Dataset Information

Investigation of Radiation-Induced Toxicity in Head and Neck Cancer Patients through Radiomics and Machine Learning: A Systematic Review.

ABSTRACT: Background. Radiation-induced toxicity represents a crucial concern in oncological treatments of patients affected by head and neck neoplasms, due to its impact on survivors' quality of life. Published reports suggested the potential of radiomics combined with machine learning methods in the prediction and assessment of radiation-induced toxicities, supporting a tailored radiation treatment management. In this paper, we present an update of the current knowledge concerning these modern approaches.

Materials and methods

A systematic review according to PICO-PRISMA methodology was conducted in MEDLINE/PubMed and EMBASE databases until June 2019. Studies assessing the use of radiomics combined with machine learning in predicting radiation-induced toxicity in head and neck cancer patients were specifically included. Four authors (two independently and two in concordance) assessed the methodological quality of the included studies using the Radiomic Quality Score (RQS). The overall score for each analyzed study was obtained by the sum of the single RQS items; the average and standard deviation values of the authors' RQS were calculated and reported.

Results

Eight included papers, presenting data on parotid glands, cochlea, masticatory muscles, and white brain matter, were specifically analyzed in this review. Only one study had an average RQS was ≤ 30% (50%), while 3 studies obtained a RQS almost ≤ 25%. Potential variability in the interpretations of specific RQS items could have influenced the inter-rater agreement in specific cases.

Conclusions

Published radiomic studies provide encouraging but still limited and preliminary data that require further validation to improve the decision-making processes in preventing and managing radiation-induced toxicities.

SUBMITTER: Carbonara R

PROVIDER: S-EPMC8211491 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Radiomics leverages existing image datasets to provide non-visible data extraction via image post-processing, with the aim of identifying prognostic, and predictive imaging features at a sub-region of interest level. However, the application of radiomics is hampered by several challenges such as lack of image acquisition/analysis method standardization, impeding generalizability. As of yet, radiomics remains intriguing, but not clinically validated. We aimed to test the feasibility of a non-custom-constructed platform for disseminating existing large, standardized databases across institutions for promoting radiomics studies. Hence, University of Texas MD Anderson Cancer Center organized two public radiomics challenges in head and neck radiation oncology domain. This was done in conjunction with MICCAI 2016 satellite symposium using Kaggle-in-Class, a machine-learning and predictive analytics platform. We drew on clinical data matched to radiomics data derived from diagnostic contrast-enhanced computed tomography (CECT) images in a dataset of 315 patients with oropharyngeal cancer. Contestants were tasked to develop models for (i) classifying patients according to their human papillomavirus status, or (ii) predicting local tumor recurrence, following radiotherapy. Data were split into training, and test sets. Seventeen teams from various professional domains participated in one or both of the challenges. This review paper was based on the contestants' feedback; provided by 8 contestants only (47%). Six contestants (75%) incorporated extracted radiomics features into their predictive model building, either alone (n = 5; 62.5%), as was the case with the winner of the "HPV" challenge, or in conjunction with matched clinical attributes (n = 2; 25%). Only 23% of contestants, notably, including the winner of the "local recurrence" challenge, built their model relying solely on clinical data. In addition to the value of the integration of machine learning into clinical decision-making, our experience sheds light on challenges in sharing and directing existing datasets toward clinical applications of radiomics, including hyper-dimensionality of the clinical/imaging data attributes. Our experience may help guide researchers to create a framework for sharing and reuse of already published data that we believe will ultimately accelerate the pace of clinical applications of radiomics; both in challenge or clinical settings.

Project description:BackgroundRadiomics can provide in-depth characterization of cancers for treatment outcome prediction. Conventional radiomics rely on extraction of image features within a pre-defined image region of interest (ROI) which are typically fed to a classification algorithm for prediction of a clinical endpoint. Deep learning radiomics allows for a simpler workflow where images can be used directly as input to a convolutional neural network (CNN) with or without a pre-defined ROI.PurposeThe purpose of this study was to evaluate (i) conventional radiomics and (ii) deep learning radiomics for predicting overall survival (OS) and disease-free survival (DFS) for patients with head and neck squamous cell carcinoma (HNSCC) using pre-treatment 18F-fluorodeoxuglucose positron emission tomography (FDG PET) and computed tomography (CT) images.Materials and methodsFDG PET/CT images and clinical data of patients with HNSCC treated with radio(chemo)therapy at Oslo University Hospital (OUS; n = 139) and Maastricht University Medical Center (MAASTRO; n = 99) were collected retrospectively. OUS data was used for model training and initial evaluation. MAASTRO data was used for external testing to assess cross-institutional generalizability. Models trained on clinical and/or conventional radiomics features, with or without feature selection, were compared to CNNs trained on PET/CT images without or with the gross tumor volume (GTV) included. Model performance was measured using accuracy, area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), and the F1 score calculated for both classes separately.ResultsCNNs trained directly on images achieved the highest performance on external data for both endpoints. Adding both clinical and radiomics features to these image-based models increased performance further. Conventional radiomics including clinical data could achieve competitive performance. However, feature selection on clinical and radiomics data lead to overfitting and poor cross-institutional generalizability. CNNs without tumor and node contours achieved close to on-par performance with CNNs including contours.ConclusionHigh performance and cross-institutional generalizability can be achieved by combining clinical data, radiomics features and medical images together with deep learning models. However, deep learning models trained on images without contours can achieve competitive performance and could see potential use as an initial screening tool for high-risk patients.

Project description:PURPOSE:This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS:The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS:For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS:The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.

Project description:PurposeDeep-learning (DL) techniques have been successful in disease-prediction tasks and could improve the prediction of mandible osteoradionecrosis (ORN) resulting from head and neck cancer (HNC) radiation therapy. In this study, we retrospectively compared the performance of DL algorithms and traditional machine-learning (ML) techniques to predict mandible ORN binary outcome in an extensive cohort of patients with HNC.Methods and materialsPatients who received HNC radiation therapy at the University of Texas MD Anderson Cancer Center from 2005 to 2015 were identified for the ML (n = 1259) and DL (n = 1236) studies. The subjects were followed for ORN development for at least 12 months, with 173 developing ORN and 1086 having no evidence of ORN. The ML models used dose-volume histogram parameters to predict ORN development. These models included logistic regression, random forest, support vector machine, and a random classifier reference. The DL models were based on ResNet, DenseNet, and autoencoder-based architectures. The DL models used each participant's dose cropped to the mandible. The effect of increasing the amount of available training data on the DL models' prediction performance was evaluated by training the DL models using increasing ratios of the original training data.ResultsThe F1 score for the logistic regression model, the best-performing ML model, was 0.3. The best-performing ResNet, DenseNet, and autoencoder-based models had F1 scores of 0.07, 0.14, and 0.23, respectively, whereas the random classifier's F1 score was 0.17. No performance increase was apparent when we increased the amount of training data available for DL model training.ConclusionsThe ML models had superior performance to their DL counterparts. The lack of improvement in DL performance with increased training data suggests that either more data are needed for appropriate DL model construction or that the image features used in DL models are not suitable for this task.

Project description:ImportancePostoperative chemoradiation is the standard of care for cancers with positive margins or extracapsular extension, but the benefit of chemotherapy is unclear for patients with other intermediate risk features.ObjectiveTo evaluate whether machine learning models could identify patients with intermediate-risk head and neck squamous cell carcinoma who would benefit from chemoradiation.Design, setting, and participantsThis cohort study included patients diagnosed with squamous cell carcinoma of the oral cavity, oropharynx, hypopharynx, or larynx from January 1, 2004, through December 31, 2016. Patients had resected disease and underwent adjuvant radiotherapy. Analysis was performed from October 1, 2019, through September 1, 2020. Patients were selected from the National Cancer Database, a hospital-based registry that captures data from more than 70% of newly diagnosed cancers in the United States. Three machine learning survival models were trained using 80% of the cohort, with the remaining 20% used to assess model performance.ExposuresReceipt of adjuvant chemoradiation or radiation alone.Main outcomes and measuresPatients who received treatment recommended by machine learning models were compared with those who did not. Overall survival for treatment according to model recommendations was the primary outcome. Secondary outcomes included frequency of recommendation for chemotherapy and chemotherapy benefit in patients recommended for chemoradiation vs radiation alone.ResultsA total of 33 527 patients (24 189 [72%] men; 28 036 [84%] aged ≤70 years) met the inclusion criteria. Median follow-up in the validation data set was 43.2 (interquartile range, 19.8-65.5) months. DeepSurv, neural multitask logistic regression, and survival forest models recommended chemoradiation for 17 589 (52%), 15 917 (47%), and 14 912 patients (44%), respectively. Treatment according to model recommendations was associated with a survival benefit, with a hazard ratio of 0.79 (95% CI, 0.72-0.85; P < .001) for DeepSurv, 0.83 (95% CI, 0.77-0.90; P < .001) for neural multitask logistic regression, and 0.90 (95% CI, 0.83-0.98; P = .01) for random survival forest models. No survival benefit for chemotherapy was seen for patients recommended to receive radiotherapy alone.Conclusions and relevanceThese findings suggest that machine learning models may identify patients with intermediate risk who could benefit from chemoradiation. These models predicted that approximately half of such patients have no added benefit from chemotherapy.

Project description:Introduction"Radiomics" extracts and mines a large number of medical imaging features in a non-invasive and cost-effective way. The underlying assumption of radiomics is that these imaging features quantify phenotypic characteristics of an entire tumor. In order to enhance applicability of radiomics in clinical oncology, highly accurate and reliable machine-learning approaches are required. In this radiomic study, 13 feature selection methods and 11 machine-learning classification methods were evaluated in terms of their performance and stability for predicting overall survival in head and neck cancer patients.MethodsTwo independent head and neck cancer cohorts were investigated. Training cohort HN1 consisted of 101 head and neck cancer patients. Cohort HN2 (n?=?95) was used for validation. A total of 440 radiomic features were extracted from the segmented tumor regions in CT images. Feature selection and classification methods were compared using an unbiased evaluation framework.ResultsWe observed that the three feature selection methods minimum redundancy maximum relevance (AUC?=?0.69, Stability?=?0.66), mutual information feature selection (AUC?=?0.66, Stability?=?0.69), and conditional infomax feature extraction (AUC?=?0.68, Stability?=?0.7) had high prognostic performance and stability. The three classifiers BY (AUC?=?0.67, RSD?=?11.28), RF (AUC?=?0.61, RSD?=?7.36), and NN (AUC?=?0.62, RSD?=?10.52) also showed high prognostic performance and stability. Analysis investigating performance variability indicated that the choice of classification method is the major factor driving the performance variation (29.02% of total variance).ConclusionOur study identified prognostic and reliable machine-learning methods for the prediction of overall survival of head and neck cancer patients. Identification of optimal machine-learning methods for radiomics-based prognostic analyses could broaden the scope of radiomics in precision oncology and cancer care.