scholarly journals Individualized discrimination of tumor recurrence from radiation necrosis in glioma patients using an integrated radiomics-based model

2019 ◽  
Vol 47 (6) ◽  
pp. 1400-1411 ◽  
Author(s):  
Kai Wang ◽  
Zhen Qiao ◽  
Xiaobin Zhao ◽  
Xiaotong Li ◽  
Xin Wang ◽  
...  
Keyword(s):  
Tumor Recurrence ◽  
Validation Cohort ◽  
Radiation Necrosis ◽  
Integrated Model ◽  
Magnetic Resonance Images ◽  
Diagnostic Model ◽  
Integrated Diagnosis ◽  
Diagnosis Model ◽  
Met Pet ◽  
Radiomics Signature

Abstract Purpose To develop and validate an integrated model for discriminating tumor recurrence from radiation necrosis in glioma patients. Methods Data from 160 pathologically confirmed glioma patients were analyzed. The diagnostic model was developed in a primary cohort (n = 112). Textural features were extracted from postoperative 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET), 11C-methionine (11C-MET) PET, and magnetic resonance images. The least absolute shrinkage and selection operator regression model was used for feature selection and radiomics signature building. Multivariable logistic regression analysis was used to develop a model for predicting tumor recurrence. The radiomics signature, quantitative PET parameters, and clinical risk factors were incorporated in the model. The clinical value of the model was then assessed in an independent validation cohort using the remaining 48 glioma patients. Results The integrated model consisting of 15 selected features was significantly associated with postoperative tumor recurrence (p < 0.001 for both primary and validation cohorts). Predictors contained in the individualized diagnosis model included the radiomics signature, the mean of tumor-background ratio (TBR) of 18F-FDG, maximum of TBR of 11C-MET PET, and patient age. The integrated model demonstrated good discrimination, with an area under the curve (AUC) of 0.988, with a 95% confidence interval (CI) of 0.975–1.000. Application in the validation cohort showed good differentiation (AUC of 0.914 and 95% CI of 0.881–0.945). Decision curve analysis showed that the integrated diagnosis model was clinically useful. Conclusions Our developed model could be used to assist the postoperative individualized diagnosis of tumor recurrence in patients with gliomas.

scholarly journals A Computed Tomography-Derived Radiomics Approach for Predicting Uncommon EGFR Mutation in Patients With NSCLC

2021 ◽  
Vol 11 ◽  
Author(s):  
Wufei Chen ◽  
Yanqing Hua ◽  
Dingbiao Mao ◽  
Hao Wu ◽  
Mingyu Tan ◽  
...  
Keyword(s):  
Egfr Mutation ◽  
Validation Cohort ◽  
Characteristic Curve ◽  
Integrated Model ◽  
Curve Analysis ◽  
Support Vector ◽  
Training Cohort ◽  
Contrast Enhanced Ct ◽  
Nsclc Patients ◽  
Radiomics Signature

PurposeThis study aims to develop a CT-based radiomics approach for identifying the uncommon epidermal growth factor receptor (EGFR) mutation in patients with non-small cell lung cancer (NSCLC).MethodsThis study involved 223 NSCLC patients (107 with uncommon EGFR mutation-positive and 116 with uncommon EGFR mutation-negative). A total of 1,269 radiomics features were extracted from the non-contrast-enhanced CT images after image segmentation and preprocessing. Support vector machine algorithm was used for feature selection and model construction. Receiver operating characteristic curve analysis was applied to evaluate the performance of the radiomics signature, the clinicopathological model, and the integrated model. A nomogram was developed and evaluated by using the calibration curve and decision curve analysis.ResultsThe radiomics signature demonstrated a good performance for predicting the uncommon EGFR mutation in the training cohort (area under the curve, AUC = 0.802; 95% confidence interval, CI: 0.736–0.858) and was verified in the validation cohort (AUC = 0.791, 95% CI: 0.642–0.899). The integrated model combined radiomics signature with clinicopathological independent predictors exhibited an incremental performance compared with the radiomics signature or the clinicopathological model. A nomogram based on the integrated model was developed and showed good calibration (Hosmer–Lemeshow test, P = 0.92 in the training cohort and 0.608 in the validation cohort) and discrimination capacity (AUC of 0.816 in the training cohort and 0.795 in the validation cohort).ConclusionRadiomics signature combined with the clinicopathological features can predict uncommon EGFR mutation in NSCLC patients.

scholarly journals SURG-04. SALVAGE RESECTION OF RECURRENT PREVIOUSLY-IRRADIATED BRAIN METASTASES: CLINICAL AND RADIOGRAPHIC OUTCOMES

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii203-ii204
Author(s):  
Jessica Wilcox ◽  
William Newman ◽  
Anne Reiner ◽  
Samantha Brown ◽  
Robert Young ◽  
...  
Keyword(s):  
Treatment Effect ◽  
Tumor Recurrence ◽  
Radiation Necrosis ◽  
Recurrence Risk ◽  
Extent Of Resection ◽  
Cancer Center ◽  
Radiographic Outcomes ◽  
Viable Tumor ◽  
Local Progression ◽  
Salvage Resection

Abstract BACKGROUND The management of brain metastasis (BrM) recurrence after stereotactic body radiotherapy (SBRT) poses a clinical challenge. The efficacy of salvage resection is undefined, and the role of adjuvant resection cavity reirradiation is unclear given the compounded risk of radiation injury. METHODS Retrospective analysis of previously-irradiated BrM that underwent resection between March 2003 and February 2020 at Memorial Sloan Kettering Cancer Center was performed. Only cases with histopathologic evidence of viable malignancy were included, and specimens were classified by the gross proportion of viable tumor versus treatment effect. Clinical and radiographic parameters were collected. Post-operative recurrence and radiation necrosis were based on RANO-BM criteria and distinguished by histopathologic, radiographic and clinical characteristics. Equivocal cases were adjudicated by a blinded neuroradiologist. RESULTS One-hundred fifty-five resected recurrent BrM following SBRT in 135 patients were evaluated. Seventeen received additional prior whole-brain radiation. Metastases derived from non-small-cell lung (36.8%), melanoma (27.1%), breast (21.3%), renal (3.9%), colorectal (1.9%) and other (9.0%) primary malignancies. Forty-eight (31.0%) had only microscopic malignant disease with extensive necrosis, 44 (28.4%) had mixed or unspecified tumor with treatment effect, and 63 (40.6%) were reported as purely viable tumor by histopathologic report. Thirty-nine (25.2%) post-operative cavities underwent adjuvant reirradiation within 60 days. At 6 and 12 months, local tumor recurrence occurred in 31.6% (95% CI: 24.4%-39.1%) and 40.4% (95% CI: 32.5%-48.2%), respectively, with a proportion of these lesions displaying mixed tumor plus treatment effect. Median overall survival was 13.4 months (95% CI: 10.5-17.7) from salvage resection. CONCLUSIONS Salvage of previously-irradiated BrM remains challenging. This represents the largest known series correlating salvage resection and histopathologically-confirmed viable recurrent BrM with long-term outcomes. Tumor recurrence risk remains high at one year. Further exploration will stratify local progression and radiation necrosis rates by features including extent of resection, degree of viable tumor and adjuvant reirradiation use.

scholarly journals Establishment and Validation of an Integrated Model to Predict Postoperative Recurrence in Patients With Atypical Meningioma

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiao-Yong Chen ◽  
Jin-Yuan Chen ◽  
Yin-Xing Huang ◽  
Jia-Heng Xu ◽  
Wei-Wei Sun ◽  
...  
Keyword(s):  
Cox Regression ◽  
Validation Cohort ◽  
Clinical Laboratory ◽  
External Validation ◽  
Postoperative Recurrence ◽  
Integrated Model ◽  
Atypical Meningioma ◽  
Tumor Diameter ◽  
Roc Curve Analysis ◽  
Training Cohort

BackgroundThis study aims to establish an integrated model based on clinical, laboratory, radiological, and pathological factors to predict the postoperative recurrence of atypical meningioma (AM).Materials and MethodsA retrospective study of 183 patients with AM was conducted. Patients were randomly divided into a training cohort (n = 128) and an external validation cohort (n = 55). Univariable and multivariable Cox regression analyses, the least absolute shrinkage and selection operator (LASSO) regression analysis, time-dependent receiver operating characteristic (ROC) curve analysis, and evaluation of clinical usage were used to select variables for the final nomogram model.ResultsAfter multivariable Cox analysis, serum fibrinogen &gt;2.95 g/L (hazard ratio (HR), 2.43; 95% confidence interval (CI), 1.05–5.63; p = 0.039), tumor located in skull base (HR, 6.59; 95% CI, 2.46-17.68; p &lt; 0.001), Simpson grades III–IV (HR, 2.73; 95% CI, 1.01–7.34; p = 0.047), tumor diameter &gt;4.91 cm (HR, 7.10; 95% CI, 2.52–19.95; p &lt; 0.001), and mitotic level ≥4/high power field (HR, 2.80; 95% CI, 1.16–6.74; p = 0.021) were independently associated with AM recurrence. Mitotic level was excluded after LASSO analysis, and it did not improve the predictive performance and clinical usage of the model. Therefore, the other four factors were integrated into the nomogram model, which showed good discrimination abilities in training cohort (C-index, 0.822; 95% CI, 0.759–0.885) and validation cohort (C-index, 0.817; 95% CI, 0.716–0.918) and good match between the predicted and observed probability of recurrence-free survival.ConclusionOur study established an integrated model to predict the postoperative recurrence of AM.

scholarly journals Technical and Tactical Diagnosis Model of Table Tennis Matches Based on BP Neural Network

2021 ◽  
Author(s):  
Wenwen Huang ◽  
Miaomiao Lu ◽  
Yuxuan Zeng ◽  
Mengyue Hu ◽  
Yi Xiao
Keyword(s):  
Neural Network ◽  
High Precision ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Diagnostic Model ◽  
Table Tennis ◽  
Winning Probability ◽  
Highly Efficient ◽  
Diagnosis Model

Abstract Background: The technical and tactical diagnosis of table tennis is extremely important for the preparation of matches, and there is a nonlinear relationship between athletes’ performance and their sports quality. As the neural network model has high nonlinear dynamic processing ability and has high fitting accuracy, the main purpose of this study was to establish a technical and tactical diagnosis model of table tennis matches based on a neural network to diagnose the influence of athletes’ techniques and tactics on the competition result. Methods: A three-layer back propagation neural network model for table tennis match diagnosis were established. The 30 technical and tactical analysis indexes that are closely related to winning a competition were selected based on the double three-phase evaluation method. And 100 table tennis matches were selected as data sample, of which 70 matches were taken as training sample to establish the diagnostic model, the other 30 matches were used to test the validity of the diagnostic model.Results: The technical and tactical diagnosis model of table tennis matches based on BP neural network had a high precision up to 99.997% and highly efficient in fitting (R2 = 0.99). It had a good ability to diagnose the technical and tactical abilities of table tennis players. The technical and tactical diagnosis results showed that the scoring rate of the fourth stroke of Harimoto had the greatest influence on the winning probability.Conclusion: The technical and tactical diagnosis model of table tennis matches based on BP neural network had a high precision and highly efficient in fitting. By using this model, the weights of the influence of athletes’ technical and tactical indexes on the winning probability of the competition can be calculated, which provides a valuable reference for formulating targeted training plans for players.

Radiation necrosis or glioma recurrence: is computer-assisted stereotactic biopsy useful?

1995 ◽  
Vol 82 (3) ◽  
pp. 436-444 ◽  
Author(s):  
Peter A. Forsyth ◽  
Patrick J. Kelly ◽  
Terrence L. Cascino ◽  
Bernd W. Scheithauer ◽  
Edward G. Shaw ◽  
...  
Keyword(s):  
Disease Progression ◽  
Tumor Recurrence ◽  
Stereotactic Biopsy ◽  
Radiation Necrosis ◽  
Low Grade ◽  
Tumor Type ◽  
Content Type ◽  
Radiation Induced ◽  
Chondroblastic Osteosarcoma ◽  
Fine Print

✓ Fifty-one patients with supratentorial glioma treated with external beam radiotherapy (median dose 59.5 Gy) who then demonstrated clinical or radiographic evidence of disease progression underwent stereotactic biopsy to differentiate tumor recurrence from radiation necrosis. The original tumor histological type was diffuse or fibrillary astrocytoma in 21 patients (41%), oligodendroglioma in 13 (26%), and oligoastrocytoma in 17 (33%); 40 tumors (78%) were low-grade (Kernohan Grade 1 or 2). The median time to suspected disease progression was 28 months. Stereotactic biopsy showed tumor recurrence in 30 patients (59%), radiation necrosis in three (6%), and a mixture of both in 17 (33%); one patient (2%) had a parenchymal radiation-induced chondroblastic osteosarcoma. The tumor type at stereotactic biopsy was similar to the original tumor type and was astrocytoma in 24 patients (47%), oligodendroglioma in eight (16%), oligoastrocytoma in 16 (31%), unclassifiable in two (4%), and chondroblastic osteosarcoma in one patient (2%). At biopsy, however, only 19 tumors (37%) were low grade (Kernohan Grade 1 or 2). Subsequent surgery confirmed the stereotactic biopsy histological findings in eight patients. Follow-up examination showed 14 patients alive with a median survival of 1 year for the entire group. Median survival times after biopsy were 0.83 year for patients with tumor recurrence and 1.86 years for patients with both tumor recurrence and radionecrosis; these findings were significantly different (p = 0.008, log-rank test). No patient with radiation necrosis alone died. Other factors associated with reduced survival were a high proportion of residual tumor (p = 0.024), a low proportion of radionecrosis (p < 0.001), and a Kernohan Grade of × or 4 (p = 0.005). In conclusion, in patients with previously irradiated supratentorial gliomas in whom radionecrosis or tumor recurrence was clinically or radiographically suspected, results of stereotactic biopsy could be used to differentiate tumor recurrence, radiation necrosis, a mixture of both lesions, or radiation-induced neoplasm. In addition, biopsy results could predict survival rates.

scholarly journals Improving the Performance of Storage Tank Fault Diagnosis by Removing Unwanted Components and Utilizing Wavelet-Based Features

Entropy ◽  
2019 ◽  
Vol 21 (2) ◽  
pp. 145 ◽  
Author(s):  
Viet Tra ◽  
Bach-Phi Duong ◽  
Jae-Young Kim ◽  
Muhammad Sohaib ◽  
Jong-Myon Kim
Keyword(s):  
Fault Diagnosis ◽  
Storage Tank ◽  
Wavelet Packet ◽  
Relative Energy ◽  
Classification Performance ◽  
Support Vector ◽  
Diagnostic Model ◽  
Spherical Tank ◽  
Useful Components ◽  
Diagnosis Model

This paper proposes a reliable fault diagnosis model for a spherical storage tank. The proposed method first used a blind source separation (BSS) technique to de-noise the input signals so that the signals acquired from a spherical tank under two types of conditions (i.e., normal and crack conditions) were easily distinguishable. BSS split the signals into different sources that provided information about the noise and useful components of the signals. Therefore, an unimpaired signal could be restored from the useful components. From the de-noised signals, wavelet-based fault features, i.e., the relative energy (REWPN) and entropy (EWPN) of a wavelet packet node, were extracted. Finally, these features were used to train one-against-all multiclass support vector machines (OAA MCSVMs), which classified the instances of normal and faulty states of the tank. The efficiency of the proposed fault diagnosis model was examined by visualizing the de-noised signals obtained from the BSS method and its classification performance. The proposed fault diagnostic model was also compared to existing techniques. Experimental results showed that the proposed method outperformed conventional techniques, yielding average classification accuracies of 97.25% and 98.48% for the two datasets used in this study.

scholarly journals Differences in the serum metabolome and lipidome identify potential biomarkers for seronegative rheumatoid arthritis versus psoriatic arthritis

2020 ◽  
Vol 79 (4) ◽  
pp. 499-506 ◽  
Author(s):  
Margarida Souto-Carneiro ◽  
Lilla Tóth ◽  
Rouven Behnisch ◽  
Konstantin Urbach ◽  
Karel D Klika ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Differential Diagnosis ◽  
Biomarker Discovery ◽  
Validation Cohort ◽  
Univariate Analysis ◽  
Proton Nuclear Magnetic Resonance ◽  
Diagnostic Model ◽  
Clinical Markers ◽  
Lipid Ratios ◽  
Specificity And Sensitivity

ObjectivesThe differential diagnosis of seronegative rheumatoid arthritis (negRA) and psoriasis arthritis (PsA) is often difficult due to the similarity of symptoms and the unavailability of reliable clinical markers. Since chronic inflammation induces major changes in the serum metabolome and lipidome, we tested whether differences in serum metabolites and lipids could aid in improving the differential diagnosis of these diseases.MethodsSera from negRA and PsA patients with established diagnosis were collected to build a biomarker-discovery cohort and a blinded validation cohort. Samples were analysed by proton nuclear magnetic resonance. Metabolite concentrations were calculated from the spectra and used to select the variables to build a multivariate diagnostic model.ResultsUnivariate analysis demonstrated differences in serological concentrations of amino acids: alanine, threonine, leucine, phenylalanine and valine; organic compounds: acetate, creatine, lactate and choline; and lipid ratios L3/L1, L5/L1 and L6/L1, but yielded area under the curve (AUC) values lower than 70%, indicating poor specificity and sensitivity. A multivariate diagnostic model that included age, gender, the concentrations of alanine, succinate and creatine phosphate and the lipid ratios L2/L1, L5/L1 and L6/L1 improved the sensitivity and specificity of the diagnosis with an AUC of 84.5%. Using this biomarker model, 71% of patients from a blinded validation cohort were correctly classified.ConclusionsPsA and negRA have distinct serum metabolomic and lipidomic signatures that can be used as biomarkers to discriminate between them. After validation in larger multiethnic cohorts this diagnostic model may become a valuable tool for a definite diagnosis of negRA or PsA patients.

scholarly journals P14.08 Bevacizumab treatment for the lesion emerging after the radiotherapy for malignant glioma

2019 ◽  
Vol 21 (Supplement_3) ◽  
pp. iii68-iii68
Author(s):  
K Miwa ◽  
T Ito ◽  
K Yokoyama ◽  
J Shinoda
Keyword(s):  
Malignant Glioma ◽  
Tumor Recurrence ◽  
Clinical Course ◽  
Radiation Necrosis ◽  
Neurological Dysfunction ◽  
Vascular Endothelial ◽  
Recurrent Malignant Glioma ◽  
Positron Emission ◽  
Bevacizumab Treatment ◽  
Endothelial Growth Factor

Abstract BACKGROUND Because blocking vascular endothelial growth factor from reaching leaky capillaries is a logical strategy for the treatment, we reasoned that bevacizumab might be an effective treatment on recurrent malignant glioma and radiation necrosis (RN). In this study, the authors examined to differentiate RN from recurrent malignant glioma, and evaluated the results of bevacizumab treatment in each diagnosis. MATERIAL AND METHODS Four patients of malignant glioma (2 glioblastomas and 2 anaplastic astrocytomas), which demonstrated symptomatic lesion after radiotherapy, were involved in this study. All four patients were treated with bevacizumab on a 10 mg/kg biweekly (one cycle), for a total dose of 30 mg/kg (3 cycles) or furthermore. RN was differentiated from local recurrence in all four patients on the basis of 11C-methionine positron emission tomography and/or clinical course. Clinical evaluation and MRI studies were obtained after bevacizumab treatment in all cases repeatedly as possible. RESULTS Two patients were diagnosed as RN, and another two patients as tumor recurrence. Of the two patients with RN, neurological dysfunction was distinctly alleviated after bevacizumab treatment. Other two patients with tumor recurrence demonstrated no remarkable improvement in neurological dysfunction after bevacizumab treatment. Of all the two patients with RN, post-treatment MRI performed after the bevacizumab therapy showed a significant reduction of the massive lesion. CONCLUSION We concluded that bevacizumab could control the symptomatic massive lesion occurring after radiotherapy, and it might be more effective with the patients of RN, than with those of recurrent tumor.

Sign in / Sign up

Export Citation Format

Share Document