Applications of neural network analyses to in vivo 1H magnetic resonance spectroscopy of epilepsy patients

Can we predict anti-seizure medication response in focal epilepsy using machine learning?

OBJECTIVE

The aim of this study was to evaluate the feasibility of machine learning approach based on clinical factors and diffusion tensor imaging (DTI) to predict anti-seizure medication (ASM) response in focal epilepsy. We hypothesized that ASM response in focal epilepsy can be predicted using a machine learning approach.

METHODS

In this retrospective study conducted at a tertiary hospital, we enrolled 160 patients with newly diagnosed focal epilepsy. All of them underwent DTI from January 2017 to July 2019, with a follow-up at least 12 months after the diagnosis of epilepsy based on regular evaluation of ASMs. We analyzed the patients' clinical characteristics, and the conventional DTI measurements and extracted the structural connectomic profiles from the DTI. We employed the support vector machine (SVM) algorithm, and a k-fold cross-validation was executed.

RESULTS

The highest accuracy of classification was ensured based on the clinical factors. A SVM classifier based on the clinical factors revealed an accuracy of 87.5% and an area under curve (AUC) of 0.882. Another SVM classifier based on the conventional DTI measures demonstrated an accuracy of 62.5% and an AUC of 0.611. In addition, an SVM classifier based on the structural connectomic profiles revealed an accuracy of 68.7% and an AUC of 0.667. The AUC of the ROC curve generated from the clinical factors was significantly higher than the ROC curves based on the conventional DTI measures or structural connectomic profiles.

CONCLUSION

Machine learning approach is useful in predicting the ASM response in focal epilepsy. The clinical factor is more important than the conventional DTI measures and structural connectomic profiles in predicting the ASM response in focal epilepsy.

Automated Identification of Surgical Candidates and Estimation of Postoperative Seizure Freedom in Children - A Focused Review

Surgery is an effective but underused treatment for drug-resistant epilepsy in children. Algorithms to identify surgical candidates and estimate the likelihood of postoperative clinical improvement may be valuable to improve access to epilepsy surgery. We provide a focused review of these approaches. For adults with epilepsy, tools to identify surgical candidates and predict seizure and cognitive outcomes (Ie, Cases for Epilepsy (toolsforepilepsy.com) and Epilepsy Surgery Grading Scale) have been validated and are in use. Analogous tools for children need development. A promising approach is to apply statistical learning tools to clinical datasets, such as electroencephalogram tracings, imaging studies, and the text of clinician notes. Demonstration projects suggest these techniques have the potential to be highly accurate, and await further validation and clinical application.

Artificial Intelligence shaping the future of neurology practice

Neurology practice has faced many challenges since Jean-Martin Charcot established its sacred tenets. Artificial Intelligence (AI) promises to revolutionize the time-tested neurology practice in unimaginable ways. AI can now diagnose stroke from CT/MRI scans, detect papilledema and diabetic retinopathy from retinal scans, interpret electroencephalogram (EEG) to prognosticate coma, detect seizure well before ictus, predict conversion of mild cognitive impairment to Alzheimer's dementia, classify neurodegenerative diseases based on gait and handwriting. Clinical practice would likely change in near future to accommodate AI as a complementary tool. The clinician should be prepared to change the perception of AI from nemesis to opportunity.

Machine learning applications in epilepsy

Machine learning leverages statistical and computer science principles to develop algorithms capable of improving performance through interpretation of data rather than through explicit instructions. Alongside widespread use in image recognition, language processing, and data mining, machine learning techniques have received increasing attention in medical applications, ranging from automated imaging analysis to disease forecasting. This review examines the parallel progress made in epilepsy, highlighting applications in automated seizure detection from electroencephalography (EEG), video, and kinetic data, automated imaging analysis and pre-surgical planning, prediction of medication response, and prediction of medical and surgical outcomes using a wide variety of data sources. A brief overview of commonly used machine learning approaches, as well as challenges in further application of machine learning techniques in epilepsy, is also presented. With increasing computational capabilities, availability of effective machine learning algorithms, and accumulation of larger datasets, clinicians and researchers will increasingly benefit from familiarity with these techniques and the significant progress already made in their application in epilepsy.

Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging

PURPOSE

To assess whether an artificial neural network (ANN) model is a useful tool for automatic detection of cancerous voxels in the prostate from (1)H-MRSI datasets and whether the addition of information about anatomical segmentation improves the detection of cancer.

MATERIALS AND METHODS

The Institutional Review Board approved this HIPAA-compliant study and waived informed consent. Eighteen men with prostate cancer (median age, 55 years; range, 36-71 years) who underwent endorectal MRI/MRSI before radical prostatectomy were included in this study. These patients had at least one cancer area on whole-mount histopathological map and at least one matching MRSI voxel suspicious for cancer detected. Two ANN models for automatic classification of MRSI voxels in the prostate were implemented and compared: model 1, which used only spectra as input, and model 2, which used the spectra plus information from anatomical segmentation. The models were trained, tested and validated using spectra from voxels that the spectroscopist had designated as cancer and that were verified on histopathological maps.

RESULTS

At ROC analysis, model 2 (AUC = 0.968) provided significantly better (P = 0.03) classification of cancerous voxels than did model 1 (AUC = 0.949).

CONCLUSION

Automatic analysis of prostate MRSI to detect cancer using ANN model is feasible. Application of anatomical segmentation from MRI as an additional input to ANN improves the accuracy of detecting cancerous voxels from MRSI.

Combining clinical assessment scores and in vivo MR spectroscopy neurometabolites in very low birth weight adolescents

OBJECTIVE

Very low birth weight (VLBW) survivors are at increased risk of neurological impairments that may persist into adolescence and adulthood. The aims of this study were to identify the most important clinical assessments that characterize differences between VLBW and control adolescents, and to look at the relationship between clinical assessments and the metabolites in in vivo MR spectra.

METHODS

At 14-15 years of age, 54 VLBW survivors and 64 term controls were examined clinically. Several neuropsychological and motor assessments were performed. The magnetic resonance (MR) brain spectra were acquired from volumes localized in the left frontal lobe and contained mainly white matter.

RESULTS

Probabilistic neural networks and support vector machines demonstrated that clinical assessments rendered a possibility of the classification of VLBW versus control adolescents. The most important clinical assessments in this classification were visual-motor integration, motor coordination, stroop test, full scale IQ, and grooved pegboard. Through the use of outer product analysis-partial least squares discriminant analysis on a subset of adolescents (n=36), the clinical assessments found to most strongly correlate with the spectral data were the global assessment scale, Wisconsin card sorting test, full scale IQ, grooved pegboard test, and motor coordination test. Clinical assessments that relate to spectral data may be especially dependent on an intact microstructure in frontal white matter.

Fast quantification of proton magnetic resonance spectroscopic imaging with artificial neural networks

Accurate quantification of the MRSI-observed regional distribution of metabolites involves relatively long processing times. This is particularly true in dealing with large amount of data that is typically acquired in multi-center clinical studies. To significantly shorten the processing time, an artificial neural network (ANN)-based approach was explored for quantifying the phase corrected (as opposed to magnitude) spectra. Specifically, in these studies radial basis function neural network (RBFNN) was used. This method was tested on simulated and normal human brain data acquired at 3T. The N-acetyl aspartate (NAA)/creatine (Cr), choline (Cho)/Cr, glutamate+glutamine (Glx)/Cr, and myo-inositol (mI)/Cr ratios in normal subjects were compared with the line fitting (LF) technique and jMRUI-AMARES analysis, and published values. The average NAA/Cr, Cho/Cr, Glx/Cr and mI/Cr ratios in normal controls were found to be 1.58+/-0.13, 0.9+/-0.08, 0.7+/-0.17 and 0.42+/-0.07, respectively. The corresponding ratios using the LF and jMRUI-AMARES methods were 1.6+/-0.11, 0.95+/-0.08, 0.78+/-0.18, 0.49+/-0.1 and 1.61+/-0.15, 0.78+/-0.07, 0.61+/-0.18, 0.42+/-0.13, respectively. These results agree with those published in literature. Bland-Altman analysis indicated an excellent agreement and minimal bias between the results obtained with RBFNN and other methods. The computational time for the current method was 15s compared to approximately 10 min for the LF-based analysis.

Cerebral metabolite differences in adolescents with low birth weight: assessment with in vivo proton MR spectroscopy

BACKGROUND

Children with very low birth weight (VLBW) have a significantly increased risk of later neurodevelopmental problems, while infants born small for gestational age (SGA) at term are also at some risk of developing neurological impairment.

OBJECTIVE

To investigate possible brain metabolite differences in adolescents with VLBW, SGA at term and controls by proton in vivo magnetic resonance spectroscopy (MRS) at 1.5 T.

MATERIALS AND METHODS

MR spectra were acquired from volumes localized in the left frontal lobe, containing mainly white matter (54 subjects). Peak areas of N-acetyl aspartate (NAA), choline (Cho) and creatine (Cr) were determined, and the peak area ratio of NAA to Cr, total Cho to Cr, or NAA to Cho calculated. Probabilistic neural network (PNN) analysis was performed utilizing the chemical shift region containing resonances from NAA, Cho and Cr as inputs.

RESULTS

No significant difference in the peak area ratios could be found using the Kruskal-Wallis test. By application of PNN, a correct classification of 52 of the 54 adolescents with a sensitivity and specificity exceeding 93% for all groups was achieved.

CONCLUSION

Small, yet systematic, differences in brain metabolite distribution among the groups were confirmed by PNN analysis.

Neural damage due to temporal lobe epilepsy: dual-nuclei (proton and phosphorus) magnetic resonance spectroscopy study

The aim of this study was to evaluate the usefulness of proton and phosphorus (1H and 31P) magnetic resonance spectroscopy (MRS) for temporal lobe epilepsy (TLE) patients, and to evaluate neural damage and metabolite dysfunction in the TLE patient brain. We performed 1H and 31P MRS of medial temporal lobes (MTL) in the same TLE patients (n = 14) with a relatively wide range of severity from almost seizure-free to intractable, and calculated the ratio of N-acetylasparate to choline-containing compounds and creatine + phosphocreatine (NAA/Cho + Cr) in 1H MRS and inorganic phosphate to all main peaks (%Pi) in 31P MRS. There was no significant correlation between NAA/(Cho + Cr) and %Pi in each side (ipsilateral, r = -0.20; contralateral, r =-0.19). The values of NAA/(Cho + Cr) showed a significant difference between ipsilateral and contralateral MTLs to the focus of TLE patients (P < 0.01, paired t-test). Although %Pi also had a tendency to show the laterality of TLE, there was no significance. Ipsilateral (r = -0.90, P < 0.0001) and contralateral (r = -0.70, P < 0.005) NAA/(Cho + Cr) decreases and contralateral %Pi increase (r = 0.81, P < 0.001) had significant correlation with seizure frequency. 1H MRS provides more important information concerning neuronal dysfunction in MTL of TLE patients than 31P MRS.

High-resolution magic angle spinning MRS of breast cancer tissue

High-resolution magic angle spinning (HR MAS) may develop into a new diagnostic tool for studying intact tissue samples, and several types of cancer have been investigated with promising results. In this study HR MAS spectra of breast cancer tissue from 10 patients have been compared to conventional high-resolution spectra of perchloric acid extracts of the same tissue type. The HR MAS spectra show resolution comparable to spectra of extracts, and two-dimensional techniques lead to identification of a majority of the constituents. More than 30 different metabolites have been detected and assigned. To our knowledge this is the most detailed assignment of biochemical components in intact human breast tissue. The spectra of intact breast cancer tissue differ from perchloric acid extracts by the presence of lipids and fewer signals in the low field region. HR MAS analysis of intact breast tissue specimens is a rapid method, providing spectra with resolution where relative quantification of the majority of the detected metabolites is possible.

Applications of neural network analyses to in vivo 1H magnetic resonance spectroscopy of Parkinson disease patients

PURPOSE

To apply neural network analyses to in vivo magnetic resonance spectra of controls and Parkinson disease (PD) patients for the purpose of classification.

MATERIALS AND METHODS

Ninety-seven in vivo proton magnetic resonance spectra of the basal ganglia were recorded from 31 patients with (PD) and 14 age-matched healthy volunteers on a 1.5-T imager. The PD patients were grouped as follows: probable PD (N = 15), possible PD (N = 11), and atypical PD (N = 5). Total acquisition times of approximately five minutes were achieved with a TE (echo time) of 135 msec, a TR (repetition time) of 2000 msec, and 128 scan averages. Neural network (back propagation, Kohonen, probabilistic, and radial basis function) and related (generative topographic mapping) data analyses were performed.

RESULTS

Conventional data analysis showed no statistically significant differences in metabolite ratios based on measuring signal intensities. The trained networks could distinguish control from PD with considerable accuracy (true positive fraction 0.971, true negative fraction 0.933). When four classes were defined, approximately 88% of the predictions were correct. The multivariate analysis indicated metabolic changes in the basal ganglia in PD.

CONCLUSION

A variety of neural network and related approaches can be successfully applied to both qualitative visualization and classification of in vivo spectra of PD patients.

A review of evidence of health benefit from artificial neural networks in medical intervention

The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rĵle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention.