A novel representation of inter-site tumour heterogeneity from pre-treatment computed tomography textures classifies ovarian cancers by clinical outcome

Uncertainty measurement of radiomics features against inherent quantum noise in computed tomography imaging

OBJECTIVES

Quantum noise is a random process in X-ray-based imaging systems. We addressed and measured the uncertainty of radiomics features against this quantum noise in computed tomography (CT) images.

METHODS

A clinical multi-detector CT scanner, two homogeneous phantom sets, and four heterogeneous samples were used. A solid tumor tissue removed from a male BALB/c mouse was included. We the placed phantom sets on the CT scanning table and repeated 20 acquisitions with identical imaging settings. Regions of interest were delineated for feature extraction. Statistical quantities-average, standard deviation, and percentage uncertainty-were calculated from these 20 repeated scans. Percentage uncertainty was used to measure and quantify feature stability against quantum noise. Twelve radiomics features were measured. Random noise was added to study the robustness of machine learning classifiers against feature uncertainty.

RESULTS

We found the ranges of percentage uncertainties from homogeneous soft tissue phantoms, homogeneous bone phantoms, and solid tumor tissue to be 0.01-2138%, 0.02-15%, and 0.18-16%, respectively. Overall, it was found that the CT features ShortRunHighGrayLevelEmpha (SRHGE) (0.01-0.18%), ShortRunLowGrayLevelEmpha (SRLGE) (0.01-0.41%), LowGrayLevelRunEmpha (LGRE) (0.01-0.39%), and LongRunLowGrayLevelEmpha (LRLGE) (0.02-0.66%) were the most stable features against the inherent quantum noise. The most unstable features were cluster shade (1-2138%) and max probability (1-16%). The impact of random noise to the prediction accuracy by different machine learning classifiers was found to be between 0 and 12%.

CONCLUSIONS

Twelve features were used for uncertainty measurements. The upper and lower bounds of percentage uncertainties were determined. The quantum noise effect on machine learning classifiers is model dependent.

KEY POINTS

• Quantum noise is a random process and is intrinsic to X-ray-based imaging systems. This inherent quantum noise creates unpredictable fluctuations in the gray-level intensities of image pixels. Extra cautions and further validations are strongly recommended when unstable radiomics features are selected by a predictive model for disease classification or treatment outcome prognosis. • We addressed and used the statistical quantity of percentage uncertainty to measure the uncertainty of radiomics features against the inherent quantum noise in computed tomography (CT) images. • A clinical multi-detector CT scanner, two homogeneous phantom sets, and four heterogeneous samples were used in the stability measurement. A solid tumor tissue removed from a male BALB/c mouse was included in the heterogeneous sample.

Radiomics Analysis of PET and CT Components of 18F-FDG PET/CT Imaging for Prediction of Progression-Free Survival in Advanced High-Grade Serous Ovarian Cancer

Objective

To investigate radiomics features extracted from PET and CT components of ¹⁸F-FDG PET/CT images integrating clinical factors and metabolic parameters of PET to predict progression-free survival (PFS) in advanced high-grade serous ovarian cancer (HGSOC).

Methods

A total of 261 patients were finally enrolled in this study and randomly divided into training (n=182) and validation cohorts (n=79). The data of clinical features and metabolic parameters of PET were reviewed from hospital information system(HIS). All volumes of interest (VOIs) of PET/CT images were semi-automatically segmented with a threshold of 42% of maximal standard uptake value (SUVmax) in PET images. A total of 1700 (850×2) radiomics features were separately extracted from PET and CT components of PET/CT images. Then two radiomics signatures (RSs) were constructed by the least absolute shrinkage and selection operator (LASSO) method. The RSs of PET (PET_RS) and CT components(CT_RS) were separately divided into low and high RS groups according to the optimum cutoff value. The potential associations between RSs with PFS were assessed in training and validation cohorts based on the Log-rank test. Clinical features and metabolic parameters of PET images (PET_MP) with P-value <0.05 in univariate and multivariate Cox regression were combined with PET_RS and CT_RS to develop prediction nomograms (Clinical, Clinical+ PET_MP, Clinical+ PET_RS, Clinical+ CT_RS, Clinical+ PET_MP + PET_RS, Clinical+ PET_MP + CT_RS) by using multivariate Cox regression. The concordance index (C-index), calibration curve, and net reclassification improvement (NRI) was applied to evaluate the predictive performance of nomograms in training and validation cohorts.

Results

In univariate Cox regression analysis, six clinical features were significantly associated with PFS. Ten PET radiomics features were selected by LASSO to construct PET_RS, and 1 CT radiomics features to construct CT_RS. PET_RS and CT_RS was significantly associated with PFS both in training (P <0.00 for both RSs) and validation cohorts (P=0.01 for both RSs). Because there was no PET_MP significantly associated with PFS in training cohorts. Only three models were constructed by 4 clinical features with P-value <0.05 in multivariate Cox regression and RSs (Clinical, Clinical+ PET_RS, Clinical+ CT_RS). Clinical+ PET_RS model showed higher prognostic performance than other models in training cohort (C-index=0.70, 95% CI 0.68-0.72) and validation cohort (C-index=0.70, 95% CI 0.66-0.74). Calibration curves of each model for prediction of 1-, 3-year PFS indicated Clinical +PET_RS model showed excellent agreements between estimated and the observed 1-, 3-outcomes. Compared to the basic clinical model, Clinical+ PET_MS model resulted in greater improvement in predictive performance in the validation cohort.

Conclusion

PET_RS can improve diagnostic accuracy and provide complementary prognostic information compared with the use of clinical factors alone or combined with CT_RS. The newly developed radiomics nomogram is an effective tool to predict PFS for patients with advanced HGSOC.

Preoperative Nomogram for Differentiation of Histological Subtypes in Ovarian Cancer Based on Computer Tomography Radiomics

Objectives

Non-invasive method to predict the histological subtypes preoperatively is essential for the overall management of ovarian cancer (OC). The feasibility of radiomics in the differentiating of epithelial ovarian cancer (EOC) and non-epithelial ovarian cancer (NEOC) based on computed tomography (CT) images was investigated.

Methods

Radiomics features were extracted from preoperative CT for 101 patients with pathologically proven OC. Radiomics signature was built using the least absolute shrinkage and selection operator (LASSO) logistic regression. A nomogram was developed with the combination of radiomics features and clinical factors to differentiate EOC and NEOC.

Results

Eight radiomics features were selected to build a radiomics signature with an area under curve (AUC) of 0.781 (95% confidence interval (CI), 0.666 -0.897) in the discrimination between EOC and NEOC. The AUC of the combined model integrating clinical factors and radiomics features was 0.869 (95% CI, 0.783 -0.955). The nomogram demonstrated that the combined model provides a better net benefit to predict histological subtypes compared with radiomics signature and clinical factors alone when the threshold probability is within a range from 0.43 to 0.97.

Conclusions

Nomogram developed with CT radiomics signature and clinical factors is feasible to predict the histological subtypes preoperative for patients with OC.

Computed Tomography Based Radiomics as a Predictor of Survival in Ovarian Cancer Patients: A Systematic Review

Simple Summary

Ovarian cancer represents the most lethal gynecological malignancy. Since many new drugs have been recently introduced as adjunctive treatments for this pathology, an early prediction of outcome might be helpful to further improve outcomes. Radiomics represents a recent advancement, relying on extraction of quantitative features from imaging examinations. Indeed, clinical images, such as computed tomography images, may contain quantitative information, reflecting the underlying pathophysiology of a tumoral tissue. Radiomic analyses can be performed in tumor regions and metastatic lesions, as well as in normal tissues. The radiomic process relies on quantitative features, usually extracted by dedicated software, and then culminates in analysis and model building, according to a defined clinical question. This systematic review aims to evaluate association between radiomics based on computed tomography images and survival (in terms of overall survival and progression free survival) in ovarian cancer patients.

Abstract

The objective of this systematic review was to assess the results of radiomics for prediction of overall survival (OS) and progression free survival (PFS) in ovarian cancer (OC) patients. A secondary objective was to evaluate the findings of papers that based their analyses on inter-site heterogeneity. This systematic review was conducted according to the PRISMA statement. After the initial retrieval of 145 articles, the final systematic review comprised six articles. Association between radiomic features and OS was evaluated in 3/6 studies (50%); all articles showed a significant association between radiomic features and OS. Association with PFS was evaluated in 5/6 (83%) articles; the period of follow-up ranged between six and 36 months. All the articles showed significant association between radiomic models and PFS. Inter-site textural features were used for analysis in 2/6 (33%) articles. They demonstrated that high levels of inter-site textural heterogeneity were significantly associated with incomplete surgical resection in breast cancer gene-negative patients, and that lower heterogeneity was associated with complete resectability. There were some differences among papers in methodology; for example, only 3/6 (50%) articles included validation cohorts. In conclusion, radiomic models have demonstrated promising results as predictors of survival in OC patients, although larger studies are needed to allow clinical applicability.

Objective responses to first-line neoadjuvant carboplatin-paclitaxel regimens for ovarian, fallopian tube, or primary peritoneal carcinoma (ICON8): post-hoc exploratory analysis of a randomised, phase 3 trial

BACKGROUND

Platinum-based neoadjuvant chemotherapy followed by delayed primary surgery (DPS) is an established strategy for women with newly diagnosed, advanced-stage epithelial ovarian cancer. Although this therapeutic approach has been validated in randomised, phase 3 trials, evaluation of response to neoadjuvant chemotherapy using Response Evaluation Criteria in Solid Tumors, version 1.1 (RECIST), and cancer antigen 125 (CA125) has not been reported. We describe RECIST and Gynecologic Cancer InterGroup (GCIG) CA125 responses in patients receiving platinum-based neoadjuvant chemotherapy followed by DPS in the ICON8 trial.

METHODS

ICON8 was an international, multicentre, randomised, phase 3 trial done across 117 hospitals in the UK, Australia, New Zealand, Mexico, South Korea, and Ireland. The trial included women aged 18 years or older with an Eastern Cooperative Oncology Group performance status of 0-2, life expectancy of more than 12 weeks, and newly diagnosed International Federation of Gynecology and Obstetrics (FIGO; 1988) stage IC-IIA high-grade serous, clear cell, or any poorly differentiated or grade 3 histological subtype, or any FIGO (1988) stage IIB-IV epithelial cancer of the ovary, fallopian tube, or primary peritoneum. Patients were randomly assigned (1:1:1) to receive intravenous carboplatin (area under the curve [AUC]5 or AUC6) and intravenous paclitaxel (175 mg/m2 by body surface area) on day 1 of every 21-day cycle (control group; group 1); intravenous carboplatin (AUC5 or AUC6) on day 1 and intravenous dose-fractionated paclitaxel (80 mg/m2 by body surface area) on days 1, 8, and 15 of every 21-day cycle (group 2); or intravenous dose-fractionated carboplatin (AUC2) and intravenous dose-fractionated paclitaxel (80 mg/m2 by body surface area) on days 1, 8, and 15 of every 21-day cycle (group 3). The maximum number of cycles of chemotherapy permitted was six. Randomisation was done with a minimisation method, and patients were stratified according to GCIG group, disease stage, and timing and outcome of cytoreductive surgery. Patients and clinicians were not masked to group allocation. The scheduling of surgery and use of neoadjuvant chemotherapy were determined by local multidisciplinary case review. In this post-hoc exploratory analysis of ICON8, progression-free survival was analysed using the landmark method and defined as the time interval between the date of pre-surgical planning radiological tumour assessment to the date of investigator-assessed clinical or radiological progression or death, whichever occurred first. This definition is different from the intention-to-treat primary progression-free survival analysis of ICON8, which defined progression-free survival as the time from randomisation to the date of first clinical or radiological progression or death, whichever occurred first. We also compared the extent of surgical cytoreduction with RECIST and GCIG CA125 responses. This post-hoc exploratory analysis includes only women recruited to ICON8 who were planned for neoadjuvant chemotherapy followed by DPS and had RECIST and/or GCIG CA125-evaluable disease. ICON8 is closed for enrolment and follow-up, and registered with ClinicalTrials.gov, NCT01654146.

FINDINGS

Between June 6, 2011, and Nov 28, 2014, 1566 women were enrolled in ICON8, of whom 779 (50%) were planned for neoadjuvant chemotherapy followed by DPS. Median follow-up was 29·5 months (IQR 15·6-54·3) for the neoadjuvant chemotherapy followed by DPS population. Of 564 women who had RECIST-evaluable disease at trial entry, 348 (62%) had a complete or partial response. Of 727 women who were evaluable by GCIG CA125 criteria at the time of diagnosis, 610 (84%) had a CA125 response. Median progression-free survival was 14·4 months (95% CI 9·2-28·0; 297 events) for patients with a RECIST complete or partial response and 13·3 months (8·1-20·1; 171 events) for those with RECIST stable disease. Median progression-free survival for women with a GCIG CA125 response was 13·8 months (95% CI 8·8-23·4; 544 events) and 9·7 months (5·8-14·5; 111 events) for those without a GCIG CA125 response. Complete cytoreduction (R0) was achieved in 187 (56%) of 335 women with a RECIST complete or partial response and 73 (42%) of 172 women with RECIST stable disease. Complete cytoreduction was achieved in 290 (50%) of 576 women with a GCIG CA125 response and 30 (30%) of 101 women without a GCIG CA125 response.

INTERPRETATION

The RECIST-defined radiological response rate was lower than that frequently quoted to patients in the clinic. RECIST and GCIG CA125 responses to neoadjuvant chemotherapy for epithelial ovarian cancer should not be used as individual predictive markers to stratify patients who are likely to benefit from DPS, but instead used in conjunction with the patient's clinical capacity to undergo cytoreductive surgery. A patient should not be denied surgery based solely on the lack of a RECIST or GCIG CA125 response.

FUNDING

Cancer Research UK, UK Medical Research Council, Health Research Board in Ireland, Irish Cancer Society, and Cancer Australia.

The Era of Radiogenomics in Precision Medicine: An Emerging Approach to Support Diagnosis, Treatment Decisions, and Prognostication in Oncology

With the rapid development of new technologies, including artificial intelligence and genome sequencing, radiogenomics has emerged as a state-of-the-art science in the field of individualized medicine. Radiogenomics combines a large volume of quantitative data extracted from medical images with individual genomic phenotypes and constructs a prediction model through deep learning to stratify patients, guide therapeutic strategies, and evaluate clinical outcomes. Recent studies of various types of tumors demonstrate the predictive value of radiogenomics. And some of the issues in the radiogenomic analysis and the solutions from prior works are presented. Although the workflow criteria and international agreed guidelines for statistical methods need to be confirmed, radiogenomics represents a repeatable and cost-effective approach for the detection of continuous changes and is a promising surrogate for invasive interventions. Therefore, radiogenomics could facilitate computer-aided diagnosis, treatment, and prediction of the prognosis in patients with tumors in the routine clinical setting. Here, we summarize the integrated process of radiogenomics and introduce the crucial strategies and statistical algorithms involved in current studies.

CT texture analysis in histological classification of epithelial ovarian carcinoma

OBJECTIVES

The study aimed to compare the ability of morphological and texture features derived from contrast-enhanced CT in histological subtyping of epithelial ovarian carcinoma (EOC).

METHODS

Consecutive 205 patients with newly diagnosed EOC who underwent contrast-enhanced CT were included and dichotomised into high-grade serous carcinoma (HGSC) and non-HGSC. Clinical information including age and cancer antigen 125 (CA-125) was documented. The pre-treatment images were analysed using commercial software, TexRAD, by two independent radiologists. Eight qualitative CT morphological features were evaluated, and 36 CT texture features at 6 spatial scale factors (SSFs) were extracted per patient. Features' reduction was based on kappa score, intra-class correlation coefficient (ICC), univariate ROC analysis and Pearson's correlation test. Texture features with ICC ≥ 0.8 were compared by histological subtypes. Patients were randomly divided into training and testing sets by 8:2. Two random forest classifiers were determined and compared: model 1 incorporating selected morphological and clinical features and model 2 incorporating selected texture and clinical features.

RESULTS

HGSC showed specifically higher texture features than non-HGSC (p < 0.05). Both models performed highly in predicting histological subtypes of EOC (model 1: AUC 0.891 and model 2: AUC 0.937), and no statistical significance was found between the two models (p = 0.464).

CONCLUSION

CT texture analysis provides objective and quantitative metrics on tumour characteristics with HGSC demonstrating specifically high texture features. The model incorporating texture analysis could classify histology subtypes of EOC with high accuracy and performed as well as morphological features.

KEY POINTS

• A number of CT morphological and texture features showed good inter- and intra-observer agreements. • High-grade serous ovarian carcinoma showed specifically higher CT texture features than non-high-grade serous ovarian carcinoma. • CT texture analysis could differentiate histological subtypes of epithelial ovarian carcinoma with high accuracy.

Radiomic analysis of MRI to Predict Sustained Complete Response after Radiofrequency Ablation in Patients with Hepatocellular Carcinoma - A Pilot Study

OBJECTIVES

To investigate whether quantitative textural features, extracted from pretreatment MRI, can predict sustained complete response to radiofrequency ablation (RFA) in patients with hepatocellular carcinoma (HCC).

METHODS

In this IRB-approved study, patients were selected from a maintained six-year database of consecutive patients who underwent both pretreatment MRI imaging with a probable or definitive imaging diagnosis of HCC (LI-RADS 4 or 5) and loco-regional treatment with RFA. An experienced radiologist manually segmented the hepatic nodules in MRI arterial and equilibrium phases to obtain the volume of interest (VOI) for extraction of 107 quantitative textural features, including shape and first- and second-order features. Statistical analysis was performed to evaluate associations between textural features and complete response.

RESULTS

The study consisted of 34 patients with 51 treated hepatic nodules. Sustained complete response was achieved by 6 patients (4 with single nodule and 2 with multiple nodules). Of the 107 features from the arterial and equilibrium phases, 20 (18%) and 25 (23%) achieved AUC >0.7, respectively. The three best performing features were found in the equilibrium phase: Dependence Non-Uniformity Normalized and Dependence Variance (both GLDM class, with AUC of 0.78 and 0.76, respectively) and Maximum Probability (GLCM class, AUC of 0.76).

CONCLUSIONS

This pilot study demonstrates that a radiomic analysis of pre-treatment MRI might be useful in identifying patients with HCC who are most likely to have a sustained complete response to RFA. Second-order features (GLDM and GLCM) extracted from equilibrium phase obtained highest discriminatory performance.

Integrated Multi-Tumor Radio-Genomic Marker of Outcomes in Patients with High Serous Ovarian Carcinoma

Purpose: Develop an integrated intra-site and inter-site radiomics-clinical-genomic marker of high grade serous ovarian cancer (HGSOC) outcomes and explore the biological basis of radiomics with respect to molecular signaling pathways and the tumor microenvironment (TME). Method: Seventy-five stage III-IV HGSOC patients from internal (N = 40) and external factors via the Cancer Imaging Archive (TCGA) (N = 35) with pre-operative contrast enhanced CT, attempted primary cytoreduction, at least two disease sites, and molecular analysis performed within TCGA were retrospectively analyzed. An intra-site and inter-site radiomics (cluDiss) measure was combined with clinical-genomic variables (iRCG) and compared against conventional (volume and number of sites) and average radiomics (N = 75) for prognosticating progression-free survival (PFS) and platinum resistance. Correlation with molecular signaling and TME derived using a single sample gene set enrichment that was measured. Results: The iRCG model had the best platinum resistance classification accuracy (AUROC of 0.78 [95% CI 0.77 to 0.80]). CluDiss was associated with PFS (HR 1.03 [95% CI: 1.01 to 1.05], p = 0.002), negatively correlated with Wnt signaling, and positively to immune TME. Conclusions: CluDiss and the iRCG prognosticated HGSOC outcomes better than conventional and average radiomic measures and could better stratify patient outcomes if validated on larger multi-center trials.

Glycolytic phenotypes in an evaluation of ovarian carcinoma based on carcinogenesis and BRCA mutation

BACKGROUNDS

Recently, a dualistic carcinogenesis model of ovarian cancer has emerged. We aimed to investigate differences in the glycolytic phenotypes of type I and type II ovarian carcinoma on the basis of FDG uptake and in the pathological features according to tumour grade and histology.

MATERIALS AND METHODS

In total, 386 epithelial ovarian carcinoma patients underwent debulking surgery, and the histopathological results of the patients were retrospectively reviewed from 2003 to 2017. Among these patients, 170 patients had histopathological data that were available due to primary cytoreductive surgery and could be analysed regarding FDG avidity in type I and type II ovarian cancer. The FDG uptake of the tumour (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG) were analysed according to the tumour grade, histology and type of ovarian carcinogenesis (type I and II) and prognosis.

RESULTS

Among the 386 patients, there was a significant difference in SUVmax among ovarian cancer subtypes. There was a significant increase in SUVmax as the tumour grade increased (8.08 ± 0.63, 10.5 ± 0.40, and 12.7 ± 0.38 for grades I, II and III, respectively, Kruskal-Wallis test, p < 0.0001). Among the 90 type I and 80 type II ovarian carcinoma patients, there was a significant difference in SUVmax (type I and II, 9.47 ± 0.54 and 12.97 ± 0.70, respectively, Mann-Whitney test, p = 0.0003). However, no significant change in SUVmax was observed between BRCA-positive and BRCA-negative patients (N = 80, 13.8 ± 5.78 and 12.4 ± 6.30, Student's t-test, p = 0.3075). Among clinicopathologic and metabolic parameters, type of ovarian cancer, MTV and CA125 were significant factors in the prediction of recurrence.

CONCLUSIONS

The glycolytic phenotype was related to tumour grade and histological subtype, with significant differences between type I and II ovarian cancer. SUVmax of the ovarian cancer would be considered in the differentiation of type I and II ovarian cancer.

Progressive Desmoid Tumor: Radiomics Compared With Conventional Response Criteria for Predicting Progression During Systemic Therapy-A Multicenter Study by the French Sarcoma Group

OBJECTIVE. The response of desmoid tumors (DTs) to chemotherapy is evaluated with Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1) in daily practice and clinical trials. MRI shows early change in heterogeneity in responding tumors due to a decrease in cellular area and an increase in fibronecrotic content before dimensional response. Heterogeneity can be quantified with radiomics. Our aim was to develop radiomics-based response criteria and to compare their performances with clinical and radiologic response criteria. MATERIALS AND METHODS. Forty-two patients (median age, 38.2 years) were included in this retrospective multicenter study because they presented with progressive DT and had an MRI examination at baseline, which we refer to as "MRI-0," and an early MRI evaluation performed after the first chemotherapy cycle (mean time after first chemotherapy cycle, 3 months [SD, 28 days]), which we refer to as "MRI-1." After signal intensity normalization, voxel size standardization, discretization, and segmentation of DT volume on fat-suppressed contrast-enhanced T1-weighted imaging, 90 baseline and delta 3D radiomics features were extracted. Using cross-validation and least absolute shrinkage and selection operator-penalized Cox regression, a radiomics score was generated. The performances of models based on the radiomics score, modified Response Evaluation Criteria in Solid Tumors, European Association for the Study of the Liver criteria, Cheson criteria, Choi criteria, and revised Choi criteria from MRI-0 to MRI-1 to predict progression-free survival (PFS, as defined by RECIST 1.1) were assessed with the concordance index. The results were adjusted for performance status, tumor volume, prior chemotherapy, current chemotherapy, and β-catenin mutation. RESULTS. There were 10 cases of progression. The radiomics score included four variables. A high score indicated a poor prognosis. The radiomics score independently correlated with PFS (adjusted hazard ratio = 5.60, p = 0.003), and none of the usual response criteria independently correlated with PFS. The prognostic model based on the radiomics score had the highest concordance index (0.84; 95% CI, 0.71-0.96). CONCLUSION. Quantifying early changes in heterogeneity through a dedicated radiomics score could improve response evaluation for patients with DT undergoing chemotherapy.

Radiomics in Lung Cancer from Basic to Advanced: Current Status and Future Directions

Ideally, radiomics features and radiomics signatures can be used as imaging biomarkers for diagnosis, staging, prognosis, and prediction of tumor response. Thus, the number of published radiomics studies is increasing exponentially, leading to a myriad of new radiomics-based evidence for lung cancer. Consequently, it is challenging for radiologists to keep up with the development of radiomics features and their clinical applications. In this article, we review the basics to advanced radiomics in lung cancer to guide young researchers who are eager to start exploring radiomics investigations. In addition, we also include technical issues of radiomics, because knowledge of the technical aspects of radiomics supports a well-informed interpretation of the use of radiomics in lung cancer.

Integrative radiogenomics for virtual biopsy and treatment monitoring in ovarian cancer

BACKGROUND

Ovarian cancer survival rates have not changed in the last 20 years. The majority of cases are High-grade serous ovarian carcinomas (HGSOCs), which are typically diagnosed at an advanced stage with multiple metastatic lesions. Taking biopsies of all sites of disease is infeasible, which challenges the implementation of stratification tools based on molecular profiling.

MAIN BODY

In this review, we describe how these challenges might be overcome by integrating quantitative features extracted from medical imaging with the analysis of paired genomic profiles, a combined approach called radiogenomics, to generate virtual biopsies. Radiomic studies have been used to model different imaging phenotypes, and some radiomic signatures have been associated with paired molecular profiles to monitor spatiotemporal changes in the heterogeneity of tumours. We describe different strategies to integrate radiogenomic information in a global and local manner, the latter by targeted sampling of tumour habitats, defined as regions with distinct radiomic phenotypes.

CONCLUSION

Linking radiomics and biological correlates in a targeted manner could potentially improve the clinical management of ovarian cancer. Radiogenomic signatures could be used to monitor tumours during the course of therapy, offering additional information for clinical decision making. In summary, radiogenomics may pave the way to virtual biopsies and treatment monitoring tools for integrative tumour analysis.

Blood Supply of Early Lung Adenocarcinomas in Mice and the Tumor-supplying Vessel Relationship: A Micro-CT Angiography Study

This study aimed to investigate the blood supply of early lung adenocarcinomas in mice and the relationship between tumors and their supplying vessels by using micro-CT. An early lung adenocarcinoma model was established in 10 female mice with subcutaneous injections of a 1-methyl-3-nitro-1-nitrosoguanidine solution. Micro-CT pulmonary and bronchial arteriography were performed to demonstrate the blood supply of early lung adenocarcinomas, especially the tumor-vessel relationships, and the findings were correlated with the pathology results. The quantitative and texture changes in the tumor-supplying vessels were analyzed. Micro-CT showed that the pulmonary artery was densely distributed in and around tumors in 141 (84%) of 167 early lung adenocarcinomas, the bronchial artery was not related to tumors, and there were four patterns of tumor-pulmonary artery relationships that correlated well with pathologic findings. Quantitative and texture analyses showed that the tumor size had positive correlations with vessel volume (VV), VV fraction (VVF), vessel thickness (VT), vessel number (VN), inverse difference moment, long run emphasis, gray level nonuniformity (GLN), and run length nonuniformity (RLN) and negative correlations with vessel separation (VS), inertia, and short run emphasis (SRE); the size of the solid component had positive correlations with VV, VVF, VT, VN, GLN, and RLN and negative correlations with VS, cluster shade, and SRE. This study concluded that early lung adenocarcinomas are mainly supplied by the pulmonary arteries in mice, and micro-CT angiography can clearly demonstrate the morphologic changes of pulmonary arteries and their relationships with tumors.

Integration of proteomics with CT-based qualitative and radiomic features in high-grade serous ovarian cancer patients: an exploratory analysis

OBJECTIVES

To investigate the association between CT imaging traits and texture metrics with proteomic data in patients with high-grade serous ovarian cancer (HGSOC).

METHODS

This retrospective, hypothesis-generating study included 20 patients with HGSOC prior to primary cytoreductive surgery. Two readers independently assessed the contrast-enhanced computed tomography (CT) images and extracted 33 imaging traits, with a third reader adjudicating in the event of a disagreement. In addition, all sites of suspected HGSOC were manually segmented texture features which were computed from each tumor site. Three texture features that represented intra- and inter-site tumor heterogeneity were used for analysis. An integrated analysis of transcriptomic and proteomic data identified proteins with conserved expression between primary tumor sites and metastasis. Correlations between protein abundance and various CT imaging traits and texture features were assessed using the Kendall tau rank correlation coefficient and the Mann-Whitney U test, whereas the area under the receiver operating characteristic curve (AUC) was reported as a metric of the strength and the direction of the association. P values < 0.05 were considered significant.

RESULTS

Four proteins were associated with CT-based imaging traits, with the strongest correlation observed between the CRIP2 protein and disease in the mesentery (p < 0.001, AUC = 0.05). The abundance of three proteins was associated with texture features that represented intra-and inter-site tumor heterogeneity, with the strongest negative correlation between the CKB protein and cluster dissimilarity (p = 0.047, τ = 0.326).

CONCLUSION

This study provides the first insights into the potential associations between standard-of-care CT imaging traits and texture measures of intra- and inter-site heterogeneity, and the abundance of several proteins.

KEY POINTS

• CT-based texture features of intra- and inter-site tumor heterogeneity correlate with the abundance of several proteins in patients with HGSOC. • CT imaging traits correlate with protein abundance in patients with HGSOC.

Radiomics predict postoperative survival of patients with primary liver cancer with different pathological types

Background

Radiomics can be used to determine the prognosis of liver cancer, but it might vary among cancer types. This study aimed to explore the clinicopathological features, radiomics, and survival of patients with hepatocellular carcinoma (HCC), mass-type cholangiocarcinoma (MCC), and combined hepatocellular-cholangiocarcinoma (CHCC).

Methods

This was a retrospective cohort study of patients with primary liver cancer operated at the department of hepatobiliary surgery of the First Affiliated Hospital of Zhejiang University from 07/2013 to 11/2015. All patients underwent preoperative liver enhanced MRI scans and diffusion-weighted imaging (DWI). The radiomics characteristics of DWI and the enhanced equilibrium phase (EP) images were extracted. The mRMR (minimum redundancy maximum relevance) was applied to filter the parameters.

Results

There were 44 patients with MCC, 59 with HCC, and 33 with CHCC. Macrovascular invasion, tumor diameter, positive ferritin preoperatively, positive AFP preoperatively, positive CEA preoperatively, Correlation, Inverse Difference Moment, and Cluster Prominence in model A (DWI and clinicopathological parameters) were independently associated with overall survival (OS) (P<0.05). Lymphadenopathy, gender, positive ferritin preoperatively, positive AFP preoperatively, positive CEA preoperatively, Uniformity, and Cluster Prominence in model B (EP and clinicopathological parameters) were independently associated with OS (P<0.05). Macrovascular invasion, lymphadenopathy, gender, positive ferritin preoperatively, positive CEA preoperatively, Uniformity_EP, GLCMEnergy_DWI, and Cluster Prominence_EP in model C (image texture and clinicopathological parameters) were independently associated with OS (P<0.05). Those factors were used to construct three nomograms to predict OS.

Conclusions

Clinicopathological and radiomics features are independently associated with the OS of patients with primary liver cancer.

Tissue-specific and interpretable sub-segmentation of whole tumour burden on CT images by unsupervised fuzzy clustering

BACKGROUND

Cancer typically exhibits genotypic and phenotypic heterogeneity, which can have prognostic significance and influence therapy response. Computed Tomography (CT)-based radiomic approaches calculate quantitative features of tumour heterogeneity at a mesoscopic level, regardless of macroscopic areas of hypo-dense (i.e., cystic/necrotic), hyper-dense (i.e., calcified), or intermediately dense (i.e., soft tissue) portions.

METHOD

With the goal of achieving the automated sub-segmentation of these three tissue types, we present here a two-stage computational framework based on unsupervised Fuzzy C-Means Clustering (FCM) techniques. No existing approach has specifically addressed this task so far. Our tissue-specific image sub-segmentation was tested on ovarian cancer (pelvic/ovarian and omental disease) and renal cell carcinoma CT datasets using both overlap-based and distance-based metrics for evaluation.

RESULTS

On all tested sub-segmentation tasks, our two-stage segmentation approach outperformed conventional segmentation techniques: fixed multi-thresholding, the Otsu method, and automatic cluster number selection heuristics for the K-means clustering algorithm. In addition, experiments showed that the integration of the spatial information into the FCM algorithm generally achieves more accurate segmentation results, whilst the kernelised FCM versions are not beneficial. The best spatial FCM configuration achieved average Dice similarity coefficient values starting from 81.94±4.76 and 83.43±3.81 for hyper-dense and hypo-dense components, respectively, for the investigated sub-segmentation tasks.

CONCLUSIONS

The proposed intelligent framework could be readily integrated into clinical research environments and provides robust tools for future radiomic biomarker validation.

Combining molecular and imaging metrics in cancer: radiogenomics

Background

Radiogenomics is the extension of radiomics through the combination of genetic and radiomic data. Because genetic testing remains expensive, invasive, and time-consuming, and thus unavailable for all patients, radiogenomics may play an important role in providing accurate imaging surrogates which are correlated with genetic expression, thereby serving as a substitute for genetic testing.

Main body

In this article, we define the meaning of radiogenomics and the difference between radiomics and radiogenomics. We provide an up-to-date review of the radiomics and radiogenomics literature in oncology, focusing on breast, brain, gynecological, liver, kidney, prostate and lung malignancies. We also discuss the current challenges to radiogenomics analysis.

Conclusion

Radiomics and radiogenomics are promising to increase precision in diagnosis, assessment of prognosis, and prediction of treatment response, providing valuable information for patient care throughout the course of the disease, given that this information is easily obtainable with imaging. Larger prospective studies and standardization will be needed to define relevant imaging biomarkers before they can be implemented into the clinical workflow.

MRI-based radiomics of rectal cancer: preoperative assessment of the pathological features

Background

This study aimed to evaluate the significance of MRI-based radiomics model derived from high-resolution T2-weighted images (T2WIs) in predicting tumor pathological features of rectal cancer.

Methods

A total of 152 patients with rectal cancer who underwent surgery without any neoadjuvant therapy between March 2017 and September 2018 were included retrospectively. The patients were scanned using a 3-T magnetic resonance imaging, and high-resolution T2WIs were obtained. Lesions were delineated, and 1029 radiomics features were extracted. Least absolute shrinkage and selection operator was used to select features, and multilayer perceptron (MLP), logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and K-nearest neighbor (KNN) were trained using fivefold cross-validation to build a prediction model. The diagnostic performance of the prediction models was assessed using the receiver operating characteristic curves.

Results

A total of 1029 features were extracted, and 15, 11, and 11 features were selected to predict the degree of differentiation, T stage, and N stage, respectively. The best performance of the radiomics model for the degree of differentiation, T stage, and N stage was obtained by SVM [area under the curve (AUC), 0.862; 95% confidence interval (CI), 0.750–0.967; sensitivity, 83.3%; specificity, 85.0%], MLP (AUC, 0.809; 95% CI, 0.690–0.905; sensitivity, 76.2%; specificity, 74.1%), and RF (AUC, 0.746; 95% CI, 0.622-0.872; sensitivity, 79.3%; specificity, 72.2%).

Conclusion

This study demonstrated that the high-resolution T2WI–based radiomics model could serve as pretreatment biomarkers in predicting pathological features of rectal cancer.

Computed Tomography-Derived Radiomic Metrics Can Identify Responders to Immunotherapy in Ovarian Cancer

PURPOSE

To determine if radiomic measures of tumor heterogeneity derived from baseline contrast-enhanced computed tomography (CE-CT) are associated with durable clinical benefit and time to off-treatment in patients with recurrent ovarian cancer (OC) enrolled in prospective immunotherapeutic trials.

MATERIALS AND METHODS

This retrospective study included 75 patients with recurrent OC who were enrolled in prospective immunotherapeutic trials (n = 74) or treated off-label (n = 1) and had baseline CE-CT scans. Disease burden (total tumor volume, number of disease sites), radiomic measures of intertumor heterogeneity (cluster-site entropy, cluster-site dissimilarity), and intratumor heterogeneity of the largest lesion (Haralick texture features) were computed. Associations of clinical, conventional imaging, and radiomic measures with durable clinical benefit and time to off-treatment were examined.

RESULTS

In univariable analysis, fewer disease sites, lower intertumor heterogeneity (lower cluster-site entropy, lower cluster-site dissimilarity), and lower intratumor heterogeneity of the largest lesion (higher energy) were significantly associated with durable clinical benefit (P ≤ .031). More disease sites, presence of pleural disease and/or distant metastases, higher intertumor heterogeneity (higher cluster-site entropy, higher cluster-site dissimilarity), and higher intratumor heterogeneity of the largest lesion (higher Contrast_{largest-lesion}) were significantly associated with shorter time to off-treatment (P ≤ .034). In multivariable analysis, higher Energy_{largest-lesion} (indicator of lower intratumor heterogeneity; P = .006; odds ratio, 1.41) and fewer disease sites (P = .003; odds ratio, 1.64) remained significant indicators of durable clinical benefit (multivariable model C-index, 0.821). Higher cluster-site dissimilarity (indicator of higher intertumor heterogeneity) was a modest but single independent indicator of shorter time to off-treatment (P = .004; hazard ratio, 1.19; C-index, 0.6).

CONCLUSION

Fewer disease sites and lower intra- and intertumor heterogeneity modeled from the baseline CE-CT may indicate better response of OC to immunotherapy.

Radiomics: an Introductory Guide to What It May Foretell

PURPOSE OF REVIEW

To briefly review the radiomics concept, its applications, and challenges in oncology in the era of precision medicine.

RECENT FINDINGS

Over the last 5 years, more than 500 studies have evaluated the role of radiomics to predict tumor diagnosis, genetic pattern, tumor response to therapy, and survival in multiple cancers. This new post-processing method is aimed at extracting multiple quantitative features from the image and converting them into mineable data. Radiomics models developed have shown promising results and may play a role in the near future in the daily patient management especially to assess tumor heterogeneity acting as a whole tumor virtual biopsy. For now, radiomics is limited by its lack of standardization; future challenges will be to provide robust and reproducible metrics extracted from large multicenter databases.

Why imaging data alone is not enough: AI-based integration of imaging, omics, and clinical data

Artificial intelligence (AI) is currently regaining enormous interest due to the success of machine learning (ML), and in particular deep learning (DL). Image analysis, and thus radiomics, strongly benefits from this research. However, effectively and efficiently integrating diverse clinical, imaging, and molecular profile data is necessary to understand complex diseases, and to achieve accurate diagnosis in order to provide the best possible treatment. In addition to the need for sufficient computing resources, suitable algorithms, models, and data infrastructure, three important aspects are often neglected: (1) the need for multiple independent, sufficiently large and, above all, high-quality data sets; (2) the need for domain knowledge and ontologies; and (3) the requirement for multiple networks that provide relevant relationships among biological entities. While one will always get results out of high-dimensional data, all three aspects are essential to provide robust training and validation of ML models, to provide explainable hypotheses and results, and to achieve the necessary trust in AI and confidence for clinical applications.

Association between CT-texture-derived tumor heterogeneity, outcomes, and BRCA mutation status in patients with high-grade serous ovarian cancer

PURPOSE

To assess the associations between inter-site texture heterogeneity parameters derived from computed tomography (CT), survival, and BRCA mutation status in women with high-grade serous ovarian cancer (HGSOC).

MATERIALS AND METHODS

Retrospective study of 88 HGSOC patients undergoing CT and BRCA mutation status testing prior to primary cytoreductive surgery. Associations between texture metrics-namely inter-site cluster variance (SCV), inter-site cluster prominence (SCP), inter-site cluster entropy (SE)-and overall survival (OS), progression-free survival (PFS) as well as BRCA mutation status were assessed.

RESULTS

Higher inter-site cluster variance (SCV) was associated with lower PFS (p = 0.006) and OS (p = 0.003). Higher inter-site cluster prominence (SCP) was associated with lower PFS (p = 0.02) and higher inter-site cluster entropy (SE) correlated with lower OS (p = 0.01). Higher values of all three metrics were significantly associated with lower complete surgical resection status in BRCA-negative patients (SE p = 0.039, SCV p = 0.006, SCP p = 0.02), but not in BRCA-positive patients (SE p = 0.7, SCV p = 0.91, SCP p = 0.67). None of the metrics were able to distinguish between BRCA mutation carrier and non-mutation carrier.

CONCLUSION

The assessment of tumoral heterogeneity in the era of personalized medicine is important, as increased heterogeneity has been associated with distinct genomic abnormalities and worse patient outcomes. A radiomics approach using standard-of-care CT scans might have a clinical impact by offering a non-invasive tool to predict outcome and therefore improving treatment effectiveness. However, it was not able to assess BRCA mutation status in women with HGSOC.

Computational Approaches in Theranostics: Mining and Predicting Cancer Data

The ability to understand the complexity of cancer-related data has been prompted by the applications of (1) computer and data sciences, including data mining, predictive analytics, machine learning, and artificial intelligence, and (2) advances in imaging technology and probe development. Computational modelling and simulation are systematic and cost-effective tools able to identify important temporal/spatial patterns (and relationships), characterize distinct molecular features of cancer states, and address other relevant aspects, including tumor detection and heterogeneity, progression and metastasis, and drug resistance. These approaches have provided invaluable insights for improving the experimental design of therapeutic delivery systems and for increasing the translational value of the results obtained from early and preclinical studies. The big question is: Could cancer theranostics be determined and controlled in silico? This review describes the recent progress in the development of computational models and methods used to facilitate research on the molecular basis of cancer and on the respective diagnosis and optimized treatment, with particular emphasis on the design and optimization of theranostic systems. The current role of computational approaches is providing innovative, incremental, and complementary data-driven solutions for the prediction, simplification, and characterization of cancer and intrinsic mechanisms, and to promote new data-intensive, accurate diagnostics and therapeutics.

Radiomics of high-grade serous ovarian cancer: association between quantitative CT features, residual tumour and disease progression within 12 months

OBJECTIVES

To determine if radiomic features, alone or combined with clinical data, are associated with residual tumour (RT) at surgery, and predict the risk of disease progression within 12 months (PD12) in ovarian cancer (OC) patients.

METHODS

This retrospective study enrolled 101 patients according to the following inclusion parameters: cytoreductive surgery performed at our institution (9 May 2007-23 February 2016), assessment of BRCA mutational status, preoperative CT available. Radiomic features of the ovarian masses were extracted from 3D structures drawn on CT images. A phantom experiment was performed to assess the reproducibility of radiomic features. The final radiomic features included in the analysis (n = 516) were grouped into clusters using a hierarchical clustering procedure. The association of each cluster's representative radiomic feature with RT and PD12 was assessed by chi-square test. Multivariate analysis was performed using logistic regression models. P values < 0.05 were considered significant.

RESULTS

Patients with values of F2-Shape/Compactness1 below the median, of F1- GrayLevelCooccurenceMatrix25/0-1InformationMeasureCorr2 below the median and of F1-GrayLevelCooccurenceMatrix25/-333-1InverseVariance above the median showed higher risk of RT (36%, 36% and 35%, respectively, as opposed to 18%, 18% and 18%). Patients with values of F4-GrayLevelRunLengthMatrix25/-333RunPercentage above the median, of F2 shape/Max3DDiameter below the median and F1-GrayLevelCooccurenceMatrix25/45-1InverseVariance above the median showed higher risk of PD12 (22%, 24% and 23%, respectively, as opposed to 6%, 5% and 6%). At multivariate analysis F2-Shape/Max3DDiameter remained significant (odds ratio (95% CI) = 11.86 (1.41-99.88)). To predict PD12, a clinical radiomics model performed better than a base clinical model.

CONCLUSION

This study demonstrated significant associations between radiomic features and prognostic factors such as RT and PD12.

KEY POINTS

• No residual tumour (RT) at surgery is the most important prognostic factor in OC. • Radiomic features related to mass size, randomness and homogeneity were associated with RT. • Progression of disease within 12 months (PD12) indicates worse prognosis in OC. • A model including clinical and radiomic features performed better than only-clinical model to predict PD12.

MR Imaging of Rectal Cancer: Radiomics Analysis to Assess Treatment Response after Neoadjuvant Therapy

Purpose To investigate the value of T2-weighted-based radiomics compared with qualitative assessment at T2-weighted imaging and diffusion-weighted (DW) imaging for diagnosis of clinical complete response in patients with rectal cancer after neoadjuvant chemotherapy-radiation therapy (CRT). Materials and Methods This retrospective study included 114 patients with rectal cancer who underwent magnetic resonance (MR) imaging after CRT between March 2012 and February 2016. Median age among women (47 of 114, 41%) was 55.9 years (interquartile range, 45.4-66.7 years) and median age among men (67 of 114, 59%) was 55 years (interquartile range, 48-67 years). Surgical histopathologic analysis was the reference standard for pathologic complete response (pCR). For qualitative assessment, two radiologists reached a consensus. For radiomics, one radiologist segmented the volume of interest on high-spatial-resolution T2-weighted images. A random forest classifier was trained to separate the patients by their outcomes after balancing the number of patients in each response category by using the synthetic minority oversampling technique. Statistical analysis was performed by using the Wilcoxon rank-sum test, McNemar test, and Benjamini-Hochberg method. Results Twenty-one of 114 patients (18%) achieved pCR. The radiomic classifier demonstrated an area under the curve of 0.93 (95% confidence interval [CI]: 0.87, 0.96), sensitivity of 100% (95% CI: 0.84, 1), specificity of 91% (95% CI: 0.84, 0.96), positive predictive value of 72% (95% CI: 0.53, 0.87), and negative predictive value of 100% (95% CI: 0.96, 1). The diagnostic performance of radiomics was significantly higher than was qualitative assessment at T2-weighted imaging or DW imaging alone (P < .02). The specificity and positive predictive values were significantly higher in radiomics than were at combined T2-weighted and DW imaging (P < .0001). Conclusion T2-weighted-based radiomics showed better classification performance compared with qualitative assessment at T2-weighted and DW imaging for diagnosing pCR in patients with locally advanced rectal cancer after CRT. ^© RSNA, 2018 Online supplemental material is available for this article.

Translational Radiomics: Defining the Strategy Pipeline and Considerations for Application-Part 1: From Methodology to Clinical Implementation

Enterprise imaging has channeled various technological innovations to the field of clinical radiology, ranging from advanced imaging equipment and postacquisition iterative reconstruction tools to image analysis and computer-aided detection tools. More recently, the advancements in the field of quantitative image analysis coupled with machine learning-based data analytics, classification, and integration have ushered us into the era of radiomics, which has tremendous potential in clinical decision support as well as drug discovery. There are important issues to consider to incorporate radiomics as a clinically applicable system and a commercially viable solution. In this two-part series, we offer insights into the development of the translational pipeline for radiomics from methodology to clinical implementation (Part 1) and from that to enterprise development (Part 2).

Emerging Molecular Imaging Techniques in Gynecologic Oncology

Molecular imaging (mainly PET and MR imaging) has played important roles in gynecologic oncology. Emerging MR-based technologies, including DWI, CEST, DCE-MR imaging, MRS, and DNP, as well as FDG-PET and many novel PET radiotracers, will continuously improve practices. In combination with radiomics analysis, a new era of decision making in personalized medicine and precisely guided radiation treatment planning or real-time surgical interventions is being entered into, which will directly impact on patient survival. Prospective trials with well-defined endpoints are encouraged to evaluate the multiple facets of these emerging imaging tools in the management of gynecologic malignancies.

Background, current role, and potential applications of radiogenomics

With the genomic revolution in the early 1990s, medical research has been driven to study the basis of human disease on a genomic level and to devise precise cancer therapies tailored to the specific genetic makeup of a tumor. To match novel therapeutic concepts conceived in the era of precision medicine, diagnostic tests must be equally sufficient, multilayered, and complex to identify the relevant genetic alterations that render cancers susceptible to treatment. With significant advances in training and medical imaging techniques, image analysis and the development of high-throughput methods to extract and correlate multiple imaging parameters with genomic data, a new direction in medical research has emerged. This novel approach has been termed radiogenomics. Radiogenomics aims to correlate imaging characteristics (ie, the imaging phenotype) with gene expression patterns, gene mutations, and other genome-related characteristics and is designed to facilitate a deeper understanding of tumor biology and capture the intrinsic tumor heterogeneity. Ultimately, the goal of radiogenomics is to develop imaging biomarkers for outcome that incorporate both phenotypic and genotypic metrics. Due to the noninvasive nature of medical imaging and its ubiquitous use in clinical practice, the field of radiogenomics is rapidly evolving and initial results are encouraging. In this article, we briefly discuss the background and then summarize the current role and the potential of radiogenomics in brain, liver, prostate, gynecological, and breast tumors.

LEVEL OF EVIDENCE

5 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;47:604-620.

Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma

We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice.