Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra

Incidental brain tumor findings in children: prevalence, natural history, management, controversies, challenges, and dilemmas

Incidental brain tumor findings in children involve the unexpected discovery of brain lesions during imaging for unrelated reasons. These findings differ significantly from those in adults, requiring a focus on pediatric-specific approaches in neurosurgery, neuroimaging, and neuro-oncology. Understanding the prevalence, progression, and management of these incidentalomas is crucial for informed decision-making, balancing patient welfare with the risks and benefits of intervention. Incidental brain tumors are observed in about 0.04-5.7% of cases, with most suspected low-grade lesions in children showing a benign course, though up to 3% may undergo malignant transformation. Treatment decisions are influenced by factors such as patient age, tumor characteristics, and family anxiety, with conservative management through surveillance often preferred. However, upfront surgery may be considered in cases with low surgical risk. Initial follow-up typically involves a comprehensive MRI after three months, with subsequent scans spaced out if the lesion remains stable. Changes in imaging or symptoms during follow-up could indicate malignant transformation, prompting consideration of surgery or biopsy. Several challenges and controversies persist, including the role of upfront biopsy for molecular profiling, the use of advanced imaging techniques like PET-CT and magnetic resonance spectroscopy, and the implications of the child's age at diagnosis. These issues highlight the need for further research to guide management and improve outcomes in pediatric patients with incidental brain tumor findings.

Characterisation of paediatric brain tumours by their MRS metabolite profiles

1H-magnetic resonance spectroscopy (MRS) has the potential to improve the noninvasive diagnostic accuracy for paediatric brain tumours. However, studies analysing large, comprehensive, multicentre datasets are lacking, hindering translation to widespread clinical practice. Single-voxel MRS (point-resolved single-voxel spectroscopy sequence, 1.5 T: echo time [TE] 23-37 ms/135-144 ms, repetition time [TR] 1500 ms; 3 T: TE 37-41 ms/135-144 ms, TR 2000 ms) was performed from 2003 to 2012 during routine magnetic resonance imaging for a suspected brain tumour on 340 children from five hospitals with 464 spectra being available for analysis and 281 meeting quality control. Mean spectra were generated for 13 tumour types. Mann-Whitney U-tests and Kruskal-Wallis tests were used to compare mean metabolite concentrations. Receiver operator characteristic curves were used to determine the potential for individual metabolites to discriminate between specific tumour types. Principal component analysis followed by linear discriminant analysis was used to construct a classifier to discriminate the three main central nervous system tumour types in paediatrics. Mean concentrations of metabolites were shown to differ significantly between tumour types. Large variability existed across each tumour type, but individual metabolites were able to aid discrimination between some tumour types of importance. Complete metabolite profiles were found to be strongly characteristic of tumour type and, when combined with the machine learning methods, demonstrated a diagnostic accuracy of 93% for distinguishing between the three main tumour groups (medulloblastoma, pilocytic astrocytoma and ependymoma). The accuracy of this approach was similar even when data of marginal quality were included, greatly reducing the proportion of MRS excluded for poor quality. Children's brain tumours are strongly characterised by MRS metabolite profiles readily acquired during routine clinical practice, and this information can be used to support noninvasive diagnosis. This study provides both key evidence and an important resource for the future use of MRS in the diagnosis of children's brain tumours.

Proton MR spectroscopy shows improved performance to segregate high-grade astrocytoma subgroups when defined with the new 2021 World Health Organization classification of central nervous system tumors

OBJECTIVES

The 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors prioritizes isocitrate dehydrogenase (IDH) mutation to define tumor types in diffuse gliomas, in contrast to the 2016 classification, which prioritized histological features. Our objective was to investigate the influence of this change in the performance of proton MR spectroscopy (1H-MRS) in segregating high-grade diffuse astrocytoma subgroups.

METHODS

Patients with CNS WHO grade 3 and 4 diffuse astrocytoma, known IDH mutation status, and available 1H-MRS were retrospectively retrieved and divided into 4 groups based on IDH mutation status and histological grade. Differences in 1H-MRS between groups were analyzed with the Kruskal-Wallis test. The points on the spectrum that showed the greatest differences were chosen to evaluate the performance of 1H-MRS in discriminating between grades 3 and 4 tumors (WHO 2016 defined), and between IDH-mutant and IDH-wildtype tumors (WHO 2021). ROC curves were constructed with these points, and AUC values were calculated and compared.

RESULTS

The study included 223 patients with high-grade diffuse astrocytoma. Discrimination between IDH-mutant and IDH-wildtype tumors showed higher AUC values (highest AUC short TE, 0.943; long TE, 0.864) and more noticeable visual differences than the discrimination between grade 3 and 4 tumors (short TE, 0.885; long TE, 0.838).

CONCLUSION

Our findings suggest that 1H-MRS is more applicable to classify high-grade astrocytomas defined with the 2021 criteria. Improved metabolomic robustness and more homogeneous groups yielded better tumor type discrimination by 1H-MRS with the new criteria.

CLINICAL RELEVANCE STATEMENT

The 2021 World Health Organization classification of brain tumors empowers molecular criteria to improve tumor characterization. This derives in greater segregation of high-grade diffuse astrocytoma subgroups by MR spectroscopy and warrants further development of brain tumor classification tools with spectroscopy.

KEY POINTS

• The new 2021 updated World Health Organization classification of central nervous system tumors maximizes the role of molecular diagnosis in the classification of brain tumors. • Proton MR spectroscopy performs better to segregate high-grade astrocytoma subgroups when defined with the new criteria. • The study provides additional evidence of improved metabolic characterization of brain tumor subgroups with the new criteria.

Early pseudoprogression and progression lesions in glioblastoma patients are both metabolically heterogeneous

The standard treatment in glioblastoma includes maximal safe resection followed by concomitant radiotherapy plus chemotherapy and adjuvant temozolomide. The first follow-up study to evaluate treatment response is performed 1 month after concomitant treatment, when contrast-enhancing regions may appear that can correspond to true progression or pseudoprogression. We retrospectively evaluated 31 consecutive patients at the first follow-up after concomitant treatment to check whether the metabolic pattern assessed with multivoxel MRS was predictive of treatment response 2 months later. We extracted the underlying metabolic patterns of the contrast-enhancing regions with a blind-source separation method and mapped them over the reference images. Pattern heterogeneity was calculated using entropy, and association between patterns and outcomes was measured with Cramér's V. We identified three distinct metabolic patterns-proliferative, necrotic, and responsive, which were associated with status 2 months later. Individually, 70% of the patients showed metabolically heterogeneous patterns in the contrast-enhancing regions. Metabolic heterogeneity was not related to the regions' size and only stable patients were less heterogeneous than the rest. Contrast-enhancing regions are also metabolically heterogeneous 1 month after concomitant treatment. This could explain the reported difficulty in finding robust pseudoprogression biomarkers.

A multivariate curve resolution analysis of multicenter proton spectroscopic imaging of the prostate for cancer localization and assessment of aggressiveness

In this study, we investigated the potential of the multivariate curve resolution alternating least squares (MCR-ALS) algorithm for analyzing three-dimensional (3D) 1 H-MRSI data of the prostate in prostate cancer (PCa) patients. MCR-ALS generates relative intensities of components representing spectral profiles derived from a large training set of patients, providing an interpretable model. Our objectives were to classify magnetic resonance (MR) spectra, differentiating tumor lesions from benign tissue, and to assess PCa aggressiveness. We included multicenter 3D 1 H-MRSI data from 106 PCa patients across eight centers. The patient cohort was divided into a training set (N = 63) and an independent test set (N = 43). Singular value decomposition determined that MR spectra were optimally represented by five components. The profiles of these components were extracted from the training set by MCR-ALS and assigned to specific tissue types. Using these components, MCR-ALS was applied to the test set for a quantitative analysis to discriminate tumor lesions from benign tissue and to assess tumor aggressiveness. Relative intensity maps of the components were reconstructed and compared with histopathology reports. The quantitative analysis demonstrated a significant separation between tumor and benign voxels (t-test, p < 0.001). This result was achieved including voxels with low-quality MR spectra. A receiver operating characteristic analysis of the relative intensity of the tumor component revealed that low- and high-risk tumor lesions could be distinguished with an area under the curve of 0.88. Maps of this component properly identified the extent of tumor lesions. Our study demonstrated that MCR-ALS analysis of 1 H-MRSI of the prostate can reliably identify tumor lesions and assess their aggressiveness. It handled multicenter data with minimal preprocessing and without using prior knowledge or quality control. These findings indicate that MCR-ALS can serve as an automated tool to assess the presence, extent, and aggressiveness of tumor lesions in the prostate, enhancing diagnostic capabilities and treatment planning of PCa patients.

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

A comparison of non-negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

Magnetic resonance spectroscopy (MRS) is an MR technique that provides information about the biochemistry of tissues in a noninvasive way. MRS has been widely used for the study of brain tumors, both preoperatively and during follow-up. In this study, we investigated the performance of a range of variants of unsupervised matrix factorization methods of the non-negative matrix underapproximation (NMU) family, namely, sparse NMU, global NMU, and recursive NMU, and compared them with convex non-negative matrix factorization (C-NMF), which has previously shown a good performance on brain tumor diagnostic support problems using MRS data. The purpose of the investigation was 2-fold: first, to ascertain the differences among the sources extracted by these methods; and second, to compare the influence of each method in the diagnostic accuracy of the classification of brain tumors, using them as feature extractors. We discovered that, first, NMU variants found meaningful sources in terms of biological interpretability, but representing parts of the spectrum, in contrast to C-NMF; and second, that NMU methods achieved better classification accuracy than C-NMF for the classification tasks when one class was not meningioma.

Tracking Therapy Response in Glioblastoma Using 1D Convolutional Neural Networks

BACKGROUND

Glioblastoma (GB) is a malignant brain tumour that is challenging to treat, often relapsing even after aggressive therapy. Evaluating therapy response relies on magnetic resonance imaging (MRI) following the Response Assessment in Neuro-Oncology (RANO) criteria. However, early assessment is hindered by phenomena such as pseudoprogression and pseudoresponse. Magnetic resonance spectroscopy (MRS/MRSI) provides metabolomics information but is underutilised due to a lack of familiarity and standardisation.

METHODS

This study explores the potential of spectroscopic imaging (MRSI) in combination with several machine learning approaches, including one-dimensional convolutional neural networks (1D-CNNs), to improve therapy response assessment. Preclinical GB (GL261-bearing mice) were studied for method optimisation and validation.

RESULTS

The proposed 1D-CNN models successfully identify different regions of tumours sampled by MRSI, i.e., normal brain (N), control/unresponsive tumour (T), and tumour responding to treatment (R). Class activation maps using Grad-CAM enabled the study of the key areas relevant to the models, providing model explainability. The generated colour-coded maps showing the N, T and R regions were highly accurate (according to Dice scores) when compared against ground truth and outperformed our previous method.

CONCLUSIONS

The proposed methodology may provide new and better opportunities for therapy response assessment, potentially providing earlier hints of tumour relapsing stages.

Using Single-Voxel Magnetic Resonance Spectroscopy Data Acquired at 1.5T to Classify Multivoxel Data at 3T: A Proof-of-Concept Study

In vivo magnetic resonance spectroscopy (MRS) has two modalities, single-voxel (SV) and multivoxel (MV), in which one or more contiguous grids of SVs are acquired.

PURPOSE

To test whether MV grids can be classified with models trained with SV.

METHODS

Retrospective study. Training dataset: Multicenter multiformat SV INTERPRET, 1.5T. Testing dataset: MV eTumour, 3T. Two classification tasks were completed: 3-class (meningioma vs. aggressive vs. normal) and 4-class (meningioma vs. low-grade glioma vs. aggressive vs. normal). Five different methods were tested for feature selection. The classification was implemented using linear discriminant analysis (LDA), random forest, and support vector machines. The evaluation was completed with balanced error rate (BER) and area under the curve (AUC) on both sets. The accuracy in class prediction was calculated by developing a solid tumor index (STI) and segmentation accuracy with the Dice score.

RESULTS

The best method was sequential forward feature selection combined with LDA, with AUCs = 0.95 (meningioma), 0.89 (aggressive), 0.82 (low-grade glioma), and 0.82 (normal). STI was 66% (4-class task) and 71% (3-class task) because two cases failed completely and two more had suboptimal STI as defined by us.

DISCUSSION

The reasons for failure in the classification of the MV test set were related to the presence of artifacts.

Clinical Decision Support Systems for Brain Tumour Diagnosis and Prognosis: A Systematic Review

CDSSs are being continuously developed and integrated into routine clinical practice as they assist clinicians and radiologists in dealing with an enormous amount of medical data, reduce clinical errors, and improve diagnostic capabilities. They assist detection, classification, and grading of brain tumours as well as alert physicians of treatment change plans. The aim of this systematic review is to identify various CDSSs that are used in brain tumour diagnosis and prognosis and rely on data captured by any imaging modality. Based on the 2020 preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol, the literature search was conducted in PubMed and Engineering Village Compendex databases. Different types of CDSSs identified through this review include Curiam BT, FASMA, MIROR, HealthAgents, and INTERPRET, among others. This review also examines various CDSS tool types, system features, techniques, accuracy, and outcomes, to provide the latest evidence available in the field of neuro-oncology. An overview of such CDSSs used to support clinical decision-making in the management and treatment of brain tumours, along with their benefits, challenges, and future perspectives has been provided. Although a CDSS improves diagnostic capabilities and healthcare delivery, there is lack of specific evidence to support these claims. The absence of empirical data slows down both user acceptance and evaluation of the actual impact of CDSS on brain tumour management. Instead of emphasizing the advantages of implementing CDSS, it is important to address its potential drawbacks and ethical implications. By doing so, it can promote the responsible use of CDSS and facilitate its faster adoption in clinical settings.

Contribution of advanced neuro-imaging (MR diffusion, perfusion and proton spectroscopy) in differentiation between low grade gliomas GII and MR morphologically similar non neoplastic lesions

Background

Non-neoplastic brain lesions can be misdiagnosed as low-grade gliomas. Conventional magnetic resonance (MR) imaging may be non-specific. Additional imaging modalities such as spectroscopy (MRS), perfusion and diffusion imaging aid in diagnosis of such lesions. However, contradictory and overlapping results are still present. Hence, our purpose was to evaluate the role of advanced neuro-imaging in differentiation between low-grade gliomas (WHO grade II) and MR morphologically similar non-neoplastic lesions and to prove which modality has the most accurate results in differentiation.

Results

All patients were classified into two main groups: patients with low-grade glioma (n = 12; mean age, 38.8 ± 16; 8 males) and patients with non-neoplastic lesions (n = 27; mean age, 36.6 ± 15; 19 males) based on the histopathological and clinical–radiological diagnosis. Using ROC curve analysis, a threshold value of 0.93 for rCBV (AUC = 0.875, PPV = 92%, NPV = 71.4%) and a threshold value of 2.5 for Cho/NAA (AUC = 0.829, PPV = 92%, NPV = 71.4%) had 85.2% sensitivity and 83.3% specificity for predicting neoplastic lesions. The area under the curve (AUC) of ROC analysis was good for relative cerebral blood volume (rCBV) and Cho/NAA ratios (> 0.80) and fair for Cho/Cr and NAA/Cr ratios (0.70–0.80). When the rCBV measurements were combined with MRS ratios, significant improvement was observed in the area under the curve (AUC) (0.969) with improved diagnostic accuracy (89.7%) and sensitivity (88.9%).

Conclusions

Evaluation of rCBV and metabolite ratios at MRS, particularly Cho/NAA ratio, may be helpful in differentiating low-grade gliomas from non-neoplastic lesions. The combination of dynamic susceptibility contrast (DSC) perfusion and MRS can significantly improve the diagnostic accuracy and can help avoiding the need for an invasive biopsy.

Convolutional neural networks to predict brain tumor grades and Alzheimer’s disease with MR spectroscopic imaging data

Purpose

To evaluate the value of convolutional neural network (CNN) in the diagnosis of human brain tumor or Alzheimer’s disease by MR spectroscopic imaging (MRSI) and to compare its Matthews correlation coefficient (MCC) score against that of other machine learning methods and previous evaluation of the same data. We address two challenges: 1) limited number of cases in MRSI datasets and 2) interpretability of results in the form of relevant spectral regions.

Methods

A shallow CNN with only one hidden layer and an ad-hoc loss function was constructed involving two branches for processing spectral and image features of a brain voxel respectively. Each branch consists of a single convolutional hidden layer. The output of the two convolutional layers is merged and fed to a classification layer that outputs class predictions for the given brain voxel.

Results

Our CNN method separated glioma grades 3 and 4 and identified Alzheimer’s disease patients using MRSI and complementary MRI data with high MCC score (Area Under the Curve were 0.87 and 0.91 respectively). The results demonstrated superior effectiveness over other popular methods as Partial Least Squares or Support Vector Machines. Also, our method automatically identified the spectral regions most important in the diagnosis process and we show that these are in good agreement with existing biomarkers from the literature.

Conclusion

Shallow CNNs models integrating image and spectral features improved quantitative and exploration and diagnosis of brain diseases for research and clinical purposes. Software is available at https://bitbucket.org/TeslaH2O/cnn_mrsi.

High Myoinositol on Proton MR Spectroscopy Could Be a Potential Signature of Papillary Tumors of the Pineal Region-Case Report of Two Patients

Papillary tumor of the pineal region (PTPR) is an uncommon entity in which a presurgical suspicion may be crucial for patient management. Maximal safe neurosurgical resection is of choice when PTPR is suspected, whereas non-surgical approaches can be considered in other tumors of the pineal region, such as pineocytoma or concrete subtypes of germ-cell tumors. In general terms, imaging features of tumors of the pineal region have been reported to be unspecific. Nevertheless, in this report, we describe two pathology-confirmed PTPRs in which presurgical proton MR spectroscopy demonstrated extremely high myoinositol, a pattern which drastically differs from that of other pineal tumors. We hypothesize that this high myoinositol may be related to PTPR’s known ependymal component, and that it could be used as a specific non-invasive diagnostic signature.

Extraction of artefactual MRS patterns from a large database using non-negative matrix factorization

Despite the success of automated pattern recognition methods in problems of human brain tumor diagnostic classification, limited attention has been paid to the issue of automated data quality assessment in the field of MRS for neuro-oncology. Beyond some early attempts to address this issue, the current standard in practice is MRS quality control through human (expert-based) assessment. One aspect of automatic quality control is the problem of detecting artefacts in MRS data. Artefacts, whose variety has already been reviewed in some detail and some of which may even escape human quality control, have a negative influence in pattern recognition methods attempting to assist tumor characterization. The automatic detection of MRS artefacts should be beneficial for radiology as it guarantees more reliable tumor characterizations, as well as the development of more robust pattern recognition-based tumor classifiers and more trustable MRS data processing and analysis pipelines. Feature extraction methods have previously been used to help distinguishing between good and bad quality spectra to apply subsequent supervised pattern recognition techniques. In this study, we apply feature extraction differently and use a variant of a method for blind source separation, namely Convex Non-Negative Matrix Factorization, to unveil MRS signal sources in a completely unsupervised way. We hypothesize that, while most sources will correspond to the different tumor patterns, some of them will reflect signal artefacts. The experimental work reported in this paper, analyzing a combined short and long echo time ¹ H-MRS database of more than 2000 spectra acquired at 1.5T and corresponding to different tumor types and other anomalous masses, provides a first proof of concept that points to the possible validity of this approach.

1H-MR spectroscopy in grading of cerebral glioma: A new view point, MRS image quality assessment

Background

Noninvasive preoperative prediction of histological grading is essential for clinical management of cerebral glioma.

Purpose

This study aimed to investigate the association between the image quality assessment of 1H magnetic resonance spectroscopy and accurate grading of glioma.

Materials and Methods

98 glioma patients confirmed by pathology were retrospectively recruited in this single-center study. All patients underwent 1H-MRS examination at 3.0T before surgery. According to WHO standards, all cases were divided into two groups: low-grade glioma (grade I and II, 48 cases) and high-grade glioma (grades III and IV, 50 cases). The metabolite ratios in both grades were calculated before and after image quality assessment. The area under the receiver operating characteristic (ROC) curve was used to evaluate the capacity of each ratio in glioma grading.

Results

The Cho/Cr, Cho/NAA and NAA/Cr metabolite ratios had certain differences in each glioma group before and after MRS image quality assessment. In the low-grade glioma group, there was a dramatic difference in the Cho/Cr ratio before and after image quality assessment (p = 0.011). After MRS image quality assessment, the accuracy of glioma grading was significantly improved. The Cho/Cr ratio with 83.3% sensitivity and 93.7% specificity is the best index of glioma grading, with the optimal cutoff value of the Cho/Cr ratio being 3.72.

Conclusion

The image quality of MRS does affect the metabolite ratios and the results of glioma grading. MRS image quality assessment can observably improve the accuracy rate of glioma grading. The Cho/Cr ratio has the best diagnostic performance in differentiating high-grade from low-grade glioma.

Added value of magnetic resonance spectroscopy for diagnosing childhood cerebellar tumours

¹ H-magnetic resonance spectroscopy (MRS) provides noninvasive metabolite profiles with the potential to aid the diagnosis of brain tumours. Prospective studies of diagnostic accuracy and comparisons with conventional MRI are lacking. The aim of the current study was to evaluate, prospectively, the diagnostic accuracy of a previously established classifier for diagnosing the three major childhood cerebellar tumours, and to determine added value compared with standard reporting of conventional imaging. Single-voxel MRS (1.5 T, PRESS, TE 30 ms, TR 1500 ms, spectral resolution 1 Hz/point) was acquired prospectively on 39 consecutive cerebellar tumours with histopathological diagnoses of pilocytic astrocytoma, ependymoma or medulloblastoma. Spectra were analysed with LCModel and predefined quality control criteria were applied, leaving 33 cases in the analysis. The MRS diagnostic classifier was applied to this dataset. A retrospective analysis was subsequently undertaken by three radiologists, blind to histopathological diagnosis, to determine the change in diagnostic certainty when sequentially viewing conventional imaging, MRS and a decision support tool, based on the classifier. The overall classifier accuracy, evaluated prospectively, was 91%. Incorrectly classified cases, two anaplastic ependymomas, and a rare histological variant of medulloblastoma, were not well represented in the original training set. On retrospective review of conventional MRI, MRS and the classifier result, all radiologists showed a significant increase (Wilcoxon signed rank test, p < 0.001) in their certainty of the correct diagnosis, between viewing the conventional imaging and MRS with the decision support system. It was concluded that MRS can aid the noninvasive diagnosis of posterior fossa tumours in children, and that a decision support classifier helps in MRS interpretation.

Voxel-level analysis of normalized DSC-PWI time-intensity curves: a potential generalizable approach and its proof of concept in discriminating glioblastoma and metastasis

OBJECTIVE

Standard DSC-PWI analyses are based on concrete parameters and values, but an approach that contemplates all points in the time-intensity curves and all voxels in the region-of-interest may provide improved information, and more generalizable models. Therefore, a method of DSC-PWI analysis by means of normalized time-intensity curves point-by-point and voxel-by-voxel is constructed, and its feasibility and performance are tested in presurgical discrimination of glioblastoma and metastasis.

METHODS

In this retrospective study, patients with histologically confirmed glioblastoma or solitary-brain-metastases and presurgical-MR with DSC-PWI (August 2007-March 2020) were retrieved. The enhancing tumor and immediate peritumoral region were segmented on CE-T1wi and coregistered to DSC-PWI. Time-intensity curves of the segmentations were normalized to normal-appearing white matter. For each participant, average and all-voxel-matrix of normalized-curves were obtained. The 10 best discriminatory time-points between each type of tumor were selected. Then, an intensity-histogram analysis on each of these 10 time-points allowed the selection of the best discriminatory voxel-percentile for each. Separate classifier models were trained for enhancing tumor and peritumoral region using binary logistic regressions.

RESULTS

A total of 428 patients (321 glioblastomas, 107 metastases) fulfilled the inclusion criteria (256 men; mean age, 60 years; range, 20-86 years). Satisfactory results were obtained to segregate glioblastoma and metastases in training and test sets with AUCs 0.71-0.83, independent accuracies 65-79%, and combined accuracies up to 81-88%.

CONCLUSION

This proof-of-concept study presents a different perspective on brain MR DSC-PWI evaluation by the inclusion of all time-points of the curves and all voxels of segmentations to generate robust diagnostic models of special interest in heterogeneous diseases and populations. The method allows satisfactory presurgical segregation of glioblastoma and metastases.

KEY POINTS

• An original approach to brain MR DSC-PWI analysis, based on a point-by-point and voxel-by-voxel assessment of normalized time-intensity curves, is presented. • The method intends to extract optimized information from MR DSC-PWI sequences by impeding the potential loss of information that may represent the standard evaluation of single concrete perfusion parameters (cerebral blood volume, percentage of signal recovery, or peak height) and values (mean, maximum, or minimum). • The presented approach may be of special interest in technically heterogeneous samples, and intrinsically heterogeneous diseases. Its application enables satisfactory presurgical differentiation of GB and metastases, a usual but difficult diagnostic challenge for neuroradiologist with vital implications in patient management.

Deep learning magnetic resonance spectroscopy fingerprints of brain tumours using quantum mechanically synthesised data

Metabolic fingerprints are valuable biomarkers for diseases that are associated with metabolic disorders. 1H magnetic resonance spectroscopy (MRS) is a unique noninvasive diagnostic tool that can depict the metabolic fingerprint based solely on the proton signal of different molecules present in the tissue. However, its performance is severely hindered by low SNR, field inhomogeneities and overlapping spectra of metabolites, which affect the quantification of metabolites. Consequently, MRS is rarely included in routine clinical protocols and has not been proven in multi-institutional trials. This work proposes an alternative approach, where instead of quantifying metabolites' concentration, deep learning (DL) is used to model the complex nonlinear relationship between diseases and their spectroscopic metabolic fingerprint (pattern). DL requires large training datasets, acquired (ideally) with the same protocol/scanner, which are very rarely available. To overcome this limitation, a novel method is proposed that can quantum mechanically synthesise MRS data for any scanner/acquisition protocol. The proposed methodology is applied to the challenging clinical problem of differentiating metastasis from glioblastoma brain tumours on data acquired across multiple institutions. DL algorithms were trained on the augmented synthetic spectra and tested on two independent datasets acquired by different scanners, achieving a receiver operating characteristic area under the curve of up to 0.96 and 0.97, respectively.

Management of incidental brain tumors in children: a systematic review

BACKGROUND

Due to technical advancements and availability of neuroimaging, detection of incidental pediatric brain tumors (IPBT) is growing rapidly. The management of these asymptomatic lesions remains unclear; radiological, pathological, and clinical risk factors for further growth and malignant transformation (MT) are not well defined.

METHODS

We systematically reviewed the literature on the dilemmas and management of IPBT suggestive of a low-grade brain tumor (LGBT). Keyword searches of the PubMed and Medline (NCBI) databases identified studies on IPBT describing the prevalence, neuroimaging, management, or risk of MT through July 2019. References of the identified articles were also reviewed.

RESULTS

A total of 2021 records were screened. Fifty-nine full-text articles were reviewed, and 34 published studies were included. IPBT are diagnosed in 0.2-5.7% of children undergoing brain imaging for various reasons. The accepted approach for management of lesions showing radiological characteristics suggestive of LGBT is radiological follow-up. The rate at which additional intervention is required during follow-up for these apparently low-grade lesions is 9.5%. Nevertheless, the dilemma of early surgical resection or biopsy vs. clinical and radiological follow-up of IPBT is still unresolved. The risk in these cases is missing a transformation to a higher grade tumor. However, MT of pediatric LGBT is very rare, occurring in less than 3% of the cases of proven low-grade gliomas in children. The risk of future MT in pediatric low-grade gliomas seems to be greater in the presence of specific molecular markers such as BRAF V-600E, CDKN2A, and H3F3A K27M.

CONCLUSIONS

The natural history, management, and prognosis of IPBT remain ambiguous. It seems that lesions suggestive of LGBT can initially be followed, since many of these lesions remain stable over time and MT is rare. However, controversy among centers concerning the ideal approach still exists. Further observational and prospective cohort studies, focusing on potential clinical and radiological characteristics or risk factors suggestive of high-grade tumors, tumor progress, or MT of IPBT, are needed.

Robust Conditional Independence maps of single-voxel Magnetic Resonance Spectra to elucidate associations between brain tumours and metabolites

The aim of the paper is two-fold. First, we show that structure finding with the PC algorithm can be inherently unstable and requires further operational constraints in order to consistently obtain models that are faithful to the data. We propose a methodology to stabilise the structure finding process, minimising both false positive and false negative error rates. This is demonstrated with synthetic data. Second, to apply the proposed structure finding methodology to a data set comprising single-voxel Magnetic Resonance Spectra of normal brain and three classes of brain tumours, to elucidate the associations between brain tumour types and a range of observed metabolites that are known to be relevant for their characterisation. The data set is bootstrapped in order to maximise the robustness of feature selection for nominated target variables. Specifically, Conditional Independence maps (CI-maps) built from the data and their derived Bayesian networks have been used. A Directed Acyclic Graph (DAG) is built from CI-maps, being a major challenge the minimization of errors in the graph structure. This work presents empirical evidence on how to reduce false positive errors via the False Discovery Rate, and how to identify appropriate parameter settings to improve the False Negative Reduction. In addition, several node ordering policies are investigated that transform the graph into a DAG. The obtained results show that ordering nodes by strength of mutual information can recover a representative DAG in a reasonable time, although a more accurate graph can be recovered using a random order of samples at the expense of increasing the computation time.

Pediatric posterior fossa incidentalomas

PURPOSE

Pediatric brain incidentalomas are increasingly being diagnosed. As the posterior fossa (PF) is the location of most brain tumors in children, lesions of this region are of special interest. Currently, the natural history of incidental lesions in the PF is unknown. We present our experience treating such lesions.

METHODS

A retrospective study was carried out in two large tertiary pediatric centers. Patients were included if they had an incidental PF lesion suspected of being a tumor, and diagnosed before the age of 20 years. We analyzed treatment strategy, pathology, and outcome of operated and non-operated cases.

RESULTS

Seventy children (31 females) with a mean age of 8.4 ± 6.1 years were included. The three most common indications for imaging were headaches (16, assumed to be unrelated to the lesions), workup of unrelated conditions (14), and unspecified reasons (14). Twenty-seven patients (39%) were operated immediately, and 43 followed, of which 12 were eventually operated due to radiological changes, 28.9 ± 16.2 months after diagnosis. The most commonly found pathology was pilocytic astrocytomas (21 of 39 operated cases). Almost 10% were found to be malignant tumors including medulloblastomas (5) and ATRT (1).

CONCLUSION

Incidental PF lesions in children include both benign and malignant tumors. While certain lesions may be followed, others may require surgical treatment. Specific treatment decisions are based on initial radiological appearance, change in radiological characteristics over time, location, and evolving symptoms. The surgical risks must be balanced vis-à-vis the risk of missing a high-grade tumor and the very rare risk of malignant transformation.

Cancer metabolism in a snapshot: MRS(I)

The contribution of MRS(I) to the in vivo evaluation of cancer-metabolism-derived metrics, mostly since 2016, is reviewed here. Increased carbon consumption by tumour cells, which are highly glycolytic, is now being sampled by ¹³ C magnetic resonance spectroscopic imaging (MRSI) following the injection of hyperpolarized [1-¹³ C] pyruvate (Pyr). Hot-spots of, mostly, increased lactate dehydrogenase activity or flow between Pyr and lactate (Lac) have been seen with cancer progression in prostate (preclinical and in humans), brain and pancreas (both preclinical) tumours. Therapy response is usually signalled by decreased Lac/Pyr ¹³ C-labelled ratio with respect to untreated or non-responding tumour. For therapeutic agents inducing tumour hypoxia, the ¹³ C-labelled Lac/bicarbonate ratio may be a better metric than the Lac/Pyr ratio. ³¹ P MRSI may sample intracellular pH changes from brain tumours (acidification upon antiangiogenic treatment, basification at fast proliferation and relapse). The steady state tumour metabolome pattern is still in use for cancer evaluation. Metrics used for this range from quantification of single oncometabolites (such as 2-hydroxyglutarate in mutant IDH1 glial brain tumours) to selected metabolite ratios (such as total choline to N-acetylaspartate (plain ratio or CNI index)) or the whole ¹ H MRSI(I) pattern through pattern recognition analysis. These approaches have been applied to address different questions such as tumour subtype definition, following/predicting the response to therapy or defining better resection or radiosurgery limits.

An update on PET-based molecular imaging in neuro-oncology: challenges and implementation for a precision medicine approach in cancer care

PET imaging using novel radiotracers show promises for tumor grading and molecular characterization through visualizing molecular and functional properties of the tumors. Application of PET tracers in brain neoplasm depends on both type of the neoplasm and the research or clinical significance required to be addressed. In clinical neuro-oncology, 18F-FDG is used mainly to differentiate tumor recurrence from radiation-induced necrosis, and novel PET agents show attractive imaging properties. Novel PET tracers can offer biologic information not visible via contrast-enhanced MRI or 18F-FDG PET. This review aims to provide an update on the complementary role of PET imaging in neuro-oncology both in research and clinical settings along with presenting interesting cases in this context.

Magnetic resonance spectroscopy in posterior fossa tumours: the tumour spectroscopic signature may improve discrimination in adults among haemangioblastoma, ependymal tumours, medulloblastoma, and metastasis

OBJECTIVES

Assessing a posterior fossa tumour in an adult can be challenging. Metastasis, haemangioblastoma, ependymal tumours, and medulloblastoma are the most common diagnostic possibilities. Our aim was to evaluate the contribution of magnetic resonance spectroscopy (MRS) in the diagnosis of these entities.

METHODS

We retrospectively evaluated 56 consecutive patients with a posterior fossa tumour and histological diagnosis of ependymal tumour, medulloblastoma, haemangioblastoma, and metastasis in which good-quality spectra at short (TE 30 ms) or/and intermediate (TE, 136 ms) TE were available. Spectra were compared using the Mann-Whitney U non-parametric test in order to select the spectral datapoints and the intensity ratios that showed significant differences between groups of lesions. Performance of these datapoints and their ratios were assessed with ROC curves.

RESULTS

The most characteristic signatures on spectroscopy were high choline (Cho) in medulloblastoma (p < 0.001), high myoinositol (mIns) in ependymal tumours (p < 0.05), and high lipids (LIP) in haemangioblastoma (p < 0.01) and metastasis (p < 0.01). Selected ratios between normalised intensity signals of resonances provided accuracy values between 79 and 95% for pairwise comparisons. Intensity ratio NI_{3.21ppm/3.55ppm} provided satisfactory discrimination between medulloblastoma and ependymal tumours (accuracy, 92%), ratio NI_{2.11ppm/1.10ppm} discriminated ependymal tumours from haemangioblastoma (accuracy, 94%), ratio NI_{3.21ppm/1.13ppm} discriminated haemangioblastoma from medulloblastoma (accuracy, 95%), and ratio NI_{1.28ppm/2.02pmm} discriminated haemangioblastoma from metastasis (accuracy, 83%).

CONCLUSIONS

MRS may improve the non-invasive diagnosis of posterior fossa tumours in adults.

KEY POINTS

• High choline suggests a medulloblastoma in a posterior fossa tumour. • High myoinositol suggests an ependymal lesion in a posterior fossa tumour. • High lipids suggest a metastasis or a haemangioblastoma in a posterior fossa tumour.

eDoctor: machine learning and the future of medicine

Machine learning (ML) is a burgeoning field of medicine with huge resources being applied to fuse computer science and statistics to medical problems. Proponents of ML extol its ability to deal with large, complex and disparate data, often found within medicine and feel that ML is the future for biomedical research, personalized medicine, computer-aided diagnosis to significantly advance global health care. However, the concepts of ML are unfamiliar to many medical professionals and there is untapped potential in the use of ML as a research tool. In this article, we provide an overview of the theory behind ML, explore the common ML algorithms used in medicine including their pitfalls and discuss the potential future of ML in medicine.

Evaluation of the INTERPRET decision-support system: can it improve the diagnostic value of magnetic resonance spectroscopy of the brain?

Purpose

We evaluated in a clinical setting the INTERPRET decision-support system (DSS), a software generated to aid in MRS analysis to achieve a specific diagnosis for brain lesions.

Methods

The material consisted of 100 examinations of focal intracranial lesions with confirmed diagnoses. MRS was obtained at 1.5 T using TE 20–30 ms. Data were processed with the LCModel for conventional analysis. The INTERPRET DSS 3.1. was used to obtain specific diagnoses. MRI and MRS were reviewed by one interpreter. DSS analysis was made by another interpreter, in 80 cases by two interpreters. The diagnoses were compared with the definitive diagnoses. For comparisons between DSS, conventional MRS analysis, and MRI, the diagnoses were categorised: high-grade tumour, low-grade tumour, non-neoplastic lesion.

Results

Interobserver agreement in choosing the diagnosis from the INTERPRET database was 75%. The diagnosis was correct in 38/100 cases, incorrect in 57 cases. No good match was found in 5/100 cases. The diagnostic category was correct with DSS/conventional MRS/MRI in 67/58/52 cases, indeterminate in 5/8/20 cases, incorrect in 28/34/28 cases. Results with DSS were not significantly better than with conventional MRS analysis. All definitive diagnoses did not exist in the INTERPRET database. In the 61 adult patients with the diagnosis included in the database, DSS/conventional MRS/MRI yielded a correct diagnosis category in 48/32/29 cases (DSS vs conventional MRS: p = 0.002, DSS vs MRI: p = 0.0004).

Conclusion

Use of the INTERPRET DSS did not improve MRS categorisation of the lesions in the unselected clinical cases. In adult patients with lesions existing in the INTERPRET database, DSS improved the results, which indicates the potential of this software with an extended database.

Electronic supplementary material

The online version of this article (10.1007/s00234-018-2129-7) contains supplementary material, which is available to authorized users.

Clinical applications of in vivo magnetic resonance spectroscopy in oncology

Magnetic resonance spectroscopy (MRS) can be performed in vivo using commercial MRI systems to obtain biochemical information about tissues and cancers. Applications in brain, prostate and breast aid lesion detection and characterisation (differential diagnosis), treatment planning and response assessment. Multi-centre clinical trials have been performed in all these tissues. Single centre studies have been performed in many other tissues including cervix, uterus, musculoskeletal and liver. While generally MRS is used to study endogenous metabolites it has also been used in drug studies, for example those that include 19F as part of their structure. Recently the hyperpolarisation of compounds enriched with 13C such as [1-13C] pyruvate has been demonstrated in animal models and now in preliminary clinical studies, permitting the monitoring of biochemical processes with unprecedented sensitivity. This review briefly introduces the underlying methods and then discusses the current status of these applications.

Prospective multicentre evaluation and refinement of an analysis tool for magnetic resonance spectroscopy of childhood cerebellar tumours

BACKGROUND

A tool for diagnosing childhood cerebellar tumours using magnetic resonance (MR) spectroscopy peak height measurement has been developed based on retrospective analysis of single-centre data.

OBJECTIVE

To determine the diagnostic accuracy of the peak height measurement tool in a multicentre prospective study, and optimise it by adding new prospective data to the original dataset.

MATERIALS AND METHODS

Magnetic resonance imaging (MRI) and single-voxel MR spectroscopy were performed on children with cerebellar tumours at three centres. Spectra were processed using standard scanner software and peak heights for N-acetyl aspartate, creatine, total choline and myo-inositol were measured. The original diagnostic tool was used to classify 26 new tumours as pilocytic astrocytoma, medulloblastoma or ependymoma. These spectra were subsequently combined with the original dataset to develop an optimised scheme from 53 tumours in total.

RESULTS

Of the pilocytic astrocytomas, medulloblastomas and ependymomas, 65.4% were correctly assigned using the original tool. An optimized scheme was produced from the combined dataset correctly assigning 90.6%. Rare tumour types showed distinctive MR spectroscopy features.

CONCLUSION

The original diagnostic tool gave modest accuracy when tested prospectively on multicentre data. Increasing the dataset provided a diagnostic tool based on MR spectroscopy peak height measurement with high levels of accuracy for multicentre data.

Malignancy probability map as a novel imaging biomarker to predict malignancy distribution: employing MRS in GBM patients

The main aim of this study was to propose a new statistical method for evaluation of spatial malignancy distribution within Magnetic Resonance Spectroscopy (MRS) grid in Glioblastoma Multiforme patients. Voxels with different malignancy probabilities were presented as a novel MRS-based Malignancy Probability Map (MPM). For this purpose, a predictive probability-based clustering approach was developed, including the two following steps: (1) Gaussian Mixture Model, (2) Quadratic Discriminate Analysis coupled with Genetic Algorithm. Clustered probability values from two methods were then integrated to exploit the MPM. Results show that the suggested method is able to estimate the malignancy distribution with over 90% sensitivity and specificity. The proposed MRS-based MPM has an acceptable accuracy for providing useful complementary information about regional diffuse glioma malignancy, with the potential to lead to better detection of tumoral regions with high probability of malignancy. So, it also may encourage the use of additional information of this map as a tool for dose painting.

Imaging in neuro-oncology

Imaging plays several key roles in managing brain tumors, including diagnosis, prognosis, and treatment response assessment. Ongoing challenges remain as new therapies emerge and there are urgent needs to find accurate and clinically feasible methods to noninvasively evaluate brain tumors before and after treatment. This review aims to provide an overview of several advanced imaging modalities including magnetic resonance imaging and positron emission tomography (PET), including advances in new PET agents, and summarize several key areas of their applications, including improving the accuracy of diagnosis and addressing the challenging clinical problems such as evaluation of pseudoprogression and anti-angiogenic therapy, and rising challenges of imaging with immunotherapy.

Supporting Emergency Medical Care Teams with an Integrated Status Display Providing Real-Time Access to Medical Best Practices, Workflow Tracking, and Patient Data

The work of a hospital's medical staff is safety critical and often occurs under severe time constraints. To provide timely and effective cognitive support to medical teams working in such contexts, guidelines in the form of best practice workflows for healthcare have been developed by medical organizations. However, the high cognitive load imposed in such stressful and rapidly changing environments poses significant challenges to the medical staff or team in adhering to these workflows. In collaboration with physicians and nurses from Carle Foundation Hospital, we first studied and modeled medical team's individual responsibilities and interactions in cardiac arrest resuscitation and decomposed their overall task into a set of distinct cognitive tasks that must be specifically supported to achieve successful human-centered system design. We then developed a medical Best Practice Guidance (BPG) system for reducing medical teams' cognitive load, thus fostering real-time adherence to best practices. We evaluated the resulting system with physicians and nurses using a professional patient simulator used for medical training and certification. The evaluation results point to a reduction of cognitive load and enhanced adherence to medical best practices.

Quality of clinical brain tumor MR spectra judged by humans and machine learning tools

PURPOSE

To investigate and compare human judgment and machine learning tools for quality assessment of clinical MR spectra of brain tumors.

METHODS

A very large set of 2574 single voxel spectra with short and long echo time from the eTUMOUR and INTERPRET databases were used for this analysis. Original human quality ratings from these studies as well as new human guidelines were used to train different machine learning algorithms for automatic quality control (AQC) based on various feature extraction methods and classification tools. The performance was compared with variance in human judgment.

RESULTS

AQC built using the RUSBoost classifier that combats imbalanced training data performed best. When furnished with a large range of spectral and derived features where the most crucial ones had been selected by the TreeBagger algorithm it showed better specificity (98%) in judging spectra from an independent test-set than previously published methods. Optimal performance was reached with a virtual three-class ranking system.

CONCLUSION

Our results suggest that feature space should be relatively large for the case of MR tumor spectra and that three-class labels may be beneficial for AQC. The best AQC algorithm showed a performance in rejecting spectra that was comparable to that of a panel of human expert spectroscopists. Magn Reson Med 79:2500-2510, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Adult Brain Tumors: Clinical Applications of Magnetic Resonance Spectroscopy

Proton magnetic resonance spectroscopy (H-MRS) may be helpful in suggesting tumor histology and tumor grade and may better define tumor extension and the ideal site for biopsy compared with conventional magnetic resonance (MR) imaging. A multifunctional approach with diffusion-weighted imaging, perfusion-weighted imaging, and permeability maps, along with H-MRS, may enhance the accuracy of the diagnosis and characterization of brain tumors and estimation of therapeutic response. Integration of advanced imaging techniques with conventional MR imaging and the clinical history help to improve the accuracy, sensitivity, and specificity in differentiating tumors and nonneoplastic lesions.

Brain metabolic pattern analysis using a magnetic resonance spectra classification software in experimental stroke

Background

Magnetic resonance spectroscopy (MRS) provides non-invasive information about the metabolic pattern of the brain parenchyma in vivo. The SpectraClassifier software performs MRS pattern-recognition by determining the spectral features (metabolites) which can be used objectively to classify spectra. Our aim was to develop an Infarct Evolution Classifier and a Brain Regions Classifier in a rat model of focal ischemic stroke using SpectraClassifier.

Results

A total of 164 single-voxel proton spectra obtained with a 7 Tesla magnet at an echo time of 12 ms from non-infarcted parenchyma, subventricular zones and infarcted parenchyma were analyzed with SpectraClassifier (http://gabrmn.uab.es/?q=sc). The spectra corresponded to Sprague-Dawley rats (healthy rats, n = 7) and stroke rats at day 1 post-stroke (acute phase, n = 6 rats) and at days 7 ± 1 post-stroke (subacute phase, n = 14). In the Infarct Evolution Classifier, spectral features contributed by lactate + mobile lipids (1.33 ppm), total creatine (3.05 ppm) and mobile lipids (0.85 ppm) distinguished among non-infarcted parenchyma (100% sensitivity and 100% specificity), acute phase of infarct (100% sensitivity and 95% specificity) and subacute phase of infarct (78% sensitivity and 100% specificity). In the Brain Regions Classifier, spectral features contributed by myoinositol (3.62 ppm) and total creatine (3.04/3.05 ppm) distinguished among infarcted parenchyma (100% sensitivity and 98% specificity), non-infarcted parenchyma (84% sensitivity and 84% specificity) and subventricular zones (76% sensitivity and 93% specificity).

Conclusion

SpectraClassifier identified candidate biomarkers for infarct evolution (mobile lipids accumulation) and different brain regions (myoinositol content).

Electronic supplementary material

The online version of this article (doi:10.1186/s12868-016-0328-x) contains supplementary material, which is available to authorized users.

Multiclass imbalance learning: Improving classification of pediatric brain tumors from magnetic resonance spectroscopy

Purpose

Classification of pediatric brain tumors from ¹H‐magnetic resonance spectroscopy (MRS) can aid diagnosis and management of brain tumors. However, varied incidence of the different tumor types leads to imbalanced class sizes and introduces difficulties in classifying rare tumor groups. This study assessed different imbalanced multiclass learning techniques and compared the use of complete spectra and quantified metabolite profiles for classification of three main childhood brain tumor types.

Methods

Single‐voxel, Short echo time MRS data were collected from 90 patients with pilocytic astrocytoma (n = 42), medulloblastoma (n = 38), or ependymoma (n = 10). Both spectra and metabolite profiles were used to develop the learning algorithms. The borderline synthetic minority oversampling technique and AdaboostM1 were used to correct for the skewed distribution. Classifiers were trained using five different pattern recognition algorithms.

Results

Use of imbalanced learning techniques improved the balanced accuracy rate (BAR) of all classification methods (average BAR over all classification methods for spectra: oversampled data = 0.81, original = 0.63, P < 0.001; metabolite concentration: oversampled‐data = 0.91, original = 0.75, P < 0.0001). Performance of all classifiers in discriminating ependymomas increased when oversampled data were used compared with original data for both complete spectra (F‐measure P < 0.01) and metabolite profile (F‐measure P < 0.001).

Conclusion

Imbalanced learning techniques improve the classification accuracy of childhood brain tumors from MRS where group sizes differ and facilitate the inclusion of rarer tumor types into clinical decision support systems. Magn Reson Med 77:2114–2124, 2017. © 2016 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

MRSI-based molecular imaging of therapy response to temozolomide in preclinical glioblastoma using source analysis

Characterization of glioblastoma (GB) response to treatment is a key factor for improving patients' survival and prognosis. MRI and magnetic resonance spectroscopic imaging (MRSI) provide morphologic and metabolic profiles of GB but usually fail to produce unequivocal biomarkers of response. The purpose of this work is to provide proof of concept of the ability of a semi-supervised signal source extraction methodology to produce images with robust recognition of response to temozolomide (TMZ) in a preclinical GB model. A total of 38 female C57BL/6 mice were used in this study. The semi-supervised methodology extracted the required sources from a training set consisting of MRSI grids from eight GL261 GBs treated with TMZ, and six control untreated GBs. Three different sources (normal brain parenchyma, actively proliferating GB and GB responding to treatment) were extracted and used for calculating nosologic maps representing the spatial response to treatment. These results were validated with an independent test set (7 control and 17 treated cases) and correlated with histopathology. Major differences between the responder and non-responder sources were mainly related to the resonances of mobile lipids (MLs) and polyunsaturated fatty acids in MLs (0.9, 1.3 and 2.8 ppm). Responding tumors showed significantly lower mitotic (3.3 ± 2.9 versus 14.1 ± 4.2 mitoses/field) and proliferation rates (29.8 ± 10.3 versus 57.8 ± 5.4%) than control untreated cases. The methodology described in this work is able to produce nosological images of response to TMZ in GL261 preclinical GBs and suitably correlates with the histopathological analysis of tumors. A similar strategy could be devised for monitoring response to treatment in patients. Copyright © 2016 John Wiley & Sons, Ltd.

Automatic quality control in clinical (1)H MRSI of brain cancer

MRSI grids frequently show spectra with poor quality, mainly because of the high sensitivity of MRS to field inhomogeneities. These poor quality spectra are prone to quantification and/or interpretation errors that can have a significant impact on the clinical use of spectroscopic data. Therefore, quality control of the spectra should always precede their clinical use. When performed manually, quality assessment of MRSI spectra is not only a tedious and time-consuming task, but is also affected by human subjectivity. Consequently, automatic, fast and reliable methods for spectral quality assessment are of utmost interest. In this article, we present a new random forest-based method for automatic quality assessment of (1)H MRSI brain spectra, which uses a new set of MRS signal features. The random forest classifier was trained on spectra from 40 MRSI grids that were classified as acceptable or non-acceptable by two expert spectroscopists. To account for the effects of intra-rater reliability, each spectrum was rated for quality three times by each rater. The automatic method classified these spectra with an area under the curve (AUC) of 0.976. Furthermore, in the subset of spectra containing only the cases that were classified every time in the same way by the spectroscopists, an AUC of 0.998 was obtained. Feature importance for the classification was also evaluated. Frequency domain skewness and kurtosis, as well as time domain signal-to-noise ratios (SNRs) in the ranges 50-75 ms and 75-100 ms, were the most important features. Given that the method is able to assess a whole MRSI grid faster than a spectroscopist (approximately 3 s versus approximately 3 min), and without loss of accuracy (agreement between classifier trained with just one session and any of the other labelling sessions, 89.88%; agreement between any two labelling sessions, 89.03%), the authors suggest its implementation in the clinical routine. The method presented in this article was implemented in jMRUI's SpectrIm plugin.

Magnetic resonance spectroscopy - Revisiting the biochemical and molecular milieu of brain tumors

Background

Magnetic resonance spectroscopy (MRS) is an established tool for in-vivo evaluation of the biochemical basis of human diseases. On one hand, such lucid depiction of ‘live biochemistry’ helps one to decipher the true nature of the pathology while on the other hand one can track the response to therapy at sub-cellular level. Brain tumors have been an area of continuous interrogation and instigation for mankind. Evaluation of these lesions by MRS plays a crucial role in the two aspects of disease management described above.

Scope of review

Presented is an overview of the window provided by MRS into the biochemical aspects of brain tumors. We systematically visit each metabolite deciphered by MRS and discuss the role of deconvoluting the biochemical aspects of pathologies (here in context of brain tumors) in the disease management cycle. We further try to unify a radiologist's perspective of disease with that of a biochemist to prove the point that preclinical work is the mother of the treatment we provide at bedside as clinicians. Furthermore, an integrated approach by various scientific experts help resolve a query encountered in everyday practice.

Major conclusions

MR spectroscopy is an integral tool for evaluation and systematic follow-up of brain tumors. A deeper understanding of this technology by a biochemist would help in a swift and more logical development of the technique while a close collaboration with radiologist would enable definitive application of the same.

General significance

The review aims at inciting closer ties between the two specialists enabling a deeper understanding of this valuable technology.

•

Magnetic resonance spectroscopy is an established technology for non-invasive assessment of pathological tissue.

•

Good understanding of the physical principles of the technique can help one exploit it maximally.

•

An array of information from the technique is available and needs deep understanding of the results.

•

Newer variations of this technology are being invented to evaluate different aspects of pathologies in a more refined manner.

•

We also discuss the limitations of this technology and possible solutions there-off.

Accurate grading of brain gliomas by soft independent modeling of class analogy based on non-negative matrix factorization of proton magnetic resonance spectra

Hydrogen magnetic resonance spectroscopy ((1) H-MRS) is a non-invasive technique which provides a 'frequency-signal intensity' spectrum of biochemical compounds of tissues in the body. Although this method is currently used in human brain studies, accurate classification of in-vivo (1) H-MRS is a challenging task in the diagnosis of brain tumors. Problems such as overlapping metabolite peaks, incomplete information on background component and low signal-to-noise ratio disturb classification results of this spectroscopic method. This study presents an alternative approach to the soft independent modeling of class analogy (SIMCA) technique, using non-negative matrix factorization (NMF) for dimensionality reduction. In the adopted strategy, the performance of SIMCA was improved by application of a robust algorithm for classification in the presence of noisy measurements. Total of 219 spectra from two databases were taken by water-suppressed short echo-time (1) H-MRS, acquired from different subjects with different stages of glial brain tumors (Grade II (26 cases), grade III (24 cases), grade IV (41 cases), as well as 25 healthy cases). The SIMCA was performed using two approaches: (i) principal component analysis (PCA) and (ii) non-negative matrix factorization (NMF), as a modified approach. Square prediction error was considered to assess the class membership of the external validation set. Finally, several figures of merit such as the correct classification rate (CCR), sensitivity and specificity were calculated. Results of SIMCA based on NMF showed significant improvement in percentage of correctly classified samples, 91.4% versus 83.5% for PCA-based model in an independent test set.

Classification of brain tumours from MR spectra: the INTERPRET collaboration and its outcomes

The INTERPRET project was a multicentre European collaboration, carried out from 2000 to 2002, which developed a decision-support system (DSS) for helping neuroradiologists with no experience of MRS to utilize spectroscopic data for the diagnosis and grading of human brain tumours. INTERPRET gathered a large collection of MR spectra of brain tumours and pseudo-tumoural lesions from seven centres. Consensus acquisition protocols, a standard processing pipeline and strict methods for quality control of the aquired data were put in place. Particular emphasis was placed on ensuring the diagnostic certainty of each case, for which all cases were evaluated by a clinical data validation committee. One outcome of the project is a database of 304 fully validated spectra from brain tumours, pseudotumoural lesions and normal brains, along with their associated images and clinical data, which remains available to the scientific and medical community. The second is the INTERPRET DSS, which has continued to be developed and clinically evaluated since the project ended. We also review here the results of the post-INTERPRET period. We evaluate the results of the studies with the INTERPRET database by other consortia or research groups. A summary of the clinical evaluations that have been performed on the post-INTERPRET DSS versions is also presented. Several have shown that diagnostic certainty can be improved for certain tumour types when the INTERPRET DSS is used in conjunction with conventional radiological image interpretation. About 30 papers concerned with the INTERPRET single-voxel dataset have so far been published. We discuss stengths and weaknesses of the DSS and the lessons learned. Finally we speculate on how the INTERPRET concept might be carried into the future.

From raw data to data-analysis for magnetic resonance spectroscopy--the missing link: jMRUI2XML

Background

Magnetic resonance spectroscopy provides metabolic information about living tissues in a non-invasive way. However, there are only few multi-centre clinical studies, mostly performed on a single scanner model or data format, as there is no flexible way of documenting and exchanging processed magnetic resonance spectroscopy data in digital format. This is because the DICOM standard for spectroscopy deals with unprocessed data.

This paper proposes a plugin tool developed for jMRUI, namely jMRUI2XML, to tackle the latter limitation. jMRUI is a software tool for magnetic resonance spectroscopy data processing that is widely used in the magnetic resonance spectroscopy community and has evolved into a plugin platform allowing for implementation of novel features.

Results

jMRUI2XML is a Java solution that facilitates common preprocessing of magnetic resonance spectroscopy data across multiple scanners. Its main characteristics are: 1) it automates magnetic resonance spectroscopy preprocessing, and 2) it can be a platform for outputting exchangeable magnetic resonance spectroscopy data. The plugin works with any kind of data that can be opened by jMRUI and outputs in extensible markup language format. Data processing templates can be generated and saved for later use.

The output format opens the way for easy data sharing- due to the documentation of the preprocessing parameters and the intrinsic anonymization - for example for performing pattern recognition analysis on multicentre/multi-manufacturer magnetic resonance spectroscopy data.

Conclusions

jMRUI2XML provides a self-contained and self-descriptive format accounting for the most relevant information needed for exchanging magnetic resonance spectroscopy data in digital form, as well as for automating its processing. This allows for tracking the procedures the data has undergone, which makes the proposed tool especially useful when performing pattern recognition analysis. Moreover, this work constitutes a first proposal for a minimum amount of information that should accompany any magnetic resonance processed spectrum, towards the goal of achieving better transferability of magnetic resonance spectroscopy studies.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0796-5) contains supplementary material, which is available to authorized users.

Audit method suited for DSS in clinical environment

This chapter presents a novel online method to audit predictive models using a Bayesian perspective. The auditing model has been specifically designed for Decision Support Systems (DSSs) suited for clinical or research environments. Taking as starting point the working diagnosis supplied by the clinician, this method compares and evaluates the predictive skills of those models able to answer to that diagnosis. The approach consists in calculating the posterior odds of a model through the composition of a prior odds, a static odds, and a dynamic odds. To do so, this method estimates the posterior odds from the cases that the comparing models had in common during the design stage and from the cases already viewed by the DSS after deployment in the clinical site. In addition, if an ontology of the classes is available, this method can audit models answering related questions, which offers a reinforcement to the decisions the user already took and gives orientation on further diagnostic steps.The main technical novelty of this approach lies in the design of an audit model adapted to suit the decision workflow of a clinical environment. The audit model allows deciding what is the classifier that best suits each particular case under evaluation and allows the detection of possible misbehaviours due to population differences or data shifts in the clinical site. We show the efficacy of our method for the problem of brain tumor diagnosis with Magnetic Resonance Spectroscopy (MRS).

Evaluation of the diagnostic performance of magnetic resonance spectroscopy in brain tumors: a systematic review and meta-analysis

Object

The aim of this study was to determine the suitability of magnetic resonance spectroscopy (MRS) for screening brain tumors, based on a systematic review and meta-analysis of published data on the diagnostic performance of MRS.

Methods

The PubMed and PHMC databases were systematically searched for relevant studies up to December 2013. The sensitivities and specificities of MRS in individual studies were calculated and the pooled diagnostic accuracies, with 95% confidence intervals (CI), were assessed under a fixed-effects model.

Results

Twenty-four studies were included, comprising a total of 1013 participants. Overall, no heterogeneity of diagnostic effects was observed between studies. The pooled sensitivity and specificity of MRS were 80.05% (95% CI = 75.97%–83.59%) and 78.46% (95% CI: 73.40%–82.78%), respectively. The area under the summary receiver operating characteristic curve was 0.78. Stratified meta analysis showed higher sensitivity and specificity in child than adult. CSI had higher sensitivity and SV had higher specificity. Higher sensitivity and specificity were obtained in short TE value.

Conclusion

Although the qualities of the studies included in the meta-analysis were moderate, current evidence suggests that MRS may be a valuable adjunct to magnetic resonance imaging for diagnosing brain tumors, but requires selection of suitable technique and TE value.

Molecular imaging coupled to pattern recognition distinguishes response to temozolomide in preclinical glioblastoma

Non-invasive monitoring of response to treatment of glioblastoma (GB) is nowadays carried out using MRI. MRS and MR spectroscopic imaging (MRSI) constitute promising tools for this undertaking. A temozolomide (TMZ) protocol was optimized for GL261 GB. Sixty-three mice were studied by MRI/MRS/MRSI. The spectroscopic information was used for the classification of control brain and untreated and responding GB, and validated against post-mortem immunostainings in selected animals. A classification system was developed, based on the MRSI-sampled metabolome of normal brain parenchyma, untreated and responding GB, with a 93% accuracy. Classification of an independent test set yielded a balanced error rate of 6% or less. Classifications correlated well both with tumor volume changes detected by MRI after two TMZ cycles and with the histopathological data: a significant decrease (p < 0.05) in the proliferation and mitotic rates and a 4.6-fold increase in the apoptotic rate. A surrogate response biomarker based on the linear combination of 12 spectral features has been found in the MRS/MRSI pattern of treated tumors, allowing the non-invasive classification of growing and responding GL261 GB. The methodology described can be applied to preclinical treatment efficacy studies to test new antitumoral drugs, and begets translational potential for early response detection in clinical studies.

Multivendor implementation and comparison of volumetric whole-brain echo-planar MR spectroscopic imaging

PURPOSE

To assess volumetric proton MR spectroscopic imaging (MRSI) of the human brain on multivendor MRI instruments.

METHODS

Echo-planar spectroscopic imaging was developed on instruments from three manufacturers, with matched specifications and acquisition protocols that accounted for differences in sampling performance, radiofrequency (RF) power, and data formats. Intersite reproducibility was evaluated for signal-normalized maps of N-acetylaspartate (NAA), creatine (Cre), and choline using phantom and human subject measurements. Comparative analyses included metrics for spectral quality, spatial coverage, and mean values in atlas-registered brain regions.

RESULTS

Intersite differences for phantom measurements were less than 1.7% for individual metabolites and less than 0.2% for ratio measurements. Spatial uniformity ranged from 79% to 91%. The human studies found differences of mean values in the temporal lobe, but good agreement in other white matter regions, with maximum differences relative to their mean of under 3.2%. For NAA/Cre, the maximum difference was 1.8%. In gray matter, a significant difference was observed for frontal lobe NAA. Primary causes of intersite differences were attributed to shim quality, B0 drift, and accuracy of RF excitation. Correlation coefficients for measurements at each site were over 0.60, indicating good reliability.

CONCLUSION

A volumetric intensity-normalized MRSI acquisition can be implemented in a comparable manner across multivendor MR instruments.