Temporal analysis of intratumoral metabolic heterogeneity characterized by textural features in cervical cancer

Is PET Radiomics Useful to Predict Pathologic Tumor Response and Prognosis in Locally Advanced Cervical Cancer?

This study investigated whether radiomic features extracted from pretreatment [18F]FDG PET could improve the prediction of both histopathologic tumor response and survival in patients with locally advanced cervical cancer (LACC) treated with neoadjuvant chemoradiotherapy followed by surgery compared with conventional PET parameters and histopathologic features. Methods: The medical records of all consecutive patients with LACC referred between July 2010 and July 2016 were reviewed. [18F]FDG PET/CT was performed before neoadjuvant chemoradiotherapy. Radiomic features were extracted from the primary tumor volumes delineated semiautomatically on the PET images and reduced by factor analysis. A receiver-operating-characteristic analysis was performed, and conventional and radiomic features were dichotomized with Liu's method according to pathologic response (pR) and cancer-specific death. According to the study protocol, only areas under the curve of more than 0.70 were selected for further analysis, including logistic regression analysis for response prediction and Cox regression analysis for survival prediction. Results: A total of 195 patients fulfilled the inclusion criteria. At pathologic evaluation after surgery, 131 patients (67.2%) had no or microscopic (≤3 mm) residual tumor (pR0 or pR1, respectively); 64 patients (32.8%) had macroscopic residual tumor (>3 mm, pR2). With a median follow-up of 76.0 mo (95% CI, 70.7-78.7 mo), 31.3% of patients had recurrence or progression and 20.0% died of the disease. Among conventional PET parameters, SUVmean significantly differed between pathologic responders and nonresponders. Among radiomic features, 1 shape and 3 textural features significantly differed between pathologic responders and nonresponders. Three radiomic features significantly differed between presence and absence of recurrence or progression and between presence and absence of cancer-specific death. Areas under the curve were less than 0.70 for all parameters; thus, univariate and multivariate regression analyses were not performed. Conclusion: In a large series of patients with LACC treated with neoadjuvant chemoradiotherapy followed by surgery, PET radiomic features could not predict histopathologic tumor response and survival. It is crucial to further explore the biologic mechanism underlying imaging-derived parameters and plan a large, prospective, multicenter study with standardized protocols for all phases of the process of radiomic analysis to validate radiomics before its use in clinical routine.

Enhancing the prediction of symptomatic radiation pneumonitis for locally advanced non-small-cell lung cancer by combining 3D deep learning-derived imaging features with dose-volume metrics: a two-center study

OBJECTIVE

This study aims to examine the ability of deep learning (DL)-derived imaging features for the prediction of radiation pneumonitis (RP) in locally advanced non-small-cell lung cancer (LA-NSCLC) patients.

MATERIALS AND METHODS

The study cohort consisted of 90 patients from the Fudan University Shanghai Cancer Center and 59 patients from the Affiliated Hospital of Jiangnan University. Occurrences of RP were used as the endpoint event. A total of 512 3D DL-derived features were extracted from two regions of interest (lung-PTV and PTV-GTV) delineated on the pre-radiotherapy planning CT. Feature selection was done using LASSO regression, and the classification models were built using the multilayered perceptron method. Performances of the developed models were evaluated by receiver operating characteristic curve analysis. In addition, the developed models were supplemented with clinical variables and dose-volume metrics of relevance to search for increased predictive value.

RESULTS

The predictive model using DL features derived from lung-PTV outperformed the one based on features extracted from PTV-GTV, with AUCs of 0.921 and 0.892, respectively, in the internal test dataset. Furthermore, incorporating the dose-volume metric V30Gy into the predictive model using features from lung-PTV resulted in an improvement of AUCs from 0.835 to 0.881 for the training data and from 0.690 to 0.746 for the validation data, respectively (DeLong p < 0.05).

CONCLUSION

Imaging features extracted from pre-radiotherapy planning CT using 3D DL networks could predict radiation pneumonitis and may be of clinical value for risk stratification and toxicity management in LA-NSCLC patients.

CLINICAL RELEVANCE STATEMENT

Integrating DL-derived features with dose-volume metrics provides a promising noninvasive method to predict radiation pneumonitis in LA-NSCLC lung cancer radiotherapy, thus improving individualized treatment and patient outcomes.

Current Status and Future Directions of Image-Guided Adaptive Brachytherapy for Locally Advanced Cervical Cancer

PURPOSE

The standard of care for patients with locally advanced cervical cancer is definitive chemoradiation followed by a brachytherapy boost. This review describes the current status and future directions of image-guided adaptive brachytherapy for locally advanced cervical cancer.

METHODS

A systematic search of the PubMed and Clinicaltrials.gov databases was performed, focusing on studies published within the last 10 years. The search queried "cervical cancer [AND] image-guided brachytherapy [OR] magnetic resonance imaging (MRI) [OR] adaptive brachytherapy".

DISCUSSION

The retroEMBRACE and EMBRACE-I trials have established the use of MRI as the standard imaging modality for brachytherapy application and planning. Quantitative imaging and radiomics have the potential to improve outcomes, with three ongoing prospective studies examining the use of radiomics to further risk-stratify patients and personalize brachytherapy. Another active area of investigation includes utilizing the superior soft tissue contrast provided by MRI to increase the dose per fraction and decrease the number of fractions needed for brachytherapy, with several retrospective studies demonstrating the safety and feasibility of three-fraction courses. For developing countries with limited access to MRI, trans-rectal ultrasound (TRUS) appears to be an effective alternative, with several retrospective studies demonstrating improved target delineation with the use of TRUS in conjunction with CT guidance.

CONCLUSIONS

Further investigation is needed to continue improving outcomes for patients with locally advanced cervical cancer treated with image-guided brachytherapy.

Early prediction of distant metastasis in patients with uterine cervical cancer treated with definitive chemoradiotherapy by deep learning using pretreatment [ 18 F]fluorodeoxyglucose positron emission tomography/computed tomography

OBJECTIVES

A deep learning (DL) model using image data from pretreatment [ 18 F]fluorodeoxyglucose ([ 18 F] FDG)-PET or computed tomography (CT) augmented with a novel imaging augmentation approach was developed for the early prediction of distant metastases in patients with locally advanced uterine cervical cancer.

METHODS

This study used baseline [18F]FDG-PET/CT images of newly diagnosed uterine cervical cancer patients. Data from 186 to 25 patients were analyzed for training and validation cohort, respectively. All patients received chemoradiotherapy (CRT) and follow-up. PET and CT images were augmented by using three-dimensional techniques. The proposed model employed DL to predict distant metastases. Receiver operating characteristic (ROC) curve analysis was performed to measure the model's predictive performance.

RESULTS

The area under the ROC curves of the training and validation cohorts were 0.818 and 0.830 for predicting distant metastasis, respectively. In the training cohort, the sensitivity, specificity, and accuracy were 80.0%, 78.0%, and 78.5%, whereas, the sensitivity, specificity, and accuracy for distant failure were 73.3%, 75.5%, and 75.2% in the validation cohort, respectively.

CONCLUSION

Through the use of baseline [ 18 F]FDG-PET/CT images, the proposed DL model can predict the development of distant metastases for patients with locally advanced uterine cervical cancer treatment by CRT. External validation must be conducted to determine the model's predictive performance.

Using Radiomics and Machine Learning Applied to MRI to Predict Response to Neoadjuvant Chemotherapy in Locally Advanced Cervical Cancer

Neoadjuvant chemotherapy plus radical surgery could be a safe alternative to chemo-radiation in cervical cancer patients who are not willing to receive radiotherapy. The response to neoadjuvant chemotherapy is the main factor influencing the need for adjunctive treatments and survival. In the present paper we aim to develop a machine learning model based on cervix magnetic resonance imaging (MRI) images to stratify the single-subject risk of cervical cancer. We collected MRI images from 72 subjects. Among these subjects, 28 patients (38.9%) belonged to the "Not completely responding" class and 44 patients (61.1%) belonged to the 'Completely responding' class according to their response to treatment. This image set was used for the training and cross-validation of different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic features could be able to capture the disease heterogeneity among the two groups. Three models consisting of three ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbor classifiers) were developed for the binary classification task of interest ("Not completely responding" vs. "Completely responding"), based on supervised learning, using response to treatment as the reference standard. The best model showed an ROC-AUC (%) of 83 (majority vote), 82.3 (mean) [79.9-84.6], an accuracy (%) of 74, 74.1 [72.1-76.1], a sensitivity (%) of 71, 73.8 [68.7-78.9], and a specificity (%) of 75, 74.2 [71-77.5]. In conclusion, our preliminary data support the adoption of a radiomic-based approach to predict the response to neoadjuvant chemotherapy.

Value of [18F]FDG PET/CT radiomic parameters in the context of response to chemotherapy in advanced cervical cancer

The first-order statistical (FOS) and second-order texture analysis on basis of Gray-Level Co-occurence Matrix (GLCM) were obtained to assess metabolic, volumetric, statistical and radiomic parameters of cervical cancer in response to chemotherapy, recurrence and age of patients. The homogeneous group of 83 patients with histologically confirmed IIIC1-IVB stage cervical cancer were analyzed, retrospectively. Before and after chemotherapy, the advancement of the disease and the effectiveness of the therapy, respectively, were established using [¹⁸F] FDG PET/CT imaging. The statistically significant differences between pre- and post-therapy parameters were observed for SUV_max, SUV_mean, TLG, MTV, asphericity (ASP, p = 0.000, Z > 0), entropy (E, p = 0.0000), correlation (COR, p = 0.0007), energy (En, p = 0.000) and homogeneity (H, p = 0.0018). Among the FOS parameters, moderate correlation was observed between pre-treatment coefficient of variation (COV) and patients' recurrence (R = 0.34, p = 0.001). Among the GLCM textural parameters, moderate positive correlation was observed for post-treatment contrast (C) with the age of patients (R = 0.3, p = 0.0038) and strong and moderate correlation was observed in the case of En and H with chemotherapy response (R = 0.54 and R = 0.46, respectively). All correlations were statistically significant. This study indicates the remarkable importance of pre- and post-treatment [¹⁸F] FDG PET statistical and textural GLCM parameters according to prediction of recurrence and chemotherapy response of cervical cancer patients.

The sub-molecular characterization identification for cervical cancer

Background

The efficacy of therapy in cervical cancer (CESC) is blocked by high molecular heterogeneity. Thus, the sub-molecular characterization remains primarily explored for personalizing the treatment of CESC patients.

Methods

Datasets with 741 CESC patients were obtained from TCGA and GEO databases. The NMF algorithm, random forest algorithm, and multivariate Cox analysis were utilized to construct a classifier for defining the sub-molecular characterization. Then, the biological characteristics, genomic variations, prognosis, and immune landscape in molecular subtypes were explored. The significance of classifier genes was validated by quantitative Real-Time PCR, cell transfection, cell colony formation assay, wound healing assay, cell proliferation assay, and Western blot.

Results

The CESC patients were classified into two subtypes, and the high classifier-score patients with significant differences in ECM-receptor interaction, PI3K-Akt signaling pathway, and MAPK signaling pathway showed a poorer prognosis in OS (p < 0.001), DFI (p = 0.016), PFI (p < 0.001) and DSS (p < 0.001), and with high the M0 Macrophage and resting Mast cells infiltration and low HLA family gene expression. Moreover, the constructed classifier owns a high identified accuracy in the tumor/normal groups (AUC: 0.993), the tumor/CIN1-CIN3 groups (AUC: 0.963), and normal/CIN1-CIN3 groups (AUC: 0.962), and the total prediction performance is better than currently published signatures in CESC (C-index: 0,763). The combined prediction performance further indicated that Nomogram (AUC = 0.837) is superior to the classifier (AUC = 0.835) and Stage (AUC = 0.568), and the C-index of calibration curves is 0.784. The potential biological function of classifier genes indicated that silencing GALNT2 inhibited the cancer cell's proliferation, migration, and colony formation; Conversely, the cancer cell's proliferation, migration, and colony formation were increased after the upregulation of GALNT2. The Epithelial-Mesenchymal Transition Experiment showed that GALNT2 knockdown might reduce the levels of Snail and Vimentin proteins and increase E-cadherin; Conversely, the levels of Snail and Vimentin proteins were increased, E-cadherin was reduced by GALNT2 upregulation.

Conclusion

The classifier we constructed may help improve our understanding of subtype characteristics and provide a new strategy for developing CESC therapeutics. Remarkably, GALNT2 may be an option to directly target drivers in CESC cancer therapy.

Utility of pre-treatment 18 F-fluorodeoxyglucose PET radiomic analysis in assessing nodal involvement in cervical cancer

OBJECTIVE

Intratumor heterogeneity has prognostic value in cervical cancer, which can be depicted on 18 F-fluorodeoxyglucose ( 18 F-FDG) PET/computed tomography (PET/CT) and then quantitatively characterized by texture features. This study aimed to evaluate the discriminative performance and predictive ability of the texture features in determining lymph node involvement in cervical cancer.

METHODS

A total of 101 patients with newly diagnosed cervical cancer, who underwent pre-treatment whole-body 18 F-FDG PET/CT imaging were retrospectively recruited. Patients were categorized based on their nodal status. Thirty-five radiomic features together with the maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of the primary cervical tumors were extracted. Conventional indices were used to build logistic regression model and texture features were used to build random forest model. The performances for differentiating nodal status were assessed by receiver operating characteristic analysis.

RESULTS

Conventional PET indices were significantly higher in patients with nodal involvement compared to those without: SUVmax = 14.22 vs. 10.05; MTV = 57.02 vs. 28.73; TLG = 492.8 vs. 188.8 ( P  < 0.05). Nineteen radiomic features describing regional heterogeneity were significantly different between nodal involvements. Area under the curves of the models with conventional indices and PET texture features for discriminating nodal status were 0.72 and 0.76, respectively.

CONCLUSION

PET-derived radiomic features had moderate performance in discriminating nodal involvement in cervical cancer; and they did not outperform model based on conventional indices.

Exploratory analysis of radiomic as prognostic biomarkers in 18F-FDG PET/CT scan in uterine cervical cancer

Objective

To evaluate the performance of 18F-fluorodeoxyglucose positron emission tomography (¹⁸F-FDG PET/CT) radiomic features to predict overall survival (OS) in patients with locally advanced uterine cervical carcinoma.

Methods

Longitudinal and retrospective study that evaluated 50 patients with cervical epidermoid carcinoma (clinical stage IB2 to IVA according to FIGO). Segmentation of the 18F-FDG PET/CT tumors was performed using the LIFEx software, generating the radiomic features. We used the Mann-Whitney test to select radiomic features associated with the clinical outcome (death), excluding the features highly correlated with each other with Spearman correlation. Subsequently, ROC curves and a Kaplan-Meier analysis were performed. A p-value < 0.05 were considered significant.

Results

The median follow-up was 23.5 months and longer than 24 months in all surviving patients. Independent predictors for OS were found-SUVpeak with an AUC of 0.74, sensitivity of 77.8%, and specificity of 72.7% (p = 0.006); and the textural feature gray-level run-length matrix GLRLM_LRLGE, with AUC of 0.74, sensitivity of 72.2%, and specificity of 81.8% (p = 0.005). When we used the derived cut-off points from these ROC curves (12.76 for SUVpeak and 0.001 for GLRLM_LRLGE) in a Kaplan-Meier analysis, we can see two different groups (one with an overall survival probability of approximately 90% and the other with 30%). These biomarkers are independent of FIGO staging.

Conclusion

By radiomic ¹⁸F-FDG PET/CT data analysis, SUVpeak and GLRLM_LRLGE textural feature presented the best performance to predict OS in patients with cervical cancer undergoing chemo-radiotherapy and brachytherapy.

Synergistic impact of motion and acquisition/reconstruction parameters on 18 F-FDG PET radiomic features in non-small cell lung cancer: phantom and clinical studies

Objectives

This study is aimed at examining the synergistic impact of motion and acquisition/reconstruction parameters on ¹⁸F‐FDG PET image radiomic features in non‐small cell lung cancer (NSCLC) patients, and investigating the robustness of features performance in differentiating NSCLC histopathology subtypes.

Methods

An in‐house developed thoracic phantom incorporating lesions with different sizes was used with different reconstruction settings, including various reconstruction algorithms, number of subsets and iterations, full‐width at half‐maximum of post‐reconstruction smoothing filter and acquisition parameters, including injected activity and test–retest with and without motion simulation. To simulate motion, a special motor was manufactured to simulate respiratory motion based on a normal patient in two directions. The lesions were delineated semi‐automatically to extract 174 radiomic features. All radiomic features were categorized according to the coefficient of variation (COV) to select robust features. A cohort consisting of 40 NSCLC patients with adenocarcinoma (n = 20) and squamous cell carcinoma (n = 20) was retrospectively analyzed. Statistical analysis was performed to discriminate robust features in differentiating histopathology subtypes of NSCLC lesions.

Results

Overall, 29% of radiomic features showed a COV ≤5% against motion. Forty‐five percent and 76% of the features showed a COV ≤ 5% against the test–retest with and without motion in large lesions, respectively. Thirty‐three percent and 45% of the features showed a COV ≤ 5% against different reconstruction parameters with and without motion, respectively. For NSCLC histopathological subtype differentiation, statistical analysis showed that 31 features were significant (p‐value < 0.05). Two out of the 31 significant features, namely, the joint entropy of GLCM (AUC = 0.71, COV = 0.019) and median absolute deviation of intensity histogram (AUC = 0.7, COV = 0.046), were robust against the motion (same reconstruction setting).

Conclusions

Motion, acquisition, and reconstruction parameters significantly impact radiomic features, just as their synergies. Radiomic features with high predictive performance (statistically significant) in differentiating histopathological subtype of NSCLC may be eliminated due to non‐reproducibility.

Radiomics-based prediction of two-year clinical outcome in locally advanced cervical cancer patients undergoing neoadjuvant chemoradiotherapy

PURPOSE

The aim of this study is to determine if radiomics features extracted from staging magnetic resonance (MR) images could predict 2-year long-term clinical outcome in patients with locally advanced cervical cancer (LACC) after neoadjuvant chemoradiotherapy (NACRT).

MATERIALS AND METHODS

We retrospectively enrolled patients with LACC diagnosis who underwent NACRT followed by radical surgery in two different institutions. Radiomics features were extracted from pre-treatment 1.5 T T2w MR images. The predictive performance of each feature was quantified in terms of Wilcoxon-Mann-Whitney test. Among the significant features, Pearson correlation coefficient (PCC) was calculated to quantify the correlation among the different predictors. A logistic regression model was calculated considering the two most significant features at the univariate analysis showing the lowest PCC value. The predictive performance of the model created was quantified out using the area under the receiver operating characteristic curve (AUC).

RESULTS

A total of 175 patients were retrospectively enrolled (142 for the training cohort and 33 for the validation one). 1896 radiomic feature were extracted, 91 of which showed significance (p < 0.05) at the univariate analysis. The radiomic model showing the highest predictive value combined the features calculated starting from the gray level co-occurrence-based features. This model achieved an AUC of 0.73 in the training set and 0.91 in the validation set.

CONCLUSIONS

The proposed radiomic model showed promising performances in predicting 2-year overall survival before NACRT. Nevertheless, the observed results should be tested in larger studies with consistent external validation cohorts, to confirm their potential clinical use.

Identification and Validation of Invasion-Related Molecular Subtypes and Prognostic Features for Cervical Cancer

Background

As one of the main causes leading to female cancer deaths, cervical cancer shows malignant features of local infiltration and invasion into adjacent organs and tissues. This study was designed to categorize novel molecular subtypes according to cervical cancer invasion and screen reliable prognostic markers.

Methods

Invasion-related gene sets and expression profiles of invasion-related genes were collected from the CancerSEA database and The Cancer Genome Atlas (TCGA), respectively. Samples were clustered by nonnegative matrix factorization (NMF) to obtain different molecular subgroups, immune microenvironment characteristics of which were further systematically compared. Limma was employed to screen differentially expressed gene sets in different subtypes, followed by Lasso analysis for dimension reduction. Multivariate and univariate Cox regression analysis was performed to determine prognostic characteristics. The Kaplan-Meier test showed the prognostic differences of patients with different risks. Additionally, receiver operating characteristic (ROC) curves were applied to validate the prognostic model performance. A nomogram model was developed using clinical and prognostic characteristics of cervical cancer, and its prediction accuracy was reflected by calibration curve.

Results

This study filtered 19 invasion-related genes with prognosis significance in cervical cancer and 2 molecular subtypes (C1, C2). Specifically, the C1 subtype had an unfavorable prognosis, which was associated with the activation of the TGF-beta signaling pathway, focal adhesion, and PI3K-Akt signaling pathway. 875 differentially expressed genes were screened, and 8 key genes were finally retained by the dimension reduction analysis. An 8-gene signature was established as an independent factor predictive of the prognosis of cervical cancer. The signature performance was even stronger when combined with N stage.

Conclusion

Based on invasion-related genes, the present study categorized two cervical cancer subtypes with distinct TME characteristics and established an 8-gene marker that can accurately and independently predict the prognosis of cervical cancer.

Machine learning based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features to predict prognosis of cervical cancer patients

PURPOSE

To examine the usefulness of machine learning to predict prognosis in cervical cancer using clinical and radiomic features of 2-deoxy-2-[¹⁸F]fluoro-D-glucose (¹⁸F-FDG) positron emission tomography/computed tomography (CT) (¹⁸F-FDG-PET/CT).

METHODS

This retrospective study included 50 cervical cancer patients who underwent ¹⁸F-FDG-PET/CT before treatment. Four clinical (age, histology, stage, and treatment) and 41 ¹⁸F-FDG-PET-based radiomic features were ranked and a subset of useful features for association with disease progression was selected based on decrease of the Gini impurity. Six machine learning algorithms (random forest, neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis.

RESULTS

The five top predictors of disease progression were: stage, surface area, metabolic tumor volume, gray-level run length non-uniformity (GLRLM_RLNU), and gray-level non-uniformity for run (GLRLM_GLNU). The naive Bayes model was the best-performing classifier for predicting disease progression (AUC = 0.872, accuracy = 0.780, F1 score = 0.781, precision = 0.788, and recall = 0.780). In the naive Bayes model, 5-year PFS was significantly higher in predicted non-progression than predicted progression (80.1% vs. 9.1%, p < 0.001) and was only the independent factor for PFS in multivariate analysis (HR, 6.89; 95% CI, 1.92-24.69; p = 0.003).

CONCLUSION

A machine learning approach based on clinical and pretreatment ¹⁸F-FDG PET-based radiomic features may be useful for predicting tumor progression in cervical cancer patients.

Radiomics Predicts for Distant Metastasis in Locally Advanced Human Papillomavirus-Positive Oropharyngeal Squamous Cell Carcinoma

Simple Summary

There is strong evidence that locally advanced human papillomavirus positive (HPV+) oropharyngeal squamous cell carcinoma (OPSCC) carries a significantly better prognosis than HPV negative OPSCC, suggesting the possibility of treatment de-escalation and, therefore, toxicity reduction in this patient population. The lack of success in clinical trials towards this end presses the need to risk stratify locally advanced HPV+ OPSCC patients who can safely have treatment de-escalated. The present study had recourse to radiomics for this purpose and showed that radiomics has the ability to discriminate patients with locally advanced HPV+ OPSCC who went on to develop distant metastasis after completion of definitive chemoradiation or radiation alone. The implications of this study aid in demonstrating the potential pivotal role of radiomics in predictive risk assessment and personalizing therapy for this patient population.

Abstract

(1) Background and purpose: clinical trials have unsuccessfully tried to de-escalate treatment in locally advanced human papillomavirus positive (HPV+) oropharyngeal squamous cell carcinoma (OPSCC) with the goal of reducing treatment toxicity. The aim of this study was to explore the role of radiomics for risk stratification in this patient population to guide treatment. (2) Methods: the study population consisted of 225 patients with locally advanced HPV+ OPSCC treated with curative-intent radiation or chemoradiation therapy. Appearance of distant metastasis was used as the endpoint event. Radiomics data were extracted from the gross tumor volumes (GTVs) identified on the planning CT, with gray level being discretized using three different bin widths (8, 16, and 32). The data extracted for the groups with and without distant metastasis were subsequently balanced using three different algorithms including synthetic minority over-sampling technique (SMOTE), adaptive synthetic sampling (ADASYN), and borderline SMOTE. From these different combinations, a total of nine radiomics datasets were derived. Top features that minimized redundancy while maximizing relevance to the endpoint were selected individually and collectively for the nine radiomics datasets to build support vector machine (SVM) based predictive classifiers. Performance of the developed classifiers was evaluated by receiver operating characteristic (ROC) curve analysis. (3) Results: of the 225 locally advanced HPV+ OPSCC patients being studied, 9.3% had developed distant metastases at last follow-up. SVM classifiers built for the nine radiomics dataset using either their own respective top features or the top consensus ones were all able to differentiate the two cohorts at a level of excellence or beyond, with ROC area under curve (AUC) ranging from 0.84 to 0.95 (median = 0.90). ROC comparisons further revealed that the majority of the built classifiers did not distinguish the two cohorts significantly better than each other. (4) Conclusions: radiomics demonstrated discriminative ability in distinguishing patients with locally advanced HPV+ OPSCC who went on to develop distant metastasis after completion of definitive chemoradiation or radiation alone and may serve to risk stratify this patient population with the purpose of guiding the appropriate therapy.

Radiomics in cervical and endometrial cancer

Radiomics is an emerging field of research that aims to find associations between quantitative information extracted from imaging examinations and clinical data to support the best clinical decision. In the last few years, some papers have been evaluating the role of radiomics in gynecological malignancies, mainly focusing on ovarian cancer. Nonetheless, cervical cancer is the most frequent gynecological malignancy in developing countries and endometrial cancer is the most common in western countries. The purpose of this narrative review is to give an overview of the latest published papers evaluating the role of radiomics in cervical and endometrial cancer, mostly evaluating association with tumor prognostic factors, with response to therapy and with prediction of recurrence and distant metastasis.

Pretreatment MRI Radiomics Based Response Prediction Model in Locally Advanced Cervical Cancer

The aim of this study was to create a radiomics model for Locally Advanced Cervical Cancer (LACC) patients to predict pathological complete response (pCR) after neoadjuvant chemoradiotherapy (NACRT) analysing T2-weighted 1.5 T magnetic resonance imaging (MRI) acquired before treatment start. Patients with LACC and an International Federation of Gynecology and Obstetrics stage from IB2 to IVA at diagnosis were retrospectively enrolled for this study. All patients underwent NACRT, followed by radical surgery; pCR―assessed on surgical specimen―was defined as absence of any residual tumour. Finally, 1889 features were extracted from MR images; features showing statistical significance in predicting pCR at the univariate analysis were selected following an iterative method, which was ad-hoc developed for this study. Based on this method, 15 different classifiers were trained considering the most significant features selected. Model selection was carried out using the area under the receiver operating characteristic curve (AUC) as target metrics. One hundred eighty-three patients from two institutions were analysed. The model, showing the highest performance with an AUC of 0.80, was the random forest method initialised with default parameters. Radiomics appeared to be a reliable tool in pCR prediction for LACC patients undergoing NACRT, supporting the identification of patient risk groups, which paves treatment pathways tailored according to the predicted outcome.

Application of a Machine Learning Approach for the Analysis of Clinical and Radiomic Features of Pretreatment [18F]-FDG PET/CT to Predict Prognosis of Patients with Endometrial Cancer

PURPOSE

To examine the prognostic significance of pretreatment 2-deoxy-2-[¹⁸F]fluoro-D-glucose ([¹⁸F]-FDG) positron emission tomography (PET)-based radiomic features using a machine learning approach in patients with endometrial cancers.

PROCEDURES

Included in this retrospective study were 53 patients with endometrial cancers who underwent [¹⁸F]-FDG PET/X-ray computed tomography (CT) before treatment. Since two different PET scanners were used, post-reconstruction harmonization was performed for all PET parameters using the ComBat harmonization method. Four clinical (age, histological type, stage, and treatment method) and 40 [¹⁸F]-FDG PET-based radiomic features were ranked, and a subset of useful features was selected based on the decrease in the Gini impurity in terms of associations with disease progression. The machine learning algorithms (random forest, neural network, k-nearest neighbors (kNN), naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC) and validated by the random sampling method. Progression-free survival (PFS) and overall survival (OS) were assessed by the Cox regression analysis.

RESULTS

The five best predictors of disease progression were coarseness, gray-level run length nonuniformity, stage, treatment method, and gray-level zone length nonuniformity. The kNN model obtained the best performance classifier for predicting the disease progression (AUC =0.890, accuracy =0.849, F1 score =0.848, precision =0.857, and recall =0.849). Coarseness which was the first ranked radiomic feature was selected for survival analyses, and only coarseness remained as a significant and independent factor for both PFS (hazard ratios (HR), 0.65; 95 % confidence interval [CI], 0.49-0.86; p=0.003) and OS (HR, 0.52; 95 % CI, 0.36-0.76; p<0.001) at multivariate Cox regression analysis.

CONCLUSIONS

[¹⁸F]-FDG PET-based radiomic analysis using a machine learning approach may be useful for predicting tumor progression and prognosis in patients with endometrial cancers.

The predictive recurrence value of MTV-s as an 18F-FDG PET/CT index in patients with IIB-IVA cervical cancer

Objectives: The aim of this study was to explore the predictive recurrence value of the PET/CT index and some clinical features in patients with IIB-IVA cervical cancer.Methods: This was a retrospective analysis of 84 patients with cervical cancer who underwent 18 F-FDG PET/CT scans before treatment. MTV-s is the sum of the metabolic volume of the primary cervical lesion (MTV-C) and the metabolic volume of the pelvic and abdominal paravascular metastatic lymph nodes (MTV-LN). We analyzed the relationships between clinical characteristics (age, FIGO stage, pathological pattern, degree of differentiation, tumor size, presence of LN metastasis), PET/CT index (SUVmax-C, SUVmax-LN, MTV-C, MTV-LN, MTV-s), and recurrence of cervical cancer using the chi-square test; the ROC curve was used to determine the PET/CT boundary parameters; and the COX proportional risk model was used for univariate and multivariate analysis of clinical features and the PET/CT index. The survival curve was drawn using the Kaplan-Meier method, comparing different groups by the log-rank test.Results: Eighty-four patients were included. During the observation period, 26 patients had tumor recurrence (31.0%). Univariate analysis showed that lymph node metastasis, lymph node SUVmax (SUVmax-LN), MTV-C, MTV-LN, and MTV-s were associated with PFS. MTV-s > 27.36 cm³ was an independent risk factor for PFS (P = 0.037). There were 41 patients with MTV-s > 27.36 cm³, and 19 of them had tumor recurrence (46.3%). There were 43 patients with MTV-s ≤ 27.36 cm³, 7 of whom had tumor recurrence (16.3%).Conclusion: MTV-s can predict recurrence in patients with stage IIB-IVA cervical cancer, with a critical value of 27.36 cm³. PET/CT can help clinicians judge the prognosis of patients more comprehensively.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

Impact of quantization algorithm and number of gray level intensities on variability and repeatability of low field strength magnetic resonance image-based radiomics texture features

PURPOSE

The purpose of this work was to investigate the impact of quantization preprocessing parameter selection on variability and repeatability of texture features derived from low field strength magnetic resonance (MR) images.

METHODS

Texture features were extracted from low field strength images of a daily image QA phantom with four texture inserts. Feature variability over time was quantified using all combinations of three quantization algorithms and four different numbers of gray level intensities. In addition, texture features were extracted using the same combinations from the low field strength MR images of the gross tumor volume (GTV) and left kidney of patients with repeated set up scans. The impact of region of interest (ROI) preprocessing on repeatability was investigated with a test-retest study design.

RESULTS

The phantom ROIs quantized to 64 Gy level intensities using the histogram equalization method resulted in the greatest number of features with the least variability. There was no clear method that resulted in the highest repeatability in the GTV or left kidney. However, eight texture features extracted from the GTV were repeatable regardless of ROI processing combination.

CONCLUSION

Low field strength MR images can provide a stable basis for texture analysis with ROIs quantized to 64 Gy levels using histogram equalization, but there is no clear optimal combination for repeatability.

Ependymoma and pilocytic astrocytoma: Differentiation using radiomics approach based on machine learning

Mandatory accurate and specific diagnosis demands have brought about increased challenges for radiologists in pediatric posterior fossa tumor prediction and prognosis. With the development of high-performance computing and machine learning technologies, radiomics provides increasing opportunities for clinical decision-making. Several studies have applied radiomics as a decision support tool in intracranial tumors differentiation. Here we seek to achieve preoperative differentiation between ependymoma (EP) and pilocytic astrocytoma (PA) using radiomics analysis method based on machine learning. A total of 135 Magnetic Resonance Imaging (MRI) slices are divided into training sets and validation sets. Three kinds of radiomics features, including Gabor transform, texture and wavelet transform based ones are used to obtain 300 multimodal features. Kruskal-Wallis test score (KWT) and support vector machines (SVM) are applied for feature selection and tumor differentiation. The performance is investigated via accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. Results show that the accuracy, sensitivity, specificity, and AUC of the selected feature set are 0.8775, 0.9292, 0.8000, and 0.8646 respectively, having no significantdifferencescomparedwiththe overall feature set. For different types of features, texture features yield the best differentiation performance and the significance analysis results are consistent with this. Our study demonstrates texture features perform better than the other features. The radiomics approach based on machine learning is efficient for pediatric posterior fossa tumors differentiation and could enhance the application of radiomics methods for assisted clinical diagnosis.

Impact of contouring variability on oncological PET radiomics features in the lung

Radiomics features extracted from oncological PET images are currently under intense scrutiny within the context of risk stratification for a variety of cancers. However, the lack of robustness assessment poses problems for their application across institutions and for broader patient populations. The objective of the current study was to examine the extent to which radiomics parameters from oncological PET vary in response to manual contouring variability in lung cancer. Imaging data employed in the study consisted of 26 PET scans with lesions in the lung being created through the use of an anthropomorphic phantom in conjunction with Monte Carlo simulations. From each of the simulated lesions, 25 radiomics features related to the gray-level co-occurrence matrices (GLCOM), gray-level size zone matrices (GLSZM), and gray-level neighborhood difference matrices (GLNDM) were extracted from ground truth contour and from manual contours provided by 10 raters in regard to four intensity discretization schemes with number of gray levels of 32, 64, 128, and 256, respectively. The impact of interrater variability in tumor delineation upon the agreement between raters on radiomics features was examined via interclass correlation and leave-p-out assessment. Only weak and moderate correlations were found between segmentation accuracy as measured by the Dice coefficient and percent feature error from ground truth for the vast majority of the features being examined. GLNDM-based texture parameters emerged as the top performing category of radiomcs features in terms of robustness against contouring variability for discretization schemes engaging number of gray levels of 32, 64, and 128 while GLCOM-based parameters stood out for discretization scheme engaging 256 gray levels. How and to what extent interrater reliability of radiomics features vary in response to the number of raters were largely feature-dependent. It was concluded that impact of contouring variability on PET-based radiomics features is present to varying degrees and could be experienced as a barrier to convey PET-based radiomics research to clinical relevance.

Preoperative CT texture features predict prognosis after curative resection in pancreatic cancer

Pancreatic cancer is a lethal disease, and resistance to chemotherapy is a critical factor influencing the postoperative prognosis. Tumour heterogeneity is an important indicator of chemoresistance. Therefore, we analysed tumour heterogeneity in preoperative computed tomography scans by performing texture analysis using the grey-level run-length matrix and analysed the correlation of survival with the value obtained in these analyses. We analysed 116 consecutive patients who underwent curative resection and had preoperative contrast-enhanced computed tomography data available for analysis. A region of interest was drawn on all slices with a visible tumour and normal pancreas on the arterial phase computed tomography scans; the correlation of pathological characteristics with grey-level run-length matrix features was analysed. We then performed Kaplan–Meier survival curve analysis among pancreatic cancer patients. The grey-level non-uniformity values in grey-level run-length matrix features for tumours were higher than those for normal pancreas. High grey-level non-uniformity values represent a non-uniform texture, i.e., heterogeneity. Grey-level run-length matrix features showed that recurrence-free survival was shorter in the group with high grey-level non-uniformity 135 values (p = 0.025). Our analyses of the correlation between pathological outcomes and grey-level run-length matrix features in pancreatic cancer patients showed that grey-level non-uniformity values were powerful prognostic indicators.

11C-methionine-PET for differentiating recurrent brain tumor from radiation necrosis: radiomics approach with random forest classifier

Differentiating recurrent brain tumor from radiation necrosis is often difficult. This study aims to investigate the efficacy of 11C-methionine (MET)-PET radiomics for distinguishing recurrent brain tumor from radiation necrosis, as compared with conventional tumor-to-normal cortex (T/N) ratio evaluation. We enrolled 41 patients with metastatic brain tumor or glioma treated using radiation therapy who underwent MET-PET. The area with a standardized uptake value > 1.3 times that of the normal brain cortex was contoured. Forty-two PET features were extracted and used in a random forest classifier and the diagnostic performance was evaluated using a 10-fold cross-validation scheme. Gini index was measured to identify relevant PET parameters for classification. The reference standard was surgical histopathological analysis or more than 6 months of follow-up with MRI. Forty-four lesions were used for the analysis. Thirty-three and 11 lesions were confirmed as recurrent brain tumor and radiation necrosis, respectively. Radiomics and T/N ratio evaluation showed sensitivities of 90.1% and 60.6%, and specificities of 93.9% and 72.7% with areas under the curve of 0.98 and 0.73, respectively. Gray level co-occurrence matrix dissimilarity was the most pertinent feature for diagnosis. MET-PET radiomics yielded excellent outcome for differentiating recurrent brain tumor from radiation necrosis, which outperformed T/N ratio evaluation.

Quantitative imaging: Erring patterns in manual delineation of PET-imaged lung lesions

BACKGROUND AND PURPOSE

Uncertainty and variability in manual contouring of PET-imaged tumor targets are well recognized; however, the error patterns associated with it were little known and rarely investigated. The present study is aimed to quantitatively assess the erring patterns inherent to manual delineation of PET-imaged lung lesions in a setting with complete ground truth.

MATERIALS AND METHODS

Images being used for assessment consisted of 26 synthetic PET datasets created by using the anthropomorphic Zubal phantom in conjunction with the Monte Carlo based SimSET computational package. Each dataset included one PET-positive lesion differing in shape, dimension, uptake heterogeneity, and anatomical location inside the lung. Target contours were provided by 10 raters and the contour accuracy was evaluated using 12 metrics from five categories - spatial overlap, pair counting, information theory, distance, and volume.

RESULTS

In terms of spatial overlap, manual contouring results intersect substantially with the ground truth whereas tend to oversegment the lesions. Shapes of the segmented tumor volumes are in general geometrically consistent with the ground truth but lack sensitivity in characterizing topographical details. No complete consensus could be achieved between manual contours and the ground truth for any of the given lesions being examined when assessing using pair counting- and informatics-based metrics thus indicating an intrinsic stochastic component of manual contouring. Evaluation based on metrics related to distance and volume demonstrated that it is at the borderline areas between the lesions and the normal tissues where the majority part of manual delineation errors occurred and the extent of volume being identified false positively as cancerous by the raters is appreciable.

CONCLUSION

Quantification of segmentation errors associated with expert manual contouring of PET positive lesion in the lung reveals general patterns in what otherwise might be thought of as randomness. Findings from the current study may allow for the formation of new hypotheses towards improving the accuracy and precision of manual delineation of PET positive tumor targets in the lung.

Can Laws Be a Potential PET Image Texture Analysis Approach for Evaluation of Tumor Heterogeneity and Histopathological Characteristics in NSCLC?

We investigated the association between the textural features obtained from ¹⁸F-FDG images, metabolic parameters (SUVmax_, SUVmean, MTV, TLG), and tumor histopathological characteristics (stage and Ki-67 proliferation index) in non-small cell lung cancer (NSCLC). The FDG-PET images of 67 patients with NSCLC were evaluated. MATLAB technical computing language was employed in the extraction of 137 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), and Laws' texture filters. Textural features and metabolic parameters were statistically analyzed in terms of good discrimination power between tumor stages, and selected features/parameters were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). We showed that one textural feature (gray-level nonuniformity, GLN) obtained using GLRLM approach and nine textural features using Laws' approach were successful in discriminating all tumor stages, unlike metabolic parameters. There were significant correlations between Ki-67 index and some of the textural features computed using Laws' method (r = 0.6, p = 0.013). In terms of automatic classification of tumor stage, the accuracy was approximately 84% with k-NN classifier (k = 3) and SVM, using selected five features. Texture analysis of FDG-PET images has a potential to be an objective tool to assess tumor histopathological characteristics. The textural features obtained using Laws' approach could be useful in the discrimination of tumor stage.

The role of 18F-FDG-PET/CT in predicting the histopathological response in locally advanced cervical carcinoma treated by chemo-radiotherapy followed by radical surgery: a prospective study

PURPOSE

This prospective study aimed to evaluate whether ¹⁸F-FDG-PET/CT performed before, during and after neoadjuvant chemo-radiotherapy (CRT) could predict histopathological response in patients with locally advanced cervical cancer (LACC) treated with CRT followed by radical surgery.

METHODS

Between October 2010 and June 2014, 88 patients with LACC were enrolled. For each patient, three ¹⁸F-FDG-PET/CT scans (baseline, early and final) were acquired and evaluated by qualitative and quantitative analysis. Maximum standardized uptake value (SUV_max), SUV_mean, metabolic tumor volume (MTV) and total lesion glycolysis (TLG) were measured as absolute values and their percentage variation (delta) (early vs. baseline and final vs. baseline). The role of ¹⁸F-FDG-PET/CT in predicting lymph node (LN) residual disease was evaluated by qualitative analysis only. Histopathology was the reference standard.

RESULTS

At histopathology, 40 patients had complete response (CR, pR0), 48 had partial response (PR: 21 microscopic [pR1] and 27 macroscopic [pR2]). At baseline, SUV_max and SUV_mean were significantly higher in pR0 than in pR1-pR2 patients. At early evaluation, MTV and TLG were significantly higher in pR1-pR2 than in pR0 patients. At final evaluation, SUV_max, SUV_mean and TLG were significantly higher in pR1-pR2 than in pR0 patients. Delta SUV parameters and delta TLG were significantly lower in PR group both during and after CRT. Delta MTV was significantly lower in patients with PR in the early phase only. In receiver operating characteristic (ROC) curve analysis, baseline SUV_mean, early delta TLG, and final delta SUV_max better discriminated PR, providing 83.3%, 67.6% and 85% positive predictive value (PPV) and 60.3%, 90% and 70.8% negative predictive value (NPV), respectively. For LN assessment, high NPV was observed at early and final ¹⁸F-FDG-PET/CT (93.5% and 92.3%, respectively).

CONCLUSION

In LACC patients treated with CRT followed by surgery, early variations in metabolic parameters effectively discriminate histopathological PR of the primary tumor, suggesting the potential role of ¹⁸F-FDG-PET/CT in early personalized treatment. The high NPV of early and final PET/CT could enable "tailored surgery" by avoiding lymphadenectomy in selected patients.

Does Measurement of First-Order and Heterogeneity Parameters Improve Response Assessment of Bone Metastases in Breast Cancer Compared to SUVmax in [18F]fluoride and [18F]FDG PET?

PURPOSE

To establish whether first-order statistical features from [18F]fluoride and 2-deoxy-2-[18F] fluoro-D-glucose ([18F]FDG) positron emission tomography/x-ray computed tomography (PET/CT) demonstrate incremental value in skeletal metastasis response assessment compared with maximum standardised uptake value (SUVmax).

PROCEDURES

Sixteen patients starting endocrine treatment for de novo or progressive breast cancer bone metastases were prospectively recruited to undergo [18F]fluoride and [18F]FDG PET/CT scans before and 8 weeks after treatment. Percentage changes in SUV parameters, metabolic tumour volume (MTV), total lesion metabolism (TLM), standard deviation (SD), entropy, uniformity and absolute changes in kurtosis and skewness, from the same ≤ 5 index lesions, were measured. Clinical response to 24 weeks, assessed by two experienced oncologists blinded to PET/CT imaging findings, was used as a reference standard and associations were made between parameters and progression free and overall survival.

RESULTS

[18F]fluoride PET/CT: In four patients (20 lesions) with progressive disease (PD), TLM and kurtosis predicted PD better than SUVmax on a patient basis (4, 4 and 3 out of 4, respectively) and TLM, entropy, uniformity and skewness on a lesion basis (18, 16, 16, 18 and 15 out of 20, respectively). Kurtosis was independently associated with PFS (p = 0.033) and OS (p = 0.008) on Kaplan-Meier analysis. [18F]FDG PET: No parameter provided incremental value over SUVmax in predicting PD or non-PD. TLM was significantly associated with OS (p = 0.041) and skewness with PFS (p = 0.005). Interlesional heterogeneity of response was seen in 11/16 and 8/16 patients on [18F]fluoride and [18F]FDG PET/CT, respectively.

CONCLUSION

With [18F]fluoride PET/CT, some first-order features, including those that take into account lesion volume but also some heterogeneity parameters, provide incremental value over SUVmax in predicting clinical response and survival in breast cancer patients with bone metastases treated with endocrine therapy. With [18F]FDG PET/CT, no first-order parameters were more accurate than SUVmax although TLM and skewness were associated with OS and PFS, respectively. Intra-patient heterogeneity of response occurs commonly between metastases with both tracers and most parameters.

A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk

Background

Breast ductal carcinoma in situ (DCIS) represent approximately 20% of screen-detected breast cancers. The overall risk for DCIS patients treated with breast-conserving surgery stems almost exclusively from local recurrence. Although a mastectomy or adjuvant radiation can reduce recurrence risk, there are significant concerns regarding patient over-/under-treatment. Current clinicopathological markers are insufficient to accurately assess the recurrence risk. To address this issue, we developed a novel machine learning (ML) pipeline to predict risk of ipsilateral recurrence using digitized whole slide images (WSI) and clinicopathologic long-term outcome data from a retrospectively collected cohort of DCIS patients (n = 344) treated with lumpectomy at Nottingham University Hospital, UK.

Methods

The cohort was split case-wise into training (n = 159, 31 with 10-year recurrence) and validation (n = 185, 26 with 10-year recurrence) sets. The sections from primary tumors were stained with H&E, then digitized and analyzed by the pipeline. In the first step, a classifier trained manually by pathologists was applied to digital slides to annotate the areas of stroma, normal/benign ducts, cancer ducts, dense lymphocyte region, and blood vessels. In the second step, a recurrence risk classifier was trained on eight select architectural and spatial organization tissue features from the annotated areas to predict recurrence risk.

Results

The recurrence classifier significantly predicted the 10-year recurrence risk in the training [hazard ratio (HR) = 11.6; 95% confidence interval (CI) 5.3–25.3, accuracy (Acc) = 0.87, sensitivity (Sn) = 0.71, and specificity (Sp) = 0.91] and independent validation [HR = 6.39 (95% CI 3.0–13.8), p < 0.0001;Acc = 0.85, Sn = 0.5, Sp = 0.91] cohorts. Despite the limitations of our cohorts, and in some cases inferior sensitivity performance, our tool showed superior accuracy, specificity, positive predictive value, concordance, and hazard ratios relative to tested clinicopathological variables in predicting recurrences (p < 0.0001). Furthermore, it significantly identified patients that might benefit from additional therapy (validation cohort p = 0.0006).

Conclusions

Our machine learning-based model fills an unmet clinical need for accurately predicting the recurrence risk for lumpectomy-treated DCIS patients.

Electronic supplementary material

The online version of this article (10.1186/s13058-019-1165-5) contains supplementary material, which is available to authorized users.

FDG-PET Imaging in Cervical Cancer

FDG-PET/CT has an established role in the initial staging of locally advanced cervical cancers, particularly in evaluation of nodal disease and distant metastases. It is common practice to perform FDG-PET/CT 3 months postcompletion of chemoradiotherapy as it can predict outcome and be used to tailor management, including adjuvant therapy and follow-up. It is also routinely used prior to pelvic exenterative surgery to ensure there is no disease outside the pelvis. There is growing evidence that FDG-PET-derived parameters are prognostic and could potentially be used to tailor therapy. This review outlines the use of FDG-PET/CT imaging in cervical cancer.

Predictive Role of Temporal Changes in Intratumoral Metabolic Heterogeneity During Palliative Chemotherapy in Patients with Advanced Pancreatic Cancer: A Prospective Cohort Study

Metabolic intratumoral heterogeneity (ITH) is known to be related to cancer treatment outcome. However, information on the temporal changes in metabolic ITH during chemotherapy and the correlations between metabolic changes and treatment outcomes in patients with pancreatic cancer is sparse. We aimed to analyze the temporal changes in metabolic ITH and the predictive role of its changes in advanced pancreatic cancer patients who underwent palliative chemotherapy. Methods: We prospectively enrolled patients with unresectable locally advanced or metastatic pancreatic cancer before first-line palliative chemotherapy. ¹⁸F-FDG PET was performed at baseline and at the first response follow-up. SUVs, volumetric parameters, and textural features of the primary pancreatic tumor were analyzed. Relationships between the parameters at baseline and first follow-up were assessed, as well as changes in the parameters with treatment response, progression-free survival (PFS), and overall survival (OS). Results: Among 63 enrolled patients, the best objective response rate was 25.8% (95% confidence interval [CI], 14.6%-37.0%). The median PFS and OS were 7.1 mo (95% CI, 5.1-9.7 mo) and 10.1 mo (95% CI, 8.6-12.7 mo), respectively. Most parameters changed significantly during the first-line chemotherapy, in a way of reducing ITH. Metabolic ITH was more profoundly reduced in responders than in nonresponders. Multiple Cox regression analysis identified high baseline compacity (P = 0.023) and smaller decreases in SUV_peak (P = 0.007) and entropy gray-level cooccurrence matrix (P = 0.033) to be independently associated with poor PFS. Patients with a high carbohydrate antigen 19-9 (P = 0.042), high pretreatment SUV_peak (P = 0.008), and high coefficient of variance at first follow-up (P = 0.04) showed worse OS. Conclusion: Reduction in metabolic ITH during palliative chemotherapy in advanced pancreatic cancer patients is associated with treatment response and might be predictive of PFS and OS.

Prediction of local relapse and distant metastasis in patients with definitive chemoradiotherapy-treated cervical cancer by deep learning from [18F]-fluorodeoxyglucose positron emission tomography/computed tomography

BACKGROUND

We designed a deep learning model for assessing ¹⁸F-FDG PET/CT for early prediction of local and distant failures for patients with locally advanced cervical cancer.

METHODS

All 142 patients with cervical cancer underwent ¹⁸F-FDG PET/CT for pretreatment staging and received allocated treatment. To augment the amount of image data, each tumor was represented as 11 slice sets each of which contains 3 2D orthogonal slices to acquire a total of 1562 slice sets. In each round of k-fold cross-validation, a well-trained proposed model and a slice-based optimal threshold were derived from a training set and used to classify each slice set in the test set into the categories of with or without local or distant failure. The classification results of each tumor were aggregated to summarize a tumor-based prediction result.

RESULTS

In total, 21 and 26 patients experienced local and distant failures, respectively. Regarding local recurrence, the tumor-based prediction result summarized from all test sets demonstrated that the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 71%, 93%, 63%, 95%, and 89%, respectively. The corresponding values for distant metastasis were 77%, 90%, 63%, 95%, and 87%, respectively.

CONCLUSION

This is the first study to use deep learning model for assessing ¹⁸F-FDG PET/CT images which is capable of predicting treatment outcomes in cervical cancer patients.

KEY POINTS

• This is the first study to use deep learning model for assessing ¹⁸ F-FDG PET/CT images which is capable of predicting treatment outcomes in cervical cancer patients. • All 142 patients with cervical cancer underwent ¹⁸ F-FDG PET/CT for pretreatment staging and received allocated treatment. To augment the amount of image data, each tumor was represented as 11 slice sets each of which contains 3 2D orthogonal slices to acquire a total of 1562 slice sets. • For local recurrence, all test sets demonstrated that the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 71%, 93%, 63%, 95%, and 89%, respectively. The corresponding values for distant metastasis were 77%, 90%, 63%, 95%, and 87%, respectively.

A review on radiomics and the future of theranostics for patient selection in precision medicine

The growing complexity and volume of clinical data and the associated decision-making processes in oncology promote the advent of precision medicine. Precision (or personalised) medicine describes preventive and/or treatment procedures that take individual patient variability into account when proscribing treatment, and has been hindered in the past by the strict requirements of accurate, robust, repeatable and preferably non-invasive biomarkers to stratify both the patient and the disease. In oncology, tumour subtypes are traditionally measured through repeated invasive biopsies, which are taxing for the patient and are cost and labour intensive. Quantitative analysis of routine clinical imaging provides an opportunity to capture tumour heterogeneity non-invasively, cost-effectively and on large scale. In current clinical practice radiological images are qualitatively analysed by expert radiologists whose interpretation is known to suffer from inter- and intra-operator variability. Radiomics, the high-throughput mining of image features from medical images, provides a quantitative and robust method to assess tumour heterogeneity, and radiomics-based signatures provide a powerful tool for precision medicine in cancer treatment. This study aims to provide an overview of the current state of radiomics as a precision medicine decision support tool. We first provide an overview of the requirements and challenges radiomics currently faces in being incorporated as a tool for precision medicine, followed by an outline of radiomics' current applications in the treatment of various types of cancer. We finish with a discussion of possible future advances that can further develop radiomics as a precision medicine tool.

Quantitative radiomics: Validating image textural features for oncological PET in lung cancer

BACKGROUND AND PURPOSE

Radiomics textural features derived from PET imaging are of broad and current interest due to recent evidence of their prognostic value during cancer management. An inherent assumption is the link between these imaging features and the underlying tumoral phenotypic spatial heterogeneity. The purpose of this work was to validate this assumption for tumors within the lung through a comparison of image based textural features and the ground truth activity distribution from which the images were created. A second purpose was to assess the level at which PET imaging introduces spatial texture not present in the associated ground truth activity distribution.

MATERIALS AND METHODS

25 lung lesions were created using an anthropomorphic phantom. Ten of the lesions had a spherical shape with a uniform activity distribution. The remaining 15 had an irregular shape with a heterogeneous activity distribution. PET images were created for each lesion using Monte Carlo simulation. 79 textural features related to the gray-level intensity histograms, co-occurrence matrices, neighborhood difference matrices, run length, and size zone matrices were derived from both the simulated PET images and ground truth activity maps. A comparison was made between the two datasets using statistical analysis.

RESULTS

For homogenous lesions, features extracted from the PET images were largely irrelevant to the underlying uniform activity distribution. Additionally, the majority of these features assumed substantial values implying that an extensive amount of spatial texture had been introduced into the final imaging data. For heterogeneous lesions, complex trends were observed in the deviation between features extracted from PET images and those extracted from the ground truth activity maps. Moreover, the extent of both the deviation and the associated dynamic range was seen to be greatly feature-dependent.

CONCLUSION

The use of image based textural features as a surrogate for tumoral phenotypic spatial heterogeneity could not be clearly validated. The association between the two is complex and a significant amount of uncertainty exist due to the introduction of incidental texture during image acquisition and reconstruction.

Predicting IDH genotype in gliomas using FET PET radiomics

Mutations in the isocitrate dehydrogenase (IDH mut) gene have gained paramount importance for the prognosis of glioma patients. To date, reliable techniques for a preoperative evaluation of IDH genotype remain scarce. Therefore, we investigated the potential of O-(2-[18F]fluoroethyl)-L-tyrosine (FET) PET radiomics using textural features combined with static and dynamic parameters of FET uptake for noninvasive prediction of IDH genotype. Prior to surgery, 84 patients with newly diagnosed and untreated gliomas underwent FET PET using a standard scanner (15 of 56 patients with IDH mut) or a dedicated high-resolution hybrid PET/MR scanner (11 of 28 patients with IDH mut). Static, dynamic and textural parameters of FET uptake in the tumor area were evaluated. Diagnostic accuracy of the parameters was evaluated using the neuropathological result as reference. Additionally, FET PET and textural parameters were combined to further increase the diagnostic accuracy. The resulting models were validated using cross-validation. Independent of scanner type, the combination of standard PET parameters with textural features increased significantly diagnostic accuracy. The highest diagnostic accuracy of 93% for prediction of IDH genotype was achieved with the hybrid PET/MR scanner. Our findings suggest that the combination of conventional FET PET parameters with textural features provides important diagnostic information for the non-invasive prediction of the IDH genotype.

Textural features of cervical cancers on FDG-PET/CT associate with survival and local relapse in patients treated with definitive chemoradiotherapy

We retrospectively reviewed the records of 142 patients with stage IB–IIIB cervical cancer who underwent ¹⁸F-FDG-PET/CT before external beam radiotherapy plus intracavitary brachytherapy and concurrent chemotherapy. The patients were divided into training and validation cohorts to confirm the reliability of predictors for recurrence. Kaplan–Meier analysis was performed and a Cox regression model was used to examine the effects of variables on overall survival (OS), progression-free survival (PFS), distant metastasis-free survival (DMFS), and pelvic relapse-free survival (PRFS). High gray-level run emphasis (HGRE) derived from gray-level run-length matrix most accurately and consistently predicted the presence of pelvic residual or recurrent tumors for both cohorts. In multivariate analysis, stages IIIA–IIIB (P = 0.001, hazard ratio [HR] = 4.07) and a low HGRE (P < 0.0001, HR = 4.34) were prognostic factors for low OS, whereas a low HGRE (P = 0.001, HR = 2.86) and nonsquamous cell histology (P = 0.003, HR = 2.76) were prognostic factors for inferior PFS. The nonsquamous cell histology (P < 0.0001, HR = 9.19) and a low HGRE (P = 0.001, HR = 4.69) were predictors for low PRFS. In cervical cancer patients receiving definitive chemoradiotherapy, pretreatment textural features on ¹⁸F-FDG-PET/CT can supplement the prognostic information.

Quantitative Radiomics: Impact of Pulse Sequence Parameter Selection on MRI-Based Textural Features of the Brain

Objectives

Radiomic features extracted from diverse MRI modalities have been investigated regarding their predictive and/or prognostic value in a variety of cancers. With the aid of a 3D realistic digital MRI phantom of the brain, the aim of this study was to examine the impact of pulse sequence parameter selection on MRI-based textural parameters of the brain.

Methods

MR images of the employed digital phantom were realized with SimuBloch, a simulation package made for fast generation of image sequences based on the Bloch equations. Pulse sequences being investigated consisted of spin echo (SE), gradient echo (GRE), spoiled gradient echo (SP-GRE), inversion recovery spin echo (IR-SE), and inversion recovery gradient echo (IR-GRE). Twenty-nine radiomic textural features related, respectively, to gray-level intensity histograms (GLIH), cooccurrence matrices (GLCOM), zone size matrices (GLZSM), and neighborhood difference matrices (GLNDM) were evaluated for the obtained MR realizations, and differences were identified.

Results

It was found that radiomic features vary considerably among images generated by the five different T1-weighted pulse sequences, and the deviations from those measured on the T1 map vary among features, from a few percent to over 100%. Radiomic features extracted from T1-weighted spin-echo images with TR varying from 360 ms to 620 ms and TE = 3.4 ms showed coefficients of variation (CV) up to 45%, while up to 70%, for T2-weighted spin-echo images with TE varying over the range 60-120 ms and TR = 6400 ms.

Conclusion

Variability of radiologic textural appearance on MR realizations with respect to the choice of pulse sequence and imaging parameters is feature-dependent and can be substantial. It calls for caution in employing MRI-derived radiomic features especially when pooling imaging data from multiple institutions with intention of correlating with clinical endpoints.

A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy

PURPOSE

Individualization of therapeutic outcomes in NSCLC radiotherapy is likely to be compromised by the lack of proper balance of biophysical factors affecting both tumor local control (LC) and side effects such as radiation pneumonitis (RP), which are likely to be intertwined. Here, we compare the performance of separate and joint outcomes predictions for response-adapted personalized treatment planning.

METHODS

A total of 118 NSCLC patients treated on prospective protocols with 32 cases of local progression and 20 cases of RP grade 2 or higher (RP2) were studied. Sixty-eight patients with 297 features before and during radiotherapy were used for discovery and 50 patients were reserved for independent testing. A multiobjective Bayesian network (MO-BN) approach was developed to identify important features for joint LC/RP2 prediction using extended Markov blankets as inputs to develop a BN predictive structure. Cross-validation (CV) was used to guide the MO-BN structure learning. Area under the free-response receiver operating characteristic (AU-FROC) curve was used to evaluate joint prediction performance.

RESULTS

Important features including single nucleotide polymorphisms (SNPs), micro RNAs, pretreatment cytokines, pretreatment PET radiomics together with lung and tumor gEUDs were selected and their biophysical inter-relationships with radiation outcomes (LC and RP2) were identified in a pretreatment MO-BN. The joint LC/RP2 prediction yielded an AU-FROC of 0.80 (95% CI: 0.70-0.86) upon internal CV. This improved to 0.85 (0.75-0.91) with additional two SNPs, changes in one cytokine and two radiomics PET image features through the course of radiotherapy in a during-treatment MO-BN. This MO-BN model outperformed combined single-objective Bayesian networks (SO-BNs) during-treatment [0.78 (0.67-0.84)]. AU-FROC values in the evaluation of the MO-BN and individual SO-BNs on the testing dataset were 0.77 and 0.68 for pretreatment, and 0.79 and 0.71 for during-treatment, respectively.

CONCLUSIONS

MO-BNs can reveal possible biophysical cross-talks between competing radiotherapy clinical endpoints. The prediction is improved by providing additional during-treatment information. The developed MO-BNs can be an important component of decision support systems for personalized response-adapted radiotherapy.

Magnetic resonance imaging (MRI)-based radiomics for prostate cancer radiotherapy

In radiotherapy (RT) of prostate cancer, dose escalation has been shown to reduce biochemical failure. Dose escalation only to determinate prostate tumor habitats has the potential to improve tumor control with less toxicity than when the entire prostate is dose escalated. Other issues in the treatment of the RT patient include the choice of the RT technique (hypo- or standard fractionation) and the use and length of concurrent/adjuvant androgen deprivation therapy (ADT). Up to 50% of high-risk men demonstrate biochemical failure suggesting that additional strategies for defining and treating patients based on improved risk stratification are required. The use of multiparametric MRI (mpMRI) is rapidly gaining momentum in the management of prostate cancer because of its improved diagnostic potential and its ability to combine functional and anatomical information. Currently, the Prostate Imaging, Reporting and Diagnosis System (PIRADS) is the standard of care for region of interest (ROI) identification and risk classification. However, PIRADS was not designed for 3D tumor volume delineation; there is a large degree of subjectivity and PIRADS does not accurately and reproducibly elucidate inter- and intra-lesional spatial heterogeneity. "Radiomics", as it refers to the extraction and analysis of large number of advanced quantitative radiological features from medical images using high throughput methods, is perfectly suited as an engine to effectively sift through the multiple series of prostate mpMRI sequences and quantify regions of interest. The radiomic efforts can be summarized in two main areas: (I) detection/segmentation of the suspicious lesion; and (II) assessment of the aggressiveness of prostate cancer. As related to RT, the goal of the latter is in particular to identify patients at high risk for metastatic disease; and the aim of the former is to identify and segment cancerous lesions and thus provide targets for radiation boost. The article is structured as follows: first, we describe the radiomic approach; and second, we discuss the radiomic pipeline as tailored for RT of prostate cancer. In this process we summarize the current efforts and progress in integrating mpMRI radiomics into the radiotherapeutic management of prostate cancer with emphasis placed on its role in treatment target definition, treatment plan strategizing, and prognostic assessment. The described concepts, methods and tools are not currently applicable to the radiation oncology practice outside of the research setting. More data are required in the form of clinical trials to assess the robustness of radiomics-based predictive models, and to maximize the efficacy of these models.

Radiomics in Nuclear Medicine Applied to Radiation Therapy: Methods, Pitfalls, and Challenges

Radiomics is a recent area of research in precision medicine and is based on the extraction of a large variety of features from medical images. In the field of radiation oncology, comprehensive image analysis is crucial to personalization of treatments. A better characterization of local heterogeneity and the shape of the tumor, depicting individual cancer aggressiveness, could guide dose planning and suggest volumes in which a higher dose is needed for better tumor control. In addition, noninvasive imaging features that could predict treatment outcome from baseline scans could help the radiation oncologist to determine the best treatment strategies and to stratify patients as at low risk or high risk of recurrence. Nuclear medicine molecular imaging reflects information regarding biological processes in the tumor thanks to a wide range of radiotracers. Many studies involving ¹⁸F-fluorodeoxyglucose positron emission tomography suggest an added value of radiomics compared with the use of conventional PET metrics such as standardized uptake value for both tumor diagnosis and prediction of recurrence or treatment outcome. However, these promising results should not hide technical difficulties that still currently prevent the approach from being widely studied or clinically used. These difficulties mostly pertain to the variability of the imaging features as a function of the acquisition device and protocol, the robustness of the models with respect to that variability, and the interpretation of the radiomic models. Addressing the impact of the variability in acquisition and reconstruction protocols is needed, as is harmonizing the radiomic feature calculation methods, to ensure the reproducibility of studies in a multicenter context and their implementation in a clinical workflow. In this review, we explain the potential impact of positron emission tomography radiomics for radiation therapy and underline the various aspects that need to be carefully addressed to make the most of this promising approach.

Evaluation of radiomic texture feature error due to MRI acquisition and reconstruction: A simulation study utilizing ground truth

The purpose of this study was to examine the dependence of image texture features on MR acquisition parameters and reconstruction using a digital MR imaging phantom. MR signal was simulated in a parallel imaging radiofrequency coil setting as well as a single element volume coil setting, with varying levels of acquisition noise, three acceleration factors, and four image reconstruction algorithms. Twenty-six texture features were measured on the simulated images, ground truth images, and clinical brain images. Subtle algorithm-dependent errors were observed on reconstructed phantom images, even in the absence of added noise. Sources of image error include Gibbs ringing at image edge gradients (tissue interfaces) and well-known artifacts due to high acceleration; two of the iterative reconstruction algorithms studied were able to mitigate these image errors. The difference of the texture features from ground truth, and their variance over reconstruction algorithm and parallel imaging acceleration factor, were compared to the clinical "effect size", i.e., the feature difference between high- and low-grade tumors on T1- and T2-weighted brain MR images of twenty glioma patients. The measured feature error (difference from ground truth) was small for some features, but substantial for others. The feature variance due to reconstruction algorithm and acceleration factor were generally smaller than the clinical effect size. Certain texture features may be preserved by MR imaging, but adequate precautions need to be taken regarding their validity and reliability. We present a general simulation framework for assessing the robustness and accuracy of radiomic textural features under various MR acquisition/reconstruction scenarios.

Prediction of cervical cancer recurrence using textural features extracted from 18F-FDG PET images acquired with different scanners

Objectives

To identify an imaging signature predicting local recurrence for locally advanced cervical cancer (LACC) treated by chemoradiation and brachytherapy from baseline ¹⁸F-FDG PET images, and to evaluate the possibility of gathering images from two different PET scanners in a radiomic study.

Methods

118 patients were included retrospectively. Two groups (G1, G2) were defined according to the PET scanner used for image acquisition. Eleven radiomic features were extracted from delineated cervical tumors to evaluate: (i) the predictive value of features for local recurrence of LACC, (ii) their reproducibility as a function of the scanner within a hepatic reference volume, (iii) the impact of voxel size on feature values.

Results

Eight features were statistically significant predictors of local recurrence in G1 (p < 0.05). The multivariate signature trained in G2 was validated in G1 (AUC=0.76, p<0.001) and identified local recurrence more accurately than SUV_max (p=0.022). Four features were significantly different between G1 and G2 in the liver. Spatial resampling was not sufficient to explain the stratification effect.

Conclusion

This study showed that radiomic features could predict local recurrence of LACC better than SUV_max. Further investigation is needed before applying a model designed using data from one PET scanner to another.

Development of a Fully Cross-Validated Bayesian Network Approach for Local Control Prediction in Lung Cancer

The purpose of this study is to demonstrate that a Bayesian network (BN) approach can explore hierarchical biophysical relationships that influence tumor response and predict tumor local control (LC) in non-small-cell lung cancer (NSCLC) patients before and during radiotherapy from a large-scale dataset. Our BN building approach has two steps. First, relevant biophysical predictors influencing LC before and during the treatment are selected through an extended Markov blanket (eMB) method. From this eMB process, the most robust BN structure for LC prediction was found via a wrapper-based approach. Sixty-eight patients with complete feature information were used to identify a full BN model for LC prediction before and during the treatment. Fifty more recent patients with some missing information were reserved for independent testing of the developed pre- and during-therapy BNs. A nested cross-validation (N-CV) was developed to evaluate the performance of the two-step BN approach. An ensemble BN model is generated from the N-CV sampling process to assess its similarity with the corresponding full BN model, and thus evaluate the sensitivity of our BN approach. Our results show that the proposed BN development approach is a stable and robust approach to identify hierarchical relationships among biophysical features for LC prediction. Furthermore, BN predictions can be improved by incorporating during treatment information.

Selected PET radiomic features remain the same

Purpose

We investigated whether PET radiomic features are affected by differences in the scanner, scan protocol, and lesion location using ¹⁸F-FDG PET/CT and PET/MR scans.

Results

SUV, TMR, skewness, kurtosis, entropy, and homogeneity strongly correlated between PET/CT and PET/MR images. SUVs were significantly higher on PET/MR_{0-2 min} and PET/MR_{0-10 min} than on PET/CT in gynecological cancer (p = 0.008 and 0.008, respectively), whereas no significant difference was observed between PET/CT, PET/MR_{0–2 min}, and PET/MR_{0–10 min} images in oral cavity/oropharyngeal cancer. TMRs on PET/CT, PET/MR_{0–2 min}, and PET/MR_{0–10 min} increased in this order in gynecological cancer and oral cavity/oropharyngeal cancer. In contrast to conventional and histogram indices, 4 textural features (entropy, homogeneity, SRE, and LRE) were not significantly different between PET/CT, PET/MR_{0–2 min}, and PET/MR_{0–10 min} images.

Conclusions

¹⁸F-FDG PET radiomic features strongly correlated between PET/CT and PET/MR images. Dixon-based attenuation correction on PET/MR images underestimated tumor tracer uptake more significantly in oral cavity/oropharyngeal cancer than in gynecological cancer. ¹⁸F-FDG PET textural features were affected less by differences in the scanner and scan protocol than conventional and histogram features, possibly due to the resampling process using a medium bin width.

Methods

Eight patients with gynecological cancer and 7 with oral cavity/oropharyngeal cancer underwent a whole-body ¹⁸F-FDG PET/CT scan and regional PET/MR scan in one day. PET/MR scans were performed for 10 minutes in the list mode, and PET/CT and 0–2 min and 0–10 min PET/MR images were reconstructed. The standardized uptake value (SUV), tumor-to-muscle SUV ratio (TMR), skewness, kurtosis, entropy, homogeneity, short-run emphasis (SRE), and long-run emphasis (LRE) were compared between PET/CT, PET/MR_{0-2 min}, and PET/MR_{0-10 min} images.

Tumor radiomic heterogeneity: Multiparametric functional imaging to characterize variability and predict response following cervical cancer radiation therapy

BACKGROUND

Robust approaches to quantify tumor heterogeneity are needed to provide early decision support for precise individualized therapy.

PURPOSE

To conduct a technical exploration of longitudinal changes in tumor heterogeneity patterns on dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI), diffusion-weighted imaging (DWI) and FDG positron emission tomography / computed tomography (PET/CT), and their association to radiation therapy (RT) response in cervical cancer.

STUDY TYPE

Prospective observational study with longitudinal MRI and PET/CT pre-RT, early-RT (2 weeks), and mid-RT (5 weeks).

POPULATION

Twenty-one FIGO IB₂ -IVA cervical cancer patients receiving definitive external beam RT and brachytherapy.

FIELD STRENGTH/SEQUENCE

1.5T, precontrast axial T₁ -weighted, axial and sagittal T₂ -weighted, sagittal DWI (multi-b values), sagittal DCE MRI (<10 sec temporal resolution), postcontrast axial T₁ -weighted.

ASSESSMENT

Response assessment 1 month after completion of treatment by a board-certified radiation oncologist from manually delineated tumor volume changes.

STATISTICAL TESTS

Intensity histogram (IH) quantiles (DCE SI_10% and DWI ADC_10% , FDG-PET SUV_max ) and distribution moments (mean, variance, skewness, kurtosis) were extracted. Differences in IH features between timepoints and modalities were evaluated by Skillings-Mack tests with Holm's correction. Area under receiver-operating characteristic curve (AUC) and Mann-Whitney testing was performed to discriminate treatment response using IH features.

RESULTS

Tumor IH means and quantiles varied significantly during RT (SUV_mean : ↓28-47%, SUV_max : ↓30-59%, SI_mean : ↑8-30%, SI_10% : ↑8-19%, ADC_mean : ↑16%, P < 0.02 for each). Among IH heterogeneity features, FDG-PET SUV_CoV (↓16-30%, P = 0.011) and DW-MRI ADC_skewness decreased (P = 0.001). FDG-PET SUV_CoV was higher than DCE-MRI SI_CoV and DW-MRI ADC_CoV at baseline (P < 0.001) and 2 weeks (P = 0.010). FDG-PET SUV_kurtosis was lower than DCE-MRI SI_kurtosis and DW-MRI ADC_kurtosis at baseline (P = 0.001). Some IH features appeared to associate with favorable tumor response, including large early RT changes in DW-MRI ADC_skewness (AUC = 0.86).

DATA CONCLUSION

Preliminary findings show tumor heterogeneity was variable between patients, modalities, and timepoints. Radiomic assessment of changing tumor heterogeneity has the potential to personalize treatment and power outcome prediction.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:1388-1396.