Validation of optimal DCE-MRI perfusion threshold to classify at-risk tumor imaging voxels in heterogeneous cervical cancer for outcome prediction

Utilization of functional MRI in the diagnosis and management of cervical cancer

Introduction

Imaging is integral part of cervical cancer management. Currently, MRI is used for staging, follow up and image guided adaptive brachytherapy. The ongoing IQ-EMBRACE sub-study is evaluating the use of MRI for functional imaging to aid in the assessment of hypoxia, metabolism, hemodynamics and tissue structure. This study reviews the current and potential future utilization of functional MRI imaging in diagnosis and management of cervical cancer.

Methods

We searched PubMed for articles characterizing the uses of functional MRI (fMRI) for cervical cancer. The current literature regarding these techniques in diagnosis and outcomes for cervical cancer were then reviewed.

Results

The most used fMRI techniques identified for use in cervical cancer include diffusion weighted imaging (DWI) and dynamic contrast enhancement (DCE). DCE-MRI indirectly reflects tumor perfusion and hypoxia. This has been utilized to either characterize a functional risk volume of tumor with low perfusion or to characterize at-risk tumor voxels by analyzing signal intensity both pre-treatment and during treatment. DCE imaging in these situations has been associated with local control and disease-free survival and may have predictive/prognostic significance, however this has not yet been clinically validated. DWI allows for creation of ADC maps, that assists with diagnosis of local malignancy or nodal disease with high sensitivity and specificity. DWI findings have also been correlated with local control and overall survival in patients with an incomplete response after definitive chemoradiotherapy and thus may assist with post-treatment follow up. Other imaging techniques used in some instances are MR-spectroscopy and perfusion weighted imaging. T2-weighted imaging remains the standard technique used for diagnosis and radiation treatment planning. In many instances, it is unclear what additional information functional-MRI techniques provide compared to standard MRI imaging.

Conclusions

Functional MRI provides potential for improved diagnosis, prediction of treatment response and prognostication in cervical cancer. Specific sequences such as DCE, DWI and ADC need to be validated in a large prospective setting prior to widespread use. The ongoing IQ-EMBRACE study will provide important clinical information regarding these imaging modalities.

Artificial Intelligence and Radiomics in Head and Neck Cancer Care: Opportunities, Mechanics, and Challenges

The advent of large-scale high-performance computing has allowed the development of machine-learning techniques in oncologic applications. Among these, there has been substantial growth in radiomics (machine-learning texture analysis of images) and artificial intelligence (which uses deep-learning techniques for "learning algorithms"); however, clinical implementation has yet to be realized at scale. To improve implementation, opportunities, mechanics, and challenges, models of imaging-enabled artificial intelligence approaches need to be understood by clinicians who make the treatment decisions. This article aims to convey the basic conceptual premises of radiomics and artificial intelligence using head and neck cancer as a use case. This educational overview focuses on approaches for head and neck oncology imaging, detailing current research efforts and challenges to implementation.

PET Imaging of Tumor Perfusion: A Potential Cancer Biomarker?

Perfusion, as measured by imaging, is considered a standard of care biomarker for the evaluation of many tumors. Measurements of tumor perfusion may be used in a number of ways, including improving the visual detection of lesions, differentiating malignant from benign findings, assessing aggressiveness of tumors, identifying ischemia and by extension hypoxia within tumors, and assessing treatment response. While most clinical perfusion imaging is currently performed with CT or MR, a number of methods for PET imaging of tumor perfusion have been described. The inert PET radiotracer 15O-water PET represents the recognized gold standard for absolute quantification of tissue perfusion in both normal tissue and a variety of pathological conditions including cancer. Other cancer PET perfusion imaging strategies include the use of radiotracers with high first-pass uptake, analogous to those used in cardiac perfusion PET. This strategy produces more visually pleasing high-contrast images that provide relative rather than absolute perfusion quantification. Lastly, multiple timepoint imaging of PET tracers such as 18F-FDG, are not specifically optimized for perfusion, but have advantages related to availability, convenience, and reimbursement. Multiple obstacles have thus far blocked the routine use of PET imaging for tumor perfusion, including tracer production and distribution, image processing, patient body coverage, clinical validation, regulatory approval and reimbursement, and finally feasible clinical workflows. Fortunately, these obstacles are being overcome, especially within larger imaging centers, opening the door for PET imaging of tumor perfusion to become standard clinical practice. In the foreseeable future, it is possible that whole-body PET perfusion imaging with 15O-water will be able to be performed in a single imaging session concurrent with standard PET imaging techniques such as 18F-FDG-PET. This approach could establish an efficient clinical workflow. The resultant ability to measure absolute tumor blood flow in combination with glycolysis will provide important complementary information to inform prognosis and clinical decisions.

DCE-MRI pharmacokinetic parameter maps for cervical carcinoma prediction

Pharmacokinetic parameters estimated from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) time course data enable the physio-biological interpretation of tissue angiogenesis. This study aims to develop machine learning approaches for cervical carcinoma prediction based on pharmacokinetic parameters. The performance of individual parameters was assessed in terms of their efficacy in differentiating cancerous tissue from normal cervix tissue. The effect of combining parameters was evaluated using the following two approaches: the first approach was based on support vector machines (SVMs) to combine the parameters from one pharmacokinetic model or across several models; the second approach was based on a novel method called APITL (artificial pharmacokinetic images for transfer learning), which was designed to fully utilize the comprehensive pharmacokinetic information acquired from DCE-MRI data. A "winner-takes-all" strategy was employed to consolidate the slice-wise prediction into subject-wise prediction. Experiments were carried out with a dataset comprising 36 patients with cervical cancer and 17 healthy subjects. The results demonstrated that parameter V_e, representing volume fraction of the extracellular extravascular space (EES), attained high discriminative power regardless of the pharmacokinetic model used for estimation. An approximately 10% improvement in the accuracy was achieved with the SVM approach. The APITL method further outperformed SVM and attained a subject-wise prediction accuracy of 94.3%. Our experiment demonstrated that APITL could predict cervical carcinoma with high accuracy and had potential in clinical applications.

A histogram analysis of diffusion and perfusion features of cervical cancer based on intravoxel incoherent motion magnetic resonance imaging

OBJECTIVE

To evaluate the diagnostic potential based on histogram analysis of IVIM parameters between uterine cervical cancers (CC) - normal myometrium (Myo) versus CC - gluteus maximus muscle (GM) and to study the feasibility of histogram analysis of IVIM parameters to differentiate the early from locally advanced stage CCs.

METHODS

64 patients with pathologically confirmed CC were enrolled. Histogram indices mean, median, 25th, and ð 75th percentile of apparent diffusion coefficient (ADC), true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f) value of entire tumor were statistically analyzed and compared between CC - GM versus CC - Myo, as well as between early and locally advanced stage CCs. A multivariate analysis was performed to identify indices that could best distinguish early from locally advanced stage CC. Receiver operating characteristic curves (ROC) were used to evaluate the diagnostic efficiency of every histogram parameter.

RESULTS

All the tested histogram indices significantly differed between the patients with CC - GM vs. CC - Myo, nonetheless, CC - GM yielded higher range area under the curve (AUC) value of 0.8-0.99 vs. 0.6-0.99. The additional significant difference was found among all the tested histogram indices of D*, mean, median, and 75th percentile of f, mean and 75th percentile of ADC, and 75th percentile of D discriminating early from locally advanced CCs. ROC curves indicated that the 75th percentile of D* value 28.17 × 10^-3 mm²/s could best differentiate early from locally advanced stage CCs, with AUC of 0.776. In the multivariate analysis, ROC indicated the 50th percentile of D* and f was the most significant with AUCs of 0.856.

CONCLUSIONS

The histogram analysis of IVIM parameters depicted that gluteus maximus served better reference tissue in comparison to myometrium. The histogram index 75th percentile of ADC, D, D*, and f may serve a diagnostic biomarker to differentiate the early from locally advanced stage CCs.

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.

The value of advanced MRI techniques in the assessment of cervical cancer: a review

OBJECTIVES

To assess the value of new magnetic resonance imaging (MRI) techniques in cervical cancer.

METHODS

We searched PubMed and MEDLINE and reviewed articles published from 1990 to 2016 to identify studies that used MRI techniques, such as diffusion weighted imaging (DWI), intravoxel incoherent motion (IVIM) and dynamic contrast enhancement (DCE) MRI, to assess parametric invasion, to detect lymph node metastases, tumour subtype and grading, and to detect and predict tumour recurrence.

RESULTS

Seventy-nine studies were included. The additional use of DWI improved the accuracy and sensitivity of the evaluation of parametrial extension. Most studies reported improved detection of nodal metastases. Functional MRI techniques have the potential to assess tumour subtypes and tumour grade differentiation, and they showed additional value in detecting and predicting treatment response. Limitations included a lack of technical standardisation, which limits reproducibility.

CONCLUSIONS

New advanced MRI techniques allow improved analysis of tumour biology and the tumour microenvironment. They can improve TNM staging and show promise for tumour classification and for assessing the risk of tumour recurrence. They may be helpful for developing optimised and personalised therapy for patients with cervical cancer.

TEACHING POINTS

• Conventional MRI plays a key role in the evaluation of cervical cancer. • DWI improves tumour delineation and detection of nodal metastases in cervical cancer. • Advanced MRI techniques show promise regarding histological grading and subtype differentiation. • Tumour ADC is a potential biomarker for response to treatment.

A practical review of magnetic resonance imaging for the evaluation and management of cervical cancer

Cervical cancer is a leading cause of mortality in women worldwide. Staging and management of cervical cancer has for many years been based on clinical exam and basic imaging such as intravenous pyelogram and x-ray. Unfortunately, despite advances in radiotherapy and the inclusion of chemotherapy in the standard plan for locally advanced disease, local control has been unsatisfactory. This situation has changed only recently with the increasing implementation of magnetic resonance image (MRI)-guided brachytherapy. The purpose of this article is therefore to provide an overview of the benefits of MRI in the evaluation and management of cervical cancer for both external beam radiotherapy and brachytherapy and to provide a practical approach if access to MRI is limited.