantly lower for Syed brachytherapy. Patients treated with Syed brachytherapy were significantly more likely to be free of acute gastrointestinal (44% vs. 21%, p = 0.003), genitourinary (58% vs. 36%, p = 0.01), and vaginal toxicities (60% vs. 33%, p = 0.001) within 6 months following treatment compared to patients treated with T&O applicators. In contrast, Syed brachytherapy patients were more likely to experience late gastrointestinal (68% vs. 49%, p = 0.082), genitourinary (51% vs. 35%, p = 0.196), and vaginal toxicities (70% vs. 57%, p = 0.264).

CONCLUSIONS

Syed-Neblett and T&O applicators are suitable for HDR brachytherapy for cervical cancer in distinct patient populations. Acute toxicities are more prevalent with T&O applicators, while patients treated with Syed-Neblett applicators are more likely to develop late toxicities.

Improving Pediatric Normal Tissue Radiation Dose-Response Modeling in Children With Cancer: A PENTEC Initiative

The development of normal tissue radiation dose-response models for children with cancer has been challenged by many factors, including small sample sizes; the long length of follow-up needed to observe some toxicities; the continuing occurrence of events beyond the time of assessment; the often complex relationship between age at treatment, normal tissue developmental dynamics, and age at assessment; and the need to use retrospective dosimetry. Meta-analyses of published pediatric outcome studies face additional obstacles of incomplete reporting of critical dosimetric, clinical, and statistical information. This report describes general methods used to address some of the pediatric modeling issues. It highlights previous single- and multi-institutional pediatric dose-response studies and summarizes how each PENTEC taskforce addressed the challenges and limitations of the reviewed publications in constructing, when possible, organ-specific dose-effect models.

Radiation Therapy Technology Advances and Mitigation of Subsequent Neoplasms in Childhood Cancer Survivors

PURPOSE

In this Pediatric Normal Tissue Effects in the Clinic (PENTEC) vision paper, challenges and opportunities in the assessment of subsequent neoplasms (SNs) from radiation therapy (RT) are presented and discussed in the context of technology advancement.

METHODS AND MATERIALS

The paper discusses the current knowledge of SN risks associated with historic, contemporary, and future RT technologies. Opportunities for research and SN mitigation strategies in pediatric patients with cancer are reviewed.

RESULTS

Present experience with radiation carcinogenesis is from populations exposed during widely different scenarios. Knowledge gaps exist within clinical cohorts and follow-up; dose-response and volume effects; dose-rate and fractionation effects; radiation quality and proton/particle therapy; age considerations; susceptibility of specific tissues; and risks related to genetic predisposition. The biological mechanisms associated with local and patient-level risks are largely unknown.

CONCLUSIONS

Future cancer care is expected to involve several available RT technologies, necessitating evidence and strategies to assess the performance of competing treatments. It is essential to maximize the utilization of existing follow-up while planning for prospective data collection, including standardized registration of individual treatment information with linkage across patient databases.

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

BACKGROUND

Radiation induced acute skin toxicity (AST) is considered as a common side effect of breast radiation therapy. The goal of this study was to design dosiomics-based machine learning (ML) models for prediction of AST, to enable creating optimized treatment plans for high-risk individuals.

METHODS

Dosiomics features extracted using Pyradiomics tool (v3.0.1), along with treatment plan-derived dose volume histograms (DVHs), and patient-specific treatment-related (PTR) data of breast cancer patients were used for modeling. Clinical scoring was done using the Common Terminology Criteria for Adverse Events (CTCAE) V4.0 criteria for skin-specific symptoms. The 52 breast cancer patients were grouped into AST 2 + (CTCAE ≥ 2) and AST 2 - (CTCAE < 2) toxicity grades to facilitate AST modeling. They were randomly divided into training (70%) and testing (30%) cohorts. Multiple prediction models were assessed through multivariate analysis, incorporating different combinations of feature groups (dosiomics, DVH, and PTR) individually and collectively. In total, seven unique combinations, along with seven classification algorithms, were considered after feature selection. The performance of each model was evaluated on the test group using the area under the receiver operating characteristic curve (AUC) and f1-score. Accuracy, precision, and recall of each model were also studied. Statistical analysis involved features differences between AST 2 - and AST 2 + groups and cutoff value calculations.

RESULTS

Results showed that 44% of the patients developed AST 2 + after Tomotherapy. The dosiomics (DOS) model, developed using dosiomics features, exhibited a noteworthy improvement in AUC (up to 0.78), when spatial information is preserved in the dose distribution, compared to DVH features (up to 0.71). Furthermore, a baseline ML model created using only PTR features for comparison with DOS models showed the significance of dosiomics in early AST prediction. By employing the Extra Tree (ET) classifiers, the DOS + DVH + PTR model achieved a statistically significant improved performance in terms of AUC (0.83; 95% CI 0.71-0.90), accuracy (0.70), precision (0.74) and sensitivity (0.72) compared to other models.

CONCLUSIONS

This study confirmed the benefit of dosiomics-based ML in the prediction of AST. However, the combination of dosiomics, DVH, and PTR yields significant improvement in AST prediction. The results of this study provide the opportunity for timely interventions to prevent the occurrence of radiation induced AST.

Determining risk and predictors of head and neck cancer treatment-related lymphedema: A clinicopathologic and dosimetric data mining approach using interpretable machine learning and ensemble feature selection

Background and purpose

The ability to determine the risk and predictors of lymphedema is vital in improving the quality of life for head and neck (HN) cancer patients. However, selecting robust features is challenging due to the multicollinearity and high dimensionality of radiotherapy (RT) data. This study aims to overcome these challenges using an ensemble feature selection technique with machine learning (ML).

Materials and methods

Thirty organs-at-risk, including bilateral cervical lymph node levels, were contoured, and dose-volume data were extracted from 76 HN treatment plans. Clinicopathologic data was collected. Ensemble feature selection was used to reduce the number of features. Using the reduced features as input to ML and competing risk models, internal and external lymphedema prediction capability was evaluated with the ML models, and time to lymphedema event and risk stratification were estimated using the risk models.

Results

Two ML models, XGBoost and random forest, exhibited robust prediction performance. They achieved average F1-scores and AUCs of 84 ± 3.3 % and 79 ± 11.9 % (external lymphedema), and 64 ± 12 % and 78 ± 7.9 % (internal lymphedema). Predictive ML and risk models identified common predictors, including bulky node involvement, high dose to various lymph node levels, and lymph nodes removed during surgery. At 180 days, removing 0-25, 26-50, and > 50 lymph nodes increased external lymphedema risk to 72.1 %, 95.6 %, and 57.7 % respectively (p = 0.01).

Conclusion

Our approach, involving the reduction of HN RT data dimensionality, resulted in effective ML models for HN lymphedema prediction. Predictive dosimetric features emerged from both predictive and competing risk models. Consistency with clinicopathologic features from other studies supports our methodology.

Artificial neural network-assisted prediction of radiobiological indices in head and neck cancer

Background and purpose

We proposed an artificial neural network model to predict radiobiological parameters for the head and neck squamous cell carcinoma patients treated with radiation therapy. The model uses the tumor specification, demographics, and radiation dose distribution to predict the tumor control probability and the normal tissue complications probability. These indices are crucial for the assessment and clinical management of cancer patients during treatment planning.

Methods

Two publicly available datasets of 31 and 215 head and neck squamous cell carcinoma patients treated with conformal radiation therapy were selected. The demographics, tumor specifications, and radiation therapy treatment parameters were extracted from the datasets used as inputs for the training of perceptron. Radiobiological indices are calculated by open-source software using dosevolume histograms from radiation therapy treatment plans. Those indices were used as output in the training of a single-layer neural network. The distribution of data used for training, validation, and testing purposes was 70, 15, and 15%, respectively.

Results

The best performance of the neural network was noted at epoch number 32 with the mean squared error of 0.0465. The accuracy of the prediction of radiobiological indices by the artificial neural network in training, validation, and test phases were determined to be 0.89, 0.87, and 0.82, respectively. We also found that the percentage volume of parotid inside the planning target volume is the significant parameter for the prediction of normal tissue complications probability.

Conclusion

We believe that the model has significant potential to predict radiobiological indices and help clinicians in treatment plan evaluation and treatment management of head and neck squamous cell carcinoma patients.

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.

Comparing Performances of Predictive Models of Toxicity after Radiotherapy for Breast Cancer Using Different Machine Learning Approaches

PURPOSE

Different ML models were compared to predict toxicity in RT on a large cohort (n = 1314).

METHODS

The endpoint was RTOG G2/G3 acute toxicity, resulting in 204/1314 patients with the event. The dataset, including 25 clinical, anatomical, and dosimetric features, was split into 984 for training and 330 for internal tests. The dataset was standardized; features with a high p-value at univariate LR and with Spearman ρ>0.8 were excluded; synthesized data of the minority were generated to compensate for class imbalance. Twelve ML methods were considered. Model optimization and sequential backward selection were run to choose the best models with a parsimonious feature number. Finally, feature importance was derived for every model.

RESULTS

The model's performance was compared on a training-test dataset over different metrics: the best performance model was LightGBM. Logistic regression with three variables (LR3) selected via bootstrapping showed performances similar to the best-performing models. The AUC of test data is slightly above 0.65 for the best models (highest value: 0.662 with LightGBM).

CONCLUSIONS

No model performed the best for all metrics: more complex ML models had better performances; however, models with just three features showed performances comparable to the best models using many (n = 13-19) features.

Shedding light on the management of acute radiation dermatitis: insight from the MASCC Oncodermatology study group

This paper highlights a collection of eleven recently published manuscripts on the prevention and management of acute radiation dermatitis. These meta-analyses provide additional evidence for the updated clinical practice guidelines by the Multinational Association of Supportive Care in Cancer (MASCC) Oncodermatology study group for prevention and management of acute radiation dermatitis. The collection of papers elucidate the currently available evidence on acute radiation dermatitis, highlighting consolidated knowledge, effective treatments, and proposed areas for future clinical trials. Overall, a total of 51 randomized controlled trials were retrieved and included for quantitative analysis of an initial systematic review of literature from 1946 to January 2023. Discussion of the clinical impact of various therapeutic interventions include: antiperspirant and deodorant use, barrier films and dressings, natural and miscellaneous agents, photobiomodulation therapy, topical corticosteroids, topical non-steroidal agents, skin hygiene and washing, as well as StrataXRT and Mepitel film in breast cancer patients. The comprehensive nature of the meta-analyses and their related findings may help reduce the discrepancies in in treatment of acute radiation dermatitis and facilitate consistency of therapeutic interventions employed in clinical practice worldwide.

Efficacy of bethanechol chloride in the treatment of radiation-induced xerostomia in patients with head and neck cancer: A systematic review and meta-analysis

BACKGROUND AND PORPUSE

Salivary glands sustain collateral damage following radiotherapy (RT) to treat cancers of the head and neck, leading to complications, including xerostomia and hyposalivation. This systematic review (SR) with meta-analysis was performed to determine the effectiveness of bethanechol chloride in preventing salivary gland dysfunction in this context.

MATERIALS AND METHODS

Medline/Pubmed, Embase, Scopus, LILACS via Portal Regional BVS and Web of Science were searched electronically in accordance with the Cochrane manual and reported PRISMA guidelines.

RESULTS

170 patients from three studies were included. Results from the meta-analysis suggest that bethanechol chloride is associated with increases in: whole stimulating saliva (WSS) after RT (Std. MD 0.66, 95% CI 0.28 to 1.03, P < 0.001); whole resting saliva (WRS) during RT (Std. MD 0.4, 95% CI 0.04 to 0.76, P = 0.03); and WRS after RT (Std. MD 0.45, 95% CI 0.04 to 0.86, P = 0.03).

CONCLUSION

The present study suggests that bethanechol chloride therapy may be effective in patients with xerostomia and hyposalivation.

A comprehensive open-access database of electron backscattering coefficients for energies ranging from 0.1 keV to 15 MeV

PURPOSE

The characterization of electron backscattering is essential in medical physics for accurately assessing dose deposited around inhomogeneities where backscattering alters the spatial energy distribution pattern and for determining Monte-Carlo code's ability to effectively describe electron scattering and does calculation in a target volume. Recent machine learning advances have provided physicists with powerful tools for effectively extracting information and trends from extensive experiment observations if sufficiently sizeable datasets are available for data mining. We report on the development of a publicly accessible database on electron backscattering coefficients for solid targets.

ACQUISITION AND VALIDATION METHODS

The first database on electron-solid interactions was assembled in 1995. Data for bulk materials, limited to normal incidence and energies up to 100 keV, were primarily focusing on electron microscopy. To accommodate broad high-energy applications and include the most recent publications we have created a comprehensive database of electron backscattering coefficients, listed as a function of target atomic number and thickness, electron energy, and incidence angle. These additions resulted in a database of 3566 data points, compared to the previous database of 1430. The data collection includes only published experimental observations (no calculations or results fitting) with no attempt to judge their accuracy or quality. A limited number of data points were compared to recently published Monte-Carlo results.

DATA FORMAT AND USAGE NOTES

The presented database provides values of electron backscattering coefficients for 50 elements and 19 compounds at electron energies ranging from 0.1 keV to 15 MeV, presented in ASCII files. Each file contains the electron energy and backscattering coefficient with target thickness or electron incidence angle included where available, and the reference number shown in the last column. Additionally, the presented data were shown in the graphs for better visualization. The online database can be accessed from the website https://doi.org/10.5281/zenodo.7810951.

POTENTIAL APPLICATIONS

The database provides the most up-to-date source of experimentally obtained electron backscattering coefficients that can be used in theoretical and MC calculations and modeling validations. The data availability is still very limited for many solids and almost non-existent for compounds. Novel machine learning methods should be well adapted to predict these unknown values for various targets, thicknesses, energies, and incident angles utilizing the presented cleaned dataset.

Bibliometric analysis of the global scientific production on machine learning applied to different cancer types

Cancer disease is one of the main causes of death in the world, with million annual cases in the last decades. The need to find a cure has stimulated the search for efficient treatments and diagnostic procedures. One of the most promising tools that has emerged against cancer in recent years is machine learning (ML), which has raised a huge number of scientific papers published in a relatively short period of time. The present study analyzes global scientific production on ML applied to the most relevant cancer types through various bibliometric indicators. We find that over 30,000 studies have been published so far and observe that cancers with the highest number of published studies using ML (breast, lung, and colon cancer) are those with the highest incidence, being the USA and China the main scientific producers on the subject. Interestingly, the role of China and Japan in stomach cancer is correlated with the number of cases of this cancer type in Asia (78% of the worldwide cases). Knowing the countries and institutions that most study each area can be of great help for improving international collaborations between research groups and countries. Our analysis shows that medical and computer science journals lead the number of publications on the subject and could be useful for researchers in the field. Finally, keyword co-occurrence analysis suggests that ML-cancer research trends are focused not only on the use of ML as an effective diagnostic method, but also for the improvement of radiotherapy- and chemotherapy-based treatments.

Prediction of toxicity outcomes following radiotherapy using deep learning-based models: A systematic review

PURPOSE

This study aims to perform a comprehensive systematic review of deep learning (DL) models in predicting RT-induced toxicity.

MATERIALS AND METHODS

A literature review was performed following the PRISMA guidelines. Systematic searches were performed in PubMed, Scopus, Cochrane and Embase databases from the earliest record up to September 2022. Related studies on deep learning models for radiotherapy toxicity prediction were selected based on predefined PICOS criteria.

RESULTS

Fourteen studies of radiotherapy-treated patients on different types of cancer [prostate (n=2), HNC (n=4), liver (n=2), lung (n=4), cervical (n=1), and oesophagus (n=1)] were eligible for inclusion in the systematic review. Information regarding patient characteristics and model development was summarized. Several approaches, such as ensemble learning, data augmentation, and transfer learning, that were utilized by selected studies were discussed.

CONCLUSION

Deep learning techniques are able to produce a consistent performance for toxicity prediction. Future research using large and diverse datasets and standardization of the study methodologies are required to improve the consistency of the research output.

Delta-radiomics-based models for toxicity prediction in radiotherapy: A systematic review and meta-analysis

INTRODUCTION

Delta-radiomics models are potentially able to improve the treatment assessment than single-time point features. The purpose of this study is to systematically synthesize the performance of delta-radiomics-based models for radiotherapy (RT)-induced toxicity.

METHODS

A literature search was performed following the PRISMA guidelines. Systematic searches were performed in PubMed, Scopus, Cochrane and Embase databases in October 2022. Retrospective and prospective studies on the delta-radiomics model for RT-induced toxicity were included based on predefined PICOS criteria. A random-effect meta-analysis of AUC was performed on the performance of delta-radiomics models, and a comparison with non-delta radiomics models was included.

RESULTS

Of the 563 articles retrieved, 13 selected studies of RT-treated patients on different types of cancer (HNC = 571, NPC = 186, NSCLC = 165, oesophagus = 106, prostate = 33, OPC = 21) were eligible for inclusion in the systematic review. Included studies show that morphological and dosimetric features may improve the predictive model performance for the selected toxicity. Four studies that reported both delta and non-delta radiomics features with AUC were included in the meta-analysis. The AUC random effects estimate for delta and non-delta radiomics models were 0.80 and 0.78 with heterogeneity, I2 of 73% and 27% respectively.

CONCLUSION

Delta-radiomics-based models were found to be promising predictors of predefined end points. Future studies should consider using standardized methods and radiomics features and external validation to the reviewed delta-radiomics model.

Radiotherapy toxicity prediction using knowledge-constrained generalized linear model

Radiation therapy (RT) is a frontline approach to treating cancer. While the target of radiation dose delivery is the tumor, there is an inevitable spill of dose to nearby normal organs causing complications. This phenomenon is known as radiotherapy toxicity. To predict the outcome of the toxicity, statistical models can be built based on dosimetric variables received by the normal organ at risk (OAR), known as Normal Tissue Complication Probability (NTCP) models. To tackle the challenge of the high dimensionality of dosimetric variables and limited clinical sample sizes, statistical models with variable selection techniques are viable choices. However, existing variable selection techniques are data-driven and do not integrate medical domain knowledge into the model formulation. We propose a knowledge-constrained generalized linear model (KC-GLM). KC-GLM includes a new mathematical formulation to translate three pieces of domain knowledge into non-negativity, monotonicity, and adjacent similarity constraints on the model coefficients. We further propose an equivalent transformation of the KC-GLM formulation, which makes it possible to solve the model coefficients using existing optimization solvers. Furthermore, we compare KC-GLM and several well-known variable selection techniques via a simulation study and on two real datasets of prostate cancer and lung cancer, respectively. These experiments show that KC-GLM selects variables with better interpretability, avoids producing counter-intuitive and misleading results, and has better prediction accuracy.

The Promise and Future of Radiomics for Personalized Radiotherapy Dosing and Adaptation

Quantitative image analysis, also known as radiomics, aims to analyze large-scale quantitative features extracted from acquired medical images using hand-crafted or machine-engineered feature extraction approaches. Radiomics has great potential for a variety of clinical applications in radiation oncology, an image-rich treatment modality that utilizes computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) for treatment planning, dose calculation, and image guidance. A promising application of radiomics is in predicting treatment outcomes after radiotherapy such as local control and treatment-related toxicity using features extracted from pretreatment and on-treatment images. Based on these individualized predictions of treatment outcomes, radiotherapy dose can be sculpted to meet the specific needs and preferences of each patient. Radiomics can aid in tumor characterization for personalized targeting, especially for identifying high-risk regions within a tumor that cannot be easily discerned based on size or intensity alone. Radiomics-based treatment response prediction can aid in developing personalized fractionation and dose adjustments. In order to make radiomics models more applicable across different institutions with varying scanners and patient populations, further efforts are needed to harmonize and standardize the acquisition protocols by minimizing uncertainties within the imaging data.

Benchmarking machine learning approaches to predict radiation-induced toxicities in lung cancer patients

Background and purpose

Radiation-induced toxicities are common adverse events in lung cancer (LC) patients undergoing radiotherapy (RT). An accurate prediction of these adverse events might facilitate an informed and shared decision-making process between patient and radiation oncologist with a clearer view of life-balance implications in treatment choices. This work provides a benchmark of machine learning (ML) approaches to predict radiation-induced toxicities in LC patients built upon a real-world health dataset based on a generalizable methodology for their implementation and external validation.

Materials and Methods

Ten feature selection (FS) methods were combined with five ML-based classifiers to predict six RT-induced toxicities (acute esophagitis, acute cough, acute dyspnea, acute pneumonitis, chronic dyspnea, and chronic pneumonitis). A real-world health dataset (RWHD) built from 875 consecutive LC patients was used to train and validate the resulting 300 predictive models. Internal and external accuracy was calculated in terms of AUC per clinical endpoint, FS method, and ML-based classifier under analysis.

Results

Best performing predictive models obtained per clinical endpoint achieved comparable performances to methods from state-of-the-art at internal validation (AUC ≥ 0.81 in all cases) and at external validation (AUC ≥ 0.73 in 5 out of 6 cases).

Conclusion

A benchmark of 300 different ML-based approaches has been tested against a RWHD achieving satisfactory results following a generalizable methodology. The outcomes suggest potential relationships between underrecognized clinical factors and the onset of acute esophagitis or chronic dyspnea, thus demonstrating the potential that ML-based approaches have to generate novel data-driven hypotheses in the field.

Dosiomics-Based Prediction of Radiation-Induced Valvulopathy after Childhood Cancer

Valvular Heart Disease (VHD) is a known late complication of radiotherapy for childhood cancer (CC), and identifying high-risk survivors correctly remains a challenge. This paper focuses on the distribution of the radiation dose absorbed by heart tissues. We propose that a dosiomics signature could provide insight into the spatial characteristics of the heart dose associated with a VHD, beyond the already-established risk induced by high doses. We analyzed data from the 7670 survivors of the French Childhood Cancer Survivors' Study (FCCSS), 3902 of whom were treated with radiotherapy. In all, 63 (1.6%) survivors that had been treated with radiotherapy experienced a VHD, and 57 of them had heterogeneous heart doses. From the heart-dose distribution of each survivor, we extracted 93 first-order and spatial dosiomics features. We trained random forest algorithms adapted for imbalanced classification and evaluated their predictive performance compared to the performance of standard mean heart dose (MHD)-based models. Sensitivity analyses were also conducted for sub-populations of survivors with spatially heterogeneous heart doses. Our results suggest that MHD and dosiomics-based models performed equally well globally in our cohort and that, when considering the sub-population having received a spatially heterogeneous dose distribution, the predictive capability of the models is significantly improved by the use of the dosiomics features. If these findings are further validated, the dosiomics signature may be incorporated into machine learning algorithms for radiation-induced VHD risk assessment and, in turn, into the personalized refinement of follow-up guidelines.

Risk assessment based on dose-responsive and time-responsive genes to build PLS-DA models for exogenously induced lung injury

Xenobiotics can easily harm human lungs owing to the openness of the respiratory system. Identifying pulmonary toxicity remains challenging owing to several reasons: 1) no biomarkers for pulmonary toxicity are available that might help to detect lung injury; 2) traditional animal experiments are time-consuming; 3) traditional detection methods solely focus on poisoning accidents; 4) analytical chemistry methods hardly achieve universal detection. An in vitro testing system able to identify the pulmonary toxicity of contaminants from food, the environment, and drugs is urgently needed. Compounds are virtually infinite, whereas toxicological mechanisms are countable. Therefore, universal methods to identify and predict the risks of contaminants can be designed based on these well-known toxicity mechanisms. In this study, we established a dataset based on transcriptome sequencing of A549 cells upon treatment with different compounds. The representativeness of our dataset was analyzed using bioinformatics methods. Artificial intelligence methods, namely partial least squares discriminant analysis (PLS-DA) models, were employed for toxicity prediction and toxicant identification. The developed model predicted the pulmonary toxicity of compounds with a 92 % accuracy. These models were submitted to an external validation using highly heterogeneous compounds, which supported the accuracy and robustness of our developed methodology. This assay exhibits universal potential applications for water quality monitoring, crop pollution detection, food and drug safety evaluation, as well as chemical warfare agent detection.

Beyond diagnosis: is there a role for radiomics in prostate cancer management?

The role of imaging in pretreatment staging and management of prostate cancer (PCa) is constantly evolving. In the last decade, there has been an ever-growing interest in radiomics as an image analysis approach able to extract objective quantitative features that are missed by human eye. However, most of PCa radiomics studies have been focused on cancer detection and characterisation. With this narrative review we aimed to provide a synopsis of the recently proposed potential applications of radiomics for PCa with a management-based approach, focusing on primary treatments with curative intent and active surveillance as well as highlighting on recurrent disease after primary treatment. Current evidence is encouraging, with radiomics and artificial intelligence appearing as feasible tools to aid physicians in planning PCa management. However, the lack of external independent datasets for validation and prospectively designed studies casts a shadow on the reliability and generalisability of radiomics models, delaying their translation into clinical practice.Key points• Artificial intelligence solutions have been proposed to streamline prostate cancer radiotherapy planning.• Radiomics models could improve risk assessment for radical prostatectomy patient selection.• Delta-radiomics appears promising for the management of patients under active surveillance.• Radiomics might outperform current nomograms for prostate cancer recurrence risk assessment.• Reproducibility of results, methodological and ethical issues must still be faced before clinical implementation.

3D deep convolution neural network for radiation pneumonitis prediction following stereotactic body radiotherapy

In this study, we investigated 3D convolutional neural networks (CNNs) with input from radiographic and dosimetric datasets of primary lung tumors and surrounding lung volumes to predict the likelihood of radiation pneumonitis (RP). Pre-treatment, 3- and 6-month follow-up computed tomography (CT) and 3D dose datasets from one hundred and ninety-three NSCLC patients treated with stereotactic body radiotherapy (SBRT) were retrospectively collected and analyzed for this study. DenseNet-121 and ResNet-50 models were selected for this study as they are deep neural networks and have been proven to have high accuracy for complex image classification tasks. Both were modified with 3D convolution and max pooling layers to accept 3D datasets. We used a minority class oversampling approach and data augmentation to address the challenges of data imbalance and data scarcity. We built two sets of models for classification of three (No RP, Grade 1 RP, Grade 2 RP) and two (No RP, Yes RP) classes as outputs. The 3D DenseNet-121 models performed better (F1 score [0.81], AUC [0.91] [three class]; F1 score [0.77], AUC [0.84] [two class]) than the 3D ResNet-50 models (F1 score [0.54], AUC [0.72] [three-class]; F1 score [0.68], AUC [0.71] [two-class]) (p = 0.017 for three class predictions). We also attempted to identify salient regions within the input 3D image dataset via integrated gradient (IG) techniques to assess the relevance of the tumor surrounding volume for RP stratification. These techniques appeared to indicate the significance of the tumor and surrounding regions in the prediction of RP. Overall, 3D CNNs performed well to predict clinical RP in our cohort based on the provided image sets and radiotherapy dose information.

Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry

Purpose

Radiation-induced skin toxicity is a common and distressing side effect of breast radiation therapy (RT). We investigated the use of quantitative spectrophotometric markers as input parameters in supervised machine learning models to develop a predictive model for acute radiation toxicity.

Methods and materials

One hundred twenty-nine patients treated for adjuvant whole-breast radiotherapy were evaluated. Two spectrophotometer variables, i.e. the melanin (I_M) and erythema (I_E) indices, were used to quantitatively assess the skin physical changes. Measurements were performed at 4-time intervals: before RT, at the end of RT and 1 and 6 months after the end of RT. Together with clinical covariates, melanin and erythema indices were correlated with skin toxicity, evaluated using the Radiation Therapy Oncology Group (RTOG) guidelines. Binary group classes were labeled according to a RTOG cut-off score of ≥ 2. The patient's dataset was randomly split into a training and testing set used for model development/validation and testing (75%/25% split). A 5-times repeated holdout cross-validation was performed. Three supervised machine learning models, including support vector machine (SVM), classification and regression tree analysis (CART) and logistic regression (LR), were employed for modeling and skin toxicity prediction purposes.

Results

Thirty-four (26.4%) patients presented with adverse skin effects (RTOG ≥2) at the end of treatment. The two spectrophotometric variables at the beginning of RT (I_M,T0 and I_E,T0), together with the volumes of breast (PTV2) and boost surgical cavity (PTV1), the body mass index (BMI) and the dose fractionation scheme (FRAC) were found significantly associated with the RTOG score groups (p<0.05) in univariate analysis. The diagnostic performances measured by the area-under-curve (AUC) were 0.816, 0.734, 0.714, 0.691 and 0.664 for IM, IE, PTV2, PTV1 and BMI, respectively. Classification performances reported precision, recall and F1-values greater than 0.8 for all models. The SVM classifier using the RBF kernel had the best performance, with accuracy, precision, recall and F-score equal to 89.8%, 88.7%, 98.6% and 93.3%, respectively. CART analysis classified patients with I_M,T0 ≥ 99 to be associated with RTOG ≥ 2 toxicity; subsequently, PTV1 and PTV2 played a significant role in increasing the classification rate. The CART model provided a very high diagnostic performance of AUC=0.959.

Conclusions

Spectrophotometry is an objective and reliable tool able to assess radiation induced skin tissue injury. Using a machine learning approach, we were able to predict grade RTOG ≥2 skin toxicity in patients undergoing breast RT. This approach may prove useful for treatment management aiming to improve patient quality of life.

Human Health during Space Travel: State-of-the-Art Review

The field of human space travel is in the midst of a dramatic revolution. Upcoming missions are looking to push the boundaries of space travel, with plans to travel for longer distances and durations than ever before. Both the National Aeronautics and Space Administration (NASA) and several commercial space companies (e.g., Blue Origin, SpaceX, Virgin Galactic) have already started the process of preparing for long-distance, long-duration space exploration and currently plan to explore inner solar planets (e.g., Mars) by the 2030s. With the emergence of space tourism, space travel has materialized as a potential new, exciting frontier of business, hospitality, medicine, and technology in the coming years. However, current evidence regarding human health in space is very limited, particularly pertaining to short-term and long-term space travel. This review synthesizes developments across the continuum of space health including prior studies and unpublished data from NASA related to each individual organ system, and medical screening prior to space travel. We categorized the extraterrestrial environment into exogenous (e.g., space radiation and microgravity) and endogenous processes (e.g., alteration of humans' natural circadian rhythm and mental health due to confinement, isolation, immobilization, and lack of social interaction) and their various effects on human health. The aim of this review is to explore the potential health challenges associated with space travel and how they may be overcome in order to enable new paradigms for space health, as well as the use of emerging Artificial Intelligence based (AI) technology to propel future space health research.

Machine learning-based normal tissue complication probability model for predicting albumin-bilirubin (ALBI) grade increase in hepatocellular carcinoma patients

PURPOSE

The aim of this study was to develop a normal tissue complication probability model using a machine learning approach (ML-based NTCP) to predict the risk of radiation-induced liver disease in hepatocellular carcinoma (HCC) patients.

MATERIALS AND METHODS

The study population included 201 HCC patients treated with radiotherapy. The patients' medical records were retrospectively reviewed to obtain the clinical and radiotherapy data. Toxicity was defined by albumin-bilirubin (ALBI) grade increase. The normal liver dose-volume histogram was reduced to mean liver dose (MLD) based on the fraction size-adjusted equivalent uniform dose (2 Gy/fraction and α/β = 2). Three types of ML-based classification models were used, a penalized logistic regression (PLR), random forest (RF), and gradient-boosted tree (GBT) model. Model performance was compared using the area under the receiver operating characteristic curve (AUROC). Internal validation was performed by 5-fold cross validation and external validation was done in 44 new patients.

RESULTS

Liver toxicity occurred in 87 patients (43.1%). The best individual model was the GBT model using baseline liver function, liver volume, and MLD as inputs and the best overall model was an ensemble of the PLR and GBT models. An AUROC of 0.82 with a standard deviation of 0.06 was achieved for the internal validation. An AUROC of 0.78 with a standard deviation of 0.03 was achieved for the external validation. The behaviors of the best GBT model were also in good agreement with the domain knowledge on NTCP.

CONCLUSION

We propose the methodology to develop an ML-based NTCP model to estimate the risk of ALBI grade increase.

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.

The correlation between pre-treatment symptoms, acute and late toxicity and patient-reported health-related quality of life in non-small cell lung cancer patients: Results of the REQUITE study

BACKGROUND AND PURPOSE

To investigate the association between clinician-scored toxicities and patient-reported health-related quality of life (HRQoL), in early-stage (ES-) and locally-advanced (LA-) non-small cell lung cancer (NSCLC) patients receiving loco-regional radiotherapy, included in the international real-world REQUITE study.

MATERIALS AND METHODS

Clinicians scored eleven radiotherapy-related toxicities (and baseline symptoms) with the Common Terminology Criteria for Adverse Events version 4. HRQoL was assessed with the European Organization for Research and Treatment of Cancer core HRQoL questionnaire (EORTC-QLQ-C30). Statistical analyses used the mixed-model method; statistical significance was set at p = 0.01. Analyses were performed for baseline and subsequent time points up to 2 years after radiotherapy and per treatment modality, radiotherapy technique and disease stage.

RESULTS

Data of 435 patients were analysed. Pre-treatment, overall symptoms, dyspnea, chest wall pain, dysphagia and cough impacted overall HRQoL and specific domains. At subsequent time points, cough and dysphagia were overtaken by pericarditis in affecting HRQoL. Toxicities during concurrent chemo-radiotherapy and 3-dimensional radiotherapy had the most impact on HRQoL. Conversely, toxicities in sequential chemo-radiotherapy and SBRT had limited impact on patients' HRQoL. Stage impacts the correlations: LA-NSCLC patients are more adversely affected by toxicity than ES-NSCLC patients, mimicking the results of radiotherapy technique and treatment modality.

CONCLUSION

Pre-treatment symptoms and acute/late toxicities variously impact HRQoL of ES- and LA-NSCLC patients undergoing different treatment approaches and radiotherapy techniques. Throughout the disease, dyspnea seems crucial in this association, highlighting the additional effect of co-existing comorbidities. Our data call for optimized radiotherapy limiting toxicities that may affect patients' HRQoL.

Artificial intelligence in radiotherapy

Radiotherapy is a discipline closely integrated with computer science. Artificial intelligence (AI) has developed rapidly over the past few years. With the explosive growth of medical big data, AI promises to revolutionize the field of radiotherapy through highly automated workflow, enhanced quality assurance, improved regional balances of expert experiences, and individualized treatment guided by multi-omics. In addition to independent researchers, the increasing number of large databases, biobanks, and open challenges significantly facilitated AI studies on radiation oncology. This article reviews the latest research, clinical applications, and challenges of AI in each part of radiotherapy including image processing, contouring, planning, quality assurance, motion management, and outcome prediction. By summarizing cutting-edge findings and challenges, we aim to inspire researchers to explore more future possibilities and accelerate the arrival of AI radiotherapy.

Machine learning in neuro-oncology: toward novel development fields

PURPOSE

Artificial Intelligence (AI) involves several and different techniques able to elaborate a large amount of data responding to a specific planned outcome. There are several possible applications of this technology in neuro-oncology.

METHODS

We reviewed, according to PRISMA guidelines, available studies adopting AI in different fields of neuro-oncology including neuro-radiology, pathology, surgery, radiation therapy, and systemic treatments.

RESULTS

Neuro-radiology presented the major number of studies assessing AI. However, this technology is being successfully tested also in other operative settings including surgery and radiation therapy. In this context, AI shows to significantly reduce resources and costs maintaining an elevated qualitative standard. Pathological diagnosis and development of novel systemic treatments are other two fields in which AI showed promising preliminary data.

CONCLUSION

It is likely that AI will be quickly included in some aspects of daily clinical practice. Possible applications of these techniques are impressive and cover all aspects of neuro-oncology.

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.

Clinical and technical challenges of cancer reirradiation: Words of wisdom

Since the development of new radiotherapy techniques that have improved healthy tissue sparing, reirradiation (reRT) has become possible. The selection of patients eligible for reRT is complex given that it can induce severe or even fatal side effects. The first step should therefore be to assess, in the context of multidisciplinary staff meeting, the patient's physical status, the presence of sequelae resulting from the first irradiation and the best treatment option available. ReRT can be performed either curatively or palliatively to treat a cancer-related symptom that is detrimental to the patient's quality of life. The selected techniques for reRT should provide the best protection of healthy tissue. The construction of target volumes and the evaluation of constraints regarding the doses that can be used in this context have not yet been fully codified. These points raised in the literature suggest that randomized studies should be undertaken to answer pending questions.

An overview of artificial intelligence in oncology

Cancer is associated with significant morbimortality globally. Advances in screening, diagnosis, management and survivorship were substantial in the last decades, however, challenges in providing personalized and data-oriented care remain. Artificial intelligence (AI), a branch of computer science used for predictions and automation, has emerged as potential solution to improve the healthcare journey and to promote precision in healthcare. AI applications in oncology include, but are not limited to, optimization of cancer research, improvement of clinical practice (eg., prediction of the association of multiple parameters and outcomes - prognosis and response) and better understanding of tumor molecular biology. In this review, we examine the current state of AI in oncology, including fundamentals, current applications, limitations and future perspectives.

Rapid Progress in Intelligent Radiotherapy and Future Implementation

Radiotherapy is one of the major approaches to cancer treatment. Artificial intelligence in radiotherapy (shortly, Intelligent radiotherapy) mainly involves big data, deep learning, extended reality, digital twin, radiomics, Internet plus and Internet of Things (IoT), which establish an automatic and intelligent network platform consisting of radiotherapy preparation, target volume delineation, treatment planning, radiation delivery, quality assurance (QA) and quality control (QC), prognosis judgment and post-treatment follow-up. Intelligent radiotherapy is an interdisciplinary frontier discipline in infancy. The review aims to summary the important implements of intelligent radiotherapy in various areas and put forward the future of unmanned radiotherapy center.

PrACTiC: A Predictive Algorithm for Chemoradiotherapy-Induced Cytopenia in Glioblastoma Patients

Background

Chemotherapy-induced cytopenia is the most frequent side effect of chemoradiotherapy in glioblastoma patients which may lead to reduced delivery of treatment. This study aims to develop a predictive model that is able to forecast the cytopenia induced by temozolomide (TMZ) during concomitant chemoradiotherapy.

Methods

Medical records of 128 patients with newly diagnosed glioblastoma were evaluated to extract the baseline complete blood test before and during the six weeks of chemoradiotherapy to create a dataset for the development of ML models. Using the constructed dataset, different ML algorithms were trained and tested.

Results

Our proposed algorithm achieved accuracies of 85.6%, 88.7%, and 89.3% in predicting thrombocytopenia, lymphopenia, and neutropenia, respectively.

Conclusions

The algorithm designed and developed in this study, called PrACTiC, showed promising results in the accurate prediction of thrombocytopenia, neutropenia, and lymphopenia induced by TMZ in glioblastoma patients. PrACTiC can provide valuable insight for physicians and help them to make the necessary treatment modifications and prevent the toxicities.

Radiomics in prostate cancer: an up-to-date review

Prostate cancer (PCa) is the most common worldwide diagnosed malignancy in male population. The diagnosis, the identification of aggressive disease, and the post-treatment follow-up needs a more comprehensive and holistic approach. Radiomics is the extraction and interpretation of images phenotypes in a quantitative manner. Radiomics may give an advantage through advancements in imaging modalities and through the potential power of artificial intelligence techniques by translating those features into clinical outcome prediction. This article gives an overview on the current evidence of methodology and reviews the available literature on radiomics in PCa patients, highlighting its potential for personalized treatment and future applications.