An advanced MRI and MRSI data fusion scheme for enhancing unsupervised brain tumor differentiation

Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps

ObjectiveCompared with anatomical magnetic resonance imaging modalities, metabolite images from magnetic resonance spectroscopic imaging often suffer from low quality and detail due to their larger voxel sizes. Conventional interpolation techniques aim to enhance these low-resolution images; however, they frequently struggle with issues such as edge preservation, blurring, and input quality limitations. This study explores an artificial intelligence-driven approach to improve the quality of synthetically generated metabolite maps.MethodsUsing an open-access database of 450 participants, we trained and tested a model on 350 participants, evaluating its performance against spline and nearest-neighbor interpolation methods. Metrics such as structural similarity index, peak signal-to-noise ratio, and learned perceptual image patch similarity were used for comparison.ResultsOur model not only increased spatial resolution but also preserved critical image details, outperforming traditional interpolation methods in both image fidelity and edge preservation.ConclusionsThis artificial intelligence-powered super-resolution technique could substantially enhance magnetic resonance spectroscopic imaging quality, aiding in more accurate neurological assessments.

Dual path parallel hierarchical diagnosis model for intracranial tumors based on multi-feature entropy weight

The grading diagnosis of intracranial tumors is a key step in formulating clinical treatment plans and surgical guidelines. To effectively grade the diagnosis of intracranial tumors, this paper proposes a dual path parallel hierarchical model that can automatically grade the diagnosis of intracranial tumors with high accuracy. In this model, prior features of solid tumor mass and intratumoral necrosis are extracted. Then the optimal division of the data set is achieved through multi-feature entropy weight. The multi-modal input is realized by the dual path structure. Multiple features are superimposed and fused to achieve the image grading. The model has been tested on the actual clinical medical images provided by the Second Affiliated Hospital of Dalian Medical University. The experiment shows that the proposed model has good generalization ability, with an accuracy of 0.990. The proposed model can be applied to clinical diagnosis and has practical application prospects.

Lipid Alterations in Glioma: A Systematic Review

Gliomas are highly lethal tumours characterised by heterogeneous molecular features, producing various metabolic phenotypes leading to therapeutic resistance. Lipid metabolism reprogramming is predominant and has contributed to the metabolic plasticity in glioma. This systematic review aims to discover lipids alteration and their biological roles in glioma and the identification of potential lipids biomarker. This systematic review was conducted using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. Extensive research articles search for the last 10 years, from 2011 to 2021, were conducted using four electronic databases, including PubMed, Web of Science, CINAHL and ScienceDirect. A total of 158 research articles were included in this study. All studies reported significant lipid alteration between glioma and control groups, impacting glioma cell growth, proliferation, drug resistance, patients' survival and metastasis. Different lipids demonstrated different biological roles, either beneficial or detrimental effects on glioma. Notably, prostaglandin (PGE2), triacylglycerol (TG), phosphatidylcholine (PC), and sphingosine-1-phosphate play significant roles in glioma development. Conversely, the most prominent anti-carcinogenic lipids include docosahexaenoic acid (DHA), eicosapentaenoic acid (EPA), and vitamin D3 have been reported to have detrimental effects on glioma cells. Furthermore, high lipid signals were detected at 0.9 and 1.3 ppm in high-grade glioma relative to low-grade glioma. This evidence shows that lipid metabolisms were significantly dysregulated in glioma. Concurrent with this knowledge, the discovery of specific lipid classes altered in glioma will accelerate the development of potential lipid biomarkers and enhance future glioma therapeutics.

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.

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.

Medical image fusion based on hybrid three-layer decomposition model and nuclear norm

The aim of medical image fusion technology is to synthesize multiple-image information to assist doctors in making scientific decisions. Existing studies have focused on preserving image details while avoiding halo artifacts and color distortions. This paper proposes a novel medical image fusion algorithm based on this research objective. First, the input image is decomposed into structure, texture, and local mean brightness layers using a hybrid three-layer decomposition model that can fully extract the features of the original images without the introduction of artifacts. Secondly, the nuclear norm of the patches, which are obtained using a sliding window, are calculated to construct the weight maps of the structure and texture layers. The weight map of the local mean brightness layer is constructed by calculating the local energy. Finally, remapping functions are applied to enhance each fusion layer, which reconstructs the final fusion image with the inverse operation of decomposition. Subjective and objective experiments confirm that the proposed algorithm has a distinct advantage compared with other state-of-the-art algorithms.

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.

Embedding MRI information into MRSI data source extraction improves brain tumour delineation in animal models

Glioblastoma is the most frequent malignant intra-cranial tumour. Magnetic resonance imaging is the modality of choice in diagnosis, aggressiveness assessment, and follow-up. However, there are examples where it lacks diagnostic accuracy. Magnetic resonance spectroscopy enables the identification of molecules present in the tissue, providing a precise metabolomic signature. Previous research shows that combining imaging and spectroscopy information results in more accurate outcomes and superior diagnostic value. This study proposes a method to combine them, which builds upon a previous methodology whose main objective is to guide the extraction of sources. To this aim, prior knowledge about class-specific information is integrated into the methodology by setting the metric of a latent variable space where Non-negative Matrix Factorisation is performed. The former methodology, which only used spectroscopy and involved combining spectra from different subjects, was adapted to use selected areas of interest that arise from segmenting the T2-weighted image. Results showed that embedding imaging information into the source extraction (the proposed semi-supervised analysis) improved the quality of the tumour delineation, as compared to those obtained without this information (unsupervised analysis). Both approaches were applied to pre-clinical data, involving thirteen brain tumour-bearing mice, and tested against histopathological data. On results of twenty-eight images, the proposed Semi-Supervised Source Extraction (SSSE) method greatly outperformed the unsupervised one, as well as an alternative semi-supervised approach from the literature, with differences being statistically significant. SSSE has proven successful in the delineation of the tumour, while bringing benefits such as 1) not constricting the metabolomic-based prediction to the image-segmented area, 2) ability to deal with signal-to-noise issues, 3) opportunity to answer specific questions by allowing researchers/radiologists define areas of interest that guide the source extraction, 4) creation of an intra-subject model and avoiding contamination from inter-subject overlaps, and 5) extraction of meaningful, good-quality sources that adds interpretability, conferring validation and better understanding of each case.

Analysis of metabolic abnormalities in high-grade glioma using MRSI and convex NMF

Clinical use of MRSI is limited by the level of experience required to properly translate MRSI examinations into relevant clinical information. To solve this, several methods have been proposed to automatically recognize a predefined set of reference metabolic patterns. Given the variety of metabolic patterns seen in glioma patients, the decision on the optimal number of patterns that need to be used to describe the data is not trivial. In this paper, we propose a novel framework to (1) separate healthy from abnormal metabolic patterns and (2) retrieve an optimal number of reference patterns describing the most important types of abnormality. Using 41 MRSI examinations (1.5 T, PRESS, T_E 135 ms) from 22 glioma patients, four different patterns describing different types of abnormality were detected: edema, healthy without Glx, active tumor and necrosis. The identified patterns were then evaluated on 17 MRSI examinations from nine different glioma patients. The results were compared against BraTumIA, an automatic segmentation method trained to identify different tumor compartments on structural MRI data. Finally, the ability to predict future contrast enhancement using the proposed approach was also evaluated.

Pre- and post-surgery MRSI predictive value in adult oligodendroglioma prognosis

PURPOSE

The aim of this study was to study the relationship between MRSI, before and after surgery, and patient survival. The accuracy of pre-operative MRSI in differentiating low- from high-grade oligodendrogliomas (ODGs) was also studied.

METHODS

Two hundred patients with ODG were retrospectively included in this study between 2000 and 2016. All patients underwent MRSI before any treatment or biopsy and/or after surgery for an intra-axial brain tumour. The R software was used for statistical data analysis. p < 0.05 was considered statistically significant. Kaplan-Meier curves were calculated for patients with low-grade ODG and high-grade ODG pre- and post-operatively, to study survival (overall survival, OS). The best threshold of each MRSI metabolite ratio was obtained using receiver operating characteristic curves (ROCs).

RESULTS

One hundred patients underwent pre-operative MRSI and 170 post-operative MRSI. N-acetylaspartate (NAA), lactate (Lac), choline (Cho) and creatine (Cr) were measured. Kapan-Meier curves showed that survival was poorer for a nCho/Cr > 3.02 in the pre-operative and nCho/Cr > 2.04, Lac/Cr > 0.743 and nCho/NAA > 3.63 in the post-operative period. Post-operative MRSI predicts survival better than pre-operative MRSI. nCho/Cr and Lac/Cr distinguished low- from high-grade ODG with a good positive predictive value.

CONCLUSION

MRSI is associated with survival. It is a non-invasive tool which completes histopathology and can predict patients' prognosis, thus improving patient management.