Dataset Information

Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases.

ABSTRACT: We sought to evaluate the utility of radiomics for Amide Proton Transfer weighted (APTw) imaging by assessing its value in differentiating brain metastases from high- and low grade glial brain tumors. We retrospectively identified 48 treatment-naïve patients (10 WHO grade 2, 1 WHO grade 3, 10 WHO grade 4 primary glial brain tumors and 27 metastases) with either primary glial brain tumors or metastases who had undergone APTw MR imaging. After image analysis with radiomics feature extraction and post-processing, machine learning algorithms (multilayer perceptron machine learning algorithm; random forest classifier) with stratified tenfold cross validation were trained on features and were used to differentiate the brain neoplasms. The multilayer perceptron achieved an AUC of 0.836 (receiver operating characteristic curve) in differentiating primary glial brain tumors from metastases. The random forest classifier achieved an AUC of 0.868 in differentiating WHO grade 4 from WHO grade 2/3 primary glial brain tumors. For the differentiation of WHO grade 4 tumors from grade 2/3 tumors and metastases an average AUC of 0.797 was achieved. Our results indicate that the use of radiomics for APTw imaging is feasible and the differentiation of primary glial brain tumors from metastases is achievable with a high degree of accuracy.

SUBMITTER: Sartoretti E

PROVIDER: S-EPMC7943598 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases.

Sartoretti Elisabeth E Sartoretti Thomas T Wyss Michael M Reischauer Carolin C van Smoorenburg Luuk L Binkert Christoph A CA Sartoretti-Schefer Sabine S Mannil Manoj M

Scientific reports 20210309 1

We sought to evaluate the utility of radiomics for Amide Proton Transfer weighted (APTw) imaging by assessing its value in differentiating brain metastases from high- and low grade glial brain tumors. We retrospectively identified 48 treatment-naïve patients (10 WHO grade 2, 1 WHO grade 3, 10 WHO grade 4 primary glial brain tumors and 27 metastases) with either primary glial brain tumors or metastases who had undergone APTw MR imaging. After image analysis with radiomics feature extraction and p ...[more]

PMID: 33750899

Similar Datasets

Project description:Background1p/19q co-deletion in low-grade gliomas (LGG, World Health Organization grade II and III) is of great significance in clinical decision making. We aim to use radiomics analysis to predict 1p/19q co-deletion in LGG based on amide proton transfer weighted (APTw), diffusion weighted imaging (DWI), and conventional MRI.MethodsThis retrospective study included 90 patients histopathologically diagnosed with LGG. We performed a radiomics analysis by extracting 8454 MRI-based features form APTw, DWI and conventional MR images and applied a least absolute shrinkage and selection operator (LASSO) algorithm to select radiomics signature. A radiomics score (Rad-score) was generated using a linear combination of the values of the selected features weighted for each of the patients. Three neuroradiologists, including one experienced neuroradiologist and two resident physicians, independently evaluated the MR features of LGG and provided predictions on whether the tumor had 1p/19q co-deletion or 1p/19q intact status. A clinical model was then constructed based on the significant variables identified in this analysis. A combined model incorporating both the Rad-score and clinical factors was also constructed. The predictive performance was validated by receiver operating characteristic curve analysis, DeLong analysis and decision curve analysis. P < 0.05 was statistically significant.ResultsThe radiomics model and the combined model both exhibited excellent performance on both the training and test sets, achieving areas under the curve (AUCs) of 0.948 and 0.966, as well as 0.909 and 0.896, respectively. These results surpassed the performance of the clinical model, which achieved AUCs of 0.760 and 0.766 on the training and test sets, respectively. After performing Delong analysis, the clinical model did not significantly differ in predictive performance from three neuroradiologists. In the training set, both the radiomic and combined models performed better than all neuroradiologists. In the test set, the models exhibited higher AUCs than the neuroradiologists, with the radiomics model significantly outperforming resident physicians B and C, but not differing significantly from experienced neuroradiologist.ConclusionsOur results suggest that our algorithm can noninvasively predict the 1p/19q co-deletion status of LGG. The predictive performance of radiomics model was comparable to that of experienced neuroradiologist, significantly outperforming the diagnostic accuracy of resident physicians, thereby offering the potential to facilitate non-invasive 1p/19q co-deletion prediction of LGG.

Project description:ImportanceThe process of brain development in children with developmental delay is not well known. Amide proton transfer-weighted (APTw) imaging is a novel molecular magnetic resonance imaging (MRI) technique that can noninvasively detect cytosolic endogenous mobile proteins and peptides involved in the myelination process, and may be useful for providing insights into brain development.ObjectiveTo assess the contribution of amide proton transfer-weighted (APTw) imaging and magnetization transfer (MT) imaging to the evaluation of children with developmental delay (DD).MethodsFifty-one patients with DD were recruited to this study. The patients were divided into two groups according to the state of myelination assessed on conventional magnetic resonance imaging (MRI). Thirty patients (10 girls, 20 boys; age range: 1-8 months; median age: 4 months) in group A showed delayed myelination on MRI, while 21 patients (3 girls, 18 boys; age range: 12-36months; median age: 25months) in group B showed normal myelination on MRI. Fifty-one age- and sex-matched children with normal developmental quotient (DQ) and normal MRI appearance were recruited as normal controls. Three-slice APTw/MT axial imaging was performed at the level of the centrum semiovale, the basal ganglia and the pons. Quantitative data of the MT ratio (MTR) and APTw were analyzed for multiple brain regions. Independent-sample t-tests were used to compare differences in APTw and MTR signals between the two DD groups and normal controls. Analysis of Covariance was conducted to correct the statistical results. The level of statistical significance was set to P < 0.05.ResultsFor group A, the MTR values were lower in all regions (P = 0.004-0.033) compared with the normal controls, while the APTw values were higher in the pons, middle cerebellar peduncle, corpus callosum, frontal white matter, occipital white matter and centrum semiovale (P = 0.004-0.040 ). For Group B, the MTR values were slightly reduced, and the APTw values were slightly increased compared with the normal controls, but the differences were not statistically significant (P > 0.05).InterpretationFor DD patients showing signs of delayed myelination on MRI, MTR and APTw imaging can help to diagnose myelination delay by quantifying semi-solid macromolecules and cytosolic endogenous mobile proteins and peptides at a molecular level, providing a new method for comprehensive evaluation of DD. For DD patients with normal myelination on MRI, the clinical values of MTR and APTw imaging remain to be explored.

Project description:PurposeRadiological assessment of primary brain neoplasms, both high (HGG) and low grade tumors (LGG), based on contrast-enhancement alone can be inaccurate. We evaluated the radiological value of amide proton transfer weighted (APTw) MRI as an imaging complement for pre-surgical radiological diagnosis of brain tumors.MethodsTwenty-six patients were evaluated prospectively; (22 males, 4 females, mean age 55 years, range 26-76 years) underwent MRI at 3T using T1-MPRAGE pre- and post-contrast administration, conventional T2w, FLAIR, and APTw imaging pre-surgically for suspected primary/secondary brain tumor. Assessment of the additional value of APTw imaging compared to conventional MRI for correct pre-surgical brain tumor diagnosis. The initial radiological pre-operative diagnosis was based on the conventional contrast-enhanced MR images. The range, minimum, maximum, and mean APTw signals were evaluated. Conventional normality testing was performed; with boxplots/outliers/skewness/kurtosis and a Shapiro-Wilk's test. Mann-Whitney U for analysis of significance for mean/max/min and range APTw signal. A logistic regression model was constructed for mean, max, range and Receiver Operating Characteristic (ROC) curves calculated for individual and combined APTw signals.ResultsConventional radiological diagnosis prior to surgery/biopsy was HGG (8 patients), LGG (12 patients), and metastasis (6 patients). Using the mean and maximum: APTw signal would have changed the pre-operative evaluation the diagnosis in 8 of 22 patients (two LGGs excluded, two METs excluded). Using a cut off value of >2.0% for mean APTw signal integral, 4 of the 12 radiologically suspected LGG would have been diagnosed as high grade glioma, which was confirmed by histopathological diagnosis. APTw mean of >2.0% and max >2.48% outperformed four separate clinical radiological assessments of tumor type, P-values = .004 and = .002, respectively.ConclusionsUsing APTw-images as part of the daily clinical pre-operative radiological evaluation may improve diagnostic precision in differentiating LGGs from HGGs, with potential improvement of patient management and treatment.

Project description:Background:Amide proton transfer-weighted (APTw) imaging has been revealed to hold great potential in the diagnosis of several brain diseases. The purpose of this proof-of-concept study was to evaluate the feasibility and value of APTw magnetic resonance imaging (MRI) in characterizing normal brain aging. Methods:A total of 106 healthy subjects were recruited and scanned at 3.0 Tesla, with APTw and conventional magnetization transfer (MT) sequences. Quantitative image analyses were performed in 12 regions of interest (ROIs) for each subject. The APTw or MT ratio (MTR) signal differences among five age groups (young, mature, middle-aged, young-old, and middle-old) were assessed using the one-way analysis of variance, with the Benjamini-Hochberg correction for multiple comparisons. The relationship between APTw and MTR signals and the age dependencies of APTw and MTR signals were assessed using the Pearson correlation and non-linear regression. Results:There were no significant differences between the APTw or MTR values for males and females in any of the 12 ROIs analyzed. Among the five age groups, there were significant differences in the three white matter regions in the temporal, occipital, and frontal lobes. Overall, the mean APTw values in the older group were higher than those in the younger group. Positive correlations were observed in relation to age in most brain regions, including four with significant positive correlations (r=0.2065-0.4182) and five with increasing trends. As a comparison, the mean MTR values did not appear to be significantly different among the five age groups. In addition, the mean APTw and MTR values revealed significant positive correlations in 10 ROIs (r=0.2214-0.7269) and a significant negative correlation in one ROI (entorhinal cortex, r=-0.2141). Conclusions:Our early results show that the APTw signal can be used as a promising and complementary imaging biomarker with which normal brain aging can be evaluated at the molecular level.

Dataset Information

Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases.

Publications

Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets