A radiomics-based comparative study on arterial spin labeling and dynamic susceptibility contrast perfusion-weighted imaging in gliomas

Hashido, Takashi; Saito, Shigeyoshi; Ishida, Takayuki

doi:10.1038/s41598-020-62658-9

Cited by 27 publications

(44 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A summary of the results is presented in Table 3 , while the method-related information is summarized in Table 4 . Three of five studies utilized a single MRI sequence acquired by either conventional or advanced imaging [ 14 , 19 , 20 ], while the remaining studies implemented both conventional and advanced ASL and DWI sequences in [ 21 , 22 ]. An imbalanced ratio was observed between the HGG and LGG datasets in the studies that used a large number of samples [ 19 , 21 ], while the remaining three studies had a ratio equal to the sample [ 14 , 20 , 22 ].…”

Section: Resultsmentioning

confidence: 99%

“…Three of five studies utilized a single MRI sequence acquired by either conventional or advanced imaging [ 14 , 19 , 20 ], while the remaining studies implemented both conventional and advanced ASL and DWI sequences in [ 21 , 22 ]. An imbalanced ratio was observed between the HGG and LGG datasets in the studies that used a large number of samples [ 19 , 21 ], while the remaining three studies had a ratio equal to the sample [ 14 , 20 , 22 ]. Two of the five studies selected feature numbers equal to or greater than the total sample size [ 14 , 20 ], while the remaining three studies selected fewer than the total sample size [ 19 , 21 , 22 ].…”

Section: Resultsmentioning

confidence: 99%

“…An imbalanced ratio was observed between the HGG and LGG datasets in the studies that used a large number of samples [ 19 , 21 ], while the remaining three studies had a ratio equal to the sample [ 14 , 20 , 22 ]. Two of the five studies selected feature numbers equal to or greater than the total sample size [ 14 , 20 ], while the remaining three studies selected fewer than the total sample size [ 19 , 21 , 22 ]. Only two studies included a testing set [ 20 ] without reporting the sample size of the testing set [ 19 ].…”

Section: Resultsmentioning

confidence: 99%

“…Two of the five studies selected feature numbers equal to or greater than the total sample size [ 14 , 20 ], while the remaining three studies selected fewer than the total sample size [ 19 , 21 , 22 ]. Only two studies included a testing set [ 20 ] without reporting the sample size of the testing set [ 19 ].…”

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

Diagnostic Accuracy of Machine Learning-Based Radiomics in Grading Gliomas: Systematic Review and Meta-Analysis

Sohn

Bisdas

2020

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Purpose. This study aimed to estimate the diagnostic accuracy of machine learning- (ML-) based radiomics in differentiating high-grade gliomas (HGG) from low-grade gliomas (LGG) and to identify potential covariates that could affect the diagnostic accuracy of ML-based radiomic analysis in classifying gliomas. Method. A primary literature search of the PubMed database was conducted to find all related literatures in English between January 1, 2009, and May 1, 2020, with combining synonyms for “machine learning,” “glioma,” and “radiomics.” Five retrospective designed original articles including LGG and HGG subjects were chosen. Pooled sensitivity, specificity, their 95% confidence interval, area under curve (AUC), and hierarchical summary receiver-operating characteristic (HSROC) models were obtained. Result. The pooled sensitivity when diagnosing HGG was higher (96% (95% CI: 0.93, 0.98)) than the specificity when diagnosing LGG (90% (95% CI 0.85, 0.93)). Heterogeneity was observed in both sensitivity and specificity. Metaregression confirmed the heterogeneity in sample sizes ( p = 0.05 ), imaging sequence types ( p = 0.02 ), and data sources ( p = 0.01 ), but not for the inclusion of the testing set ( p = 0.19 ), feature extraction number ( p = 0.36 ), and selection of feature number ( p = 0.18 ). The results of subgroup analysis indicate that sample sizes of more than 100 and feature selection numbers less than the total sample size positively affected the diagnostic performance in differentiating HGG from LGG. Conclusion. This study demonstrates the excellent diagnostic performance of ML-based radiomics in differentiating HGG from LGG.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Diagnostic Accuracy of Machine Learning-Based Radiomics in Grading Gliomas: Systematic Review and Meta-Analysis

Sohn

Bisdas

2020

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…Currently, the most commonly used techniques to measure perfusion are 15 O positron emission tomography (PET) [ 8 , 9 , 10 ], xenon-enhanced computed tomography (CT) [ 11 , 12 ], single photon emission computed tomography (SPECT) [ 3 , 8 , 13 ], and arterial spin labeling (ASL) magnetic resonance imaging (MRI) [ 1 , 14 , 15 , 16 , 17 , 18 ]. In addition, dynamic susceptibility contrast (DSC) and dynamic contrast enhanced (DCE) MRI are frequently used for perfusion imaging [ 19 , 20 , 21 ]. Although these techniques are well-established, each has some serious drawbacks.…”

Section: Introductionmentioning

confidence: 99%

Hyperpolarized 129Xe Time-of-Flight MR Imaging of Perfusion and Brain Function

et al. 2020

View full text Add to dashboard Cite

Perfusion measurements can provide vital information about the homeostasis of an organ and can therefore be used as biomarkers to diagnose a variety of cardiovascular, renal, and neurological diseases. Currently, the most common techniques to measure perfusion are 15O positron emission tomography (PET), xenon-enhanced computed tomography (CT), single photon emission computed tomography (SPECT), dynamic contrast enhanced (DCE) MRI, and arterial spin labeling (ASL) MRI. Here, we show how regional perfusion can be quantitively measured with magnetic resonance imaging (MRI) using time-resolved depolarization of hyperpolarized (HP) xenon-129 (129Xe), and the application of this approach to detect changes in cerebral blood flow (CBF) due to a hemodynamic response in response to brain stimuli. The investigated HP 129Xe Time-of-Flight (TOF) technique produced perfusion images with an average signal-to-noise ratio (SNR) of 10.35. Furthermore, to our knowledge, the first hemodynamic response (HDR) map was acquired in healthy volunteers using the HP 129Xe TOF imaging. Responses to visual and motor stimuli were observed. The acquired HP TOF HDR maps correlated well with traditional proton blood oxygenation level-dependent functional MRI. Overall, this study expands the field of HP MRI with a novel dynamic imaging technique suitable for rapid and quantitative perfusion imaging.

show abstract

Diagnostic performance of perfusion‐weighted imaging combined with serum MMP‐2 and ‐9 levels in tumor recurrence after postoperative concomitant chemoradiotherapy of glioblastoma

2022

J of Clinical Ultrasound

View full text Add to dashboard Cite

Objective To evaluate diagnostic accuracy of dynamic susceptibility contrast‐ perfusion weighted imaging (DSC‐PWI) combined with serum MMP‐2 and ‐9 levels in differentiating recurrent glioblastoma (GBM). Methods We enrolled a total of 220 GBM patients, including recurrent cases (n = 150) and non‐recurrent cases (n = 70) after postoperative concomitant chemoradiotherapy. All patients performed preoperative and follow‐up DSC‐PWI, and two parameters [normalized cerebral blood volume (nCBV) and cerebral blood flow (nCBF)] were obtained. Preoperative serum levels of MMP‐2 and MMP‐9 were detected using ELISA. The diagnostic performance was evaluated by analyzing receiver operating characteristic (ROC) and area under the curve (AUC). Results At baseline, the recurrence patients had higher nCBF and nCBV than the non‐recurrence patients, accompanying by the increased MMP‐2 and MMP‐9 levels in serum. Serum MMP‐2 level were positively associated with MMP‐9 in recurrent patients. In patients classified as recurrence, both MMP‐9 and MMP‐2 in serum had a significant correlation with nCBV and nCBF. A sensitivity and specificity of nCBF for recurrence vs. non‐recurrence were 94.29% and 63.33%, respectively. nCBV also could provide high discrimination between recurrence and non‐recurrence patients (sensitivity: 84.29%, specificity: 62.67%, AUC: 0.821). In ROC analyses, both MMP‐2 and MMP‐9 distinguished recurrence from non‐recurrence with AUC values of 0.883 and 0.900, respectively. Finally, the combination of DSC‐PWI parameters (nCBF and nCBV) and serum MMP‐2 and ‐9 levels showed much better discrimination capacity between recurrence and non‐recurrence patients with a sensitivity of 92.86%, specificity of 79.33% and AUC of 0.899. Conclusion The combination of DSC‐PWI parameters together with serum MMP‐2 and ‐9 levels offered an attractive approach to noninvasively distinguish recurrence after postoperative radiotherapy of GBM.

show abstract

A radiomics-based comparative study on arterial spin labeling and dynamic susceptibility contrast perfusion-weighted imaging in gliomas

Cited by 27 publications

References 34 publications

Diagnostic Accuracy of Machine Learning-Based Radiomics in Grading Gliomas: Systematic Review and Meta-Analysis

Diagnostic Accuracy of Machine Learning-Based Radiomics in Grading Gliomas: Systematic Review and Meta-Analysis

Hyperpolarized 129Xe Time-of-Flight MR Imaging of Perfusion and Brain Function

Diagnostic performance of perfusion‐weighted imaging combined with serum MMP‐2 and ‐9 levels in tumor recurrence after postoperative concomitant chemoradiotherapy of glioblastoma

Contact Info

Product

Resources

About