MR Imaging in the 21st Century: Technical Innovation over the First Two Decades

Kabasawa, Hiroyuki

doi:10.2463/mrms.rev.2021-0011

Cited by 22 publications

(10 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MRI is one of the most commonly used imaging tools for CNS diseases [ 29 , 30 ]. In conventional MRI, the T1WI sequence reflects the T1 relaxation difference of each tissue, focusing on the anatomical structure of the tissue; the T2WI sequence reflects the T2 relaxation difference of each tissue, focusing on abnormal changes in the tissue; the T2-Fair sequence is mainly used to distinguish the free water and the bound water in the tissue; the DWI sequence is used to evaluate the diffusion movement of water molecules in the tissue, which can indicate microstructural differences in diseased tissues; and CE-T1WI uses gadolinium as a contrast agent, which can shorten the T1 relaxation time, thereby enhancing the signal and reflecting the difference in gadolinium absorption between tumor tissue and normal tissue, and high-blood-flow tissues exhibit high signal intensity during CE-T1WI scanning due to the high content of gadolinium.…”

Section: Discussionmentioning

confidence: 99%

Predicting Histopathological Grading of Adult Gliomas Based On Preoperative Conventional Multimodal MRI Radiomics: A Machine Learning Model

Liu

Wu³

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

Purpose: The accurate preoperative histopathological grade diagnosis of adult gliomas is of great significance for the formulation of a surgical plan and the implementation of a subsequent treatment. The aim of this study is to establish a predictive model for classifying adult gliomas into grades 2–4 based on preoperative conventional multimodal MRI radiomics. Patients and Methods: Patients with pathologically confirmed gliomas at Huashan Hospital, Fudan University, between February 2017 and July 2019 were retrospectively analyzed. Two regions of interest (ROIs), called the maximum anomaly region (ROI1) and the tumor region (ROI2), were delineated on the patients’ preoperative MRIs utilizing the tool ITK-SNAP, and Pyradiomics 3.0 was applied to execute feature extraction. Feature selection was performed utilizing a least absolute shrinkage and selection operator (LASSO) filter. Six classifiers, including Gaussian naive Bayes (GNB), random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM) with a linear kernel, adaptive boosting (AB), and multilayer perceptron (MLP) were used to establish predictive models, and the predictive performance of the six classifiers was evaluated through five-fold cross-validation. The performance of the predictive models was evaluated using the AUC and other metrics. After that, the model with the best predictive performance was tested using the external data from The Cancer Imaging Archive (TCIA). Results: According to the inclusion and exclusion criteria, 240 patients with gliomas were identified for inclusion in the study, including 106 grade 2, 68 grade 3, and 66 grade 4 gliomas. A total of 150 features was selected, and the MLP classifier had the best predictive performance among the six classifiers based on T2-FLAIR (mean AUC of 0.80 ± 0.07). The SVM classifier had the best predictive performance among the six classifiers based on DWI (mean AUC of 0.84 ± 0.05); the SVM classifier had the best predictive performance among the six classifiers based on CE-T1WI (mean AUC of 0.85 ± 0.06). Among the six classifiers, based on ROI1, the MLP classifier had the best prediction performance (mean AUC of 0.78 ± 0.07); among the six classifiers, based on ROI2, the SVM classifier had the best prediction performance (mean AUC of 0.82 ± 0.07). Among the six classifiers, based on the multimodal MRI of all the ROIs, the SVM classifier had the best prediction performance (average AUC of 0.85 ± 0.04). The SVM classifier, based on the multimodal MRI of all the ROIs, achieved an AUC of 0.81 using the external data from TCIA. Conclusions: The prediction model, based on preoperative conventional multimodal MRI radiomics, established in this study can conveniently, accurately, and noninvasively classify adult gliomas into grades 2–4, providing certain assistance for the precise diagnosis and treatment of patients and optimizing their clinical management.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting Histopathological Grading of Adult Gliomas Based On Preoperative Conventional Multimodal MRI Radiomics: A Machine Learning Model

Liu

Wu³

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

show abstract

“…Several diseases mimic MS [48]. In some cases, they were mistakenly diagnosed with MS, especially before the MRI era (i.e., before the 1980s [49]). Similarly, the diagnosis of epileptic seizures and epilepsy in MS patients can be challenging.…”

Section: Limitationsmentioning

confidence: 99%

Seizures in Multiple Sclerosis are, above all, a Matter of Brain Viability

Kavčič,

E Hofmann

2024

SciBase Neurol

View full text Add to dashboard Cite

Objectives: Most patients with Multiple Sclerosis (MS) never have a seizure, although they are at risk for seizures since the onset of MS. This paradox leads us to suppose that MS plays a minor role in seizure generation and epileptogenesis. Methods: Qualitative study using data triangulation and inductive content analysis. A comprehensive literature search was carried out in four electronic databases (MEDLINE, Embase, Web of Science, and Google Scholar). Results: In MS patients, unprovoked seizures occur rarely (in about 3 percent of cases). Pediatric MS involves seizures more common than adult or late-onset MS. In general, children with seizures do not have poorer MS prognoses than children without seizures. Contrary to the general population, seizures do not peak in older MS patients. Since the use of disease-modifying therapies in the treatment of MS (i.e., since 1993), the frequency of seizures in MS patients has not changed considerably. Epilepsy syndrome cannot be recognized in MS patients with seizures. As a rule, seizures in MS are not difficult to treat. A sudden unexpected death in MS patients with seizures has not been observed more commonly than in the general epilepsy population. A disruption of the blood–brain barrier is the most obvious proconvulsive factor of MS. However, neither MS relapses nor a high rate of MS relapses is normally accompanied by seizures. Structural brain abnormalities usually accumulate over the course of MS. However, a high brain magnetic resonance imaging lesion load does not have a substantial impact on seizure occurrence in MS. Conclusion: MS does not have a major role in seizure generation and epileptogenesis. In most cases, the seizure-promoting effects of MS can be successfully counteracted by the brain´s protective mechanisms.

show abstract

“…Developing efficient acquisition techniques such as turbo spin-echo and gradient echo, as well as acceleration techniques such as parallel imaging 15 and compressed sensing, 16 have enabled the acquisition of multiple MR images in a clinically acceptable scan time. 17 Recently, quantitative imaging has been developing fast, and various methods, which are roughly categorized into indirect and direct measurement methods, 18 can be used to acquire T1 and T2 relaxation times and proton density maps simultaneously (Fig. 1 ).…”

Section: Acquisition Of Multiparametric Mr Imagesmentioning

confidence: 99%

Multiparametric MRI

et al. 2023

View full text Add to dashboard Cite

With the recent advancements in rapid imaging methods, higher numbers of contrasts and quantitative parameters can be acquired in less and less time. Some acquisition models simultaneously obtain multiparametric images and quantitative maps to reduce scan times and avoid potential issues associated with the registration of different images. Multiparametric magnetic resonance imaging (MRI) has the potential to provide complementary information on a target lesion and thus overcome the limitations of individual techniques. In this review, we introduce methods to acquire multiparametric MRI data in a clinically feasible scan time with a particular focus on simultaneous acquisition techniques, and we discuss how multiparametric MRI data can be analyzed as a whole rather than each parameter separately. Such data analysis approaches include clinical scoring systems, machine learning, radiomics, and deep learning. Other techniques combine multiple images to create new quantitative maps associated with meaningful aspects of human biology. They include the magnetic resonance g-ratio, the inner to the outer diameter of a nerve fiber, and the aerobic glycolytic index, which captures the metabolic status of tumor tissues.

show abstract

MR Imaging in the 21st Century: Technical Innovation over the First Two Decades

Cited by 22 publications

References 85 publications

Predicting Histopathological Grading of Adult Gliomas Based On Preoperative Conventional Multimodal MRI Radiomics: A Machine Learning Model

Predicting Histopathological Grading of Adult Gliomas Based On Preoperative Conventional Multimodal MRI Radiomics: A Machine Learning Model

Seizures in Multiple Sclerosis are, above all, a Matter of Brain Viability

Multiparametric MRI

Contact Info

Product

Resources

About