MITK-ModelFit: A generic open-source framework for model fits and their exploration in medical imaging - design, implementation and application on the example of DCE-MRI

aXonica: A support package for MRI based Neuroimaging

Magnetic Resonance Imaging (MRI) assists in studying the nervous system. MRI scans undergo significant processing before presenting the final images to medical practitioners. These processes are executed with ease due to excellent software pipelines. However, establishing software workstations is non-trivial and requires researchers in life sciences to be comfortable in downloading, installing, and scripting software that is non-user-friendly and may lack basic GUI. As researchers struggle with these skills, there is a dire need to develop software packages that can automatically install software pipelines speeding up building software workstations and laboratories. Previous solutions include NeuroDebian, BIDS Apps, Flywheel, QMENTA, Boutiques, Brainlife and Neurodesk. Overall, all these solutions complement each other. NeuroDebian covers neuroscience and has a wider scope, providing only 51 tools for MRI. Whereas, BIDS Apps is committed to the BIDS format, covering only 45 software related to MRI. Boutiques is more flexible, facilitating its pipelines to be easily installed as separate containers, validated, published, and executed. Whereas, both Flywheel and Qmenta are propriety, leaving four for users looking for 'free for use' tools, i.e., NeuroDebian, Brainlife, Neurodesk, and BIDS Apps. This paper presents an extensive survey of 317 tools published in MRI-based neuroimaging in the last ten years, along with 'aXonica,' an MRI-based neuroimaging support package that is unbiased towards any formatting standards and provides 130 applications, more than that of NeuroDebian (51), BIDS App (45), Flywheel (70), and Neurodesk (85). Using a technology stack that employs GUI as the front-end and shell scripted back-end, aXonica provides (i) 130 tools that span the entire MRI-based neuroimaging analysis, and allow the user to (ii) select the software of their choice, (iii) automatically resolve individual dependencies and (iv) installs them. Hence, aXonica can serve as an important resource for researchers and teachers working in the field of MRI-based Neuroimaging to (a) develop software workstations, and/or (b) install newer tools in their existing workstations.

Efficient estimation of pharmacokinetic parameters from breast dynamic contrast-enhanced MRI based on a convolutional neural network for predicting molecular subtypes

Objective. Tracer kinetic models allow for estimating pharmacokinetic (PK) parameters, which are related to pathological characteristics, from breast dynamic contrast-enhanced magnetic resonance imaging. However, existing tracer kinetic models subject to inaccuracy are time-consuming for PK parameters estimation. This study aimed to accurately and efficiently estimate PK parameters for predicting molecular subtypes based on convolutional neural network (CNN).Approach. A CNN integrating global and local features (GL-CNN) was trained using synthetic data where known PK parameters map was used as the ground truth, and subsequently used to directly estimate PK parameters (volume transfer constantKtransand flux rate constantKep) map. The accuracy assessed by the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and concordance correlation coefficient (CCC) was compared between the GL-CNN and Tofts-based PK parameters in synthetic data. Radiomic features were calculated from the PK parameters map in 208 breast tumors. A random forest classifier was constructed to predict molecular subtypes using a discovery cohort (n= 144). The diagnostic performance evaluated on a validation cohort (n= 64) using the area under the receiver operating characteristic curve (AUC) was compared between the GL-CNN and Tofts-based PK parameters.Main results. The average PSNR (48.8884), SSIM (0.9995), and CCC (0.9995) between the GL-CNN-basedKtransmap and ground truth were significantly higher than those between the Tofts-basedKtransmap and ground truth. The GL-CNN-basedKtransobtained significantly better diagnostic performance (AUCs = 0.7658 and 0.8528) than the Tofts-basedKtransfor luminal B and HER2 tumors. The GL-CNN method accelerated the computation by speed approximately 79 times compared to the Tofts method for the whole breast of all patients.Significance. Our results indicate that the GL-CNN method can be used to accurately and efficiently estimate PK parameters for predicting molecular subtypes.

A Quantitative Multiparametric MRI Analysis Platform for Estimation of Robust Imaging Biomarkers in Clinical Oncology

There is a need to develop user-friendly imaging tools estimating robust quantitative biomarkers (QIBs) from multiparametric (mp)MRI for clinical applications in oncology. Quantitative metrics derived from (mp)MRI can monitor and predict early responses to treatment, often prior to anatomical changes. We have developed a vendor-agnostic, flexible, and user-friendly MATLAB-based toolkit, MRI-Quantitative Analysis and Multiparametric Evaluation Routines ("MRI-QAMPER", current release v3.0), for the estimation of quantitative metrics from dynamic contrast-enhanced (DCE) and multi-b value diffusion-weighted (DW) MR and MR relaxometry. MRI-QAMPER's functionality includes generating numerical parametric maps from these methods reflecting tumor permeability, cellularity, and tissue morphology. MRI-QAMPER routines were validated using digital reference objects (DROs) for DCE and DW MRI, serving as initial approval stages in the National Cancer Institute Quantitative Imaging Network (NCI/QIN) software benchmark. MRI-QAMPER has participated in DCE and DW MRI Collaborative Challenge Projects (CCPs), which are key technical stages in the NCI/QIN benchmark. In a DCE CCP, QAMPER presented the best repeatability coefficient (RC = 0.56) across test-retest brain metastasis data, out of ten participating DCE software packages. In a DW CCP, QAMPER ranked among the top five (out of fourteen) tools with the highest area under the curve (AUC) for prostate cancer detection. This platform can seamlessly process mpMRI data from brain, head and neck, thyroid, prostate, pancreas, and bladder cancer. MRI-QAMPER prospectively analyzes dose de-escalation trial data for oropharyngeal cancer, which has earned it advanced NCI/QIN approval for expanded usage and applications in wider clinical trials.

Open source code for the generation of digital reference objects for dynamic contrast-enhanced MRI analysis software validation

OBJECTIVES

Dynamic contrast-enhanced MR images can be analyzed through the application of a wide range of kinetic models. This process is prone to variability and a lack of standardization that can affect the measured metrics. There is a need for customized digital reference objects (DROs) for the validation of DCE-MRI software packages that undertake kinetic model analysis. DROs are currently available only for a small subset of the kinetic models commonly applied to DCE-MRI data. This work aimed to address this gap.

METHODS

Code was written in the MATLAB programming environment to generate customizable DROs. This modular code allows the insertion of a plug-in to describe the kinetic model to be tested. We input our generated DROs into three commercial and open-source analysis packages and assessed the agreement of kinetic model parameter values output with the 'ground-truth' values used in the DRO generation.

RESULTS

For the five kinetic models tested, the concordance correlation coefficient values were >98%, indicating excellent agreement of the results with 'ground-truth'.

CONCLUSIONS

Testing our DROs on three independent software packages produced concordant results, strongly suggesting our DRO generation code is correct. This implies that our DROs can be used to validate other third party software for the kinetic model analysis of DCE-MRI data.

ADVANCES IN KNOWLEDGE

This work extends published work of others to allow customized generation of test objects for any applied kinetic model and allows the incorporation of B1 mapping into the DRO for application at higher field strengths.

calf - Software for CEST Analysis with Lorentzian Fitting

Analysis of chemical exchange saturation transfer (CEST) MRI data requires sophisticated methods to obtain reliable results about metabolites in the tissue under study. CEST generates z-spectra with multiple components, each originating from individual molecular groups. The individual lines with Lorentzian line shape are mostly overlapping and disturbed by various effects. We present an elaborate method based on an adaptive nonlinear least squares algorithm that provides robust quantification of z-spectra and incorporates prior knowledge in the fitting process. To disseminate CEST to the research community, we developed software as part of this study that runs on the Microsoft Windows operating system and will be made freely available to the community. Special attention has been paid to establish a low entrance threshold and high usability, so that even less experienced users can successfully analyze CEST data.

qMRI-BIDS: An extension to the brain imaging data structure for quantitative magnetic resonance imaging data

The Brain Imaging Data Structure (BIDS) established community consensus on the organization of data and metadata for several neuroimaging modalities. Traditionally, BIDS had a strong focus on functional magnetic resonance imaging (MRI) datasets and lacked guidance on how to store multimodal structural MRI datasets. Here, we present and describe the BIDS Extension Proposal 001 (BEP001), which adds a range of quantitative MRI (qMRI) applications to the BIDS. In general, the aim of qMRI is to characterize brain microstructure by quantifying the physical MR parameters of the tissue via computational, biophysical models. By proposing this new standard, we envision standardization of qMRI through multicenter dissemination of interoperable datasets. This way, BIDS can act as a catalyst of convergence between qMRI methods development and application-driven neuroimaging studies that can help develop quantitative biomarkers for neural tissue characterization. In conclusion, this BIDS extension offers a common ground for developers to exchange novel imaging data and tools, reducing the entrance barrier for qMRI in the field of neuroimaging.

Physics-informed neural networks for myocardial perfusion MRI quantification

Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data with multi-compartment exchange models is desirable, as they are physiologically plausible and resolve directly for blood flow and microvascular function. However, the reliability of model fitting is limited by the low signal-to-noise ratio, temporal resolution, and acquisition length. This may result in inaccurate parameter estimates. This study introduces physics-informed neural networks (PINNs) as a means to perform myocardial perfusion MR quantification, which provides a versatile scheme for the inference of kinetic parameters. These neural networks can be trained to fit the observed perfusion MR data while respecting the underlying physical conservation laws described by a multi-compartment exchange model. Here, we provide a framework for the implementation of PINNs in myocardial perfusion MR. The approach is validated both in silico and in vivo. In the in silico study, an overall decrease in mean-squared error with the ground-truth parameters was observed compared to a standard non-linear least squares fitting approach. The in vivo study demonstrates that the method produces parameter values comparable to those previously found in literature, as well as providing parameter maps which match the clinical diagnosis of patients.

DCE-MRI detected vascular permeability changes in the rat spinal cord do not explain shorter latency times for paresis after carbon ions relative to photons

BACKGROUND AND PURPOSE

Radiation-induced myelopathy, an irreversible complication occurring after a long symptom-free latency time, is preceded by a fixed sequence of magnetic resonance- (MR-) visible morphological alterations. Vascular degradation is assumed the main reason for radiation-induced myelopathy. We used dynamic contrast-enhanced (DCE-) MRI to identify different vascular changes after photon and carbon ion irradiation, which precede or coincide with morphological changes.

MATERIALS AND METHODS

The cervical spinal cord of rats was irradiated with iso-effective photon or carbon (¹²C-)ion doses. Afterwards, animals underwent frequent DCE-MR imaging until they developed symptomatic radiation-induced myelopathy (paresis II). Measurements were performed at certain time points: 1 month, 2 months, 3 months, 4 months, and 6 months after irradiation, and when animals showed morphological (such as edema/syrinx/contrast agent (CA) accumulation) or neurological alterations (such as, paresis I, and paresis II). DCE-MRI data was analyzed using the extended Toft's model.

RESULTS

Fit quality improved with gradual disintegration of the blood spinal cord barrier (BSCB) towards paresis II. Vascular permeability increased three months after photon irradiation, and rapidly escalated after animals showed MR-visible morphological changes until paresis II. After ¹²C-ion irradiation, vascular permeability increased when animals showed morphological alterations and increased further until animals had paresis II. The volume transfer constant and the plasma volume showed no significant changes.

CONCLUSION

Only after photon irradiation, DCE-MRI provides a temporal advantage in detecting early physiological signs in radiation-induced myelopathy compared to morphological MRI. As a generally lower level of vascular permeability after ¹²C-ions led to an earlier development of paresis as compared to photons, we conclude that other mechanisms dominate the development of paresis II.

PAGAT gel dosimetry for everyone: gel production, measurement and evaluation

Polymer gel (PG) dosimetry is a valuable tool to measure complex dose distributions in 3D with a high spatial resolution. However, due to complex protocols that need to be followed for in-house produced PGs and the high costs of commercially available gels, PG gels are only rarely applied in quality assurance procedures worldwide. In this work, we provide an introduction to perform highly standardized dosimetric PG experiments using PAGAT (PolyAcrylamide Gelatine gel fabricated at ATmospheric conditions) dosimetry gel. PAGAT gel can be produced at atmospheric conditions, at low costs and is evaluated using magnetic resonance imaging (MRI). The conduction of PG experiments is described in great detail including the gel production, treatment planning, irradiation, MRI evaluation and post-processing procedure. Furthermore, a plugin in an open source image processing tool for post-processing is provided free of charge that allows a standardized and reproducible analysis of PG experiments.

Analysis Protocol for Dynamic Contrast Enhanced (DCE) MRI of Renal Perfusion and Filtration

Here we present an analysis protocol for dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) data of the kidneys. It covers comprehensive steps to facilitate signal to contrast agent concentration mapping via T1 mapping and the calculation of renal perfusion and filtration parametric maps using model-free approaches, model free analysis using deconvolution, the Toft's model and a Bayesian approach.This chapter is based upon work from the COST Action PARENCHIMA, a community-driven network funded by the European Cooperation in Science and Technology (COST) program of the European Union, which aims to improve the reproducibility and standardization of renal MRI biomarkers. This analysis protocol chapter is complemented by two separate chapters describing the basic concept and experimental procedure.

De-Identification of Facial Features in Magnetic Resonance Images: Software Development Using Deep Learning Technology

Background

High-resolution medical images that include facial regions can be used to recognize the subject’s face when reconstructing 3-dimensional (3D)-rendered images from 2-dimensional (2D) sequential images, which might constitute a risk of infringement of personal information when sharing data. According to the Health Insurance Portability and Accountability Act (HIPAA) privacy rules, full-face photographic images and any comparable image are direct identifiers and considered as protected health information. Moreover, the General Data Protection Regulation (GDPR) categorizes facial images as biometric data and stipulates that special restrictions should be placed on the processing of biometric data.

Objective

This study aimed to develop software that can remove the header information from Digital Imaging and Communications in Medicine (DICOM) format files and facial features (eyes, nose, and ears) at the 2D sliced-image level to anonymize personal information in medical images.

Methods

A total of 240 cranial magnetic resonance (MR) images were used to train the deep learning model (144, 48, and 48 for the training, validation, and test sets, respectively, from the Alzheimer's Disease Neuroimaging Initiative [ADNI] database). To overcome the small sample size problem, we used a data augmentation technique to create 576 images per epoch. We used attention-gated U-net for the basic structure of our deep learning model. To validate the performance of the software, we adapted an external test set comprising 100 cranial MR images from the Open Access Series of Imaging Studies (OASIS) database.

Results

The facial features (eyes, nose, and ears) were successfully detected and anonymized in both test sets (48 from ADNI and 100 from OASIS). Each result was manually validated in both the 2D image plane and the 3D-rendered images. Furthermore, the ADNI test set was verified using Microsoft Azure's face recognition artificial intelligence service. By adding a user interface, we developed and distributed (via GitHub) software named “Deface program” for medical images as an open-source project.

Conclusions

We developed deep learning–based software for the anonymization of MR images that distorts the eyes, nose, and ears to prevent facial identification of the subject in reconstructed 3D images. It could be used to share medical big data for secondary research while making both data providers and recipients compliant with the relevant privacy regulations.

High Doses of Photons and Carbon Ions Comparably Increase Vascular Permeability in R3327-HI Prostate Tumors: A Dynamic Contrast-Enhanced MRI Study

Carbon- (12C-) ion radiotherapy exhibits enhanced biological effectiveness compared to photon radiotherapy, however, the contribution of its interaction with the vasculature remains debatable. The effect of high-dose 12C-ion and photon irradiation on vascular permeability in moderately differentiated rat prostate tumors was compared using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Syngeneic R3327-HI rat prostate tumors were irradiated with a single dose of either 18 or 37 Gy 12C ions, or 37 or 75 Gy 6-MV photons (sub-curative and curative dose levels, respectively). DCE-MRI was performed one day prior to and 3, 7, 14 and 21 days postirradiation. Voxel-based tumor concentration-time curves were clustered based on their curve shape and treatment response was assessed as the longitudinal changes in the relative abundance per cluster. Radiation-induced vascular damage and increased permeability occurred at day 7 postirradiation for all treatment groups except for the 75 Gy photon-irradiated group, where the onset of vascular damage was delayed until day 14. No differences between irradiation modalities were found. Therefore, early vascular damage cannot explain the higher effectiveness of 12C ions relative to photons in terms of local tumor control for this moderately differentiated prostate tumor and the applied single high doses.

Impact of Single Dose Photons and Carbon Ions on Perfusion and Vascular Permeability: A Dynamic Contrast-Enhanced MRI Pilot Study in the Anaplastic Rat Prostate Tumor R3327-AT1

We collected initial quantitative information on the effects of high-dose carbon (¹²C) ions compared to photons on vascular damage in anaplastic rat prostate tumors, with the goal of elucidating differences in response to high-LET radiation, using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Syngeneic R3327-AT1 rat prostate tumors received a single dose of either 16 or 37 Gy ¹²C ions or 37 or 85 Gy 6 MV photons (iso-absorbed and iso-effective doses, respectively). The animals underwent DCE-MRI prior to, and on days 3, 7, 14 and 21 postirradiation. The extended Tofts model was used for pharmacokinetic analysis. At day 21, tumors were dissected and histologically examined. The results of this work showed the following: 1. ¹²C ions led to stronger vascular changes compared to photons, independent of dose; 2. Tumor growth was comparable for all radiation doses and modalities until day 21; 3. Nonirradiated, rapidly growing control tumors showed a decrease in all pharmacokinetic parameters (area under the curve, K_trans, v_e, v_p) over time; 4. ¹²C-ion-irradiated tumors showed an earlier increase in area under the curve and K_trans than photon-irradiated tumors; 5. ¹²C-ion irradiation resulted in more homogeneous parameter maps and histology compared to photons; and 6. ¹²C-ion irradiation led to an increased microvascular density and decreased proliferation activity in a largely dose-independent manner compared to photons. Postirradiation changes related to ¹²C ions and photons were detected using DCE-MRI, and correlated with histological parameters in an anaplastic experimental prostate tumor. In summary, this pilot study demonstrated that exposure to ¹²C ions increased the perfusion and/or permeability faster and led to larger changes in DCE-MRI parameters resulting in increased vessel density and presumably less hypoxia at the end of the observation period when compared to photons. Within this study no differences were found between curative and sub-curative doses in either modality.

Bayesian pharmacokinetic modeling of dynamic contrast-enhanced magnetic resonance imaging: validation and application

Tracer-kinetic analysis of dynamic contrast-enhanced magnetic resonance imaging data is commonly performed with the well-known Tofts model and nonlinear least squares (NLLS) regression. This approach yields point estimates of model parameters, uncertainty of these estimates can be assessed e.g. by an additional bootstrapping analysis. Here, we present a Bayesian probabilistic modeling approach for tracer-kinetic analysis with a Tofts model, which yields posterior probability distributions of perfusion parameters and therefore promises a robust and information-enriched alternative based on a framework of probability distributions. In this manuscript, we use the quantitative imaging biomarkers alliance (QIBA) Tofts phantom to evaluate the Bayesian tofts model (BTM) against a bootstrapped NLLS approach. Furthermore, we demonstrate how Bayesian posterior probability distributions can be employed to assess treatment response in a breast cancer DCE-MRI dataset using Cohen's d. Accuracy and precision of the BTM posterior distributions were validated and found to be in good agreement with the NLLS approaches, and assessment of therapy response with respect to uncertainty in parameter estimates was found to be excellent. In conclusion, the Bayesian modeling approach provides an elegant means to determine uncertainty via posterior distributions within a single step and provides honest information about changes in parameter estimates.

Bolus arrival time estimation in dynamic contrast-enhanced magnetic resonance imaging of small animals based on spline models

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is used to quantify perfusion and vascular permeability. In most cases a bolus arrival time (BAT) delay exists between the arterial input function (AIF) and the contrast agent arrival in the tissue of interest which needs to be estimated. Existing methods for BAT estimation are tailored to tissue concentration curves, which have a fast upslope to the peak as frequently observed in patient data. However, they may give poor results for curves that do not have this characteristic shape such as tissue concentration curves of small animals. In this paper, we propose a method for BAT estimation of signals that do not have a fast upslope to their peak. The model is based on splines which are able to adapt to a large variety of concentration curves. Furthermore, the method estimates BATs on a continuous time scale. All relevant model parameters are automatically determined by generalized cross validation. We use simulated concentration curves of small animal and patient settings to assess the accuracy and robustness of our approach. The proposed method outperforms a state-of-the-art method for small animal data and it gives competitive results for patient data. Finally, it is tested on in vivo acquired rat data where accuracy of BAT estimation was also improved upon the state-of-the-art method. The results indicate that the proposed method is suitable for accurate BAT estimation of DCE-MRI data, especially for small animals.

Feasibility and robustness of dynamic 18F-FET PET based tracer kinetic models applied to patients with recurrent high-grade glioma prior to carbon ion irradiation

The aim of this study was to analyze the robustness and diagnostic value of different compartment models for dynamic 18F-FET PET in recurrent high-grade glioma (HGG). Dynamic 18F-FET PET data of patients with recurrent WHO grade III (n:7) and WHO grade IV (n: 9) tumors undergoing re-irradiation with carbon ions were analyzed by voxelwise fitting of the time-activity curves with a simplified and an extended one-tissue compartment model (1TCM) and a two-tissue compartment model (2TCM), respectively. A simulation study was conducted to assess robustness and precision of the 2TCM. Parameter maps showed enhanced detail on tumor substructure. Neglecting the blood volume VB in the 1TCM yields insufficient results. Parameter K1 from both 1TCM and 2TCM showed correlation with overall patient survival after carbon ion irradiation (p = 0.043 and 0.036, respectively). The 2TCM yields realistic estimates for tumor blood volume, which was found to be significantly higher in WHO IV compared to WHO III (p = 0.031). Simulations on the 2TCM showed that K1 yields good accuracy and robustness while k2 showed lowest stability of all parameters. The 1TCM provides the best compromise between parameter stability and model accuracy; however application of the 2TCM is still feasible and provides a more accurate representation of tracer-kinetics at the cost of reduced robustness. Detailed tracer kinetic analysis of 18F-FET PET with compartment models holds valuable information on tumor substructures and provides additional diagnostic and prognostic value.