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 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 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 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.

scholarly journals Extended Cranial Ultrasound Views in Infants with Acute Brain Stem/Infratentorial Lesions: Diagnosis of a Progressive Midline Glioma in a 6-Week-Old Infant

2021 ◽  
Vol 11 (01) ◽  
pp. e262-e264
Author(s):  
Matthias Lange ◽  
Bernd Mitzlaff ◽  
Florian Beske ◽  
Holger Koester ◽  
Wiebke Aumann ◽  
...  
Keyword(s):  
Clinical Presentation ◽  
World Health ◽  
Cranial Ultrasound ◽  
Anterior Fontanel ◽  
Resonance Imaging ◽  
Who Grade ◽  
Magnetic Resonance Imaging Mri ◽  
Health Organization ◽  
Mastoid Fontanelle ◽  
Diffuse Midline Glioma

AbstractCentral nervous system (CNS) tumors are the most common solid tumors in children and adolescents. However, in neonates and children aged younger than a year, they are very rare. Clinical presentation in neonates is often subtle and nonspecific. When neurological symptoms are apparent at this age, cranial ultrasound (CUS) is often done as the initial evaluation, with a standard approach through the anterior fontanel (AF), followed by further imaging, such as magnetic resonance imaging (MRI), if necessary. We report the first neonatal case of a rapidly progressive diffuse midline glioma positive for histone H3 K27M mutation (World Health Organization [WHO] grade IV) in which using extended (transmastoid) CUS studies through the mastoid fontanelle (MF) in the second month of life defined the lesion in the brainstem.

Stereotactic radiation treatment for recurrent nonbenign meningiomas

2007 ◽  
Vol 106 (5) ◽  
pp. 846-854 ◽  
Author(s):  
Carlos A. Mattozo ◽  
Antonio A. F. De Salles ◽  
Ivan A. Klement ◽  
Alessandra Gorgulho ◽  
David McArthur ◽  
...  
Keyword(s):  
Radiation Treatment ◽  
Progression Free Survival ◽  
Malignant Progression ◽  
World Health ◽  
Who Grade ◽  
Stereotactic Radiation ◽  
Grade Ii ◽  
Health Organization ◽  
Grade Iii

Object The authors analyzed the results of stereotactic radiosurgery (SRS) and stereotactic radiotherapy (SRT) for the treatment of recurrent meningiomas that were described at initial resection as showing aggressive, atypical, or malignant features (nonbenign). Methods Twenty-five patients who underwent SRS and/or SRT for nonbenign meningiomas between December 1992 and August 2004 were included. Thirteen of these patients underwent treatment for multiple primary or recurrent lesions. In all, 52 tumors were treated. All histological sections were reviewed and reclassified according to World Health Organization (WHO) 2000 guidelines as benign (Grade I), atypical (Grade II), or anaplastic (Grade III) meningiomas. The median follow-up period was 42 months. Seventeen (68%) of the cases were reclassified as follows: WHO Grade I (five cases), Grade II (11 cases), and Grade III (one case). Malignant progression occurred in eight cases (32%) during the follow-up period; these cases were considered as a separate group. The 3-year progression-free survival (PFS) rates for the Grades I, II, and III, and malignant progression groups were 100, 83, 0, and 11%, respectively (p < 0.001). In the Grade II group, the 3-year PFS rates for patients treated with SRS and SRT were 100 and 33%, respectively (p = 0.1). After initial treatment, 22 new tumors required treatment using SRS or SRT; 17 (77%) of them occurred inside the original resection cavity. Symptomatic edema developed in one patient (4%). Conclusions Stereotactic radiation treatment provided effective local control of “aggressive” Grade I and Grade II meningiomas, whereas Grade III lesions were associated with poor outcome. The outcome of cases in the malignant progression group was intermediate between that of the Grade II and Grade III groups, with the lesions showing a tendency toward malignancy.

scholarly journals Oligodendroglioma with Sarcomatous Transformation: Case Report and Literature Review

2019 ◽  
Vol 38 (02) ◽  
pp. 128-136
Author(s):  
Gonçalo Cerdeira Figueiredo ◽  
Célia Maria Pinheiro ◽  
Alfredo Luís Calheiros
Keyword(s):  
Spinal Metastasis ◽  
Poor Response ◽  
World Health ◽  
Rapid Progression ◽  
Who Grade ◽  
Genetic Characteristics ◽  
Oligodendroglial Component ◽  
The Central Nervous System ◽  
Grade Ii ◽  
Health Organization

AbstractOligodendrogliomas are infiltrative tumors of the central nervous system considered to be morphologically stable and to offer a better prognosis. Here, we describe the case of a 36-year-old man with an initial diagnosis of oligodendroglioma, World Health Organization (WHO) grade II, who presented transformation to a sarcomatous form, while maintaining the oligodendroglial component as well as the genetic characteristics of the initial tumor without having undergone any complementary treatments previously. Despite the favorable genetic characteristics, the tumor presented poor response to complementary treatments, and rapid progression, including spinal metastasis.

scholarly journals Benign meningiomas (WHO Grade I) with atypical histological features: correlation of histopathological features with clinical outcomes

2016 ◽  
Vol 124 (1) ◽  
pp. 106-114 ◽  
Author(s):  
Ariel E. Marciscano ◽  
Anat O. Stemmer-Rachamimov ◽  
Andrzej Niemierko ◽  
Mykol Larvie ◽  
William T. Curry ◽  
...  
Keyword(s):  
Prognostic Significance ◽  
Risk Groups ◽  
World Health ◽  
Who Grade ◽  
Simpson Grade ◽  
Atypical Features ◽  
Additional Surgery ◽  
Increased Risk ◽  
Grade Ii ◽  
Health Organization

OBJECT World Health Organization (WHO) Grade I (benign) meningiomas with atypical features may behave more aggressively than similarly graded tumors without atypical features. Here, the prognostic significance of atypical features in benign meningiomas was determined. METHODS Data from patients diagnosed with WHO Grade I benign meningiomas per the 2007 WHO criteria and who underwent surgery between 2002 and 2012 were retrospectively reviewed. Patients were stratified by the absence or presence of 1 to 2 atypical features with review of the clinical and histological factors. RESULTS A total of 148 patients met the inclusion criteria (n = 77 with atypia; n = 71 without atypia). The median follow-up duration after pathological diagnosis was 37.5 months. Thirty patients had progression/recurrence (P/R) after initial treatment, and 22 (73%) of 30 patients with P/R had 1–2 atypical features. The presence of atypical features was significantly associated with P/R (p = 0.03) and independent of the MIB-1 labeling index. The 1-year and 5-year actuarial rates of P/R were 9.6% versus 1.4% and 30.8% versus 13.8% fortumors with and without atypical features, respectively. Higher Simpson grade resection (II–IV vs I) was associated with the increased risk of P/R (p < 0.001). Stratification of patients into low-risk (Simpson Grade I), intermediate-risk (Simpson Grade II–IV with no atypical features), and high-risk groups (Simpson Grade II–IV with atypical features) was significantly correlated with increased risk of P/R (p < 0.001). CONCLUSIONS Patients with benign meningiomas with atypical features and those undergoing Simpson Grade II–IV resection are at significantly increased risk of P/R. Patients with these features may benefit from the consideration of additional surgery and/or radiation therapy.

Sign in / Sign up

Export Citation Format

Share Document