Predicting outcomes in radiation oncology--multifactorial decision support systems

Identification of Calculous Pyonephrosis by CT-Based Radiomics and Deep Learning

Urgent detection of calculous pyonephrosis is crucial for surgical planning and preventing severe outcomes. This study aims to evaluate the performance of computed tomography (CT)-based radiomics and a three-dimensional convolutional neural network (3D-CNN) model, integrated with independent clinical factors, to identify patients with calculous pyonephrosis. We recruited 182 patients receiving either percutaneous nephrostomy tube placement or percutaneous nephrolithotomy for calculous hydronephrosis or pyonephrosis. The regions of interest were manually delineated on plain CT images and the CT attenuation value (HU) was measured. Radiomics analysis was performed using least absolute shrinkage and selection operator (LASSO). A 3D-CNN model was also developed. The better-performing machine-learning model was combined with independent clinical factors to build a comprehensive clinical machine-learning model. The performance of these models was assessed using receiver operating characteristic analysis and decision curve analysis. Fever, blood neutrophils, and urine leukocytes were independent risk factors for pyonephrosis. The radiomics model showed higher area under the curve (AUC) than the 3D-CNN model and HU (0.876 vs. 0.599, 0.578; p = 0.003, 0.002) in the testing cohort. The clinical machine-learning model surpassed the clinical model in both the training (0.975 vs. 0.904, p = 0.019) and testing (0.967 vs. 0.889, p = 0.045) cohorts.

Radiomics in Diagnosis, Grading, and Treatment Response Assessment of Soft Tissue Sarcomas: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

To evaluate radiomics in soft tissue sarcomas (STSs) for diagnostic accuracy, grading, and treatment response assessment, with a focus on clinical relevance.

METHODS

In this diagnostic accuracy study, radiomics was applied using multiple MRI sequences and AI classifiers, with histopathological diagnosis as the reference standard. Statistical analysis involved meta-analysis, random-effects model, and Deeks' funnel plot asymmetry test.

RESULTS

Among 579 unique titles and abstracts, 24 articles were included in the systematic review, with 21 used for meta-analysis. Radiomics demonstrated a pooled sensitivity of 84% (95% CI: 80-87) and specificity of 63% (95% CI: 56-70), AUC of 0.93 for diagnosis, sensitivity of 84% (95% CI: 82-87) and specificity of 73% (95% CI: 68-77), AUC of 0.91 for grading, and sensitivity of 83% (95% CI: 67-94) and specificity of 67% (95% CI: 59-74), AUC of 0.87 for treatment response assessment.

CONCLUSION

Radiomics exhibits potential for accurate diagnosis, grading, and treatment response assessment in STSs, emphasizing the need for standardization and prospective trials.

CLINICAL RELEVANCE STATEMENT

Radiomics offers precise tools for STS diagnosis, grading, and treatment response assessment, with implications for optimizing patient care and treatment strategies in this complex malignancy.

Predictive machine learning models for ascending aortic dilatation in patients with bicuspid and tricuspid aortic valves undergoing cardiothoracic surgery: a prospective, single-centre and observational study

OBJECTIVES

The objective of this study was to develop clinical classifiers aiming to identify prevalent ascending aortic dilatation in patients with bicuspid aortic valve (BAV) and tricuspid aortic valve (TAV).

DESIGN AND SETTING

A prospective, single-centre and observational cohort.

PARTICIPANTS

The study involved 543 BAV and 491 TAV patients with aortic valve disease and/or ascending aortic dilatation, excluding those with coronary artery disease, undergoing cardiothoracic surgery at the Karolinska University Hospital (Sweden).

MAIN OUTCOME MEASURES

Predictors of high risk of ascending aortic dilatation (defined as ascending aorta with a diameter above 40 mm) were identified through the application of machine learning algorithms and classic logistic regression models.

EXPOSURES

Comprehensive multidimensional data, including valve morphology, clinical information, family history of cardiovascular diseases, prevalent diseases, demographic details, lifestyle factors, and medication.

RESULTS

BAV patients, with an average age of 60.4±12.4 years, showed a higher frequency of aortic dilatation (45.3%) compared with TAV patients, who had an average age of 70.4±9.1 years (28.9% dilatation, p <0.001). Aneurysm prediction models for TAV patients exhibited mean area under the receiver-operating-characteristic curve (AUC) values above 0.8, with the absence of aortic stenosis being the primary predictor, followed by diabetes and high-sensitivity C reactive protein. Conversely, prediction models for BAV patients resulted in AUC values between 0.5 and 0.55, indicating low usefulness for predicting aortic dilatation. Classification results remained consistent across all machine learning algorithms and classic logistic regression models.

CONCLUSION AND RECOMMENDATION

Cardiovascular risk profiles appear to be more predictive of aortopathy in TAV patients than in patients with BAV. This adds evidence to the fact that BAV-associated and TAV-associated aortopathy involves different pathways to aneurysm formation and highlights the need for specific aneurysm preventions in these patients. Further, our results highlight that machine learning approaches do not outperform classical prediction methods in addressing complex interactions and non-linear relations between variables.

Rationale and design of the GOLDEN BRIDGE II: a cluster-randomised multifaceted intervention trial of an artificial intelligence-based cerebrovascular disease clinical decision support system to improve stroke outcomes and care quality in China

BACKGROUND

Given the swift advancements in artificial intelligence (AI), the utilisation of AI-based clinical decision support systems (AI-CDSSs) has become increasingly prevalent in the medical domain, particularly in the management of cerebrovascular disease.

AIMS

To describe the design, rationale and methods of a cluster-randomised multifaceted intervention trial aimed at investigating the effect of cerebrovascular disease AI-CDSS on the clinical outcomes of patients who had a stroke and on stroke care quality.

DESIGN

The GOLDEN BRIDGE II trial is a multicentre, open-label, cluster-randomised multifaceted intervention study. A total of 80 hospitals in China were randomly assigned to the AI-CDSS intervention group or the control group. For eligible participants with acute ischaemic stroke in the AI-CDSS intervention group, cerebrovascular disease AI-CDSS will provide AI-assisted imaging analysis, auxiliary stroke aetiology and pathogenesis analysis, and guideline-based treatment recommendations. In the control group, patients will receive the usual care. The primary outcome is the occurrence of new vascular events (composite of ischaemic stroke, haemorrhagic stroke, myocardial infarction or vascular death) at 3 months after stroke onset. The sample size was estimated to be 21 689 with a 26% relative reduction in the incidence of new composite vascular events at 3 months by using multiple quality-improving interventions provided by AI-CDSS. All analyses will be performed according to the intention-to-treat principle and accounted for clustering using generalised estimating equations.

CONCLUSIONS

Once the effectiveness is verified, the cerebrovascular disease AI-CDSS could improve stroke care and outcomes in China.

TRIAL REGISTRATION NUMBER

NCT04524624.

CT radiomics for predicting the prognosis of patients with stage II rectal cancer during the three-year period after surgery, chemotherapy and radiotherapy

Objective

Pre-treatment enhanced CT image data were used to train and build models to predict the efficacy of non-small cell lung cancer after conventional radiotherapy and chemotherapy using two classification algorithms, Logistic Regression (LR) and Gaussian Naive Baye (GNB).

Methods

In this study, we used pre-treatment enhanced CT image data for region of interest (ROI) sketching and feature extraction. We utilized the least absolute shrinkage and selection operator (LASSO) mutual confidence method for feature screening. We pre-screened logistic regression (LR) and Gaussian naive Bayes (GNB) classification algorithms and trained and modeled the screened features. We plotted 5-fold and 10-fold cross-validated receiver operating characteristic (ROC) curves to calculate the area under the curve (AUC). We performed DeLong's test for validation and plotted calibration curves and decision curves to assess model performance.

Results

A total of 102 patients were included in this study, and after a comparative analysis of the two models, LR had only slightly lower specificity than GNB, and higher sensitivity, accuracy, AUC value, precision, and F1 value than GNB (training set accuracy: 0.787, AUC value: 0.851; test set accuracy: 0.772, AUC value: 0.849), and the LR model has better performance in both the decision curve and the calibration curve.

Conclusion

CT can be used for efficacy prediction after radiotherapy and chemotherapy in NSCLC patients. LR is more suitable for predicting whether NSCLC prognosis is in remission without considering the computing speed.

Artificial general intelligence for radiation oncology

The emergence of artificial general intelligence (AGI) is transforming radiation oncology. As prominent vanguards of AGI, large language models (LLMs) such as GPT-4 and PaLM 2 can process extensive texts and large vision models (LVMs) such as the Segment Anything Model (SAM) can process extensive imaging data to enhance the efficiency and precision of radiation therapy. This paper explores full-spectrum applications of AGI across radiation oncology including initial consultation, simulation, treatment planning, treatment delivery, treatment verification, and patient follow-up. The fusion of vision data with LLMs also creates powerful multimodal models that elucidate nuanced clinical patterns. Together, AGI promises to catalyze a shift towards data-driven, personalized radiation therapy. However, these models should complement human expertise and care. This paper provides an overview of how AGI can transform radiation oncology to elevate the standard of patient care in radiation oncology, with the key insight being AGI's ability to exploit multimodal clinical data at scale.

Standardized Radiomics Analysis of Clinical Myocardial Perfusion Stress SPECT Images to Identify Coronary Artery Calcification

PURPOSE

Myocardial perfusion (MP) stress single-photon emission computed tomography (SPECT) is an established diagnostic test for patients suspected of coronary artery disease (CAD). Meanwhile, coronary artery calcification (CAC) scoring obtained from diagnostic CT is a highly sensitive test, offering incremental diagnostic information in identifying patients with significant CAD yet normal MP stress SPECT (MPSS) scans. However, after decades of wide utilization of MPSS, CAC is not commonly reimbursed (e.g. by the CMS), nor widely deployed in community settings. We studied the potential of complementary information deduced from the radiomics analysis of normal MPSS scans in predicting the CAC score.

METHODS

We collected data from 428 patients with normal (non-ischemic) MPSS (99mTc-sestamibi; consensus reading). A nuclear medicine physician verified iteratively reconstructed images (attenuation-corrected) to be free from fixed perfusion defects and artifactual attenuation. Three-dimensional images were automatically segmented into four regions of interest (ROIs), including myocardium and three vascular segments (left anterior descending [LAD]-left circumference [LCX]-right coronary artery [RCA]). We used our software package, standardized environment for radiomics analysis (SERA), to extract 487 radiomic features in compliance with the image biomarker standardization initiative (IBSI). Isotropic cubic voxels were discretized using fixed bin-number discretization (eight schemes). We first performed blind-to-outcome feature selection focusing on a priori usefulness, dynamic range, and redundancy of features. Subsequently, we performed univariate and multivariate machine learning analyses to predict CAC scores from i) selected radiomic features, ii) 10 clinical features, and iii) combined radiomics + clinical features. Univariate analysis invoked Spearman correlation with Benjamini-Hotchberg false-discovery correction. The multivariate analysis incorporated stepwise linear regression, where we randomly selected a 15% test set and divided the other 85% of data into 70% training and 30% validation sets. Training started from a constant (intercept) model, iteratively adding/removing features (stepwise regression), invoking the Akaike information criterion (AIC) to discourage overfitting. Validation was run similarly, except that the training output model was used as the initial model. We randomized training/validation sets 20 times, selecting the best model using log-likelihood for evaluation in the test set. Assessment in the test set was performed thoroughly by running the entire operation 50 times, subsequently employing Fisher's method to verify the significance of independent tests.

RESULTS

Unsupervised feature selection significantly reduced 8×487 features to 56. In univariate analysis, no feature survived the false-discovery rate (FDR) to directly correlate with CAC scores. Applying Fisher's method to the multivariate regression results demonstrated combining radiomics with the clinical features to enhance the significance of the prediction model across all cardiac segments.  Conclusions: Our standardized and statistically robust multivariate analysis demonstrated significant prediction of the CAC score for all cardiac segments when combining MPSS radiomic features with clinical features, suggesting radiomics analysis can add diagnostic or prognostic value to standard MPSS for wide clinical usage.

Predicting the Tumour Response to Radiation by Modelling the Five Rs of Radiotherapy Using PET Images

Despite the intensive use of radiotherapy in clinical practice, its effectiveness depends on several factors. Several studies showed that the tumour response to radiation differs from one patient to another. The non-uniform response of the tumour is mainly caused by multiple interactions between the tumour microenvironment and healthy cells. To understand these interactions, five major biologic concepts called the "5 Rs" have emerged. These concepts include reoxygenation, DNA damage repair, cell cycle redistribution, cellular radiosensitivity and cellular repopulation. In this study, we used a multi-scale model, which included the five Rs of radiotherapy, to predict the effects of radiation on tumour growth. In this model, the oxygen level was varied in both time and space. When radiotherapy was given, the sensitivity of cells depending on their location in the cell cycle was taken in account. This model also considered the repair of cells by giving a different probability of survival after radiation for tumour and normal cells. Here, we developed four fractionation protocol schemes. We used simulated and positron emission tomography (PET) imaging with the hypoxia tracer 18F-flortanidazole (18F-HX4) images as input data of our model. In addition, tumour control probability curves were simulated. The result showed the evolution of tumours and normal cells. The increase in the cell number after radiation was seen in both normal and malignant cells, which proves that repopulation was included in this model. The proposed model predicts the tumour response to radiation and forms the basis for a more patient-specific clinical tool where related biological data will be included.

Artificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy

The rapid development of artificial intelligence (AI) technologies in the context of the vast amount of collectable data obtained from high-throughput sequencing has led to an unprecedented understanding of cancer and accelerated the advent of a new era of clinical oncology with a tone of precision treatment and personalized medicine. However, the gains achieved by a variety of AI models in clinical oncology practice are far from what one would expect, and in particular, there are still many uncertainties in the selection of clinical treatment options that pose significant challenges to the application of AI in clinical oncology. In this review, we summarize emerging approaches, relevant datasets and open-source software of AI and show how to integrate them to address problems from clinical oncology and cancer research. We focus on the principles and procedures for identifying different antitumor strategies with the assistance of AI, including targeted cancer therapy, conventional cancer therapy, and cancer immunotherapy. In addition, we also highlight the current challenges and directions of AI in clinical oncology translation. Overall, we hope this article will provide researchers and clinicians with a deeper understanding of the role and implications of AI in precision cancer therapy, and help AI move more quickly into accepted cancer guidelines.

Prediction of preoperative in-hospital mortality rate in patients with acute aortic dissection by machine learning: a two-centre, retrospective cohort study

OBJECTIVES

To conduct a comprehensive analysis of demographic information, medical history, and blood pressure (BP) and heart rate (HR) variability during hospitalisation so as to establish a predictive model for preoperative in-hospital mortality of patients with acute aortic dissection (AD) by using machine learning techniques.

DESIGN

Retrospective cohort study.

SETTING

Data were collected from the electronic records and the databases of Shanghai Ninth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine and the First Affiliated Hospital of Anhui Medical University between 2004 and 2018.

PARTICIPANTS

380 inpatients diagnosed with acute AD were included in the study.

PRIMARY OUTCOME

Preoperative in-hospital mortality rate.

RESULTS

A total of 55 patients (14.47%) died in the hospital before surgery. The results of the areas under the receiver operating characteristic curves, decision curve analysis and calibration curves indicated that the eXtreme Gradient Boosting (XGBoost) model had the highest accuracy and robustness. According to the SHapley Additive exPlanations analysis of the XGBoost model, Stanford type A, maximum aortic diameter >5.5 cm, high variability in HR, high variability in diastolic BP and involvement of the aortic arch had the greatest impact on the occurrence of in-hospital deaths before surgery. Moreover, the predictive model can accurately predict the preoperative in-hospital mortality rate at the individual level.

CONCLUSION

In the current study, we successfully constructed machine learning models to predict the preoperative in-hospital mortality of patients with acute AD, which can help identify high-risk patients and optimise the clinical decision-making. Further applications in clinical practice require the validation of these models using a large-sample, prospective database.

TRIAL REGISTRATION NUMBER

ChiCTR1900025818.

Clinical application of MR-Linac in tumor radiotherapy: a systematic review

Recent years have seen both a fresh knowledge of cancer and impressive advancements in its treatment. However, the clinical treatment paradigm of cancer is still difficult to implement in the twenty-first century due to the rise in its prevalence. Radiotherapy (RT) is a crucial component of cancer treatment that is helpful for almost all cancer types. The accuracy of RT dosage delivery is increasing as a result of the quick development of computer and imaging technology. The use of image-guided radiation (IGRT) has improved cancer outcomes and decreased toxicity. Online adaptive radiotherapy will be made possible by magnetic resonance imaging-guided radiotherapy (MRgRT) using a magnetic resonance linear accelerator (MR-Linac), which will enhance the visibility of malignancies. This review's objectives are to examine the benefits of MR-Linac as a treatment approach from the perspective of various cancer patients' prognoses and to suggest prospective development areas for additional study.

Automated Contouring and Planning in Radiation Therapy: What Is 'Clinically Acceptable'?

Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is 'clinical acceptability'? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of 'clinical acceptability' and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.

Tools for large-scale data analytics of an international multi-center study in radiation oncology for cervical cancer

PURPOSE

To develop and implement a software that enables centers, treating patients with state-of-the-art radiation oncology, to compare their patient, treatment, and outcome data to a reference cohort, and to assess the quality of their treatment approach.

MATERIALS AND METHODS

A comprehensive data dashboard was designed, which al- lowed holistic assessment of institutional treatment approaches. The software was tested in the ongoing EMBRACE-II study for locally advanced cervical cancer. The tool created individualized dashboards and automatic analysis scripts, verified pro- tocol compliance and checked data for inconsistencies. Identified quality assurance (QA) events were analysed. A survey among users was conducted to assess usability.

RESULTS

The survey indicated favourable feedback to the prototype and highlighted its value for internal monitoring. Overall, 2302 QA events were identified (0.4% of all collected data). 54% were due to missing or incomplete data, and 46% originated from other causes. At least one QA event was found in 519/1001 (52%) of patients. QA events related to primary study endpoints were found in 16% of patients. Sta- tistical methods demonstrated good performance in detecting anomalies, with precisions ranging from 71% to 100%. Most frequent QA event categories were Treatment Technique (27%), Patient Characteristics (22%), Dose Reporting (17%), Outcome 156 (15%), Outliers (12%), and RT Structures (8%).

CONCLUSION

A software tool was developed and tested within a clinical trial in radia- tion oncology. It enabled the quantitative and qualitative comparison of institutional patient and treatment parameters with a large multi-center reference cohort. We demonstrated the value of using statistical methods to automatically detect implau- sible data points and highlighted common pitfalls and uncertainties in radiotherapy for cervical cancer.

Iterated cross validation method for prediction of survival in diffuse large B-cell lymphoma for small size dataset

Efforts have been made to improve the risk stratification model for patients with diffuse large B-cell lymphoma (DLBCL). This study aimed to evaluate the disease prognosis using machine learning models with iterated cross validation (CV) method. A total of 122 patients with pathologically confirmed DLBCL and receiving rituximab-containing chemotherapy were enrolled. Contributions of clinical, laboratory, and metabolic imaging parameters from fluorine-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) scans to the prognosis were evaluated using five regression models, namely logistic regression, random forest, support vector classifier (SVC), deep neural network (DNN), and fuzzy neural network models. Binary classification predictions for 3-year progression free survival (PFS) and 3-year overall survival (OS) were conducted. The 10-iterated fivefold CV with shuffling process was conducted to predict the capability of learning machines. The median PFS and OS were 41.0 and 43.6 months, respectively. Two indicators were found to be independent predictors for prognosis: international prognostic index and total metabolic tumor volume (MTVsum) from FDG PET/CT. For PFS, SVC and DNN (both with accuracy 71%) have the best predictive results, of which outperformed other algorithms. For OS, the DNN has the best predictive result (accuracy 76%). Using clinical and metabolic parameters as input variables, the machine learning methods with iterated CV method add the predictive values for PFS and OS evaluation in DLBCL patients.

Predicting Local Failure after Partial Prostate Re-Irradiation Using a Dosiomic-Based Machine Learning Model

The aim of this study is to predict local failure after partial prostate re-irradiation for the treatment of isolated locally recurrent prostate cancer by using a machine learning classifier based on radiomic features from pre-treatment computed tomography (CT), positron-emission tomography (PET) and biological effective dose distribution (BED) of the radiotherapy plan. The analysis was conducted on a monocentric dataset of 43 patients with evidence of isolated intraprostatic recurrence of prostate cancer after primary external beam radiotherapy. All patients received partial prostate re-irradiation delivered by volumetric modulated arc therapy. The gross tumor volume (GTV) of each patient was manually contoured from planning CT, choline-PET and dose maps. An ensemble machine learning pipeline including unbalanced data correction and feature selection was trained using the radiomic and dosiomic features as input for predicting occurrence of local failure. The model performance was assessed using sensitivity, specificity, accuracy and area under receiver operating characteristic curves of the score function in 10-fold cross validation repeated 100 times. Local failure was observed in 13 patients (30%), with a median time to recurrence of 36.7 months (range = 6.1–102.4 months). A four variables ensemble machine learning model resulted in accuracy of 0.62 and AUC 0.65. According to our results, a dosiomic machine learning classifier can predict local failure after partial prostate re-irradiation.

Development and Validation of a DeepSurv Nomogram to Predict Survival Outcomes and Guide Personalized Adjuvant Chemotherapy in Non-Small Cell Lung Cancer

Objective

To develop and validate a DeepSurv nomogram based on radiomic features extracted from computed tomography images and clinicopathological factors, to predict the overall survival and guide individualized adjuvant chemotherapy in patients with non-small cell lung cancer (NSCLC).

Patients and Methods

This retrospective study involved 976 consecutive patients with NSCLC (training cohort, n=683; validation cohort, n=293). DeepSurv was constructed based on 1,227 radiomic features, and the risk score was calculated for each patient as the output. A clinical multivariate Cox regression model was built with clinicopathological factors to determine the independent risk factors. Finally, a DeepSurv nomogram was constructed by integrating the risk score and independent clinicopathological factors. The discrimination capability, calibration, and clinical usefulness of the nomogram performance were assessed using concordance index evaluation, the Greenwood-Nam-D’Agostino test, and decision curve analysis, respectively. The treatment strategy was analyzed using a Kaplan–Meier curve and log-rank test for the high- and low-risk groups.

Results

The DeepSurv nomogram yielded a significantly better concordance index (training cohort, 0.821; validation cohort 0.768) with goodness-of-fit (P<0.05). The risk score, age, thyroid transcription factor-1, Ki-67, and disease stage were the independent risk factors for NSCLC.The Greenwood-Nam-D’Agostino test showed good calibration performance (P=0.39). Both high- and low-risk patients did not benefit from adjuvant chemotherapy, and chemotherapy in low-risk groups may lead to a poorer prognosis.

Conclusions

The DeepSurv nomogram, which is based on the risk score and independent risk factors, had good predictive performance for survival outcome. Further, it could be used to guide personalized adjuvant chemotherapy in patients with NSCLC.

Applicability of a pathological complete response magnetic resonance-based radiomics model for locally advanced rectal cancer in intercontinental cohort

BACKGROUND

Predicting pathological complete response (pCR) in patients affected by locally advanced rectal cancer (LARC) who undergo neoadjuvant chemoradiotherapy (nCRT) is a challenging field of investigation, but many of the published models are burdened by a lack of reliable external validation. Aim of this study was to evaluate the applicability of a magnetic resonance imaging (MRI) radiomic-based pCR model developed and validated in Europe, to a different cohort of patients from an intercontinental cancer center.

METHODS

The original model was based on two clinical and two radiomics features extracted from T2-weighted 1.5 T MRI of 161 LARC patients acquired before nCRT, considered as training set. Such model is here validated using the T2-w 1.5 and 3 T staging MRI of 59 LARC patients with different clinical characteristics consecutively treated in mainland Chinese cancer center from March 2017 to January 2018. Model performance were evaluated in terms of area under the receiver operator characteristics curve (AUC) and relative parameters, such as accuracy, specificity, negative and positive predictive value (NPV and PPV).

RESULTS

An AUC of 0.83 (CI 95%, 0.71-0.96) was achieved for the intercontinental cohort versus a value of 0.75 (CI 95%, 0.61-0.88) at the external validation step reported in the original experience. Considering the best cut-off threshold identified in the first experience (0.26), the following predictive performance were obtained: 0.65 as accuracy, 0.64 as specificity, 0.70 as sensitivity, 0.91 as NPV and 0.28 as PPV.

CONCLUSIONS

Despite the introduction of significant different factors, the proposed model appeared to be replicable on a real-world data extra-European patients' cohort, achieving a TRIPOD 4 level.

RadSigBench: a framework for benchmarking functional genomics signatures of cancer cell radiosensitivity

Multiple transcriptomic predictors of tumour cell radiosensitivity (RS) have been proposed, but they have not been benchmarked against one another or to control models. To address this, we present RadSigBench, a comprehensive benchmarking framework for RS signatures. The approach compares candidate models to those developed from randomly resampled control signatures and from cellular processes integral to the radiation response. Robust evaluation of signature accuracy, both overall and for individual tissues, is performed. The NCI60 and Cancer Cell Line Encyclopaedia datasets are integrated into our workflow. Prediction of two measures of RS is assessed: survival fraction after 2 Gy and mean inactivation dose. We apply the RadSigBench framework to seven prominent published signatures of radiation sensitivity and test for equivalence to control signatures. The mean out-of-sample R2 for the published models on test data was very poor at 0.01 (range: -0.05 to 0.09) for Cancer Cell Line Encyclopedia and 0.00 (range: -0.19 to 0.19) in the NCI60 data. The accuracy of both published and cellular process signatures investigated was equivalent to the resampled controls, suggesting that these signatures contain limited radiation-specific information. Enhanced modelling strategies are needed for effective prediction of intrinsic RS to inform clinical treatment regimes. We make recommendations for methodological improvements, for example the inclusion of perturbation data, multiomics, advanced machine learning and mechanistic modelling. Our validation framework provides for robust performance assessment of ongoing developments in intrinsic RS prediction.

Multitask Learning Radiomics on Longitudinal Imaging to Predict Survival Outcomes following Risk-Adaptive Chemoradiation for Non-Small Cell Lung Cancer

Medical imaging provides quantitative and spatial information to evaluate treatment response in the management of patients with non-small cell lung cancer (NSCLC). High throughput extraction of radiomic features on these images can potentially phenotype tumors non-invasively and support risk stratification based on survival outcome prediction. The prognostic value of radiomics from different imaging modalities and time points prior to and during chemoradiation therapy of NSCLC, relative to conventional imaging biomarker or delta radiomics models, remains uncharacterized. We investigated the utility of multitask learning of multi-time point radiomic features, as opposed to single-task learning, for improving survival outcome prediction relative to conventional clinical imaging feature model benchmarks. Survival outcomes were prospectively collected for 45 patients with unresectable NSCLC enrolled on the FLARE-RT phase II trial of risk-adaptive chemoradiation and optional consolidation PD-L1 checkpoint blockade (NCT02773238). FDG-PET, CT, and perfusion SPECT imaging pretreatment and week 3 mid-treatment was performed and 110 IBSI-compliant pyradiomics shape-/intensity-/texture-based features from the metabolic tumor volume were extracted. Outcome modeling consisted of a fused Laplacian sparse group LASSO with component-wise gradient boosting survival regression in a multitask learning framework. Testing performance under stratified 10-fold cross-validation was evaluated for multitask learning radiomics of different imaging modalities and time points. Multitask learning models were benchmarked against conventional clinical imaging and delta radiomics models and evaluated with the concordance index (c-index) and index of prediction accuracy (IPA). FDG-PET radiomics had higher prognostic value for overall survival in test folds (c-index 0.71 [0.67, 0.75]) than CT radiomics (c-index 0.64 [0.60, 0.71]) or perfusion SPECT radiomics (c-index 0.60 [0.57, 0.63]). Multitask learning of pre-/mid-treatment FDG-PET radiomics (c-index 0.71 [0.67, 0.75]) outperformed benchmark clinical imaging (c-index 0.65 [0.59, 0.71]) and FDG-PET delta radiomics (c-index 0.52 [0.48, 0.58]) models. Similarly, the IPA for multitask learning FDG-PET radiomics (30%) was higher than clinical imaging (26%) and delta radiomics (15%) models. Radiomics models performed consistently under different voxel resampling conditions. Multitask learning radiomics for outcome modeling provides a clinical decision support platform that leverages longitudinal imaging information. This framework can reveal the relative importance of different imaging modalities and time points when designing risk-adaptive cancer treatment strategies.

Evaluation of Prognostic and Predictive Models in the Oncology Clinic

Predictive and prognostic models hold great potential to support clinical decision making in oncology and could ultimately facilitate a paradigm shift to a more personalised form of treatment. While a large number of models relevant to the field of oncology have been developed, few have been translated into clinical use and assessment of clinical utility is not currently considered a routine part of model development. In this narrative review of the clinical evaluation of prediction models in oncology, we propose a high-level process diagram for the life cycle of a clinical model, encompassing model commissioning, clinical implementation and ongoing quality assurance, which aims to bridge the gap between model development and clinical implementation.

Radiomic Phenotypes for Improving Early Prediction of Survival in Stage III Non-Small Cell Lung Cancer Adenocarcinoma after Chemoradiation

We evaluate radiomic phenotypes derived from CT scans as early predictors of overall survival (OS) after chemoradiation in stage III primary lung adenocarcinoma. We retrospectively analyzed 110 thoracic CT scans acquired between April 2012-October 2018. Patients received a median radiation dose of 66.6 Gy at 1.8 Gy/fraction delivered with proton (55.5%) and photon (44.5%) beam treatment, as well as concurrent chemotherapy (89%) with carboplatin-based (55.5%) and cisplatin-based (36.4%) doublets. A total of 56 death events were recorded. Using manual tumor segmentations, 107 radiomic features were extracted. Feature harmonization using ComBat was performed to mitigate image heterogeneity due to the presence or lack of intravenous contrast material and variability in CT scanner vendors. A binary radiomic phenotype to predict OS was derived through the unsupervised hierarchical clustering of the first principal components explaining 85% of the variance of the radiomic features. C-scores and likelihood ratio tests (LRT) were used to compare the performance of a baseline Cox model based on ECOG status and age, with a model integrating the radiomic phenotype with such clinical predictors. The model integrating the radiomic phenotype (C-score = 0.69, 95% CI = (0.62, 0.77)) significantly improved (p<0.005) upon the baseline model (C-score = 0.65, CI = (0.57, 0.73)). Our results suggest that harmonized radiomic phenotypes can significantly improve OS prediction in stage III NSCLC after chemoradiation.

A predictive model for personalization of nanotechnology-based phototherapy in cancer treatment

A major challenge in radiation oncology is the prediction and optimization of clinical responses in a personalized manner. Recently, nanotechnology-based cancer treatments are being combined with photodynamic therapy (PDT) and photothermal therapy (PTT). Predictive models based on machine learning techniques can be used to optimize the clinical setup configuration, including such parameters as laser radiation intensity, treatment duration, and nanoparticle features. In this article we demonstrate a methodology that can be used to identify the optimal treatment parameters for PDT and PTT by collecting data from in vitro cytotoxicity assay of PDT/PTT-induced cell death using a single nanocomplex. We construct three machine learning prediction models, employing regression, interpolation, and low- degree analytical function fitting, to predict the laser radiation intensity and duration settings that maximize the treatment efficiency. To examine the accuracy of these prediction models, we construct a dedicated dataset for PDT, PTT, and a combined treatment; this dataset is based on cell death measurements after light radiation treatment and is divided into training and test sets. The preliminary results show that the performance of all three models is sufficient, with death rate errors of 0.09, 0.15, and 0.12 for the regression, interpolation, and analytical function fitting approaches, respectively. Nevertheless, due to its simple form, the analytical function method has an advantage in clinical application and can be used for further analysis of the sensitivity of performance to the treatment parameters. Overall, the results of this study form a baseline for a future personalized prediction model based on machine learning in the domain of combined nanotechnology- and phototherapy-based cancer treatment.

Transparency of deep neural networks for medical image analysis: A review of interpretability methods

Artificial Intelligence (AI) has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown the same or better performance than clinicians in many tasks owing to the rapid increase in the available data and computational power. In order to conform to the principles of trustworthy AI, it is essential that the AI system be transparent, robust, fair, and ensure accountability. Current deep neural solutions are referred to as black-boxes due to a lack of understanding of the specifics concerning the decision-making process. Therefore, there is a need to ensure the interpretability of deep neural networks before they can be incorporated into the routine clinical workflow. In this narrative review, we utilized systematic keyword searches and domain expertise to identify nine different types of interpretability methods that have been used for understanding deep learning models for medical image analysis applications based on the type of generated explanations and technical similarities. Furthermore, we report the progress made towards evaluating the explanations produced by various interpretability methods. Finally, we discuss limitations, provide guidelines for using interpretability methods and future directions concerning the interpretability of deep neural networks for medical imaging analysis.

Development of a hoRizontal data intEgration classifier for NOn-invasive early diAgnosis of breasT cancEr: the RENOVATE study protocol

INTRODUCTION

Standard procedures aimed at the early diagnosis of breast cancer (BC) present suboptimal accuracy and imply the execution of invasive and sometimes unnecessary tissue biopsies. The assessment of circulating biomarkers for diagnostic purposes, together with radiomics, is of great potential in BC management.

METHODS AND ANALYSIS

This is a prospective translational study investigating the accuracy of the combined assessment of multiple circulating analytes together with radiomic variables for early BC diagnosis. Up to 750 patients will be recruited at their presentation at the Diagnostic Senology Unit of Ospedale Policlinico San Martino (Genoa, IT) for the execution of a diagnostic biopsy after the detection of a suspect breast lesion (t0). Each recruited patient will be asked to donate peripheral blood and urine before undergoing breast biopsy. Blood and urine samples will also be collected from a cohort of 100 patients with negative mammography. For cases with histological diagnosis of invasive BC, a second sample of blood and urine will be collected after breast surgery. Circulating tumour DNA, cell-free methylated DNA and circulating proteins will be assessed in samples collected at t0 from patients with stage I-IIA BC at surgery together with those collected from patients with histologically confirmed benign lesions of similar size and from healthy controls with negative mammography. These analyses will be combined with radiomic variables extracted with freeware algorithms applied to cases and matched controls for which digital mammography is available. The overall goal of the present study is to develop a horizontal data integration classifier for the early diagnosis of BC.

ETHICS AND DISSEMINATION

This research protocol has been approved by Regione Liguria Ethics Committee (reference number: 2019/75, study ID: 4452). Patients will be required to provide written informed consent. Results will be published in international peer-reviewed scientific journals.

TRIAL REGISTRATION NUMBER

NCT04781062.

The barriers and facilitators of radical innovation implementation in secondary healthcare: a systematic review

PURPOSE

This study aimed to identify the barriers and facilitators related to the implementation of radical innovations in secondary healthcare.

DESIGN/METHODOLOGY/APPROACH

A systematic review was conducted and presented in accordance with a PRISMA flowchart. The databases PubMed and Web of Science were searched for original publications in English between the 1st of January 2010 and 6th of November 2020. The level of radicalness was determined based on five characteristics of radical innovations. The level of evidence was classified according to the level of evidence scale of the University of Oxford. The Consolidated Framework for Implementation Research was used as a framework to classify the barriers and facilitators.

FINDINGS

Based on the inclusion and exclusion criteria, nine publications were included, concerning six technological, two organizational and one treatment innovation. The main barriers for radical innovation implementation in secondary healthcare were lack of human, material and financial resources, and lack of integration and organizational readiness. The main facilitators included a supportive culture, sufficient training, education and knowledge, and recognition of the expected added value.

ORIGINALITY/VALUE

To our knowledge, this is the first systematic review examining the barriers and facilitators of radical innovation implementation in secondary healthcare. To ease radical innovation implementation, alternative performance systems may be helpful, including the following prerequisites: (1) Money, (2) Added value, (3) Timely knowledge and integration, (4) Culture, and (5) Human resources (MATCH). This study highlights the need for more high-level evidence studies in this area.

Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma

Objective

This study was conducted in order to investigate the association between radiomics features and frontal glioma-associated epilepsy (GAE) and propose a reliable radiomics-based model to predict frontal GAE.

Methods

This retrospective study consecutively enrolled 166 adult patients with frontal glioma (111 in the training cohort and 55 in the testing cohort). A total 1,130 features were extracted from T2 fluid-attenuated inversion recovery images, including first-order statistics, 3D shape, texture, and wavelet features. Regions of interest, including the entire tumor and peritumoral edema, were drawn manually. Pearson correlation coefficient, 10-fold cross-validation, area under curve (AUC) analysis, and support vector machine were adopted to select the most relevant features to build a clinical model, a radiomics model, and a clinical-radiomics model for GAE. The receiver operating characteristic curve (ROC) and AUC were used to evaluate the classification performance of the models in each cohort, and DeLong's test was used to compare the performance of the models. A two-sided t-test and Fisher's exact test were used to compare the clinical variables. Statistical analysis was performed using SPSS software (version 22.0; IBM, Armonk, New York), and p <0.05 was set as the threshold for significance.

Results

The classification accuracy of seven scout models, except the wavelet first-order model (0.793) and the wavelet texture model (0.784), was <0.75 in cross-validation. The clinical-radiomics model, including 17 magnetic resonance imaging-based features selected among the 1,130 radiomics features and two clinical features (patient age and tumor grade), achieved better discriminative performance for GAE prediction in both the training [AUC = 0.886, 95% confidence interval (CI) = 0.819-0.940] and testing cohorts (AUC = 0.836, 95% CI = 0.707-0.937) than the radiomics model (p = 0.008) with 82.0% and 78.2% accuracy, respectively.

Conclusion

Radiomics analysis can non-invasively predict GAE, thus allowing adequate treatment of frontal glioma. The clinical-radiomics model may enable a more precise prediction of frontal GAE. Furthermore, age and pathology grade are important risk factors for GAE.

MRI-based delta-radiomics predicts pathologic complete response in high-grade soft-tissue sarcoma patients treated with neoadjuvant therapy

PURPOSE

In high-grade soft-tissue sarcomas (STS) the standard of care encompasses multimodal therapy regimens. While there is a growing body of evidence for prognostic pretreatment radiomic models, we hypothesized that temporal changes in radiomic features following neoadjuvant treatment ("delta-radiomics") may be able to predict the pathological complete response (pCR).

METHODS

MRI scans (T1-weighted with fat-saturation and contrast-enhancement (T1FSGd) and T2-weighted with fat-saturation (T2FS)) of patients with STS of the extremities and trunk treated with neoadjuvant therapy were gathered from two independent institutions (training: 103, external testing: 53 patients). pCR was defined as <5% viable cells. After segmentation and preprocessing, 105 radiomic features were extracted. Delta-radiomic features were calculated by subtraction of features derived from MRI scans obtained before and after neoadjuvant therapy. After feature reduction, machine learning modeling was performed in 100 iterations of 3-fold nested cross-validation. Delta-radiomic models were compared with single timepoint models in the testing cohort.

RESULTS

The combined delta-radiomic models achieved the best area under the receiver operating characteristic curve (AUC) of 0.75. Pre-therapeutic tumor volume was the best conventional predictor (AUC 0.70). The T2FS-based delta-radiomic model had the most balanced classification performance with a balanced accuracy of 0.69. Delta-radiomic models achieved better reproducibility than single timepoint radiomic models, RECIST or the peri-therapeutic volume change. Delta-radiomic models were significantly associated with survival in multivariate Cox regression.

CONCLUSION

This exploratory analysis demonstrated that MRI-based delta-radiomics improves prediction of pCR over tumor volume and RECIST. Delta-radiomics may one day function as a biomarker for personalized treatment adaptations.

Enhanced CT-Based Radiomics to Predict Micropapillary Pattern Within Lung Invasive Adenocarcinoma

Objective

We aimed to investigate whether enhanced CT-based radiomics can predict micropapillary pattern (MPP) of lung invasive adenocarcinoma (IAC) in the pre-op phase and to develop an individual diagnostic predictive model for MPP in IAC.

Methods

170 patients who underwent complete resection for pathologically confirmed lung IAC were included in our study. Of these 121 were used as a training cohort and the other 49 as a test cohort. Clinical features and enhanced CT images were collected and assessed. Quantitative CT analysis was performed based on feature types including first order, shape, gray-level co-occurrence matrix-based, gray-level size zone matrix-based, gray-level run length matrix-based, gray-level dependence matrix-based, neighboring gray tone difference matrix-based features and transform types including Log, wavelet and local binary pattern. Receiver operating characteristic (ROC) and area under the curve (AUC) were used to value the ability to identify the lung IAC with MPP using these characteristics.

Results

Using quantitative CT analysis, one thousand three hundred and seventeen radiomics features were deciphered from R (https://www.r-project.org/). Then these radiomic features were decreased to 14 features after dimension reduction using the least absolute shrinkage and selection operator (LASSO) method in R. After correlation analysis, 5 key features were obtained and used as signatures for predicting MPP within IAC. The individualized prediction model which included age, smoking, family tumor history and radiomics signature had better identification (AUC=0.739) in comparison with the model consisting only of radiomics features (AUC=0.722). DeLong test showed that the difference in AUC between the two models was statistically significant (P<0.01). Compared with the simple radiomics model, the more comprehensive individual prediction model has better prediction performance.

Conclusion

The use of radiomics approach is of great value in the diagnosis of tumors by non-invasive means. The individualized prediction model in the study, when incorporated with age, smoking and radiomics signature, had effective predictive performance of lung IAC with MPP lesions. The combination of imaging features and clinical features can provide additional diagnostic value to identify the micropapillary pattern in IAC and can affect clinical diagnosis and treatment.

Improving Early Identification of Significant Weight Loss Using Clinical Decision Support System in Lung Cancer Radiation Therapy

PURPOSE

Early identification of patients who may be at high risk of significant weight loss (SWL) is important for timely clinical intervention in lung cancer radiotherapy (RT). A clinical decision support system (CDSS) for SWL prediction was implemented within the routine clinical workflow and assessed on a prospective cohort of patients.

MATERIALS AND METHODS

CDSS incorporated a machine learning prediction model on the basis of radiomics and dosiomics image features and was connected to a web-based dashboard for streamlined patient enrollment, feature extraction, SWL prediction, and physicians' evaluation processes. Patients with lung cancer (N = 37) treated with definitive RT without prior RT were prospectively enrolled in the study. Radiomics and dosiomics features were extracted from CT and 3D dose volume, and SWL probability (≥ 0.5 considered as SWL) was predicted. Two physicians predicted whether the patient would have SWL before and after reviewing the CDSS prediction. The physician's prediction performance without and with CDSS and prediction changes before and after using CDSS were compared.

RESULTS

CDSS showed significantly better prediction accuracy than physicians (0.73 v 0.54) with higher specificity (0.81 v 0.50) but with lower sensitivity (0.55 v 0.64). Physicians changed their original prediction after reviewing CDSS prediction for four cases (three correctly and one incorrectly), for all of which CDSS prediction was correct. Physicians' prediction was improved with CDSS in accuracy (0.54-0.59), sensitivity (0.64-0.73), specificity (0.50-0.54), positive predictive value (0.35-0.40), and negative predictive value (0.76-0.82).

CONCLUSION

Machine learning-based CDSS showed the potential to improve SWL prediction in lung cancer RT. More investigation on a larger patient cohort is needed to properly interpret CDSS prediction performance and its benefit in clinical decision making.

Privacy preserving distributed learning classifiers - Sequential learning with small sets of data

BACKGROUND

Artificial intelligence (AI) typically requires a significant amount of high-quality data to build reliable models, where gathering enough data within a single institution can be particularly challenging. In this study we investigated the impact of using sequential learning to exploit very small, siloed sets of clinical and imaging data to train AI models. Furthermore, we evaluated the capacity of such models to achieve equivalent performance when compared to models trained with the same data over a single centralized database.

METHODS

We propose a privacy preserving distributed learning framework, learning sequentially from each dataset. The framework is applied to three machine learning algorithms: Logistic Regression, Support Vector Machines (SVM), and Perceptron. The models were evaluated using four open-source datasets (Breast cancer, Indian liver, NSCLC-Radiomics dataset, and Stage III NSCLC).

FINDINGS

The proposed framework ensured a comparable predictive performance against a centralized learning approach. Pairwise DeLong tests showed no significant difference between the compared pairs for each dataset.

INTERPRETATION

Distributed learning contributes to preserve medical data privacy. We foresee this technology will increase the number of collaborative opportunities to develop robust AI, becoming the default solution in scenarios where collecting enough data from a single reliable source is logistically impossible. Distributed sequential learning provides privacy persevering means for institutions with small but clinically valuable datasets to collaboratively train predictive AI while preserving the privacy of their patients. Such models perform similarly to models that are built on a larger central dataset.

Non-melanoma Skin Cancer Treated by Contact High-dose-rate Radiotherapy (Brachytherapy): A Mono-institutional Series and Literature Review

BACKGROUND/AIM

Non-melanoma skin cancers (NMSC) are the most common neoplasms worldwide and their incidence has been proven to increase in recent years and their treatment should aim at cancer cure as well as cosmetic and functional results. The aim of the study was to report the results of our mono-institutional series of high-dose-rate radiotherapy (cHDR-RT) in NMSC, based on a homogenous technique and two different treatment schedules.

PATIENTS AND METHODS

All patients affected by NMSC who were consecutively evaluated and treated at our Interventional Oncology Center from October 2018 to August 2020, were included. Patients underwent cHDR-RT using flap applicators and remotely afterloaded Ir-192 sources.

RESULTS

Overall, 51 patients were treated for a total of 67 lesions. Local control (LC) and disease-specific survival (DSS) were 94.0% and 100%, respectively. Grade 1, grade 2, grade 3 and grade 4 acute toxicity rates were 24.6%, 3.5%, 3.5%, and 0.0%, respectively. The cosmetic results were graded as excellent/good, fair, and poor in 73.7%, 19.3%, and 7.0%.

CONCLUSION

cHDR-RT of NMSC is an effective alternative to surgery due to excellent outcomes both in terms of local control and aesthetic results especially in the face.

Evaluation of DNA double-strand break repair capacity in human cells: Critical overview of current functional methods

DNA double-strand breaks (DSBs) are highly deleterious lesions, responsible for mutagenesis, chromosomal translocation or cell death. DSB repair (DSBR) is therefore a critical part of the DNA damage response (DDR) to restore molecular and genomic integrity. In humans, this process is achieved through different pathways with various outcomes. The balance between DSB repair activities varies depending on cell types, tissues or individuals. Over the years, several methods have been developed to study variations in DSBR capacity. Here, we mainly focus on functional techniques, which provide dynamic information regarding global DSB repair proficiency or the activity of specific pathways. These methods rely on two kinds of approaches. Indirect techniques, such as pulse field gel electrophoresis (PFGE), the comet assay and immunofluorescence (IF), measure DSB repair capacity by quantifying the time-dependent decrease in DSB levels after exposure to a DNA-damaging agent. On the other hand, cell-free assays and reporter-based methods directly track the repair of an artificial DNA substrate. Each approach has intrinsic advantages and limitations and despite considerable efforts, there is currently no ideal method to quantify DSBR capacity. All techniques provide different information and can be regarded as complementary, but some studies report conflicting results. Parameters such as the type of biological material, the required equipment or the cost of analysis may also limit available options. Improving currently available methods measuring DSBR capacity would be a major step forward and we present direct applications in mechanistic studies, drug development, human biomonitoring and personalized medicine, where DSBR analysis may improve the identification of patients eligible for chemo- and radiotherapy.

Combination of computed tomography imaging-based radiomics and clinicopathological characteristics for predicting the clinical benefits of immune checkpoint inhibitors in lung cancer

BACKGROUND

In this study, we tested whether a combination of radiomic features extracted from baseline pre-immunotherapy computed tomography (CT) images and clinicopathological characteristics could be used as novel noninvasive biomarkers for predicting the clinical benefits of non-small cell lung cancer (NSCLC) patients treated with immune checkpoint inhibitors (ICIs).

METHODS

The data from 92 consecutive patients with lung cancer who had been treated with ICIs were retrospectively analyzed. In total, 88 radiomic features were selected from the pretreatment CT images for the construction of a random forest model. Radiomics model 1 was constructed based on the Rad-score. Using multivariate logistic regression analysis, the Rad-score and significant predictors were integrated into a single predictive model (radiomics nomogram model 1) to predict the durable clinical benefit (DCB) of ICIs. Radiomics model 2 was developed based on the same Rad-score as radiomics model 1.Using multivariate Cox proportional hazards regression analysis, the Rad-score, and independent risk factors, radiomics nomogram model 2 was constructed to predict the progression-free survival (PFS).

RESULTS

The models successfully predicted the patients who would benefit from ICIs. For radiomics model 1, the area under the receiver operating characteristic curve values for the training and validation cohorts were 0.848 and 0.795, respectively, whereas for radiomics nomogram model 1, the values were 0.902 and 0.877, respectively. For the PFS prediction, the Harrell's concordance indexes for the training and validation cohorts were 0.717 and 0.760, respectively, using radiomics model 2, whereas they were 0.749 and 0.791, respectively, using radiomics nomogram model 2.

CONCLUSIONS

CT-based radiomic features and clinicopathological factors can be used prior to the initiation of immunotherapy for identifying NSCLC patients who are the most likely to benefit from the therapy. This could guide the individualized treatment strategy for advanced NSCLC.

Machine learning applications in radiation oncology

Machine learning technology has a growing impact on radiation oncology with an increasing presence in research and industry. The prevalence of diverse data including 3D imaging and the 3D radiation dose delivery presents potential for future automation and scope for treatment improvements for cancer patients. Harnessing this potential requires standardization of tools and data, and focused collaboration between fields of expertise. The rapid advancement of radiation oncology treatment technologies presents opportunities for machine learning integration with investments targeted towards data quality, data extraction, software, and engagement with clinical expertise. In this review, we provide an overview of machine learning concepts before reviewing advances in applying machine learning to radiation oncology and integrating these techniques into the radiation oncology workflows. Several key areas are outlined in the radiation oncology workflow where machine learning has been applied and where it can have a significant impact in terms of efficiency, consistency in treatment and overall treatment outcomes. This review highlights that machine learning has key early applications in radiation oncology due to the repetitive nature of many tasks that also currently have human review. Standardized data management of routinely collected imaging and radiation dose data are also highlighted as enabling engagement in research utilizing machine learning and the ability integrate these technologies into clinical workflow to benefit patients. Physicists need to be part of the conversation to facilitate this technical integration.

Preoperative Prediction of Metastasis for Ovarian Cancer Based on Computed Tomography Radiomics Features and Clinical Factors

Background

There is urgent need for an accurate preoperative prediction of metastatic status to optimize treatment for patients with ovarian cancer (OC). The feasibility of predicting the metastatic status based on radiomics features from preoperative computed tomography (CT) images alone or combined with clinical factors were investigated.

Methods

A total of 101 OC patients who underwent primary debulking surgery were enrolled. Radiomics features were extracted from the tumor volumes contoured on CT images with LIFEx package. Mann-Whitney U tests, least absolute shrinkage selection operator (LASSO), and Ridge Regression were applied to select features and to build prediction models. Univariate and regression analysis were applied to select clinical factors for metastatic prediction. The performance of models generated with radiomics features alone, clinical factors, and combined factors were evaluated and compared.

Results

Nine radiomics features were screened out from 184 extracted features to classify patients with and without metastasis. Age and cancer antigen 125 (CA125) were the two clinical factors that were associated with metastasis. The area under curves (AUCs) for the radiomics signature, clinical factors model, and combined model were 0.82 (95% CI, 0.66-0.98; sensitivity = 0.90, specificity = 0.70), 0.83 (95% CI, 0.67-0.95; sensitivity = 0.71, specificity = 0.8), and 0.86 (95% CI, 0.72-0.99, sensitivity = 0.81, specificity = 0.8), respectively.

Conclusions

Radiomics features alone or radiomics features combined with clinical factors are feasible and accurate enough to predict the metastatic status for OC patients.

Modeling-Based Decision Support System for Radical Prostatectomy Versus External Beam Radiotherapy for Prostate Cancer Incorporating an In Silico Clinical Trial and a Cost-Utility Study

Simple Summary

Low–intermediate prostate cancer has a number of viable treatment options, such as radical prostatectomy and radiotherapy, with similar survival outcomes but different treatment-related side effects. The aim of this study is to facilitate patient-specific treatment selection by developing a decision support system (DSS) that incorporates predictive models for cancer-free survival and treatment-related side effects. We challenged this DSS by validating it against randomized clinical trials and assessing the benefit through a cost–utility analysis. We aim to expand upon the applications of this DSS by using it as the basis for an in silico clinical trial for an underrepresented patient group. This modeling study shows that DSS-based treatment decisions will result in a clinically relevant increase in the patients’ quality of life and can be used for in silico trials.

Abstract

The aim of this study is to build a decision support system (DSS) to select radical prostatectomy (RP) or external beam radiotherapy (EBRT) for low- to intermediate-risk prostate cancer patients. We used an individual state-transition model based on predictive models for estimating tumor control and toxicity probabilities. We performed analyses on a synthetically generated dataset of 1000 patients with realistic clinical parameters, externally validated by comparison to randomized clinical trials, and set up an in silico clinical trial for elderly patients. We assessed the cost-effectiveness (CE) of the DSS for treatment selection by comparing it to randomized treatment allotment. Using the DSS, 47.8% of synthetic patients were selected for RP and 52.2% for EBRT. During validation, differences with the simulations of late toxicity and biochemical failure never exceeded 2%. The in silico trial showed that for elderly patients, toxicity has more influence on the decision than TCP, and the predicted QoL depends on the initial erectile function. The DSS is estimated to result in cost savings (EUR 323 (95% CI: EUR 213–433)) and more quality-adjusted life years (QALYs; 0.11 years, 95% CI: 0.00–0.22) than randomized treatment selection.

Artificial Intelligence in magnetic Resonance guided Radiotherapy: Medical and physical considerations on state of art and future perspectives

Over the last years, technological innovation in Radiotherapy (RT) led to the introduction of Magnetic Resonance-guided RT (MRgRT) systems. Due to the higher soft tissue contrast compared to on-board CT-based systems, MRgRT is expected to significantly improve the treatment in many situations. MRgRT systems may extend the management of inter- and intra-fraction anatomical changes, offering the possibility of online adaptation of the dose distribution according to daily patient anatomy and to directly monitor tumor motion during treatment delivery by means of a continuous cine MR acquisition. Online adaptive treatments require a multidisciplinary and well-trained team, able to perform a series of operations in a safe, precise and fast manner while the patient is waiting on the treatment couch. Artificial Intelligence (AI) is expected to rapidly contribute to MRgRT, primarily by safely and efficiently automatising the various manual operations characterizing online adaptive treatments. Furthermore, AI is finding relevant applications in MRgRT in the fields of image segmentation, synthetic CT reconstruction, automatic (on-line) planning and the development of predictive models based on daily MRI. This review provides a comprehensive overview of the current AI integration in MRgRT from a medical physicist's perspective. Medical physicists are expected to be major actors in solving new tasks and in taking new responsibilities: their traditional role of guardians of the new technology implementation will change with increasing emphasis on the managing of AI tools, processes and advanced systems for imaging and data analysis, gradually replacing many repetitive manual tasks.

Radiomic biomarkers of tumor immune biology and immunotherapy response

Immunotherapies are leading to improved outcomes for many cancers, including those with devastating prognoses. As therapies like immune checkpoint inhibitors (ICI) become a mainstay in treatment regimens, many concurrent challenges have arisen - for instance, delineating clinical responders from non-responders. Predicting response has proven to be difficult given a lack of consistent and accurate biomarkers, heterogeneity of the tumor microenvironment (TME), and a poor understanding of resistance mechanisms. For the most part, imaging data have remained an untapped, yet abundant, resource to address these challenges. In recent years, quantitative image analyses have highlighted the utility of medical imaging in predicting tumor phenotypes, prognosis, and therapeutic response. These studies have been fueled by an explosion of resources in high-throughput mining of image features (i.e. radiomics) and artificial intelligence. In this review, we highlight current progress in radiomics to understand tumor immune biology and predict clinical responses to immunotherapies. We also discuss limitations in these studies and future directions for the field, particularly if high-dimensional imaging data are to play a larger role in precision medicine.

Radiomic and radiogenomic modeling for radiotherapy: strategies, pitfalls, and challenges

The power of predictive modeling for radiotherapy outcomes has historically been limited by an inability to adequately capture patient-specific variabilities; however, next-generation platforms together with imaging technologies and powerful bioinformatic tools have facilitated strategies and provided optimism. Integrating clinical, biological, imaging, and treatment-specific data for more accurate prediction of tumor control probabilities or risk of radiation-induced side effects are high-dimensional problems whose solutions could have widespread benefits to a diverse patient population-we discuss technical approaches toward this objective. Increasing interest in the above is specifically reflected by the emergence of two nascent fields, which are distinct but complementary: radiogenomics, which broadly seeks to integrate biological risk factors together with treatment and diagnostic information to generate individualized patient risk profiles, and radiomics, which further leverages large-scale imaging correlates and extracted features for the same purpose. We review classical analytical and data-driven approaches for outcomes prediction that serve as antecedents to both radiomic and radiogenomic strategies. Discussion then focuses on uses of conventional and deep machine learning in radiomics. We further consider promising strategies for the harmonization of high-dimensional, heterogeneous multiomics datasets (panomics) and techniques for nonparametric validation of best-fit models. Strategies to overcome common pitfalls that are unique to data-intensive radiomics are also discussed.

Impact of feature selection methods and subgroup factors on prognostic analysis with CT-based radiomics in non-small cell lung cancer patients

Background

Radiomics is a new technology to noninvasively predict survival prognosis with quantitative features extracted from medical images. Most radiomics-based prognostic studies of non-small-cell lung cancer (NSCLC) patients have used mixed datasets of different subgroups. Therefore, we investigated the radiomics-based survival prediction of NSCLC patients by focusing on subgroups with identical characteristics.

Methods

A total of 304 NSCLC (Stages I–IV) patients treated with radiotherapy in our hospital were used. We extracted 107 radiomic features (i.e., 14 shape features, 18 first-order statistical features, and 75 texture features) from the gross tumor volume drawn on the free breathing planning computed tomography image. Three feature selection methods [i.e., test–retest and multiple segmentation (FS1), Pearson's correlation analysis (FS2), and a method that combined FS1 and FS2 (FS3)] were used to clarify how they affect survival prediction performance. Subgroup analysis for each histological subtype and each T stage applied the best selection method for the analysis of All data. We used a least absolute shrinkage and selection operator Cox regression model for all analyses and evaluated prognostic performance using the concordance-index (C-index) and the Kaplan–Meier method. For subgroup analysis, fivefold cross-validation was applied to ensure model reliability.

Results

In the analysis of All data, the C-index for the test dataset is 0.62 (FS1), 0.63 (FS2), and 0.62 (FS3). The subgroup analysis indicated that the prediction model based on specific histological subtypes and T stages had a higher C-index for the test dataset than that based on All data (All data, 0.64 vs. SCC_all, 060; ADC_all, 0.69; T1, 0.68; T2, 0.65; T3, 0.66; T4, 0.70). In addition, the prediction models unified for each T stage in histological subtype showed a different trend in the C-index for the test dataset between ADC-related and SCC-related models (ADC_T1–ADC_T4, 0.72–0.83; SCC_T1–SCC_T4, 0.58–0.71).

Conclusions

Our results showed that feature selection methods moderately affected the survival prediction performance. In addition, prediction models based on specific subgroups may improve the prediction performance. These results may prove useful for determining the optimal radiomics-based predication model.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-021-01810-9.

Combining liquid biopsy and radiomics for personalized treatment of lung cancer patients. State of the art and new perspectives

Lung cancer has become a paradigm for precision medicine in oncology, and liquid biopsy (LB) together with radiomics may have a great potential in this scenario. They are both minimally invasive, easy to perform, and can be repeated during patient's follow-up. Also, increasing evidence suggest that LB and radiomics may provide an efficient way to screen and diagnose tumors at an early stage, including the monitoring of any change in the tumor molecular profile. This could allow treatment optimization, improvement of patients' quality of life, and healthcare-related costs reduction. Latest reports on lung cancer patients suggest a combination of these two strategies, along with cutting-edge data analysis, to decode valuable information regarding tumor type, aggressiveness, progression, and response to treatment. The approach seems more compatible with clinical practice than the current standard, and provides new diagnostic companions being able to suggest the best treatment strategy compared to conventional methods. To implement radiomics and liquid biopsy directly into clinical practice, an artificial intelligence (AI)-based system could help to link patients' clinical data together with tumor molecular profiles and imaging characteristics. AI could also solve problems and limitations related to LB and radiomics methodologies. Further work is needed, including new health policies and the access to large amounts of high-quality and well-organized data, allowing a complementary and synergistic combination of LB and imaging, to provide an attractive choice e in the personalized treatment of lung cancer.

Comparison of machine learning methods for prediction of osteoradionecrosis incidence in patients with head and neck cancer

OBJECTIVES

Mandible osteoradionecrosis (ORN) is one of the most severe toxicities in patients with head and neck cancer (HNC) undergoing radiotherapy (RT). The existing literature focuses on the correlation of mandible ORN and clinical and dosimetric factors. This study proposes the use of machine learning (ML) methods as prediction models for mandible ORN incidence.

METHODS

A total of 96 patients (ORN incidence ratio of 1:1) treated between 2011 and 2015 were selected from the local HNC toxicity database. Demographic, clinical and dosimetric data (based on the mandible dose-volume histogram) were considered as model variables. Prediction accuracy (measured using a stratified fivefold nested cross-validation), sensitivity, specificity, precision and negative predictive value were used to evaluate the prediction performance of a multivariate logistic regression (LR) model, a support vector machine (SVM) model, a random forest (RF) model, an adaptive boosting (AdaBoost) model and an artificial neural network (ANN) model. The different models were compared based on their prediction accuracy and using the McNemar's hypothesis test.

RESULTS

The ANN model (77% accuracy), closely followed by the SVM (76%), AdaBoost (75%) and LR (75%) models, showed the highest overall prediction accuracy. The RF model (71%) showed the lowest prediction accuracy. However, based on the McNemar's test applied to all model pair combinations, no statistically significant difference between the models was found.

CONCLUSION

Based on our results, we encourage the use of ML-based prediction models for ORN incidence as has already been done for other HNC toxicity end points.

ADVANCES IN KNOWLEDGE

This research opens a new path towards personalised RT for HNC using ML to predict mandible ORN incidence.

Artificial intelligence-based clinical decision support in modern medical physics: Selection, acceptance, commissioning, and quality assurance

Background

Recent advances in machine and deep learning based on an increased availability of clinical data have fueled renewed interest in computerized clinical decision support systems (CDSSs). CDSSs have shown great potential to improve healthcare, increase patient safety and reduce costs. However, the use of CDSSs is not without pitfalls, as an inadequate or faulty CDSS can potentially deteriorate the quality of healthcare and put patients at risk. In addition, the adoption of a CDSS might fail because its intended users ignore the output of the CDSS due to lack of trust, relevancy or actionability.

Aim

In this article, we provide guidance based on literature for the different aspects involved in the adoption of a CDSS with a special focus on machine and deep learning based systems: selection, acceptance testing, commissioning, implementation and quality assurance.

Results

A rigorous selection process will help identify the CDSS that best fits the preferences and requirements of the local site. Acceptance testing will make sure that the selected CDSS fulfills the defined specifications and satisfies the safety requirements. The commissioning process will prepare the CDSS for safe clinical use at the local site. An effective implementation phase should result in an orderly roll out of the CDSS to the well‐trained end‐users whose expectations have been managed. And finally, quality assurance will make sure that the performance of the CDSS is maintained and that any issues are promptly identified and solved.

Conclusion

We conclude that a systematic approach to the adoption of a CDSS will help avoid pitfalls, improve patient safety and increase the chances of success.

Radiomics in Stroke Neuroimaging: Techniques, Applications, and Challenges

Stroke is a leading cause of disability and mortality worldwide, resulting in substantial economic costs for post-stroke care each year. Neuroimaging, such as cranial computed tomography or magnetic resonance imaging, is the backbone of stroke management strategies, which can guide treatment decision-making (thrombolysis or hemostasis) at an early stage. With advances in computational technologies, particularly in machine learning, visual image information can now be converted into numerous quantitative features in an objective, repeatable, and high-throughput manner, in a process known as radiomics. Radiomics is mainly used in the field of oncology, which remains an area of active research. Over the past few years, investigators have attempted to apply radiomics to stroke in the hope of gaining benefits similar to those obtained in cancer management, i.e., in promoting the development of personalized precision medicine. Currently, radiomic analysis has shown promise for a variety of applications in stroke, including the diagnosis of stroke lesions, early prediction of outcomes, and evaluation for long-term prognosis. In this article, we elaborate the contributions of radiomics to stroke, as well as the subprocesses and techniques involved in radiomics studies. We also discuss the potential challenges facing its widespread implementation in routine practice and the directions for future research.

Au-Pt Nanoparticle Formulation as a Radiosensitizer for Radiotherapy with Dual Effects

Background

Radiotherapy occupies an essential position as one of the most significant approaches for the clinical treatment of cancer. However, we cannot overcome the shortcoming of X-rays which is the high value of the oxygen enhancement ratio (OER). Radiosensitizers with the ability to enhance the radiosensitivity of tumor cells provide an alternative to changing X-rays to protons and heavy ion radiotherapy.

Materials and Methods

We prepared the Au-Pt nanoparticles (Au-Pt NPs) using a one-step method. The characteristics of the Au-Pt NPs were determined using TEM, HAADF-STEM, elemental mapping images, and DLS. The enhanced radiotherapy was demonstrated in vitro using MTT assays, colony formation assays, fluorescence imaging, and flow cytometric analyses of the apoptosis. The biodistribution of the Au-Pt NPs was analyzed using ICP-OES, and thermal images. The enhanced radiotherapy was demonstrated in vitro using immunofluorescence images, tumor volume and weigh, and hematoxylin & eosin (H&E) staining.

Results

Polyethylene glycol (PEG) functionalized nanoparticles composed of the metallic elements Au and Pt were designed to increase synergistic radiosensitivity. The mechanism demonstrated that heavy metal NPs possess a high X-ray photon capture cross-section and Compton scattering effect which increased DNA damage. Furthermore, the Au-Pt NPs exhibited enzyme-mimicking activities by catalyzing the decomposition of endogenous H₂O₂ to O₂ in the solid tumor microenvironment (TME).

Conclusion

Our work provides a systematically administered radiosensitizer that can selectively reside in a tumor via the EPR effect and enhances the efficiency of treating cancer with radiotherapy.