QIN DAWG Validation of Gradient Nonlinearity Bias Correction Workflow for Quantitative Diffusion-Weighted Imaging in Multicenter Trials

Variabilities in apparent diffusion coefficient (ADC) measurements of the spleen and the paraspinal muscle: A single center large cohort study

Purpose

Evaluation of the variabilities in apparent diffusion coefficient (ADC) measurements of the spleen (ADC_spleen) and the paraspinal muscles (ADC_muscle) to identify the reference organ for normalizing the ADC from the abdominal diffusion weighted imaging (DWI).

Methods

Two MRI scanners, with 314 abdominal exams on the GE and 929 on the Siemens system, were used for MRI examinations including DWI (b-values, 50 and 800 s/mm²). For a subset of 73 exams on the Siemens system a second exam was conducted. Four regions of interest (ROIs) in each exam were placed to measure the ADC_spleen and the bilateral ADC_muscle. ADC variability between patients (on each scanner separately), ADC variability due to ROI placement between the two ROIs in each organ, and variability in the subset between the first and second exams were assessed.

Results

The ADC_spleen was more scattered and variable than the ADC_muscle in the comparability (n = 929 and 314 for two MRI scanners, respectively) and repeatability (n = 73) datasets. The Bland-Altmann bias and limits of agreement (LoAs) for the ADC_spleen (ICC, 0.47; CV, 0.070) and ADC_muscle (ICC, 0.67; CV, 0.023) in the repeatability datasets (n = 73) were -0.1 (-25.7%-25.6%) and -0.3 (-8.8%-8.1%), respectively. For the Siemens system, the Bland-Altmann bias and LoAs for the ADC_spleen (ICC, 0.72; CV, 0.061) and ADC_muscle (ICC, 0.53; CV, 0.030) in the comparability datasets (n = 929) were 2.1 (-20.0%-24.2%) and 0.7 (-10.0%-11.4%), respectively. Similar findings have been found in the GE system (n = 314). The CVs for the ADC_muscle measurements were lower than those of the ADC_spleen both in the repeatability and the comparability analyses (all p < 0.001).

Conclusion

Paraspinal muscles demonstrate better reference characteristics than the spleen in estimating ADC variability of abdominal DWI.

Diffusion-Weighted Imaging of the Abdomen: Correction for Gradient Nonlinearity Bias in Apparent Diffusion Coefficient

BACKGROUND

Gradient nonlinearity (GNL) introduces spatial nonuniformity bias in apparent diffusion coefficient (ADC) measurements, especially at large offsets from the magnet isocenter.

PURPOSE

To investigate the effects of GNL in abdominal ADC measurements and to develop an ADC bias correction procedure.

STUDY TYPE

Retrospective.

PHANTOM/POPULATION

Two homemade ultrapure water phantoms/25 patients with histologically confirmed pancreatic ductal adenocarcinoma (PDAC).

FIELD STRENGTH/SEQUENCE

A 3.0 T/diffusion-weighted imaging (DWI) with single-shot echo-planar imaging sequence.

ASSESSMENT

ADC bias was computed in the three orthogonal directions at different offset locations. The spatial-dependent correctors of ADC bias were generated from the ADCs of phantom 1. The ADCs were estimated before and after corrections for the phantom 1 with both the proposed approach and the theoretical GNL correction method. For the patients, ADCs were measured in abdominal tissues including left and right liver lobes, PDAC, spleen, bilateral kidneys, and bilateral paraspinal muscles.

STATISTICAL TEST

Friedman tests and Wilcoxon tests.

RESULTS

The ADC bias measured by phantom 1 was 9.7% and 12.6% higher in the right-left and anterior-posterior directions and 9.2% lower in the superior-inferior direction at the 150 mm offsets from the magnetic isocenter. The corrected vs. the uncorrected ADCs measurements (median: 2.20 × 10^-3  mm² /sec for both the proposed method and the theoretical GNL method vs. 2.31 × 10^-3  mm² /sec, respectively) and their relative ADC errors (0.014, 0.016, and 0.054, respectively) were lower in the phantom 1. The relative ADC errors substantially decreased after correction in the phantom 2 (median: 0.048 and -0.008, respectively). The ADCs of all the abdominal tissues were lower after correction except for the left liver lobes (P = 0.13).

DATA CONCLUSION

GNL bias in abdominal ADC can be measured by a DWI phantom. The proposed correction procedure was successfully applied for the bias correction in abdominal ADC.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 1.

Co-Clinical Imaging Resource Program (CIRP): Bridging the Translational Divide to Advance Precision Medicine

The National Institutes of Health’s (National Cancer Institute) precision medicine initiative emphasizes the biological and molecular bases for cancer prevention and treatment. Importantly, it addresses the need for consistency in preclinical and clinical research. To overcome the translational gap in cancer treatment and prevention, the cancer research community has been transitioning toward using animal models that more fatefully recapitulate human tumor biology. There is a growing need to develop best practices in translational research, including imaging research, to better inform therapeutic choices and decision-making. Therefore, the National Cancer Institute has recently launched the Co-Clinical Imaging Research Resource Program (CIRP). Its overarching mission is to advance the practice of precision medicine by establishing consensus-based best practices for co-clinical imaging research by developing optimized state-of-the-art translational quantitative imaging methodologies to enable disease detection, risk stratification, and assessment/prediction of response to therapy. In this communication, we discuss our involvement in the CIRP, detailing key considerations including animal model selection, co-clinical study design, need for standardization of co-clinical instruments, and harmonization of preclinical and clinical quantitative imaging pipelines. An underlying emphasis in the program is to develop best practices toward reproducible, repeatable, and precise quantitative imaging biomarkers for use in translational cancer imaging and therapy. We will conclude with our thoughts on informatics needs to enable collaborative and open science research to advance precision medicine.

Retrospective Correction of ADC for Gradient Nonlinearity Errors in Multicenter Breast DWI Trials: ACRIN6698 Multiplatform Feasibility Study

The presented analysis of multisite, multiplatform clinical oncology trial data sought to enhance quantitative utility of the apparent diffusion coefficient (ADC) metric, derived from diffusion-weighted magnetic resonance imaging, by reducing technical interplatform variability owing to systematic gradient nonlinearity (GNL). This study tested the feasibility and effectiveness of a retrospective GNL correction (GNC) implementation for quantitative quality control phantom data, as well as in a representative subset of 60 subjects from the ACRIN 6698 breast cancer therapy response trial who were scanned on 6 different gradient systems. The GNL ADC correction based on a previously developed formalism was applied to trace-DWI using system-specific gradient-channel fields derived from vendor-provided spherical harmonic tables. For quantitative DWI phantom images acquired in typical breast imaging positions, the GNC improved interplatform accuracy from a median of 6% down to 0.5% and reproducibility of 11% down to 2.5%. Across studied trial subjects, GNC increased low ADC (<1 µm²/ms) tumor volume by 16% and histogram percentiles by 5%–8%, uniformly shifting percentile-dependent ADC thresholds by ∼0.06 µm²/ms. This feasibility study lays the grounds for retrospective GNC implementation in multiplatform clinical imaging trials to improve accuracy and reproducibility of ADC metrics used for breast cancer treatment response prediction.

Repeatability of Apparent Diffusion Coefficient at 3.0 Tesla in Normal Pancreas

Purpose: To evaluate the apparent diffusion coefficient (ADC) test-retest repeatability of the normal pancreas based on diffusion-weighted imaging (DWI).

Methods: Twenty-six healthy volunteers (mean 47.6 years; 13 men) were included and scanned twice with reposition for a DWI sequence at 3.0-T. Two readers measured the ADCs of pancreatic head, body and tail for two DWIs, independently. The mean ADCs of the pancreatic head, body and tail were calculated as the global pancreatic ADC. Test-retest repeatability and agreement of ADC measurement were evaluated by the Bland-Altman analysis, intra-class correlation coefficient (ICC) and coefficient of variation (CV).

Results: The global pancreatic ADC showed the best test-retest repeatability (mean difference ± limits of agreement were 0.05 ± 0.25×10^-3 mm²/s; ICC, 0.79; CV, 6%). Test-retest repeatabilities for ADC of pancreatic head, body or tail were scattered, with mean difference ± limits of agreement between two tests were 0.03 ± 0.47, 0.05 ± 0.42 and 0.06 ± 0.31 (×10^-3 mm²/s) (ICCs, 0.81, 0.52 and 0.68; CVs, 9%, 8% and 8%), respectively. Both intra-observer repeatability and inter-observer reproducibility were acceptable for global pancreatic ADC between measurements of the two DWIs.

Conclusions:The best test-retest repeatability of ADC in the normal pancreas was only for the whole pancreas with a CV of 6%. Cautions should be taken in interpreting longitudinal clinical changes in ADC values of the normal pancreas for the measurements do have an inherent variability by locations.

Towards integration of 64Cu-DOTA-trastuzumab PET-CT and MRI with mathematical modeling to predict response to neoadjuvant therapy in HER2 + breast cancer

While targeted therapies exist for human epidermal growth factor receptor 2 positive (HER2 +) breast cancer, HER2 + patients do not always respond to therapy. We present the results of utilizing a biophysical mathematical model to predict tumor response for two HER2 + breast cancer patients treated with the same therapeutic regimen but who achieved different treatment outcomes. Quantitative data from magnetic resonance imaging (MRI) and 64Cu-DOTA-trastuzumab positron emission tomography (PET) are used to estimate tumor density, perfusion, and distribution of HER2-targeted antibodies for each individual patient. MRI and PET data are collected prior to therapy, and follow-up MRI scans are acquired at a midpoint in therapy. Given these data types, we align the data sets to a common image space to enable model calibration. Once the model is parameterized with these data, we forecast treatment response with and without HER2-targeted therapy. By incorporating targeted therapy into the model, the resulting predictions are able to distinguish between the two different patient responses, increasing the difference in tumor volume change between the two patients by > 40%. This work provides a proof-of-concept strategy for processing and integrating PET and MRI modalities into a predictive, clinical-mathematical framework to provide patient-specific predictions of HER2 + treatment response.

QIN Benchmarks for Clinical Translation of Quantitative Imaging Tools

The Quantitative Imaging Network of the National Cancer Institute is in its 10th year of operation, and research teams within the network are developing and validating clinical decision support software tools to measure or predict the response of cancers to various therapies. As projects progress from development activities to validation of quantitative imaging tools and methods, it is important to evaluate the performance and clinical readiness of the tools before committing them to prospective clinical trials. A variety of tests, including special challenges and tool benchmarking, have been instituted within the network to prepare the quantitative imaging tools for service in clinical trials. This article highlights the benchmarking process and provides a current evaluation of several tools in their transition from development to validation.

Consensus-based technical recommendations for clinical translation of renal diffusion-weighted MRI

Objectives

Standardization is an important milestone in the validation of DWI-based parameters as imaging biomarkers for renal disease. Here, we propose technical recommendations on three variants of renal DWI, monoexponential DWI, IVIM and DTI, as well as associated MRI biomarkers (ADC, D, D*, f, FA and MD) to aid ongoing international efforts on methodological harmonization.

Materials and methods

Reported DWI biomarkers from 194 prior renal DWI studies were extracted and Pearson correlations between diffusion biomarkers and protocol parameters were computed. Based on the literature review, surveys were designed for the consensus building. Survey data were collected via Delphi consensus process on renal DWI preparation, acquisition, analysis, and reporting. Consensus was defined as ≥ 75% agreement.

Results

Correlations were observed between reported diffusion biomarkers and protocol parameters. Out of 87 survey questions, 57 achieved consensus resolution, while many of the remaining questions were resolved by preference (65–74% agreement). Summary of the literature and survey data as well as recommendations for the preparation, acquisition, processing and reporting of renal DWI were provided.

Discussion

The consensus-based technical recommendations for renal DWI aim to facilitate inter-site harmonization and increase clinical impact of the technique on a larger scale by setting a framework for acquisition protocols for future renal DWI studies. We anticipate an iterative process with continuous updating of the recommendations according to progress in the field.

Electronic supplementary material

The online version of this article (10.1007/s10334-019-00790-y) contains supplementary material, which is available to authorized users.

Mechanism-Based Modeling of Tumor Growth and Treatment Response Constrained by Multiparametric Imaging Data

Multiparametric imaging is a critical tool in the noninvasive study and assessment of cancer. Imaging methods have evolved over the past several decades to provide quantitative measures of tumor and healthy tissue characteristics related to, for example, cell number, blood volume fraction, blood flow, hypoxia, and metabolism. Mechanistic models of tumor growth also have matured to a point where the incorporation of patient-specific measures could provide clinically relevant predictions of tumor growth and response. In this review, we identify and discuss approaches that use multiparametric imaging data, including diffusion-weighted magnetic resonance imaging, dynamic contrast-enhanced magnetic resonance imaging, diffusion tensor imaging, contrast-enhanced computed tomography, [18F]fluorodeoxyglucose positron emission tomography, and [18F]fluoromisonidazole positron emission tomography to initialize and calibrate mechanistic models of tumor growth and response. We focus the discussion on brain and breast cancers; however, we also identify three emerging areas of application in kidney, pancreatic, and lung cancers. We conclude with a discussion of the future directions for incorporating multiparametric imaging data and mechanistic modeling into clinical decision making for patients with cancer.

Multisite concordance of apparent diffusion coefficient measurements across the NCI Quantitative Imaging Network

Diffusion weighted MRI has become ubiquitous in many areas of medicine, including cancer diagnosis and treatment response monitoring. Reproducibility of diffusion metrics is essential for their acceptance as quantitative biomarkers in these areas. We examined the variability in the apparent diffusion coefficient (ADC) obtained from both postprocessing software implementations utilized by the NCI Quantitative Imaging Network and online scan time-generated ADC maps. Phantom and in vivo breast studies were evaluated for two ([Formula: see text]) and four ([Formula: see text]) [Formula: see text]-value diffusion metrics. Concordance of the majority of implementations was excellent for both phantom ADC measures and in vivo [Formula: see text], with relative biases [Formula: see text] ([Formula: see text]) and [Formula: see text] (phantom [Formula: see text]) but with higher deviations in ADC at the lowest phantom ADC values. In vivo [Formula: see text] concordance was good, with typical biases of [Formula: see text] to 3% but higher for online maps. Multiple b-value ADC implementations were separated into two groups determined by the fitting algorithm. Intergroup mean ADC differences ranged from negligible for phantom data to 2.8% for [Formula: see text] in vivo data. Some higher deviations were found for individual implementations and online parametric maps. Despite generally good concordance, implementation biases in ADC measures are sometimes significant and may be large enough to be of concern in multisite studies.

Special Section Guest Editorial: Quantitative Imaging and the Pioneering Efforts of Laurence P. Clarke

This guest editorial introduces the Special Section honoring Dr. Laurence P. Clarke.