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 Preoperative Radiomics Analysis of 1p/19q Status in WHO Grade II Gliomas

2021 ◽  
Vol 11 ◽  
Author(s):  
Ziwen Fan ◽  
Zhiyan Sun ◽  
Shengyu Fang ◽  
Yiming Li ◽  
Xing Liu ◽  
...  
Keyword(s):  
Cross Validation ◽  
Magnetic Resonance Images ◽  
World Health ◽  
Support Vector ◽  
Posterior Probabilities ◽  
Who Grade ◽  
Significant Difference ◽  
Grade Ii ◽  
Who Grade Ii Gliomas ◽  
Fold Cross Validation

PurposeThe present study aimed to preoperatively predict the status of 1p/19q based on radiomics analysis in patients with World Health Organization (WHO) grade II gliomas.MethodsThis retrospective study enrolled 157 patients with WHO grade II gliomas (76 patients with astrocytomas with mutant IDH, 16 patients with astrocytomas with wild-type IDH, and 65 patients with oligodendrogliomas with mutant IDH and 1p/19q codeletion). Radiomic features were extracted from magnetic resonance images, including T1-weighted, T2-weighted, and contrast T1-weighted images. Elastic net and support vector machines with radial basis function kernel were applied in nested 10-fold cross-validation loops to predict the 1p/19q status. Receiver operating characteristic analysis and precision-recall analysis were used to evaluate the model performance. Student’s t-tests were then used to compare the posterior probabilities of 1p/19q co-deletion prediction in the group with different 1p/19q status.ResultsSix valuable radiomic features, along with age, were selected with the nested 10-fold cross-validation loops. Five features showed significant difference in patients with different 1p/19q status. The area under curve and accuracy of the predictive model were 0.8079 (95% confidence interval, 0.733–0.8755) and 0.758 (0.6879–0.8217), respectively, and the F1-score of the precision-recall curve achieved 0.6667 (0.5201–0.7705). The posterior probabilities in the 1p/19q co-deletion group were significantly different from the non-deletion group.ConclusionCombined radiomics analysis and machine learning showed potential clinical utility in the preoperative prediction of 1p/19q status, which can aid in making customized neurosurgery plans and glioma management strategies before postoperative pathology.

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 Machine learning algorithm for improving performance on 3 AQ-screening classification

2019 ◽  
Vol 4 (2) ◽  
pp. 44-49
Author(s):  
Taftazani Ghazi Pratama ◽  
Rudy Hartanto ◽  
Noor Akhmad Setiawan
Keyword(s):  
Machine Learning ◽  
Cross Validation ◽  
Learning Algorithm ◽  
Autism Spectrum ◽  
Support Vector ◽  
Autism Spectrum Quotient ◽  
Machine Learning Algorithm ◽  
Study Support ◽  
Artificial Neural Network Ann ◽  
Fold Cross Validation

Autism Spectrum Disorder (ASD) classification using machine learning can help parents, caregivers, psychiatrists, and patients to obtain the results of early detection of ASD. In this study, the dataset used is the autism-spectrum quotient for child, adolescent and adult, namely AQ-child, AQ-adolescent, AQ-adult. This study aims to improve the sensitivity and specificity of previous studies so that the classification results of ASD are better characterized by the reduced misclassification. The algorithm applied in this study: support vector machine (SVM), random forest (RF), artificial neural network (ANN). The evaluation results using 10-fold cross validation showed that RF succeeded in producing higher adult AQ sensitivity, which was 87.89%. The increase in the specificity level of AQ-Adolescents is better produced using an SVM of 86.33%.

Association between fluorine-18–labeled fluorodeoxyglucose uptake and 1p and 19q loss of heterozygosity in World Health Organization Grade II gliomas

2007 ◽  
Vol 106 (4) ◽  
pp. 633-637 ◽  
Author(s):  
Florian Stockhammer ◽  
Ulrich-Wilhelm Thomale ◽  
Michail Plotkin ◽  
Christian Hartmann ◽  
Andreas von Deimling
Keyword(s):  
World Health Organization ◽  
Fdg Pet ◽  
Magnetic Resonance Images ◽  
World Health ◽  
Low Grade ◽  
Who Grade ◽  
Fdg Uptake ◽  
Grade Ii ◽  
Health Organization ◽  
Who Grade Ii Gliomas

Object Oligodendroglial tumors harboring combined 1p and 19q loss (1p/19q LOH) are characterized by a favorable prognosis and response to chemotherapy and radiotherapy, but detection of 1p/19q LOH relies on postoperative procedures. The authors investigated the potential of fluorine-18–labeled fluorodeoxyglucose (FDG) uptake in positron emission tomography (PET) to predict 1p/19q LOH preoperatively in tumors whose appearance on initial magnetic resonance images was consistent with that of low-grade glioma. Methods The study population comprised 25 patients who had undergone preoperative FDG-PET followed by tumor resection. Neuronavigation ensured a precise match of FDG uptake wi th the site of biopsy. All tumor specimens were graded according to the World Health Organization (WHO) classification system. Microsatellite analysis was used to identify 1p/19q LOH. In this series, 16 of 25 gliomas corresponded to WHO Grade II. In eight of these 16, 1p/19q LOH was detected. Raised glucose utilization within the tumor was seen in the six of eight WHO Grade II gliomas with 1p/19q LOH and in none of the WHO Grade II gliomas without this genetic alteration (p = 0.003). Conclusions These findings demonstrate the potential of FDG-PET to predict 1p/19q LOH in WHO Grade II gliomas.

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.

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.

scholarly journals Seizure response to temozolomide chemotherapy in patients with WHO grade II oligodendroglioma: a single-institution descriptive study

2018 ◽  
Vol 6 (3) ◽  
pp. 203-208 ◽  
Author(s):  
Aya Haggiagi ◽  
Edward K Avila
Keyword(s):  
Disease Progression ◽  
Seizure Frequency ◽  
World Health ◽  
Low Grade ◽  
Inclusion Criteria ◽  
Who Grade ◽  
Seizure Reduction ◽  
Grade Ii ◽  
Health Organization

Abstract Background Tumor-related epilepsy (TRE) is common in patients with low-grade oligodendrogliomas. TRE is difficult to control despite multiple antiepileptic drugs (AEDs) in up to 30% of patients. Chemotherapy has been used for treatment to avoid potential radiotherapy-related neurotoxicity. This study evaluates the effect of temozolomide on seizure frequency in a homogeneous group with World Health Organization (WHO) grade II oligodendrogliomas. Methods A retrospective analysis was conducted of adult patients with WHO grade II oligodendrogliomas and TRE followed at Memorial Sloan Kettering between 2005 and 2015 who were treated with temozolomide alone either as initial treatment or for disease progression. All had seizures 3 months prior to starting temozolomide. Seizure frequency was reviewed every 2 cycles and at the end of temozolomide treatment. Seizure reduction of ≥50% compared to baseline was defined as improvement. Results Thirty-nine individuals met inclusion criteria. Median follow-up since starting temozolomide was 6 years (0.8-13 years). Reduction in seizure frequency occurred in 35 patients (89.7%). Improvement was independent of AED regimen adjustments or prior antitumor treatment in 16 (41%); of these, AED dosage was successfully reduced or completely eliminated in 10 (25.6%). Twenty-five patients (64.1%) remained on a stable AED regimen. The majority (n = 32, 82%) had radiographically stable disease, 5 (12.8%) had objective radiographic response, and 2 (5.2%) had disease progression. Conclusions Temozolomide may result in reduced seizure frequency, and permit discontinuation of AEDs in patients with WHO II oligodendroglioma. Improvement was observed irrespective of objective tumor response on MRI, emphasizing the importance of incorporating seizure control in assessing response to tumor-directed therapy.

scholarly journals Demographics and outcome of histologically confirmed intracranial meningiomas

2019 ◽  
Vol 3 (2) ◽  
pp. 2514183X1989494
Author(s):  
Maria Kamenova ◽  
Raphael Guzman ◽  
Jehuda Soleman
Keyword(s):  
Demographic Data ◽  
Tumor Location ◽  
Morbidity And Mortality ◽  
World Health ◽  
Proliferation Index ◽  
Who Grade ◽  
Primary Tumors ◽  
Radiological Data ◽  
Grade Ii ◽  
Health Organization

Objective: Meningiomas represent the most common intracranial extraaxial neoplasia in adults, accounting for a third of all diagnosed primary tumors of the brain. Despite decades of research, relatively little data on demographics of meningiomas exist. The aim of our study was to undertake an analysis of demographics and outcome of patients who underwent meningioma surgery over an 8-year time period at our institution. Methods: We reviewed 187 consecutive patients with histologically confirmed meningioma. Demographic data, tumor location and side, surgical resection grade, and histopathological and radiological data were collected and assessed for all patients. Furthermore, recurrence, morbidity, and mortality were evaluated. Results: Of the 187 consecutive patients undergoing meningioma resection over a period of 8 years, 131 (70.1%) were women ( p < 0.001). Meningiomas were classified as World Health Organization (WHO) grade I, grade II, and grade III in 66.8%, 31.0%, and 2.1%, of the cases, respectively ( p < 0.001). MIB-1 proliferation index was <1 in 7.5%, 1–5 in 52.9%, 6–10 in 22.4%, >10 in 11.8% of the lesions ( p < 0.001). In 82.4% of the cases, gross total resection was achieved. Recurrence occurred in 23 patients (12.3%), while overall morbidity and mortality rate was 41.2% and 7.7%, respectively. Conclusion: Based on our results, women are more than twice as likely to be affected, and the peak age is between 60 years and 70 years. Recurrence rate in our cohort was relatively low when compared to the data in the literature. The diagnosis of WHO grade II meningiomas, 31% in our cohort, is increasing since the 2007 WHO criteria have been published.

Sign in / Sign up

Export Citation Format

Share Document