Prognostic value of radiomic analysis of iodine overlay maps from dual-energy computed tomography in patients with resectable lung cancer

Multiparameter spectral CT-based radiomics in predicting the expression of programmed death ligand 1 in non-small-cell lung cancer

AIM

To explore the value of radiomics for predicting the expression of programmed death ligand 1 (PD-L1) in non-small-cell lung cancer (NSCLC) based on multiparameter spectral computed tomography (CT) images.

MATERIALS AND METHODS

A total of 220 patients with NSCLC were enrolled retrospectively and divided into the training (n=176) and testing (n=44) cohorts. The radiomics features were extracted from the conventional CT images, mono-energy 40 keV images, iodine density (ID) maps, Z-effective maps, and electron density maps. The logistic regression (LR) and support vector machine (SVM) algorithms were employed to build models based on radiomics signatures. The prediction abilities were qualified by the area under the curve (AUC) obtained from the receiver operating characteristic (ROC) curve. Internal validation was performed on the independent testing dataset.

RESULTS

The combined model for PD-L1 ≥1%, which consisted of the radiomics score (rad-score; p<0.0001), white blood cell (WBC; p=0.027) counts, and air bronchogram (p=0.003), reached the highest performance with the AUCs of 0.873 and 0.917 in the training and testing dataset, respectively, which was better than the radiomics model with the AUCs of 0.842 and 0.886. The combined model for PD-L1 ≥50%, which consisted of rad-score (p<0.0001) and WBC counts (p=0.027), achieved the highest performance in the training and testing dataset with AUCs of 0.932 and 0.903, respectively, which was better than the radiomics model with AUCs of 0.920 and 0.892, respectively.

CONCLUSION

The radiomics model based on the multiparameter images of spectral CT can predict the expression level of PD-L1 in NSCLC. The combined model can obtain higher prediction efficiency and serves as a promising method for immunotherapy selection.

Differentiating gastric schwannoma from gastric stromal tumor (≤5 cm) by histogram analysis based on iodine-based material decomposition images: a preliminary study

Objective

This study aims to investigate the value of histogram analysis based on iodine-based material decomposition (IMD) images obtained through dual-energy computed tomography (DECT) to differentiate gastric schwannoma (GS) from gastric stromal tumor (GST) (≤5 cm) preoperatively.

Methods

From January 2015 to January 2023, 15 patients with GS and 30 patients with GST (≤5 cm) who underwent biphasic contrast-enhanced scans using DECT were enrolled in this study. For each tumor, we reconstructed IMD images at the arterial phase (AP) and venous phase (VP). Nine histogram parameters were automatically extracted and selected using MaZda software based on the IMD of AP and VP, respectively, including mean, 1st, 10th, 50th, 90th, and 99th percentile of the iodine concentration value (Perc.01, Perc.10, Perc.50, Perc.90, and Perc.99), variance, skewness, and kurtosis. The extracted IMD histogram parameters were compared using the Mann-Whitney U-test. The optimal IMD histogram parameters were selected using receiver operating characteristic (ROC) curves.

Results

Among the IMD histogram parameters of AP, the mean, Perc.50, Perc.90, Perc.99, variance, and skewness of the GS group were lower than that of the GST group (all P < 0.05). Among the IMD histogram parameters of VP, Perc.90, Perc.99, and the variance of the GS group was lower than those of the GST group (all P < 0.05). The ROC analysis showed that Perc.99 (AP) generated the best diagnostic performance with the area under the curve, sensitivity, and specificity being 0.960, 86.67%, and 93.33%, respectively, when using 71.00 as the optimal threshold.

Conclusion

Histogram analysis based on IMD images obtained through DECT holds promise as a valuable tool for the preoperative distinction between GS and GST (≤5 cm).

Avoid non-diagnostic EUS-FNA: a DNN model as a possible gatekeeper to distinguish pancreatic lesions prone to inconclusive biopsy

OBJECTIVE

This work aimed to explore the utility of CT radiomics with machine learning for distinguishing the pancreatic lesions prone to non-diagnostic ultrasound-guided fine-needle aspiration (EUS-FNA).

METHODS

498 patients with pancreatic EUS-FNA were retrospectively reviewed [Development cohort: 147 pancreatic ductal adenocarcinoma (PDAC); Validation cohort: 37 PDAC]. Pancreatic lesions not PDAC were also tested exploratively. Radiomics extracted from contrast-enhanced CT was integrated with deep neural networks (DNN) after dimension reduction. The receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) were performed for model evaluation. And, the explainability of the DNN model was analyzed by integrated gradients.

RESULTS

The DNN model was effective in distinguishing PDAC lesions prone to non-diagnostic EUS-FNA (Development cohort: AUC = 0.821, 95% CI: 0.742-0.900; Validation cohort: AUC = 0.745, 95% CI: 0.534-0.956). In all cohorts, the DNN model showed better utility than the logistic model based on traditional lesion characteristics with NRI >0 (p < 0.05). And, the DNN model had net benefits of 21.6% at the risk threshold of 0.60 in the validation cohort. As for the model explainability, gray-level co-occurrence matrix (GLCM) features contributed the most averagely and the first-order features were the most important in the sum attribution.

CONCLUSION

The CT radiomics-based DNN model can be a useful auxiliary tool for distinguishing the pancreatic lesions prone to nondiagnostic EUS-FNA and provide alerts for endoscopists preoperatively to reduce unnecessary EUS-FNA.

ADVANCES IN KNOWLEDGE

This is the first investigation into the utility of CT radiomics-based machine learning in avoiding non-diagnostic EUS-FNA for patients with pancreatic masses and providing potential pre-operative assistance for endoscopists.

Thoracic Diseases: Technique and Applications of Dual-Energy CT

Dual-energy computed tomography (DECT) is one of the most promising technological innovations made in the field of imaging in recent years. Thanks to its ability to provide quantitative and reproducible data, and to improve radiologists' confidence, especially in the less experienced, its applications are increasing in number and variety. In thoracic diseases, DECT is able to provide well-known benefits, although many recent articles have sought to investigate new perspectives. This narrative review aims to provide the reader with an overview of the applications and advantages of DECT in thoracic diseases, focusing on the most recent innovations. The research process was conducted on the databases of Pubmed and Cochrane. The article is organized according to the anatomical district: the review will focus on pleural, lung parenchymal, breast, mediastinal, lymph nodes, vascular and skeletal applications of DECT. In conclusion, considering the new potential applications and the evidence reported in the latest papers, DECT is progressively entering the daily practice of radiologists, and by reading this simple narrative review, every radiologist will know the state of the art of DECT in thoracic diseases.

Virtual biopsy using CT radiomics for evaluation of disagreement in pathology between endoscopic biopsy and postoperative specimens in patients with gastric cancer: a dual-energy CT generalizability study

PURPOSE

To develop a noninvasive radiomics-based nomogram for identification of disagreement in pathology between endoscopic biopsy and postoperative specimens in gastric cancer (GC).

MATERIALS AND METHODS

This observational study recruited 181 GC patients who underwent pre-treatment computed tomography (CT) and divided them into a training set (n = 112, single-energy CT, SECT), a test set (n = 29, single-energy CT, SECT) and a validation cohort (n = 40, dual-energy CT, DECT). Radiomics signatures (RS) based on five machine learning algorithms were constructed from the venous-phase CT images. AUC and DeLong test were used to evaluate and compare the performance of the RS. We assessed the dual-energy generalization ability of the best RS. An individualized nomogram combined the best RS and clinical variables was developed, and its discrimination, calibration, and clinical usefulness were determined.

RESULTS

RS obtained with support vector machine (SVM) showed promising predictive capability with AUC of 0.91 and 0.83 in the training and test sets, respectively. The AUC of the best RS in the DECT validation cohort (AUC, 0.71) was significantly lower than that of the training set (Delong test, p = 0.035). The clinical-radiomic nomogram accurately predicted pathologic disagreement in the training and test sets, fitting well in the calibration curves. Decision curve analysis confirmed the clinical usefulness of the nomogram.

CONCLUSION

CT-based radiomics nomogram showed potential as a clinical aid for predicting pathologic disagreement status between biopsy samples and resected specimens in GC. When practicability and stability are considered, the SECT-based radiomics model is not recommended for DECT generalization.

CRITICAL RELEVANCE STATEMENT

Radiomics can identify disagreement in pathology between endoscopic biopsy and postoperative specimen.

Patterns of Postoperative Changes in Lung Volume and Perfusion Assessed by Dual-Energy CT: Comparison of Lobectomy and Limited Resection

BACKGROUND. Pulmonary function tests (PFTs) and perfusion scintigraphy have limited utility for evaluating postoperative changes in regional pulmonary function after lung cancer resection surgery. OBJECTIVE. The purpose of this study is to compare postoperative changes in lung volume and perfusion, as assessed by dual-energy CT (DECT), between patients undergoing surgical resection of lung cancer by lobectomy versus limited resection as well as to assess associations between such changes and the lobar location of the resected tumor. METHODS. This study entailed a retrospective post hoc analysis of a prospective study that enrolled patients awaiting lung cancer resection surgery between March 2019 and February 2020. Eighty-one patients (38 men and 43 women; mean age, 60.5 ± 8.9 [SD] years), 43 of whom underwent lobectomy and 38 of whom underwent limited resection, were included. Patients underwent thoracic DECT and PFT evaluation preoperatively and at 6 months postoperatively. Pulmonary lobes were segmented. Lobar lung volume and lung perfusion ratios (both relative to whole-lung values) were computed. Perfusion measures reflected DECT-derived iodine content. Patients completed 6-month postoperative quality-of-life (QOL) questionnaires. RESULTS. Patients undergoing lobectomy, compared with those undergoing limited resection, had greater increases in the lung volume ratio of the ipsilateral nonresected lobe(s) (mean, 42.3% ± 24.2% [SD] vs 22.9% ± 13.2%, p < .001) and the contralateral lung (mean, 14.6% ± 14.0% vs 6.4% ± 6.9%, p = .002) as well as greater increases in the lung perfusion ratio of the ipsilateral nonresected lobe(s) (mean, 39.9% ± 20.7% [SD] vs 22.8% ± 17.8%, p < .001) and the contralateral lung (mean, 20.9% ± 9.4% vs 4.3% ± 5.6%, p < .001). In patients with right lower lobe tumors, the largest postoperative increases in the lung volume ratio were in the right middle lobe in those undergoing lobectomy (mean, 44.1% ± 21.0%) and limited resection (mean, 24.6% ± 14.5%), whereas the largest postoperative increase in the lung perfusion ratio was in the left lower lobe in those undergoing lobectomy (mean, 53.9% ± 8.6%) and in the right middle lobe in those undergoing limited resection (mean, 32.5% ± 24.1%). Otherwise, the largest increases in lung volume and perfusion ratios occurred in the ipsilateral nonresected lobes (vs the contra-lateral lobes), regardless of the operative approach used and the lobar location. Changes in the lung volume and perfusion ratios in the ipsilateral lobe(s) and the contralateral lung showed weak correlations with certain quality-of-life scores (e.g., for role functioning: ρ = 0.234-0.279 [volume] and -0.233 to -0.284 [perfusion]). CONCLUSION. DECT depicts patterns of lung volume and perfusion changes after lung cancer surgery, depending on the surgical approach (lobectomy vs limited resection) used and the lobar location of the tumor. CLINICAL IMPACT. DECT-derived metrics can help understand variable physiologic impacts of lung cancer resection surgeries.

Iodine map histogram metrics in early-stage breast cancer: prediction of axillary lymph node metastasis status

BACKGROUND

Variations in axillary lymph node (ALN) metastatic potential between different breast cancers lead to microscopical alterations in tumor perfusion heterogeneity. This study investigated the usefulness of histogram metrics from iodine maps in the preoperative diagnosis of metastatic ALNs in patients with early-stage breast cancer.

METHODS

Between October 2020 and November 2021 enhanced spectral computed tomography (CT) was performed in female patients with breast cancer. Quantitative spectral CT parameters and histogram parameters (mean, median, maximum, minimum, 10th percentiles, 90th percentiles, kurtosis, skewness, energy, range, and variance) from iodine maps were compared between patients with metastatic and nonmetastatic ALNs. Continuous variables were compared using Student's t-test or Mann-Whitney U test. Categorical variables were compared using Pearson's chi-square tests or Fisher's exact tests. Associations between ALN status and imaging features were evaluated using Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis.

RESULTS

This study included 113 female patients (62 and 51 in the ALN-negative and ALN-positive groups, respectively). Tumor size, molecular subtypes, and location differed significantly between the ALN-negative and ALN-positive groups (P<0.05). None of the quantitative spectral CT parameters of mass between metastatic and nonmetastatic ALN groups were significantly different (P>0.05). Histogram parameters of iodine maps for breast cancers, including maximum, 10th percentile, range, and energy, were significantly higher in the metastatic ALNs group compared with the nonmetastatic ALNs group (P<0.05). Multivariable logistic regression analyses showed that tumor location and energy were independent predictors of metastatic ALNs in breast cancers. The combination of independent predictors yielded an area under the curve (AUC) of 0.824 (sensitivity 72.5%; specificity 74.2%).

CONCLUSIONS

Whole-lesion histogram parameters derived from spectral CT iodine maps may be used as a complementary noninvasive means for the preoperative identification of ALN metastases in patients with early-stage breast cancer.

Radiomic and Volumetric Measurements as Clinical Trial Endpoints—A Comprehensive Review

Simple Summary

The extraction of quantitative data from standard-of-care imaging modalities offers opportunities to improve the relevance and salience of imaging biomarkers used in drug development. This review aims to identify the challenges and opportunities for discovering new imaging-based biomarkers based on radiomic and volumetric assessment in the single-site solid tumor sites: breast cancer, rectal cancer, lung cancer and glioblastoma. Developing approaches to harmonize three essential areas: segmentation, validation and data sharing may expedite regulatory approval and adoption of novel cancer imaging biomarkers.

Abstract

Clinical trials for oncology drug development have long relied on surrogate outcome biomarkers that assess changes in tumor burden to accelerate drug registration (i.e., Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST v1.1) criteria). Drug-induced reduction in tumor size represents an imperfect surrogate marker for drug activity and yet a radiologically determined objective response rate is a widely used endpoint for Phase 2 trials. With the addition of therapies targeting complex biological systems such as immune system and DNA damage repair pathways, incorporation of integrative response and outcome biomarkers may add more predictive value. We performed a review of the relevant literature in four representative tumor types (breast cancer, rectal cancer, lung cancer and glioblastoma) to assess the preparedness of volumetric and radiomics metrics as clinical trial endpoints. We identified three key areas—segmentation, validation and data sharing strategies—where concerted efforts are required to enable progress of volumetric- and radiomics-based clinical trial endpoints for wider clinical implementation.

Combined whole-lesion radiomic and iodine analysis for differentiation of pulmonary tumors

Quantitative radiomic and iodine imaging features have been explored for diagnosis and characterization of tumors. In this work, we invistigate combined whole-lesion radiomic and iodine analysis for the differentiation of pulmonary tumors on contrast-enhanced dual-energy CT (DECT) chest images. 100 biopsy-proven solid lung lesions on contrast-enhanced DECT chest exams within 3 months of histopathologic sampling were identified. Lesions were volumetrically segmented using open-source software. Lesion segmentations and iodine density volumes were loaded into a radiomics prototype for quantitative analysis. Univariate analysis was performed to determine differences in volumetric iodine concentration (mean, median, maximum, minimum, 10th percentile, 90th percentile) and first and higher order radiomic features (n = 1212) between pulmonary tumors. Analyses were performed using a 2-sample t test, and filtered for false discoveries using Benjamini–Hochberg method. 100 individuals (mean age 65 ± 13 years; 59 women) with 64 primary and 36 metastatic lung lesions were included. Only one iodine concentration parameter, absolute minimum iodine, significantly differed between primary and metastatic pulmonary tumors (FDR-adjusted p = 0.015, AUC 0.69). 310 (FDR-adjusted p = 0.0008 to p = 0.0491) radiomic features differed between primary and metastatic lung tumors. Of these, 21 features achieved AUC ≥ 0.75. In subset analyses of lesions imaged by non-CTPA protocol (n = 72), 191 features significantly differed between primary and metastatic tumors, 19 of which achieved AUC ≥ 0.75. In subset analysis of tumors without history of prior treatment (n = 59), 40 features significantly differed between primary and metastatic tumors, 11 of which achieved AUC ≥ 0.75. Volumetric radiomic analysis provides differentiating capability beyond iodine quantification. While a high number of radiomic features differentiated primary versus metastatic pulmonary tumors, fewer features demonstrated good individual discriminatory utility.

Can radiomic analysis of a single-phase dual-energy CT improve the diagnostic accuracy of differentiating enhancing from non-enhancing small renal lesions?

BACKGROUND

The value of dual-energy computed tomography (DECT)-based radiomics in renal lesions is unknown.

PURPOSE

To develop DECT-based radiomic models and assess their incremental values in comparison to conventional measurements for differentiating enhancing from non-enhancing small renal lesions.

MATERIAL AND METHODS

A total of 349 patients with 519 small renal lesions (390 non-enhancing, 129 enhancing) who underwent contrast-enhanced nephrographic phase DECT examinations between June 2013 and January 2020 on multiple DECT platforms were retrospectively recruited. Cohort A included all lesions, while cohort B included Bosniak II-IV and solid enhancing renal lesions. Radiomic models were built with features selected by the least absolute shrinkage and selection operator regression (LASSO). ROC analyses were performed to compare the diagnostic accuracy among conventional and radiomic models for predicting enhancing renal lesions.

RESULTS

The individual iodine concentration (IC), normalized IC, mean attenuation on 75-keV images, radiomic model of iodine images, 75-keV images and a combined model integrating all the above-mentioned features all demonstrated high AUCs for predicting renal lesion enhancement in cohort A (AUCs = 0.934-0.979) as well as in the test dataset (AUCs = 0.892-0.962) of cohort B (P values with Bonferroni correction >0.003). The AUC (0.864) of mean attenuation on 75-keV images was significantly lower than those of other models (all P values ≤0.001) except the radiomic model of 75-keV images (P = 0.038) in the training dataset of cohort B.

CONCLUSION

No incremental value was found by adding radiomic and machine learning analyses to iodine images for differentiating enhancing from non-enhancing renal lesions.

Iodine Maps from Dual-Energy CT to Predict Extrathyroidal Extension and Recurrence in Papillary Thyroid Cancer Based on a Radiomics Approach

BACKGROUND AND PURPOSE

Accurate prediction of extrathyroidal extension and subsequent recurrence is crucial in papillary thyroid cancer clinical management. Our aim was to conduct iodine map-based radiomics to predict extrathyroidal extension and to explore its prognostic value for recurrence-free survival in papillary thyroid cancer.

MATERIALS AND METHODS

A total of 452 patients with papillary thyroid cancer were retrospectively recruited between June 2017 and June 2020. Radiomics features were extracted from noncontrast images, dual-phase mixed images, and iodine maps, respectively. Random forest and least absolute shrinkage and selection operator (LASSO) were applied to build 6 radiomics scores (noncontrast radiomics score_random forest; noncontrast rad-score_LASSO; mixed rad-score_random forest; mixed rad-score_LASSO; iodine radiomics score_random forest; iodine radiomics score_LASSO) respectively. Logistic regression was used to construct 6 radiomics models incorporating 6 radiomics scores with clinical risk factors and to compare them with the clinical model. A radiomics model that achieved the highest performance was presented as a nomogram and assessed by discrimination, calibration, clinical usefulness, and prognosis evaluation.

RESULTS

Iodine radiomics scores performed significantly better than mixed radiomics scores. Both of them outperformed noncontrast radiomics scores. Iodine map-based radiomics models significantly surpassed the clinical model. A radiomics nomogram incorporating size, capsule contact, and iodine radiomics score_random forest was built with the highest performance (training set, area under the curve = 0.78; validation set, area under the curve  = 0.84). Stratified analysis confirmed the nomogram stability, especially in group negative for CT-reported extrathyroidal extension (area under the curve  = 0.69). Nomogram-predicted extrathyroidal extension risk was an independent predictor of recurrence-free survival. A high risk for extrathyroidal extension portended significantly lower recurrence-free survival than low risk (P < .001).

CONCLUSIONS

Iodine map-based radiomics might be a supporting tool for predicting extrathyroidal extension and subsequent recurrence risk in patients with papillary thyroid cancer, thus facilitating clinical decision-making.

Robustness of CT radiomics features: consistency within and between single-energy CT and dual-energy CT

Objectives

To evaluate inter- and intra- scan mode and scanner repeatability and reproducibility of radiomics features within and between single-energy CT (SECT) and dual-energy CT (DECT).

Methods

A standardized phantom with sixteen rods of clinical-relevant densities was scanned on seven DECT-capable scanners and three SECT-only scanners. The acquisition parameters were selected to present typical abdomen-pelvic examinations with the same voxel size. Images of SECT at 120 kVp and corresponding 120 kVp-like virtual monochromatic images (VMIs) in DECT which were generated according to scanners were analyzed. Regions of interest were drawn with rigid registrations to avoid variations due to segmentation. Radiomics features were extracted via Pyradiomics platform. Test-retest repeatability was evaluated by Bland-Altman analysis for repeated scans. Intra-scanner reproducibility for different scan modes was tested by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC). Inter-scanner reproducibility among different scanners for same scan mode was assessed by coefficient of variation (CV) and quartile coefficient of dispersion (QCD).

Results

The test-retest analysis presented that 92.91% and 87.02% of the 94 assessed features were repeatable for SECT 120kVp and DECT 120 kVp-like VMIs, respectively. The intra-scanner analysis for SECT 120kVp vs DECT 120 kVp-like VMIs demonstrated that 10.76% and 10.28% of features were with ICC > 0.90 and CCC > 0.90, respectively. The inter-scanner analysis showed that 17.09% and 27.73% of features for SECT 120kVp were with CV < 10% and QCD < 10%, and 15.16% and 32.78% for DECT 120 kVp-like VMIs, respectively.

Conclusions

The majority of radiomics features were non-reproducible within and between SECT and DECT.

Key Points

• Although the test-retest analysis showed high repeatability for radiomics features, the overall reproducibility of radiomics features within and between SECT and DECT was low.

• Only about one-tenth of radiomics features extracted from SECT images and corresponding DECT images did match each other, even their average photon energy levels were considered alike, indicating that the scan mode potentially altered the radiomics features.

• Less than one-fifth of radiomics features were reproducible among multiple SECT and DECT scanners, regardless of their fixed acquisition and reconstruction parameters, suggesting the necessity of scanning protocol adjustment and post-scan harmonization process.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-022-08628-3.

A Machine learning model trained on dual-energy CT radiomics significantly improves immunotherapy response prediction for patients with stage IV melanoma

BACKGROUND

To assess the additive value of dual-energy CT (DECT) over single-energy CT (SECT) to radiomics-based response prediction in patients with metastatic melanoma preceding immunotherapy.

MATERIAL AND METHODS

A total of 140 consecutive patients with melanoma (58 female, 63±16 years) for whom baseline DECT tumor load assessment revealed stage IV and who were subsequently treated with immunotherapy were included. Best response was determined using the clinical reports (81 responders: 27 complete response, 45 partial response, 9 stable disease). Individual lesion response was classified manually analogous to RECIST 1.1 through 1291 follow-up examinations on a total of 776 lesions (6.7±7.2 per patient). The patients were sorted chronologically into a study and a validation cohort (each n=70). The baseline DECT was examined using specialized tumor segmentation prototype software, and radiomic features were analyzed for response predictors. Significant features were selected using univariate statistics with Bonferroni correction and multiple logistic regression. The area under the receiver operating characteristic curve of the best subset was computed (AUROC). For each combination (SECT/DECT and patient response/lesion response), an individual random forest classifier with 10-fold internal cross-validation was trained on the study cohort and tested on the validation cohort to confirm the predictive performance.

RESULTS

We performed manual RECIST 1.1 response analysis on a total of 6533 lesions. Multivariate statistics selected significant features for patient response in SECT (min. brightness, R²=0.112, padj. ≤0.001) and DECT (textural coarseness, R²=0.121, padj. ≤0.001), as well as lesion response in SECT (mean absolute voxel intensity deviation, R²=0.115, padj. ≤0.001) and DECT (iodine uptake metrics, R²≥0.12, padj. ≤0.001). Applying the machine learning models to the validation cohort confirmed the additive predictive power of DECT (patient response AUROC SECT=0.5, DECT=0.75; lesion response AUROC SECT=0.61, DECT=0.85; p<0.001).

CONCLUSION

The new method of DECT-specific radiomic analysis provides a significant additive value over SECT radiomics approaches for response prediction in patients with metastatic melanoma preceding immunotherapy, especially on a lesion-based level. As mixed tumor response is not uncommon in metastatic melanoma, this lends a powerful tool for clinical decision-making and may potentially be an essential step toward individualized medicine.

A Pilot Study to Evaluate Early Predictive Value of Thorax Perfusion-CT in Advanced NSCLC

Simple Summary

The use of targeted drugs has brought about the development of new imaging techniques which are able to assess in vivo processes and changes in vascularization parameters can be captured as part of the antitumor response to antiangiogenic therapies. This pilot study (IMPACT trial, NCT02316327) aimed to explore the capacity of Perfusion-Computed Tomography (pCT) to detect early changes in tumor vascularization in non-small cell lung cancer (NSCLC) patients treated with an antiangiogenic-based therapy. Our results confirm the feasibility of pCT to capture early changes in tumor vasculature and suggest the potential of blood volume (BV) to early identify differential tumor responses to antiangiogenic therapy.

Abstract

Background: The role of perfusion computed tomography (pCT) in detecting changes in tumor vascularization as part of a response to antiangiogenic therapy in non-small cell lung cancer (NSCLC) remains unclear. Methods: In this prospective pilot study (IMPACT trial, NCT02316327), we aimed to determine the ability of pCT to detect early changes in blood flow (BF), blood volume (BV), and permeability (PMB), and to explore whether these changes could predict the response at day +42 in patients with advanced, treatment-naive, non-squamous NSCLC treated with cisplatin and gemcitabine plus bevacizumab. Results: All of the perfusion parameters showed a consistent decrease during the course of treatment. The BV difference between baseline and early assessment was significant (p = 0.013), whereas all perfusion parameters showed significant differences between baseline and day +42 (p = 0.003, p = 0.049, and p = 0.002, respectively). Among the 16 patients evaluable for efficacy, a significant decline in BV at day +7 from baseline was observed in tumors with no response (p = 0.0418). Conclusions: Our results confirm that pCT can capture early changes in tumor vasculature. A substantial early decline of BV from baseline might identify tumors less likely responsive to antiangiogenic-drugs.

Predicting Response to Systemic Chemotherapy for Advanced Gastric Cancer Using Pre-Treatment Dual-Energy CT Radiomics: A Pilot Study

Objective

To build and assess a pre-treatment dual-energy CT-based clinical-radiomics nomogram for the individualized prediction of clinical response to systemic chemotherapy in advanced gastric cancer (AGC).

Methods

A total of 69 pathologically confirmed AGC patients who underwent dual-energy CT before systemic chemotherapy were enrolled from two centers in this retrospective study. Treatment response was determined with follow-up CT according to the RECIST standard. Quantitative radiomics metrics of the primary lesion were extracted from three sets of monochromatic images (40, 70, and 100 keV) at venous phase. Univariate analysis and least absolute shrinkage and selection operator (LASSO) were used to select the most relevant radiomics features. Multivariable logistic regression was performed to establish a clinical model, three monochromatic radiomics models, and a combined multi-energy model. ROC analysis and DeLong test were used to evaluate and compare the predictive performance among models. A clinical-radiomics nomogram was developed; moreover, its discrimination, calibration, and clinical usefulness were assessed.

Result

Among the included patients, 24 responded to the systemic chemotherapy. Clinical stage and the iodine concentration (IC) of the tumor were significant clinical predictors of chemotherapy response (all p < 0.05). The multi-energy radiomics model showed a higher predictive capability (AUC = 0.914) than two monochromatic radiomics models and the clinical model (AUC: 40 keV = 0.747, 70 keV = 0.793, clinical = 0.775); however, the predictive accuracy of the 100-keV model (AUC: 0.881) was not statistically different (p = 0.221). The clinical-radiomics nomogram integrating the multi-energy radiomics signature with IC value and clinical stage showed good calibration and discrimination with an AUC of 0.934. Decision curve analysis proved the clinical usefulness of the nomogram and multi-energy radiomics model.

Conclusion

The pre-treatment DECT-based clinical-radiomics nomogram showed good performance in predicting clinical response to systemic chemotherapy in AGC, which may contribute to clinical decision-making and improving patient survival.

MRI based radiomics in nasopharyngeal cancer: Systematic review and perspectives using radiomic quality score (RQS) assessment

BACKGROUND

MRI based radiomics has the potential to better define tumor biology compared to qualitative MRI assessment and support decisions in patients affected by nasopharyngeal carcinoma. Aim of this review was to systematically evaluate the methodological quality of studies using MRI- radiomics for nasopharyngeal cancer patient evaluation.

METHODS

A systematic search was performed in PUBMED, WEB OF SCIENCE and SCOPUS using "MRI, magnetic resonance imaging, radiomic, texture analysis, nasopharyngeal carcinoma, nasopharyngeal cancer" in all possible combinations. The methodological quality of study included ( = 24) was evaluated according to the RQS (Radiomic quality score). Subgroup, for journal type (imaging/clinical) and biomarker (prognostic/predictive), and correlation, between RQS and journal Impact Factor, analyses were performed. Mann-Whitney U test and Spearman's correlation were performed. P value < .05 were defined as statistically significant.

RESULTS

Overall, no studies reported a phantom study or a test re-test for assessing stability in image, biological correlation or open science data. Only 8% of them included external validation. Almost half of articles (45 %) performed multivariable analysis with non-radiomics features. Only 1 study was prospective (4%). The mean RQS was 7.5 ± 5.4. No significant differences were detected between articles published in clinical/imaging journal and between studies with a predictive or prognostic biomarker. No significant correlation was found between total RQS and Impact Factor of the year of publication (p always > 0.05).

CONCLUSIONS

Radiomic articles in nasopharyngeal cancer are mostly of low methodological quality. The greatest limitations are the lack of external validation, biological correlates, prospective design and open science.

Iodine Map Radiomics in Breast Cancer: Prediction of Metastatic Status

Simple Summary

Early and accurate diagnosis of breast cancer that has spread to other organs and tissues is crucial, as therapeutic decisions and outcome expectations might change. Computed tomography (CT) is often used to detect breast cancer’s spread, but this method has its weaknesses. The computer-assisted technique “radiomics” extracts grey-level patterns, so-called radiomic features, from medical images, which may reflect underlying biological processes. Our retrospective study therefore evaluated whether breast cancer spread can be predicted by radiomic features derived from iodine maps, an application on a new generation of CT scanners visualizing tissue blood flow. Based on 77 patients with newly diagnosed breast cancer, we found that this approach might indeed predict cancer spread to other organs/tissues. In the future, radiomics may serve as an additional tool for cancer detection and risk assessment.

Abstract

Dual-energy CT (DECT) iodine maps enable quantification of iodine concentrations as a marker for tissue vascularization. We investigated whether iodine map radiomic features derived from staging DECT enable prediction of breast cancer metastatic status, and whether textural differences exist between primary breast cancers and metastases. Seventy-seven treatment-naïve patients with biopsy-proven breast cancers were included retrospectively (41 non-metastatic, 36 metastatic). Radiomic features including first-, second-, and higher-order metrics as well as shape descriptors were extracted from volumes of interest on iodine maps. Following principal component analysis, a multilayer perceptron artificial neural network (MLP-NN) was used for classification (70% of cases for training, 30% validation). Histopathology served as reference standard. MLP-NN predicted metastatic status with AUCs of up to 0.94, and accuracies of up to 92.6 in the training and 82.6 in the validation datasets. The separation of primary tumor and metastatic tissue yielded AUCs of up to 0.87, with accuracies of up to 82.8 in the training, and 85.7 in the validation dataset. DECT iodine map-based radiomic signatures may therefore predict metastatic status in breast cancer patients. In addition, microstructural differences between primary and metastatic breast cancer tissue may be reflected by differences in DECT radiomic features.

A New Outlook on the Ability to Accumulate an Iodine Contrast Agent in Solid Lung Tumors Based on Virtual Monochromatic Images in Dual Energy Computed Tomography (DECT): Analysis in Two Phases of Contrast Enhancement

For some time, dual energy computed tomography (DECT) has been an established method used in a vast array of clinical applications, including lung nodule assessment. The aim of this study was to analyze (using monochromatic DECT images) how the X-ray absorption of solitary pulmonary nodules (SPNs) depends on the iodine contrast agent and when X-ray absorption is no longer dependent on the accumulated contrast agent. Sixty-six patients with diagnosed solid lung tumors underwent DECT scans in the late arterial phase (AP) and venous phase (VP) between January 2017 and June 2018. Statistically significant correlations (p ≤ 0.001) of the iodine contrast concentration were found in the energy range of 40–90 keV in the AP phase and in the range of 40–80 keV in the VP phase. The strongest correlation was found between the concentrations of the contrast agent and the scanning energy of 40 keV. At the higher scanning energy, no significant correlations were found. We concluded that it is most useful to evaluate lung lesions in DECT virtual monochromatic images (VMIs) in the energy range of 40–80 keV. We recommend assessing SPNs in only one phase of contrast enhancement to reduce the absorbed radiation dose.

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.

Structural and functional radiomics for lung cancer

INTRODUCTION

Lung cancer ranks second in new cancer cases and first in cancer-related deaths worldwide. Precision medicine is working on altering treatment approaches and improving outcomes in this patient population. Radiological images are a powerful non-invasive tool in the screening and diagnosis of early-stage lung cancer, treatment strategy support, prognosis assessment, and follow-up for advanced-stage lung cancer. Recently, radiological features have evolved from solely semantic to include (handcrafted and deep) radiomic features. Radiomics entails the extraction and analysis of quantitative features from medical images using mathematical and machine learning methods to explore possible ties with biology and clinical outcomes.

METHODS

Here, we outline the latest applications of both structural and functional radiomics in detection, diagnosis, and prediction of pathology, gene mutation, treatment strategy, follow-up, treatment response evaluation, and prognosis in the field of lung cancer.

CONCLUSION

The major drawbacks of radiomics are the lack of large datasets with high-quality data, standardization of methodology, the black-box nature of deep learning, and reproducibility. The prerequisite for the clinical implementation of radiomics is that these limitations are addressed. Future directions include a safer and more efficient model-training mode, merge multi-modality images, and combined multi-discipline or multi-omics to form "Medomics."

Texture analysis of iodine maps and conventional images for k-nearest neighbor classification of benign and metastatic lung nodules

BACKGROUND

The purpose of this study was to analyze if the use of texture analysis on spectral detector CT (SDCT)-derived iodine maps (IM) in addition to conventional images (CI) improves lung nodule differentiation, when being applied to a k-nearest neighbor (KNN) classifier.

METHODS

183 cancer patients who underwent contrast-enhanced, venous phase SDCT of the chest were included: 85 patients with 146 benign lung nodules (BLN) confirmed by either prior/follow-up CT or histopathology and 98 patients with 425 lung metastases (LM) verified by histopathology, 18F-FDG-PET-CT or unequivocal change during treatment. Semi-automatic 3D segmentation of BLN/LM was performed, and volumetric HU attenuation and iodine concentration were acquired. For conventional images and iodine maps, average, standard deviation, entropy, kurtosis, mean of the positive pixels (MPP), skewness, uniformity and uniformity of the positive pixels (UPP) within the volumes of interests were calculated. All acquired parameters were transferred to a KNN classifier.

RESULTS

Differentiation between BLN and LM was most accurate, when using all CI-derived features combined with the most significant IM-derived feature, entropy (Accuracy:0.87; F1/Dice:0.92). However, differentiation accuracy based on the 4 most powerful CI-derived features performed only slightly inferior (Accuracy:0.84; F1/Dice:0.89, p=0.125). Mono-parametric lung nodule differentiation based on either feature alone (i.e. attenuation or iodine concentration) was poor (AUC=0.65, 0.58, respectively).

CONCLUSIONS

First-order texture feature analysis of contrast-enhanced staging SDCT scans of the chest yield accurate differentiation between benign and metastatic lung nodules. In our study cohort, the most powerful iodine map-derived feature slightly, yet insignificantly increased classification accuracy  compared to classification based on conventional image features only.

Improved differentiation between primary lung cancer and pulmonary metastasis by combining dual-energy CT-derived biomarkers with conventional CT attenuation

OBJECTIVES

To assess the clinical utility of dual-energy CT (DE-CT)-derived iodine concentration (IC) and effective Z (Z^eff) in addition to conventional CT attenuation (HU) for the discrimination between primary lung cancer (LC) and pulmonary metastases (PM) from different primary malignancies.

METHODS

DE-CT scans of 79 patients with LC (3 histopathologic subgroups) and 89 patients with PM (5 histopathologic subgroups) were evaluated. Quantitative IC, Z^eff, and conventional HU values were extracted and normalized to the thoracic aorta. Differences between groups were assessed by pairwise Welch's t test. Correlation and linear regression analyses were used to examine the relationship of imaging parameters in LC and PM. Diagnostic accuracy was measured by the area under receiver operator characteristic curve (AUC) and validated based on resampling methods.

RESULTS

Significant differences between subgroups of LC and PMs were noted for all imaging parameters, with the highest number of significant pairs for IC. In univariate analysis, only IC was a significant diagnostic feature for discriminating LC from PM (p = 0.03). All quantitative imaging parameters correlated significantly (p < 0.0001, respectively), with the highest correlation between IC and Z^eff (r = 0.91), followed by IC and HU (r = 0.76) and Z^eff and HU (r = 0.73). Diagnostic models combining IC or Z^eff with HU (IC+HU: AUC = 0.73; Z^eff+HU: AUC = 0.69; IC+Z^eff+HU: AUC = 0.73) were not significantly different and outperformed individual parameters (IC: AUC = 0.57; Z^eff: AUC = 0.57; HU: AUC = 0.55) in diagnostic accuracy (p < 0.05, respectively).

CONCLUSION

DE-CT-derived IC or Z^eff and conventional HU represent complementary imaging parameters, which, if used in combination, may improve the differentiation between LC and PM.

KEY POINTS

• Individual quantitative imaging parameters derived from DE-CT (iodine concentration, effective Z) and conventional CT (HU) provide complementary diagnostic information for the differentiation of primary lung cancer and pulmonary metastases. • A combination of conventional HU and DE-CT parameters enhances the diagnostic utility of individual parameters.

Assessment of Solitary Pulmonary Nodules Based on Virtual Monochrome Images and Iodine-Dependent Images Using a Single-Source Dual-Energy CT with Fast kVp Switching

With lung cancer being the most common malignancy diagnosed worldwide, lung nodule assessment has proved to be one of big challenges of modern medicine. The aim of this study was to examine the usefulness of Dual Energy Computed Tomography (DECT) in solitary pulmonary nodule (SPN) assessment. Between January 2017 and June 2018; 65 patients (42 males and 23 females) underwent DECT scans in the late arterial phase (AP) and venous phase (VP). We concluded that imaging at an energy level of 65 keV was the most accurate in detecting malignancy in solitary pulmonary nodules (SPNs) measuring ≤30 mm in diameter on virtual monochromatic maps. Both virtual monochromatic images and iodine concentration maps prove to be highly useful in differentiating benign and malignant pulmonary nodules. As for iodine concentration maps, the analysis of venous phase images resulted in the highest clinical usefulness. To summarize, DECT may be a useful tool in the differentiation of benign and malignant SPNs. A single-phase DECT examination with scans acquired 90 s after contrast media injection is recommended.

MRI-Based Texture Features as Potential Prognostic Biomarkers in Anaplastic Astrocytoma Patients Undergoing Surgical Treatment

Objectives. The purpose of this study was to investigate whether texture features from magnetic resonance imaging (MRI) were associated with the overall survival (OS) of anaplastic astrocytoma (AA) patients undergoing surgical treatment. Methods. A total of 51 qualified patients who were diagnosed with AA and underwent surgical interventions in our institution were enrolled in this retrospective study. Patients were followed up for at least 30 months or until death. Texture features derived from histogram-based matrix (HISTO) and grey-level co-occurrence matrix (GLCM) were extracted from preoperative contrast-enhanced T1-weighted images. Each texture feature was dichotomized based on its optimal cutoff value calculated by receiver operating characteristics curve analysis. Kaplan–Meier analysis and log rank test were conducted to compare the 30-month OS between the dichotomized subgroups. Multivariate Cox regression analysis was performed to determine independent prognostic factors. Results. Three HISTO-derived features (HISTO-Energy, HISTO-Entropy, and HISTO-Skewness) and five GLCM-derived features (GLCM-Contrast, GLCM-Energy, GLCM-Entropy, GLCM-Homogeneity, and GLCM-Dissimilarity) were found to be significantly correlated with 30-month OS. Moreover, GLCM-Homogeneity (p=0.001, hazard ratio = 6.351) was suggested to be the independent predictor of the patient survival. Conclusion. MRI-based texture features have the potential to be applied as prognostic biomarkers in AA patients undergoing surgical treatment.

Radiomics analysis of dual-energy CT-derived iodine maps for diagnosing metastatic cervical lymph nodes in patients with papillary thyroid cancer

OBJECTIVE

To investigate the value of radiomics analysis of dual-energy computed tomography (DECT)-derived iodine maps for preoperative diagnosing cervical lymph nodes (LNs) metastasis in patients with papillary thyroid cancer (PTC).

METHODS

Two hundred and fifty-five LNs (143 non-metastatic and 112 metastatic) were enrolled and allocated to training and validation sets (7:3 ratio). Radiomics features were extracted from arterial and venous phase iodine maps, respectively. Radiomics signature was constructed based on reproducible features using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm with 10-fold cross-validation. Logistic regression modeling was employed to build models based on CT image features (model 1), radiomics signature (model 2), and the combined (model 3). A nomogram was plotted for the combined model and decision curve analysis was applied for clinical use. Diagnostic performance was assessed and compared. Internal validation was performed on an independent set containing 78 LNs.

RESULTS

Model 3 showed optimal diagnostic performance in both training (AUC = 0.933) and validation set (AUC = 0.895), followed by model 2 (training set, AUC = 0.910; validation set, AUC = 0.847). Both these two models outperformed model 1 in both training (AUC = 0.763) (p < 0.05) and validation set (AUC = 0.728) (p < 0.05).

CONCLUSION

Radiomics analysis of DECT-derived iodine maps showed better diagnostic performance than qualitative evaluation of CT image features in preoperative diagnosing cervical LN metastasis in PTC patients. Radiomics signature integrated with CT image features can serve as a promising imaging biomarker for the differentiation.

KEY POINTS

• Conventional CT image features have limited value for the diagnosis of metastatic LNs in PTC patients. • Radiomics analysis of dual-energy CT-derived iodine maps significantly outperformed qualitative CT image features in differentiating metastatic from non-metastatic LNs. • Radiomics signature integrated with qualitative CT image features can serve as a useful tool in judging LNs status, thus aiding clinical decision-making.

Association of MRI-derived radiomic biomarker with disease-free survival in patients with early-stage cervical cancer

Pre-treatment survival prediction plays a key role in many diseases. We aimed to determine the prognostic value of pre-treatment Magnetic Resonance Imaging (MRI) based radiomic score for disease-free survival (DFS) in patients with early-stage (IB-IIA) cervical cancer.

Methods: A total of 248 patients with early-stage cervical cancer underwent radical hysterectomy were included from two institutions between January 1, 2011 and December 31, 2017, whose MR imaging data, clinicopathological data and DFS data were collected. Patients data were randomly divided into the training cohort (n = 166) and the validation cohort (n=82). Radiomic features were extracted from the pre-treatment T2-weighted (T2w) and contrast-enhanced T1-weighted (CET1w) MR imagings for each patient. Least absolute shrinkage and selection operator (LASSO) regression and Cox proportional hazard model were applied to construct radiomic score (Rad-score). According to the cutoff of Rad-score, patients were divided into low- and high- risk groups. Pearson's correlation and Kaplan-Meier analysis were used to evaluate the association of Rad-score with DFS. A combined model incorporating Rad-score, lymph node metastasis (LNM) and lymphovascular space invasion (LVI) by multivariate Cox proportional hazard model was constructed to estimate DFS individually.

Results: Higher Rad-scores were significantly associated with worse DFS in the training and validation cohorts (P<0.001 and P=0.011, respectively). The Rad-score demonstrated better prognostic performance in estimating DFS (C-index, 0.753; 95% CI: 0.696-0.805) than the clinicopathological features (C-index, 0.632; 95% CI: 0.567-0.700). However, the combined model showed no significant improvement (C-index, 0.714; 95%CI: 0.642-0.784).

Conclusion: The results demonstrated that MRI-derived Rad-score can be used as a prognostic biomarker for patients with early-stage (IB-IIA) cervical cancer, which can facilitate clinical decision-making.

Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement

OBJECTIVES

To evaluate radiomics studies according to radiomics quality score (RQS) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to provide objective measurement of radiomics research.

MATERIALS AND METHODS

PubMed and Embase were searched for studies published in high clinical imaging journals until December 2018 using the terms "radiomics" and "radiogenomics." Studies were scored against the items in the RQS and TRIPOD guidelines. Subgroup analyses were performed for journal type (clinical vs. imaging), intended use (diagnostic vs. prognostic), and imaging modality (CT vs. MRI), and articles were compared using Fisher's exact test and Mann-Whitney analysis.

RESULTS

Seventy-seven articles were included. The mean RQS score was 26.1% of the maximum (9.4 out of 36). The RQS was low in demonstration of clinical utility (19.5%), test-retest analysis (6.5%), prospective study (3.9%), and open science (3.9%). None of the studies conducted a phantom or cost-effectiveness analysis. The adherence rate for TRIPOD was 57.8% (mean) and was particularly low in reporting title (2.6%), stating study objective in abstract and introduction (7.8% and 16.9%), blind assessment of outcome (14.3%), sample size (6.5%), and missing data (11.7%) categories. Studies in clinical journals scored higher and more frequently adopted external validation than imaging journals.

CONCLUSIONS

The overall scientific quality and reporting of radiomics studies is insufficient. Scientific improvements need to be made to feature reproducibility, analysis of clinical utility, and open science categories. Reporting of study objectives, blind assessment, sample size, and missing data is deemed to be necessary.

KEY POINTS

• The overall scientific quality and reporting of radiomics studies is insufficient. • The RQS was low in demonstration of clinical utility, test-retest analysis, prospective study, and open science. • Room for improvement was shown in TRIPOD in stating study objective in abstract and introduction, blind assessment of outcome, sample size, and missing data categories.

Pretreatment MRI radiomics analysis allows for reliable prediction of local recurrence in non-metastatic T4 nasopharyngeal carcinoma

BACKGROUND

To identify a radiomics signature to predict local recurrence in patients with non-metastatic T4 nasopharyngeal carcinoma (NPC).

METHODS

A total of 737 patients from Sun Yat-sen University Cancer Center (training cohort: n = 360; internal validation cohort: n = 120) and Wuzhou Red Cross Hospital (external validation cohort: n = 257) underwent feature extraction from the largest axial area of the tumor on pretreatment magnetic resonance imaging scans. Feature selection was based on the prognostic performance and feature stability in the training cohort. Radscores were generated using the Cox proportional hazards regression model with the selected features in the training cohort and then validated in the internal and external validation cohorts. We also constructed a nomogram for predicting local recurrence-free survival (LRFS).

FINDINGS

Eleven features were selected to construct the Radscore, which was significantly associated with LRFS. For the training, internal validation, and external validation cohorts, the Radscore (C-index: 0.741 vs. 0.753 vs. 0.730) outperformed clinical prognostic variables (C-index for primary gross tumor volume: 0.665 vs. 0.672 vs. 0.577; C-index for age: 0.571 vs. 0.629 vs. 0.605) in predicting LRFS. The generated radiomics nomogram, which integrated the Radscore and clinical variables, exhibited a satisfactory prediction performance (C-index: 0.810 vs. 0.807 vs. 0.753). The nomogram-defined high-risk group had a shorter LRFS than did the low-risk group (5-year LRFS: 73.6% vs. 95.3%, P < .001; 79.6% vs 95.8%, P = .006; 85.7% vs 96.7%, P = .005).

INTERPRETATION

The Radscore can reliably predict LRFS in patients with non-metastatic T4 NPC, which might guide individual treatment decisions. FUND: This study was funded by the Health & Medical Collaborative Innovation Project of Guangzhou City, China.