scholarly journals Better  efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

2019 ◽  
Author(s):  
Sha-Sha Zhao ◽  
Xiu-Long Feng ◽  
Yu-Chuan Hu ◽  
Yu Han ◽  
Qiang Tian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inversion Recovery ◽  
World Health ◽  
Diagnostic Efficacy ◽  
Who Grade ◽  
Superior Efficacy ◽  
Contrast Enhanced ◽  
Fluid Attenuated Inversion Recovery ◽  
T1 Contrast ◽  
Grade Ii

Abstract Background: The medical imaging to differentiate World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas still remains a challenge. We investigated whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1CE) and fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) offered superior efficacy. Methods: Thirty-six patients with histologically confirmed ODGs underwent T1CE and 33 of them underwent FLAIR MR examination before any intervention from January 2015 to July 2017 were retrospectively recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1CE and FLAIR slice by slice using ITK-SNAP and a total of 1072 features were extracted from the VOI using 3-D slicer software. Random forest (RF) algorithm was applied to differentiate ODG2 from ODG3 and the efficacy was tested with 5-fold cross validation. The diagnostic efficacy of radiomics-based machine learning and radiologist’s assessment were also compared. Results: Nineteen ODG2 and 17 ODG3 were included in this study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The AUC, ACC, sensitivity, and specificity of radiomics were 0.798, 0.735, 0.672, 0.789 for T1CE, 0.774, 0.689, 0.700, 0.683 for FLAIR, as well as 0.861, 0.781, 0.778, 0.783 for the combination, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics was superior to the radiologists' assessment. Conclusions: Machine-learning based on radiomics of T1CE and FLAIR offered superior efficacy to that of radiologists in differentiating ODG2 from ODG3.

scholarly journals Better  efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

2020 ◽  
Author(s):  
Sha-Sha Zhao ◽  
Xiu-Long Feng ◽  
Yu-Chuan Hu ◽  
Yu Han ◽  
Qiang Tian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inversion Recovery ◽  
World Health ◽  
Diagnostic Efficacy ◽  
Who Grade ◽  
Superior Efficacy ◽  
Contrast Enhanced ◽  
Fluid Attenuated Inversion Recovery ◽  
T1 Contrast ◽  
Grade Ii

Abstract Background: The medical imaging to differentiate World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas still remains a challenge. We investigated whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1CE) and fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) offered superior efficacy. Methods: Thirty-six patients with histologically confirmed ODGs underwent T1CE and 33 of them underwent FLAIR MR examination before any intervention from January 2015 to July 2017 were retrospectively recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1CE and FLAIR slice by slice using ITK-SNAP and a total of 1072 features were extracted from the VOI using 3-D slicer software. Random forest (RF) algorithm was applied to differentiate ODG2 from ODG3 and the efficacy was tested with 5-fold cross validation. The diagnostic efficacy of radiomics-based machine learning and radiologist’s assessment were also compared. Results: Nineteen ODG2 and 17 ODG3 were included in this study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The AUC, ACC, sensitivity, and specificity of radiomics were 0.798, 0.735, 0.672, 0.789 for T1CE, 0.774, 0.689, 0.700, 0.683 for FLAIR, as well as 0.861, 0.781, 0.778, 0.783 for the combination, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics was superior to the radiologists' assessment. Conclusions: Machine-learning based on radiomics of T1CE and FLAIR offered superior efficacy to that of radiologists in differentiating ODG2 from ODG3.

scholarly journals Better  efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

2020 ◽  
Author(s):  
Sha-Sha Zhao ◽  
Xiu-Long Feng ◽  
Yu-Chuan Hu ◽  
Yu Han ◽  
Qiang Tian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inversion Recovery ◽  
World Health ◽  
Diagnostic Efficacy ◽  
Who Grade ◽  
Superior Efficacy ◽  
Contrast Enhanced ◽  
Fluid Attenuated Inversion Recovery ◽  
T1 Contrast ◽  
Grade Ii

Abstract Abstract Background: The medical imaging to differentiate World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas still remains a challenge. We investigated whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1CE) and fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) offered superior efficacy. Methods: Thirty-six patients with histologically confirmed ODGs underwent T1CE and 33 of them underwent FLAIR MR examination before any intervention from January 2015 to July 2017 were retrospectively recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1CE and FLAIR slice by slice using ITK-SNAP and a total of 1072 features were extracted from the VOI using 3-D slicer software. Random forest (RF) algorithm was applied to differentiate ODG2 from ODG3 and the efficacy was tested with 5-fold cross validation. The diagnostic efficacy of radiomics-based machine learning and radiologist’s assessment were also compared. Results: Nineteen ODG2 and 17 ODG3 were included in this study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The AUC, ACC, sensitivity, and specificity of radiomics were 0.798, 0.735, 0.672, 0.789 for T1CE, 0.774, 0.689, 0.700, 0.683 for FLAIR, as well as 0.861, 0.781, 0.778, 0.783 for the combination, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics was superior to the radiologists' assessment. Conclusions: Machine-learning based on radiomics of T1CE and FLAIR offered superior efficacy to that of radiologists in differentiating ODG2 from ODG3.

scholarly journals Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery imagines

2019 ◽  
Author(s):  
Sha-Sha Zhao ◽  
Xiu-Long Feng ◽  
Yu-Chuan Hu ◽  
Yu Han ◽  
Qiang Tian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inversion Recovery ◽  
World Health ◽  
Diagnostic Efficacy ◽  
Who Grade ◽  
Superior Efficacy ◽  
Contrast Enhanced ◽  
Fluid Attenuated Inversion Recovery ◽  
T1 Contrast ◽  
Grade Ii

Abstract Background: The medical imaging to differentiate World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas still remains a challenge. We investigated whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1CE) and fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) offered superior efficacy. Methods: Thirty-six patients with histologically confirmed ODGs underwent T1CE and 33 of them underwent FLAIR MR examination before any intervention from January 2015 to July 2017 were retrospectively recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1CE and FLAIR slice by slice using ITK-SNAP and a total of 1072 features were extracted from the VOI using 3-D slicer software. Random forest (RF) algorithm was applied to differentiate ODG2 from ODG3 and the efficacy was tested with 5-fold cross validation. The diagnostic efficacy of radiomics-based machine learning and radiologist’s assessment were also compared. Results: Nineteen ODG2 and 17 ODG3 were included in this study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The AUC, ACC, sensitivity, and specificity of radiomics were 0.798, 0.735, 0.672, 0.789 for T1CE, 0.774, 0.689, 0.700, 0.683 for FLAIR, as well as 0.861, 0.781, 0.778, 0.783 for the combination, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics was superior to the radiologists' assessment. Conclusions: Machine-learning based on radiomics of T1CE and FLAIR offered superior efficacy to that of radiologists in differentiating ODG2 from ODG3.

scholarly journals Comparable efficacies in differentiating WHO grade II from III oligodendrogliomas with machine-learning and radiologist’s reading

2019 ◽  
Author(s):  
Sha-Sha Zhao ◽  
Lin-Feng Yan ◽  
Xiu-Long Feng ◽  
Yu-Chuan Hu ◽  
Yu Han ◽  
...  
Keyword(s):  
Machine Learning ◽  
World Health ◽  
Comparable Efficacy ◽  
Diagnostic Efficiency ◽  
Who Grade ◽  
Machine Leaning ◽  
T1 Contrast ◽  
Grade Ii ◽  
Magnetic Resonance Imaging Mri ◽  
Health Organization

Abstract Abstract (236 words) Background: The medical imaging differentiation of World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas remains a challenge. We investigate whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1CE) magnetic resonance imaging (MRI) can offer improved efficacy. Methods: Thirty-six patients with histologically confirmed ODGs who underwent the T1CE MR examination before any intervention between January 2015 and July 2017 were recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1CE slice by slice using ITK-SNAP and a total of 1044 features were extracted from the VOI using Analysis-Kinetics software. Random forest (RF) algorithm and 5-fold cross validation were applied to differentiate ODG2 from ODG3. The diagnostic efficacies of radiomics-based machine learning and radiologist’s assessment were also compared. Results: Nineteen ODG2 and 17 ODG3 were included in the current study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The RF strategy with radiomics features produced the stable diagnostic efficiency, with an AUC, ACC, sensitivity, and specificity of 0.765, 0.763, 82.8% and 70.0%, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics is comparable to that of radiologist. Conclusions: Machine-learning based on radiomics of T1CE offered comparable efficacy to that of radiologist on differentiating ODG2 from ODG3.

scholarly journals Photopenic defects on O-(2-[18F]-fluoroethyl)-L-tyrosine PET: clinical relevance in glioma patients

2019 ◽  
Vol 21 (10) ◽  
pp. 1331-1338 ◽  
Author(s):  
Norbert Galldiks ◽  
Marcus Unterrainer ◽  
Natalie Judov ◽  
Gabriele Stoffels ◽  
Marion Rapp ◽  
...  
Keyword(s):  
Standardized Uptake Value ◽  
Progression Free Survival ◽  
Tracer Uptake ◽  
World Health ◽  
Diffuse Astrocytoma ◽  
Who Grade ◽  
Fet Pet ◽  
Fluid Attenuated Inversion Recovery ◽  
Grade Ii ◽  
Health Organization

Abstract Background O-(2-[18F]-fluoroethyl)-L-tyrosine (FET) PET has a sensitivity of more than 90% to detect gliomas. In the remaining small fraction of gliomas without increased tracer uptake, some tumors even show photopenic defects whose clinical significance is unclear. Methods Glioma patients with a negative FET PET scan prior to neuropathological confirmation were identified retrospectively. Gliomas were rated visually as (i) having indifferent FET uptake or (ii) photopenic, if FET uptake was below background activity. FET uptake in the area of signal hyperintensity on the T2/fluid attenuated inversion recovery–weighted MRI was evaluated by mean standardized uptake value (SUV) and mean tumor-to-brain ratio (TBR). The progression-free survival (PFS) of photopenic gliomas was compared with that of gliomas with indifferent FET uptake. Results Of 100 FET-negative gliomas, 40 cases with photopenic defects were identified. Fifteen of these 40 cases (38%) had World Health Organization (WHO) grades III and IV gliomas. FET uptake in photopenic gliomas was significantly decreased compared with both the healthy-appearing brain tissue (SUV, 0.89 ± 0.26 vs 1.08 ± 0.23; P < 0.001) and gliomas with indifferent FET uptake (TBR, 0.82 ± 0.09 vs 0.96 ± 0.13; P < 0.001). Irrespective of the applied treatment, isocitrate dehydrogenase (IDH)–mutated WHO grade II diffuse astrocytoma patients with indifferent FET uptake (n = 25) had a significantly longer PFS than patients with IDH-mutated diffuse astrocytomas (WHO grade II) with photopenic defects (n = 11) (51 vs 24 mo; P = 0.027). The multivariate survival analysis indicated that photopenic defects predict an unfavorable PFS (P = 0.009). Conclusion Photopenic gliomas in negative FET PET scans should be managed more actively, as they seem to have a higher risk of harboring a higher-grade glioma and an unfavorable outcome.

scholarly journals Radiomics Features Predict Telomerase Reverse Transcriptase Promoter Mutations in World Health Organization Grade II Gliomas via a Machine-Learning Approach

2021 ◽  
Vol 10 ◽  
Author(s):  
Shengyu Fang ◽  
Ziwen Fan ◽  
Zhiyan Sun ◽  
Yiming Li ◽  
Xing Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cross Validation ◽  
Learning Algorithm ◽  
World Health ◽  
Machine Learning Algorithm ◽  
Who Grade ◽  
Grade Ii ◽  
Health Organization ◽  
Who Grade Ii Gliomas ◽  
Fold Cross Validation

The detection of mutations in telomerase reverse transcriptase promoter (pTERT) is important since preoperative diagnosis of pTERT status helps with evaluating prognosis and determining the surgical strategy. Here, we aimed to establish a radiomics-based machine-learning algorithm and evaluated its performance with regard to the prediction of mutations in pTERT in patients with World Health Organization (WHO) grade II gliomas. In total, 164 patients with WHO grade II gliomas were enrolled in this retrospective study. We extracted a total of 1,293 radiomics features from multi-parametric magnetic resonance imaging scans. Elastic net (used for feature selection) and support vector machine with linear kernel were applied in nested 10-fold cross-validation loops. The predictive model was evaluated by receiver operating characteristic and precision-recall analyses. We performed an unpaired t-test to compare the posterior predictive probabilities among patients with differing pTERT statuses. We selected 12 valuable radiomics features using nested 10-fold cross-validation loops. The area under the curve (AUC) was 0.8446 (95% confidence interval [CI], 0.7735–0.9065) with an optimal summed value of sensitivity of 0.9355 (95% CI, 0.8802–0.9788) and specificity of 0.6197 (95% CI, 0.5071–0.7371). The overall accuracy was 0.7988 (95% CI, 0.7378–0.8598). The F1-score was 0.8406 (95% CI, 0.7684–0.902) with an optimal precision of 0.7632 (95% CI, 0.6818–0.8364) and recall of 0.9355 (95% CI, 0.8802–0.9788). Posterior probabilities of pTERT mutations were significantly different between patients with wild-type and mutant TERT promoters. Our findings suggest that a radiomics analysis with a machine-learning algorithm can be useful for predicting pTERT status in patients with WHO grade II glioma and may aid in glioma management.

scholarly journals Extracranial metastases in secondary glioblastoma multiforme: a case report

BMC Neurology ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Jessica Rossi ◽  
Lucia Giaccherini ◽  
Francesco Cavallieri ◽  
Manuela Napoli ◽  
Claudio Moratti ◽  
...  
Keyword(s):  
Brain Lesion ◽  
Rare Event ◽  
Subsequent Development ◽  
World Health ◽  
Who Grade ◽  
Systemic Involvement ◽  
Grade Ii ◽  
The Stability ◽  
Health Organization ◽  
Extracranial Metastases

Abstract Background Glioblastoma (GBM) is known for its devastating intracranial infiltration and its unfavorable prognosis, while extracranial involvement is a very rare event, more commonly attributed to IDH wild-type (primary) GBM evolution. Case presentation We present a case of a young woman with a World Health Organization (WHO) grade II Astrocytoma evolved to WHO grade IV IDH mutant glioblastoma, with subsequent development of lymphatic and bone metastases, despite the favorable biomolecular pattern and the stability of the primary brain lesion. Conclusions Our case highlights that grade II Astrocytoma may evolve to a GBM and rarely lead to a secondary metastatic diffusion, which can progress quite rapidly; any symptoms referable to a possible systemic involvement should be carefully investigated.

Identification of WHO II/III gliomas by 16 prognostic-related gene signatures using machine learning methods

2021 ◽  
Vol 28 ◽  
Author(s):  
YaMeng Wu ◽  
Yu Sa ◽  
Yu Guo ◽  
QiFeng Li ◽  
Ning Zhang
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Overall Survival ◽  
High Risk ◽  
Who Grade ◽  
Machine Learning Methods ◽  
Medium Risk ◽  
Grade Ii ◽  
Fully Connected ◽  
Genome Atlas

Background: It is found that the prognosis of gliomas of the same grade has large differences among World Health Organization(WHO) grade II and III in clinical observation. Therefore, a better understanding of the genetics and molecular mechanisms underlying WHO grade II and III gliomas is required, with the aim of developing a classification scheme at the molecular level rather than the conventional pathological morphology level. Method: We performed survival analysis combined with machine learning methods of Least Absolute Shrinkage and Selection Operator using expression datasets downloaded from the Chinese Glioma Genome Atlas as well as The Cancer Genome Atlas. Risk scores were calculated by the product of expression level of overall survival-related genes and their multivariate Cox proportional hazards regression coefficients. WHO grade II and III gliomas were categorized into the low-risk subgroup, medium-risk subgroup, and high-risk subgroup. We used the 16 prognostic-related genes as input features to build a classification model based on prognosis using a fully connected neural network. Gene function annotations were also performed. Results: The 16 genes (AKNAD1, C7orf13, CDK20, CHRFAM7A, CHRNA1, EFNB1, GAS1, HIST2H2BE, KCNK3, KLHL4, LRRK2, NXPH3, PIGZ, SAMD5, ERINC2, and SIX6) related to the glioma prognosis were screened. The 16 selected genes were associated with the development of gliomas and carcinogenesis. The accuracy of an external validation data set of the fully connected neural network model from the two cohorts reached 95.5%. Our method has good potential capability in classifying WHO grade II and III gliomas into low-risk, medium-risk, and high-risk subgroups. The subgroups showed significant (P<0.01) differences in overall survival. Conclusion: This resulted in the identification of 16 genes that were related to the prognosis of gliomas. Here we developed a computational method to discriminate WHO grade II and III gliomas into three subgroups with distinct prognoses. The gene expression-based method provides a reliable alternative to determine the prognosis of gliomas.

Contrast-enhanced Fast Fluid-attenuated Inversion Recovery MR Imaging in Patients with Brain Tumors

2000 ◽  
Vol 43 (3) ◽  
pp. 257
Author(s):  
Chan Kyo Kim ◽  
Dong Gyu Na ◽  
Wook Jae Ryoo ◽  
Hong Sik Byun ◽  
Hye Kyung Yoon ◽  
...  
Keyword(s):  
Brain Tumors ◽  
Mr Imaging ◽  
Inversion Recovery ◽  
Contrast Enhanced ◽  
Fluid Attenuated Inversion Recovery
Sign in / Sign up

Export Citation Format

Share Document