Radiomic signature: A novel magnetic resonance imaging-based prognostic biomarker in patients with skull base chordoma

A dosiomics approach to treatment outcome modeling in carbon ion radiotherapy for skull base chordomas

PURPOSE

To investigate the role of dosiomics features extracted from physical dose (DPHYS), RBE-weighted dose (DRBE) and dose-averaged Linear Energy Transfer (LETd), to predict the risk of local recurrence (LR) in skull base chordoma (SBC) treated with Carbon Ion Radiotherapy (CIRT). Thus, define and evaluate dosiomics-driven tumor control probability (TCP) models.

MATERIALS AND METHODS

54 SBC patients were retrospectively selected for this study. A regularized Cox proportional hazard model (r-Cox) and Survival Support Vector Machine (s-SVM) were tuned within a repeated Cross Validation (CV) and patients were stratified in low/high risk of LR. Models' performance was evaluated through Harrell's concordance statistic (C-index), and survival was represented through Kaplan-Meier (KM) curves. A multivariable logistic regression was fit to the selected feature sets to generate a dosiomics-driven TCP model for each map. These were compared to a reference model built with clinical parameters in terms of f-score and accuracy.

RESULTS

The LETd maps reached a test C-index of 0.750 and 0.786 with r-Cox and s-SVM, and significantly separated KM curves. DPHYS maps and clinical parameters showed promising CV outcomes with C-index above 0.8, despite a poorer performance on the test set and patients stratification. The LETd-based TCP showed a significatively higher f-score (0.67[0.52-0.70], median[IQR]) compared to the clinical model (0.4[0.32-0.63], p < 0.025), while DPHYS achieved a significatively higher accuracy (DPHYS: 0.73[0.65-0.79], Clinical: 0.6 [0.52-0.72]).

CONCLUSION

This analysis supports the role of LETd as relevant source of prognostic factors for LR in SBC treated with CIRT. This is reflected in the TCP modeling, where LETd and DPHYS showed an improved performance with respect to clinical models.

A Computed Tomography Radiomics Nomogram in Differentiating Chordoma From Giant Cell Tumor in the Axial Skeleton

OBJECTIVE

The aim of the study is to develop and validate a computed tomography (CT) radiomics nomogram for preoperatively differentiating chordoma from giant cell tumor (GCT) in the axial skeleton.

METHODS

Seventy-three chordomas and 38 GCTs in axial skeleton were retrospectively included and were divided into a training cohort (n = 63) and a test cohort (n = 48). The radiomics features were extracted from CT images. A radiomics signature was developed by using the least absolute shrinkage and selection operator model, and a radiomics score (Rad-score) was acquired. By combining the Rad-score with independent clinical risk factors using multivariate logistic regression model, a radiomics nomogram was established. Calibration and receiver operator characteristic curves were used to assess the performance of the nomogram.

RESULTS

Five features were selected to construct the radiomics signature. The radiomics signature showed favorable discrimination in the training cohort (area under the curve [AUC], 0.860; 95% confidence interval [CI], 0.760-0.960) and the test cohort (AUC, 0.830; 95% CI, 0.710-0.950). Age and location were the independent clinical factors. The radiomics nomogram combining the Rad-score with independent clinical factors showed good discrimination capability in the training cohort (AUC, 0.930; 95% CI, 0.880-0.990) and the test cohort (AUC, 0.980; 95% CI, 0.940-1.000) and outperformed the radiomics signature (z = 2.768, P = 0.006) in the test cohort.

CONCLUSIONS

The CT radiomics nomogram shows good predictive efficacy in differentiating chordoma from GCT in the axial skeleton, which might facilitate clinical decision making.

Microstructural parameters from DW-MRI for tumour characterization and local recurrence prediction in particle therapy of skull-base chordoma

BACKGROUND

Quantitative imaging such as Diffusion-Weighted MRI (DW-MRI) can be exploited to non-invasively derive patient-specific tumor microstructure information for tumor characterization and local recurrence risk prediction in radiotherapy.

PURPOSE

To characterize tumor microstructure according to proliferative capacity and predict local recurrence through microstructural markers derived from pre-treatment conventional DW-MRI, in skull-base chordoma (SBC) patients treated with proton (PT) and carbon ion (CIRT) radiotherapy.

METHODS

Forty-eight patients affected by SBC, who underwent conventional DW-MRI before treatment and were enrolled for CIRT (n = 25) or PT (n = 23), were retrospectively selected. Clinically verified local recurrence information (LR) and histological information (Ki-67, proliferation index) were collected. Apparent diffusion coefficient (ADC) maps were calculated from pre-treatment DW-MRI and, from these, a set of microstructural parameters (cellular radius R, volume fraction vf, diffusion D) were derived by applying a fine-tuning procedure to a framework employing Monte Carlo simulations on synthetic cell substrates. In addition, apparent cellularity (ρ_app ) was estimated from vf and R for an easier clinical interpretation. Histogram-based metrics (mean, median, variance, entropy) from estimated parameters were considered to investigate differences (Mann-Whitney U-test, α = 0.05) in estimated tumor microstructure in SBCs characterized by low or high cell proliferation (Ki-67). Recurrence-free survival analyses were also performed to assess the ability of the microstructural parameters to stratify patients according to the risk of local recurrence (Kaplan-Meier curves, log-rank test α = 0.05).

RESULTS

Refined microstructural markers revealed optimal capabilities in discriminating patients according to cell proliferation, achieving best results with mean values (p-values were 0.0383, 0.0284, 0.0284, 0.0468, and 0.0088 for ADC, R, vf, D, and ρ_app, respectively). Recurrence-free survival analyses showed significant differences between populations at high and low risk of local recurrence as stratified by entropy values of estimated microstructural parameters (p = 0.0110).

CONCLUSION

Patient-specific microstructural information was non-invasively derived providing potentially useful tools for SBC treatment personalization and optimization in particle therapy.

Preoperative computed tomography-based tumoral radiomic features prediction for overall survival in resectable non-small cell lung cancer

Objectives

The purpose of this study was to evaluate whether preoperative radiomics features could meliorate risk stratification for the overall survival (OS) of non-small cell lung cancer (NSCLC) patients.

Methods

After rigorous screening, the 208 NSCLC patients without any pre-operative adjuvant therapy were eventually enrolled. We segmented the 3D volume of interest (VOI) based on malignant lesion of computed tomography (CT) imaging and extracted 1542 radiomics features. Interclass correlation coefficients (ICC) and LASSO Cox regression analysis were utilized to perform feature selection and radiomics model building. In the model evaluation phase, we carried out stratified analysis, receiver operating characteristic (ROC) curve, concordance index (C-index), and decision curve analysis (DCA). In addition, integrating the clinicopathological trait and radiomics score, we developed a nomogram to predict the OS at 1 year, 2 years, and 3 years, respectively.

Results

Six radiomics features, including gradient_glcm_InverseVariance, logarithm_firstorder_Median, logarithm_firstorder_RobustMeanAbsoluteDeviation, square_gldm_LargeDependenceEmphasis, wavelet_HLL_firstorder_Kurtosis, and wavelet_LLL_firstorder_Maximum, were selected to construct the radiomics signature, whose areas under the curve (AUCs) for 3-year prediction reached 0.857 in the training set (n=146) and 0.871 in the testing set (n=62). The results of multivariate analysis revealed that the radiomics score, radiological sign, and N stage were independent prognostic factors in NSCLC. Moreover, compared with clinical factors and the separate radiomics model, the established nomogram exhibited a better performance in predicting 3-year OS.

Conclusions

Our radiomics model may provide a promising non-invasive approach for preoperative risk stratification and personalized postoperative surveillance for resectable NSCLC patients.

Integrated radiomics, dose-volume histogram criteria and clinical features for early prediction of saliva amount reduction after radiotherapy in nasopharyngeal cancer patients

PURPOSE

Previously, the evaluation of xerostomia depended on subjective grading systems, rather than the accurate saliva amount reduction. Our aim was to quantify acute xerostomia with reduced saliva amount, and apply radiomics, dose-volume histogram (DVH) criteria and clinical features to predict saliva amount reduction by machine learning techniques.

MATERIAL AND METHODS

Computed tomography (CT) of parotid glands, DVH, and clinical data of 52 patients were collected to extract radiomics, DVH criteria and clinical features, respectively. Firstly, radiomics, DVH criteria and clinical features were divided into 3 groups for feature selection, in order to alleviate the masking effect of the number of features in different groups. Secondly, the top features in the 3 groups composed integrated features, and features selection was performed again for integrated features. In this study, feature selection was used as a combination of eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) to alleviate multicollinearity. Finally, 6 machine learning techniques were used for predicting saliva amount reduction. Meanwhile, top radiomics features were modeled using the same machine learning techniques for comparison.

RESULT

17 integrated features (10 radiomics, 4 clinical, 3 DVH criteria) were selected to predict saliva amount reduction, with a mean square error (MSE) of 0.6994 and a R² score of 0.9815. Top 17 and 10 selected radiomics features predicted saliva amount reduction, with MSE of 0.7376, 0.7519, and R² score of 0.9805, 0.9801, respectively.

CONCLUSION

With the same number of features, integrated features (radiomics + DVH criteria + clinical) performed better than radiomics features alone. The important DVH criteria and clinical features mainly included, white blood cells (WBC), parotid_glands_Dmax, Age, parotid_glands_V15, hemoglobin (Hb), BMI and parotid_glands_V45.

Development and validation of a preoperative MRI-based radiomics nomogram to predict progression-free survival in patients with clival chordomas

Objectives

The aim of this study was to establish and validate a MRI-based radiomics nomogram to predict progression-free survival (PFS) of clival chordoma.

Methods

A total of 174 patients were enrolled in the study (train cohort: 121 cases, test cohort: 53 cases). Radiomic features were extracted from multiparametric MRIs. Intraclass correlation coefficient analysis and a Lasso and Elastic-Net regularized generalized linear model were used for feature selection. Then, a nomogram was established via univariate and multivariate Cox regression analysis in the train cohort. The performance of this nomogram was assessed by area under curve (AUC) and calibration curve.

Results

A total of 3318 radiomic features were extracted from each patient, of which 2563 radiomic features were stable features. After feature selection, seven radiomic features were selected. Cox regression analysis revealed that 2 clinical factors (degree of resection, and presence or absence of primary chordoma) and 4 radiomic features were independent prognostic factors. The AUC of the established nomogram was 0.747, 0.807, and 0.904 for PFS prediction at 1, 3, and 5 years in the train cohort, respectively, compared with 0.582, 0.852, and 0.914 in the test cohort. Calibration and risk score stratified survival curves were satisfactory in the train and test cohort.

Conclusions

The presented nomogram demonstrated a favorable predictive accuracy of PFS, which provided a novel tool to predict prognosis and risk stratification. Our results suggest that radiomic analysis can effectively help neurosurgeons perform individualized evaluations of patients with clival chordomas.

Prognostic molecular biomarkers in chordomas: A systematic review and identification of clinically usable biomarker panels

Introduction and objective

Despite the improvements in management and treatment of chordomas over time, the risk of disease recurrence remains high. Consequently, there is a push to develop effective systemic therapeutics for newly diagnosed and recurrent disease. In order to tailor treatment for individual chordoma patients and develop effective surveillance strategies, suitable clinical biomarkers need to be identified. The objective of this study was to systematically review all prognostic biomarkers for chordomas reported to date in order to classify them according to localization, study design and statistical analysis.

Methods

Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed published studies reporting biomarkers that correlated with clinical outcomes. We included time-to-event studies that evaluated biomarkers in skull base or spine chordomas. To be included in our review, the study must have analyzed the outcomes with univariate and/or multivariate methods (log-rank test or a Cox-regression model).

Results

We included 68 studies, of which only 5 were prospective studies. Overall, 103 biomarkers were analyzed in 3183 patients. According to FDA classification, 85 were molecular biomarkers (82.5%) mainly located in nucleus and cytoplasm (48% and 27%, respectively). Thirty-four studies analyzed biomarkers with Cox-regression model. Within these studies, 32 biomarkers (31%) and 22 biomarkers (21%) were independent prognostic factors for PFS and OS, respectively.

Conclusion

Our analysis identified a list of 13 biomarkers correlating with tumor control rates and survival. The future point will be gathering all these results to guide the clinical validation for a chordoma biomarker panel. Our identified biomarkers have strengths and weaknesses according to FDA’s guidelines, some are affordable, have a low-invasive collection method and can be easily measured in any health care setting (RDW and D-dimer), but others molecular biomarkers need specialized assay techniques (microRNAs, PD-1 pathway markers, CDKs and somatic chromosome deletions were more chordoma-specific). A focused list of biomarkers that correlate with local recurrence, metastatic spread and survival might be a cornerstone to determine the need of adjuvant therapies.

An MRI-Based Radiomics Model for Predicting the Benignity and Malignancy of BI-RADS 4 Breast Lesions

Objectives

The probability of Breast Imaging Reporting and Data Systems (BI-RADS) 4 lesions being malignant is 2%–95%, which shows the difficulty to make a diagnosis. Radiomics models based on magnetic resonance imaging (MRI) can replace clinicopathological diagnosis with high performance. In the present study, we developed and tested a radiomics model based on MRI images that can predict the malignancy of BI-RADS 4 breast lesions.

Methods

We retrospective enrolled a total of 216 BI-RADS 4 patients MRI and clinical information. We extracted 3,474 radiomics features from dynamic contrast-enhanced (DCE), T₂-weighted images (T₂WI), and diffusion-weighted imaging (DWI) MRI images. Least absolute shrinkage and selection operator (LASSO) and logistic regression were used to select features and build radiomics models based on different sequence combinations. We built eight radiomics models which were based on DCE, DWI, T₂WI, DCE+DWI, DCE+T₂WI, DWI+T₂WI, and DCE+DWI+T₂WI and a clinical predictive model built based on the visual assessment of radiologists. A nomogram was constructed with the best radiomics signature combined with patient characteristics. The calibration curves for the radiomics signature and nomogram were conducted, combined with the Hosmer-Lemeshow test.

Results

Pearson’s correlation was used to eliminate 3,329 irrelevant features, and then LASSO and logistic regression were used to screen the remaining feature coefficients for each model we built. Finally, 12 related features were obtained in the model which had the best performance. These 12 features were used to build a radiomics model in combination with the actual clinical diagnosis of benign or malignant lesion labels we have obtained. The best model built by 12 features from the 3 sequences has an AUC value of 0.939 (95% CI, 0.884-0.994) and an accuracy of 0.931 in the testing cohort. The sensitivity, specificity, precision and Matthews correlation coefficient (MCC) of testing cohort are 0.932, 0.923, 0.982, and 0.791, respectively. The nomogram has also been verified to have calibration curves with good overlap.

Conclusions

Radiomics is beneficial in the malignancy prediction of BI-RADS 4 breast lesions. The radiomics predictive model built by the combination of DCE, DWI, and T₂WI sequences has great application potential.

[Artificial intelligence, radiomics and pathomics to predict response and survival of patients treated with radiations]

Artificial intelligence approaches in medicine are more and more used and are extremely promising due to the growing number of data produced and the variety of data they allow to exploit. Thus, the computational analysis of medical images in particular, radiological (radiomics), or anatomopathological (pathomics), has shown many very interesting results for the prediction of the prognosis and the response of cancer patients. Radiotherapy is a discipline that particularly benefits from these new approaches based on computer science and imaging. This review will present the main principles of an artificial intelligence approach and in particular machine learning, the principles of a radiomic and pathomic approach and the potential of their use for the prediction of the prognosis of patients treated with radiotherapy.

Vertebral MRI-based radiomics model to differentiate multiple myeloma from metastases: influence of features number on logistic regression model performance

OBJECTIVES

This study aimed to use the most frequent features to establish a vertebral MRI-based radiomics model that could differentiate multiple myeloma (MM) from metastases and compare the model performance with different features number.

METHODS

We retrospectively analyzed conventional MRI (T1WI and fat-suppression T2WI) of 103 MM patients and 138 patients with metastases. The feature selection process included four steps. The first three steps defined as conventional feature selection (CFS), carried out 50 times (ten times with 5-fold cross-validation), included variance threshold, SelectKBest, and least absolute shrinkage and selection operator. The most frequent fixed features were selected for modeling during the last step. The number of events per independent variable (EPV) is the number of patients in a smaller subgroup divided by the number of radiomics features considered in developing the prediction model. The EPV values considered were 5, 10, 15, and 20. Therefore, we constructed four models using the top 16, 8, 6, and 4 most frequent features, respectively. The models constructed with features selected by CFS were also compared.

RESULTS

The AUCs of 20EPV-Model, 15EPV-Model, and CSF-Model (AUC = 0.71, 0.81, and 0.78) were poor than 10EPV-Model (AUC = 0.84, p < 0.001). The AUC of 10EPV-Model was comparable with 5EPV-Model (AUC = 0.85, p = 0.480).

CONCLUSIONS

The radiomics model constructed with an appropriate small number of the most frequent features could well distinguish metastases from MM based on conventional vertebral MRI. Based on our results, we recommend following the 10 EPV as the rule of thumb for feature selection.

KEY POINTS

• The developed radiomics model could distinguish metastases from multiple myeloma based on conventional vertebral MRI. • An accurate model based on just a handful of the most frequent features could be constructed by utilizing multiple feature reduction techniques. • An event per independent variable value of 10 is recommended as a rule of thumb for modeling feature selection.

Prognostic Value of Pre-Treatment CT Radiomics and Clinical Factors for the Overall Survival of Advanced (IIIB-IV) Lung Adenocarcinoma Patients

Purpose

The purpose of this study was to investigate the prognostic value of pre-treatment CT radiomics and clinical factors for the overall survival (OS) of advanced (IIIB–IV) lung adenocarcinoma patients.

Methods

This study involved 165 patients with advanced lung adenocarcinoma. The Lasso–Cox regression model was used for feature selection and radiomics signature building. Then a clinical model was built based on clinical factors; a combined model in the form of nomogram was constructed with both clinical factors and the radiomics signature. Harrell’s concordance index (C-Index) and Receiver operating characteristic (ROC) curves at cut-off time points of 1-, 2-, and 3- year were used to estimate and compare the predictive ability of all three models. Finally, the discriminatory ability and calibration of the nomogram were analyzed.

Results

Thirteen significant features were selected to build the radiomics signature whose C-indexes were 0.746 (95% CI, 0.699 to 0.792) in the training cohort and 0.677 (95% CI, 0.597 to 0.766) in the validation cohort. The C-indexes of combined model achieved 0.799 (95% CI, 0.757 to 0.84) in the training cohort and 0.733 (95% CI, 0.656 to 0.81) in the validation cohort, which outperformed the clinical model and radiomics signature. Moreover, the areas under the curve (AUCs) of the radiomic signature for 2-year prediction was superior to that of the clinical model. The combined model had the best AUCs for 2- and 3-year predictions.

Conclusions

Radiomic signatures and clinical factors have prognostic value for OS in advanced (IIIB–IV) lung adenocarcinoma patients. The optimal model should be selected according to different cut-off time points in clinical application.

Prognostic Modeling of Patients Undergoing Surgery Alone for Esophageal Squamous Cell Carcinoma: A Histopathological and Computed Tomography Based Quantitative Analysis

Objective

To evaluate the effectiveness of a novel computerized quantitative analysis based on histopathological and computed tomography (CT) images for predicting the postoperative prognosis of esophageal squamous cell carcinoma (ESCC) patients.

Methods

We retrospectively reviewed the medical records of 153 ESCC patients who underwent esophagectomy alone and quantitatively analyzed digital histological specimens and diagnostic CT images. We cut pathological images (6000 × 6000) into 50 × 50 patches; each patient had 14,400 patches. Cluster analysis was used to process these patches. We used the pathological clusters to all patches ratio (PCPR) of each case for pathological features and we obtained 20 PCPR quantitative features. Totally, 125 computerized quantitative (20 PCPR and 105 CT) features were extracted. We used a recursive feature elimination approach to select features. A Cox hazard model with L1 penalization was used for prognostic indexing. We compared the following prognostic models: Model A: clinical features; Model B: quantitative CT and clinical features; Model C: quantitative histopathological and clinical features; and Model D: combined information of clinical, CT, and histopathology. Indices of concordance (C-index) and leave-one-out cross-validation (LOOCV) were used to assess prognostic model accuracy.

Results

Five PCPR and eight CT features were treated as significant indicators in ESCC prognosis. C-indices adjusted for LOOCV were comparable among four models, 0.596 (Model A) vs. 0.658 (Model B) vs. 0.651 (Model C), and improved to 0.711with Model D combining information of clinical, CT, and histopathology (all p<0.05). Using Model D, we stratified patients into low- and high-risk groups. The 3-year overall survival rates of low- and high-risk patients were 38.0% and 25.0%, respectively (p<0.001).

Conclusion

Quantitative prognostic modeling using a combination of clinical data, histopathological, and CT images can stratify ESCC patients with surgery alone into high-risk and low-risk groups.

Non-Invasive Radiomics Approach Predict Invasiveness of Adamantinomatous Craniopharyngioma Before Surgery

Purpose

Craniopharyngiomas (CPs) are benign tumors, complete tumor resection is considered to be the optimal treatment. However, although histologically benign, the local invasiveness of CPs commonly contributes to incomplete resection and a poor prognosis. At present, some advocate less aggressive surgery combined with radiotherapy as a more reasonable and effective means of protecting hypothalamus function and preventing recurrence in patients with tight tumor adhesion to the hypothalamus. Hence, if a method can be developed to predict the invasiveness of CP preoperatively, it will help in the development of a more personalized surgical strategy. The aim of the study was to report a radiomics-clinical nomogram for the individualized preoperative prediction of the invasiveness of adamantinomatous CP (ACPs) before surgery.

Methods

In total, 1,874 radiomics features were extracted from whole tumors on contrast-enhanced T1-weighted images. A support vector machine trained a predictive model that was validated using receiver operating characteristic (ROC) analysis on an independent test set. Moreover, a nomogram was constructed incorporating clinical characteristics and the radiomics signature for individual prediction.

Results

Eleven features associated with the invasiveness of ACPs were selected by using the least absolute shrinkage and selection operator (LASSO) method. These features yielded area under the curve (AUC) values of 79.09 and 73.5% for the training and test sets, respectively. The nomogram incorporating peritumoral edema and the radiomics signature yielded good calibration in the training and test sets with the AUCs of 84.79 and 76.48%, respectively.

Conclusion

The developed model yields good performance, indicating that the invasiveness of APCs can be predicted using noninvasive radiological data. This reliable, noninvasive tool can help clinical decision making and improve patient prognosis.

Radiomics and Dosiomics for Predicting Local Control after Carbon-Ion Radiotherapy in Skull-Base Chordoma

Skull-base chordoma (SBC) can be treated with carbon ion radiotherapy (CIRT) to improve local control (LC). The study aimed to explore the role of multi-parametric radiomic, dosiomic and clinical features as prognostic factors for LC in SBC patients undergoing CIRT. Before CIRT, 57 patients underwent MR and CT imaging, from which tumour contours and dose maps were obtained. MRI and CT-based radiomic, and dosiomic features were selected and fed to two survival models, singularly or by combining them with clinical factors. Adverse LC was given by in-field recurrence or tumour progression. The dataset was split in development and test sets and the models' performance evaluated using the concordance index (C-index). Patients were then assigned a low- or high-risk score. Survival curves were estimated, and risk groups compared through log-rank tests (after Bonferroni correction α = 0.0083). The best performing models were built on features describing tumour shape and dosiomic heterogeneity (median/interquartile range validation C-index: 0.80/024 and 0.79/0.26), followed by combined (0.73/0.30 and 0.75/0.27) and CT-based models (0.77/0.24 and 0.64/0.28). Dosiomic and combined models could consistently stratify patients in two significantly different groups. Dosiomic and multi-parametric radiomic features showed to be promising prognostic factors for LC in SBC treated with CIRT.

Application of radiomics and machine learning in head and neck cancers

With the continuous development of medical image informatics technology, more and more high-throughput quantitative data could be extracted from digital medical images, which has resulted in a new kind of omics-Radiomics. In recent years, in addition to genomics, proteomics and metabolomics, radiomic has attracted the interest of more and more researchers. Compared to other omics, radiomics can be perfectly integrated with clinical data, even with the pathology and molecular biomarker, so that the study can be closer to the clinical reality and more revealing of the tumor development. Mass data will also be generated in this process. Machine learning, due to its own characteristics, has a unique advantage in processing massive radiomic data. By analyzing mass amounts of data with strong clinical relevance, people can construct models that more accurately reflect tumor development and progression, thereby providing the possibility of personalized and sequential treatment of patients. As one of the cancer types whose treatment and diagnosis rely on imaging examination, radiomics has a very broad application prospect in head and neck cancers (HNC). Until now, there have been some notable results in HNC. In this review, we will introduce the concepts and workflow of radiomics and machine learning and their current applications in head and neck cancers, as well as the directions and applications of artificial intelligence in the treatment and diagnosis of HNC.

Development and Validation of a 6-miRNA Prognostic Signature in Spinal Chordoma

BACKGROUND

Published data have suggested a critical role for microRNA (miRNA) expression in chordoma progression. However, most of these studies focus on single miRNA and no multi-miRNA prognostic signature has been currently established for chordoma. In this study, we sought to develop and validate a 6-miRNA risk score (miRscore) model for survival prediction.

METHODS

Medline, Embase, and Google scholar searches (from inception to July 20, 2018) were conducted to identify candidate miRNAs with prognostic value as per predefined criteria. Quantitative RT-PCR was used to measure miRNA levels in 114 spinal chordoma (54 in the training and 60 in the validation cohort) and 20 control specimens. Subsequently, the miRscore was built based on miRNAs data.

RESULTS

Literature searches identified six prognostic miRNAs (miR-574-3p, miR-1237-3p, miR-140-3p, miR-1, miR-155, and miR-1290) with differential expression in tumor tissues. Bioinformatical analysis revealed an important regulatory role for miR-574-3p/EGFR signaling in chordoma and showed that the target genes of these prognostic miRNAs were mainly enriched in transcription regulation, protein binding and cancer-related pathways. In both cohorts, the miRscore was associated with surrounding muscle invasion by tumor and/or other aggressive features. The miRscore model well predicted local recurrence-free survival and overall survival, which remained after adjusting for other relevant covariates. Further time-dependent receiver operating characteristics analysis in the two cohorts found that the miRscore classifier had stronger prognostic power than known clinical predictors and improved the ability of Enneking staging to predict outcomes. Importantly, recursive-partitioning analysis of both samples combined separated patients into four prognostically distinct risk subgroups for recurrence and survival (both P < 0.001).

CONCLUSIONS

These data suggest the miRscore as a useful prognostic stratification tool in spinal chordoma and may represent an important step toward future personalized treatment of patients.

Reinventing radiation therapy with machine learning and imaging bio-markers (radiomics): State-of-the-art, challenges and perspectives

Radiation therapy is a pivotal cancer treatment that has significantly progressed over the last decade due to numerous technological breakthroughs. Imaging is now playing a critical role on deployment of the clinical workflow, both for treatment planning and treatment delivery. Machine-learning analysis of predefined features extracted from medical images, i.e. radiomics, has emerged as a promising clinical tool for a wide range of clinical problems addressing drug development, clinical diagnosis, treatment selection and implementation as well as prognosis. Radiomics denotes a paradigm shift redefining medical images as a quantitative asset for data-driven precision medicine. The adoption of machine-learning in a clinical setting and in particular of radiomics features requires the selection of robust, representative and clinically interpretable biomarkers that are properly evaluated on a representative clinical data set. To be clinically relevant, radiomics must not only improve patients' management with great accuracy but also be reproducible and generalizable. Hence, this review explores the existing literature and exposes its potential technical caveats, such as the lack of quality control, standardization, sufficient sample size, type of data collection, and external validation. Based upon the analysis of 165 original research studies based on PET, CT-scan, and MRI, this review provides an overview of new concepts, and hypotheses generating findings that should be validated. In particular, it describes evolving research trends to enhance several clinical tasks such as prognostication, treatment planning, response assessment, prediction of recurrence/relapse, and prediction of toxicity. Perspectives regarding the implementation of an AI-based radiotherapy workflow are presented.

MRI Signal Intensity and Electron Ultrastructure Classification Predict the Long-Term Outcome of Skull Base Chordomas

BACKGROUND AND PURPOSE

MR imaging is a useful and widely used evaluation for chordomas. Prior studies have classified chordomas into cell-dense type and matrix-rich type according to the ultrastructural features. However, the relationship between the MR imaging signal intensity and ultrastructural classification is unknown. We hypothesized that MR imaging signal intensity may predict both tumor ultrastructural classification and prognosis.

MATERIALS AND METHODS

Seventy-nine patients with skull base chordomas who underwent 95 operations were included in this retrospective single-center series. Preoperative tumor-to-pons MR imaging signal intensity ratios were calculated and designated as ratio on T1 FLAIR sequence (R_T1), ratio on T2 sequence (R_T2), and ratio on enhanced T1 FLAIR sequence (R_EN), respectively. We assessed the relationships among signal intensity ratios, ultrastructural classification, and survival.

RESULTS

Compared with the matrix-rich type group, the cell-dense type chordomas showed lower R_T2 (cell-dense type: 1.90 ± 0.38; matrix-rich type: 2.61 ± 0.60 P < .001). The model of predicting cell-dense type based on R_T2 had an area under the curve of 0.83 (95% CI, 0.75-0.92). In patients without radiation therapy, both progression-free survival (P = .003) and overall survival (P = .002) were longer in the matrix-rich type group than in the cell-dense type group. R_EN was a risk factor for progression-free survival (hazard ratio = 10.24; 95% CI, 1.73-60.79); R_T2 was a protective factor for overall survival (hazard ratio  = 0.33; 95% CI, 0.12-0.87); and R_EN was a risk factor for overall survival (hazard ratio = 4.76; 95% CI, 1.51-15.01).

CONCLUSIONS

The difference in MR imaging signal intensity in chordomas can be explained by electron microscopic features. Both signal intensity ratios and electron microscopic features may be prognostic factors.

Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study

Purpose: The majority of patients with low-grade gliomas (LGGs) experience tumor-related epilepsy during the disease course. Our study aimed to build a radiomic prediction model for LGG-related epilepsy type based on magnetic resonance imaging (MRI) data.

Methods: A total of 205 cases with LGG-related epilepsy were enrolled in the retrospective study and divided into training and validation cohorts (1:1) according to their surgery time. Seven hundred thirty-four radiomic features were extracted from T2-weighted imaging, including six location features. Pearson correlation coefficient, univariate area under curve (AUC) analysis, and least absolute shrinkage and selection operator regression were adopted to select the most relevant features for the epilepsy type to build a radiomic signature. Furthermore, a novel radiomic nomogram was developed for clinical application using the radiomic signature and clinical variables from all patients.

Results: Four MRI-based features were selected from the 734 radiomic features, including one location feature. Good discriminative performances were achieved in both training (AUC = 0.859, 95% CI = 0.787–0.932) and validation cohorts (AUC = 0.839, 95% CI = 0.761–0.917) for the type of epilepsy. The accuracies were 80.4 and 80.6%, respectively. The radiomic nomogram also allowed for a high degree of discrimination. All models presented favorable calibration curves and decision curve analyses.

Conclusion: Our results suggested that the MRI-based radiomic analysis may predict the type of LGG-related epilepsy to enable individualized therapy for patients with LGG-related epilepsy.