scholarly journals Hepatic Alveolar Echinococcosis: Predictive Biological Activity Based on Radiomics of MRI

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Bo Ren ◽  
Jian Wang ◽  
Zhoulin Miao ◽  
Yuwei Xia ◽  
Wenya Liu ◽  
...  
Keyword(s):  
Biological Activity ◽  
Alveolar Echinococcosis ◽  
Characteristic Curve ◽  
Three Dimensional ◽  
Classification Performance ◽  
Support Vector ◽  
Lasso Regression ◽  
Hepatic Alveolar Echinococcosis ◽  
Positron Emission ◽  
Pet Ct

Background. To evaluate the role of radiomics based on magnetic resonance imaging (MRI) in the biological activity of hepatic alveolar echinococcosis (HAE). Methods. In this study, 90 active and 46 inactive cases of HAE patients were analyzed retrospectively. All the subjects underwent MRI and positron emission tomography computed tomography (PET-CT) before surgery. A total of 1409 three-dimensional radiomics features were extracted from the T2-weighted MR images (T2WI). The inactive group in the training cohort was balanced via the synthetic minority oversampling technique (SMOTE) method. The least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were logistic regression (LR), multilayer perceptron (MLP), and support vector machine (SVM). We used a fivefold cross-validation strategy in the training cohorts. The classification performance of the radiomics signature was evaluated using receiver operating characteristic curve (ROC) analysis in the training and test cohorts. Results. The radiomics features were significantly associated with the biological activity, and 10 features were selected to construct the radiomics model. The best performance of the radiomics model for the biological activity prediction was obtained by MLP ( AUC = 0.830 ± 0.053 ; accuracy = 0.817 ; sensitivity = 0.822 ; specificity = 0.811 ). Conclusions. We developed and validated a radiomics model as an adjunct tool to predict the HAE biological activity by combining T2WI images, which achieved results nearly equal to the PET-CT findings.

scholarly journals A CT-Based Radiomics Nomogram To Predict The Biological Activity of Hepatic Alveolar Echinococcosis

2021 ◽  
Author(s):  
Jian Wang ◽  
Tieliang Zhang ◽  
Yi Jiang ◽  
Yafei Zhao ◽  
Wenyao Xu ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Biological Activity ◽  
Alveolar Echinococcosis ◽  
Model Performance ◽  
K Nearest Neighbors ◽  
Hepatic Alveolar Echinococcosis ◽  
Positron Emission ◽  
Pet Ct ◽  
Combined Models ◽  
Selection Operator

Abstract BackgroundThis study aims to establish a computed tomography (CT) - based radiomics nomogram to predict the biological activity of hepatic alveolar echinococcosis (HAE).MethodsA total of 174 HAE patients (139 for training, 35 for test) were enrolled whose CT and positron emission tomography-computed tomography (PET/CT) examinations were performed before surgery, and the biological activity was evaluated according to the PET/CT. Radiomic features were extracted from CT images, based on which radiomic scores (Rad-score) were calculated with the least absolute shrinkage and selection operator logistic regression. Three radiomics models (K-Nearest Neighbors, Logical regression, and Multilayer Perceptron), including only radiomic features and a radiomics nomogram, comprised of demographics, clinical indexes, and radiomic features were constructed respectively to predict the biological activity of HAE. The model performance was evaluated by area under curve (AUC), decision curve, and calibration curve.Results30 features in total were selected as optimal radiomic features and considered as input to calculate the Rad-score. There were no significant differences in the predictive efficacy between the combined models and the radiomics models from the perspective of the decision curve. The radiomics models was unparalleled, with an AUC of 0.952 (95%CI=0.902~0.981, P<0.0001) and 0.800 (95%CI=0.631~0.916, P<0.0020) in the training and testing cohort, respectively.ConclusionThe radiomics nomogram model showed great potential in identifying HAE biological activity.

scholarly journals PSA and PSA Kinetics Thresholds for the Presence of 68Ga-PSMA-11 PET/CT-Detectable Lesions in Patients with Biochemical Recurrent Prostate Cancer

Cancers ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 398 ◽  
Author(s):  
Manuela Andrea Hoffmann ◽  
Hans-Georg Buchholz ◽  
Helmut J. Wieler ◽  
Matthias Miederer ◽  
Florian Rosar ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Characteristic Curve ◽  
Specific Antigen ◽  
Recurrent Prostate Cancer ◽  
Psa Kinetics ◽  
Scan Time ◽  
Positron Emission ◽  
Pet Ct ◽  
Positive Scan ◽  
Previously Treated

68Ga-PSMA-11 positron-emission tomography/computed tomography (PET/CT) is commonly used for restaging recurrent prostate cancer (PC) in European clinical practice. The goal of this study is to determine the optimum time for performing these PET/CT scans in a large cohort of patients by identifying the prostate-specific-antigen (PSA) and PSA kinetics thresholds for detecting and localizing recurrent PC. This retrospective analysis includes 581 patients with biochemical recurrence (BC) by definition. The performance of 68Ga-PSMA-11 PET/CT in relation to the PSA value at the scan time as well as PSA kinetics was assessed by the receiver-operating-characteristic-curve (ROC) generated by plotting sensitivity versus 1-specificity. Malignant prostatic lesions were identified in 77%. For patients that were treated with radical prostatectomy (RP) a PSA value of 1.24 ng/mL was found to be the optimal cutoff level for predicting positive and negative scans, while for patients previously treated with radiotherapy (RT) it was 5.75 ng/mL. In RP-patients with PSA value <1.24 ng/mL, 52% scans were positive, whereas patients with PSA ≥1.24 ng/mL had positive scan results in 87%. RT-patients with PSA <5.75 ng/mL had positive scans in 86% and for those with PSA ≥5.75 ng/mL 94% had positive scans. This study identifies the PSA and PSA kinetics threshold levels for the presence of 68Ga-PSMA-11 PET/CT-detectable PC-lesions in BC patients.

Successful surgical management of hepatic alveolar echinococcosis by inductive therapy with albendazole – a case report

2020 ◽  
Vol 58 (01) ◽  
pp. 63-67 ◽  
Author(s):  
Michael Bartels ◽  
Thomas Schmidt ◽  
Christoph Lübbert
Keyword(s):  
Hepatic Vein ◽  
Fdg Pet ◽  
Alveolar Echinococcosis ◽  
Postoperative Treatment ◽  
Blood Levels ◽  
Hepatic Alveolar Echinococcosis ◽  
Pet Ct ◽  
18F Fdg ◽  
The Right ◽  
Fdg Pet Ct

AbstractWe report the case of a 65-year-old female patient with hepatic alveolar echinococcosis (AE) caused by Echinococcus multilocularis. This infrequent zoonosis has a considerable morbidity and mortality. The malignant appearing hepatic mass was initially misdiagnosed as cholangiocarcinoma of the right hepatic lobe (segments VII, VIII, and IVa, sized 10.9 cm × 7.6 cm) involving the right and middle hepatic vein and extending close to the left hepatic vein. During exploratory laparotomy, the frozen-section biopsy was indicative of AE (World Health Organization [WHO] classification: stage P3N0M0). Due to the high operative risk, it was decided to pretreat the patient with albendazole as inductive therapy in order to remove the AE secondarily in accordance with the patient’s request. After year-long treatment with albendazole (under strict control of the maximum blood levels), a right hemihepatectomy was successfully performed. Postoperative treatment with albendazole had to be stopped prematurely after 11 months due to considerable subjective intolerance and a more-than-tenfold elevation of transaminases despite normal therapeutic albendazole blood levels. A 18F-FDG-PET/CT scan revealed no evidence of AE residues. Conducting follow-up examinations by 18F-FDG-PET/CT scans every 2 years is planned in order to recognize possible recurrence at an early stage.

A New Algorithm for Analysis of MiRNA Expression Profiles—SVM-RFE-FKNN

2021 ◽  
Author(s):  
Duan Mei ◽  
Qiang Liu
Keyword(s):  
Mirna Expression ◽  
Nearest Neighbor ◽  
Expression Profiles ◽  
Binary Classification ◽  
Characteristic Curve ◽  
Classification Performance ◽  
Recursive Feature Elimination ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Mirna Expression Profiles

Based on MicroRNA (miRNA) expression profiles, this article proposes a new algorithm—SVM-RFE-FKNN, which combines the support vector machine-recursive feature elimination (SVM-RFE) algorithm and the fuzzy K -nearest neighbor (FKNN) algorithm, to realize binary classification of tumors. First, the SVM-RFE algorithm was used to select features from the miRNA expression profile dataset to constitute feature subsets and to determine the maximum number of support vectors. Next, this maximum number was regarded as the upper limit of the parameter K in the FKNN algorithm that was then used to classify the samples to be tested. Finally, the leave-one-out cross-validation method was adopted to assess the classification performance of the proposed algorithm. Through experiments, our proposed algorithm was compared with other twelve classification methods, and the result shows that our algorithm had better classification performance. Specifically, with only a few miRNA biomarkers, the proposed algorithm could reach an accuracy of 99.46% and an area under the receiver operating characteristic curve (AUC) of 0.9874.

Quantitative Musculoskeletal Tumor Imaging

2020 ◽  
Vol 24 (04) ◽  
pp. 428-440
Author(s):  
B Matthew Howe ◽  
Stephen M. Broski ◽  
Laurel A. Littrell ◽  
Kay M. Pepin ◽  
Doris E. Wenger
Keyword(s):  
Tumor Imaging ◽  
Three Dimensional ◽  
Musculoskeletal Tumor ◽  
Dynamic Contrast Enhancement ◽  
Three Dimensional Printing ◽  
Musculoskeletal Tumors ◽  
Quantitative Pet ◽  
Positron Emission ◽  
Pet Ct ◽  
Magnetic Resonance Imaging Mri

AbstractThe role of quantitative magnetic resonance imaging (MRI) and positron emission tomography/computed tomography (PET/CT) techniques continues to grow and evolve in the evaluation of musculoskeletal tumors. In this review we discuss the MRI quantitative techniques of volumetric measurement, chemical shift imaging, diffusion-weighted imaging, elastography, spectroscopy, and dynamic contrast enhancement. We also review quantitative PET techniques in the evaluation of musculoskeletal tumors, as well as virtual surgical planning and three-dimensional printing.

scholarly journals Support Vector Machine Parameter Optimization for Positron Emission Tomography Images for Estimation of Recurrent Laryngeal Nerve Injury with Thyroid Nodules

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Jiyuan Wang ◽  
Hanqing Zou ◽  
Shaokun Sun ◽  
Wenqian Xu ◽  
Jie Jin
Keyword(s):  
Positron Emission Tomography ◽  
Classification Accuracy ◽  
Thyroid Nodules ◽  
Laryngeal Nerve ◽  
Emission Tomography ◽  
Support Vector ◽  
Positron Emission ◽  
Pet Ct ◽  
Svm Algorithm ◽  
Group B

This study aimed to explore positron emission tomography-computed tomography (PET-CT) images based on support vector machine (SVM) algorithm for the classification of thyroid nodules (TN) and its evaluation value in postoperative injury rate (PPIR) of recurrent laryngeal nerve (RLN). The parameters of the SVM algorithm were optimized using the particle swarm optimization (PSO) algorithm. A total of 58 patients who were diagnosed with TN by PET/CT at a hospital were divided into a group with benign nodules (group B, 25 cases) and a group with malignant nodules (group M, 33 cases). The characteristics of the PET-CT images and difference in the max standardized uptake value (SUVmax) of PET-CT were analyzed. The PPIR of RLN was calculated. It was found that when the number of iterations was 19, the fitness and the classification accuracy of the SVM algorithm was 98.3% and 91.1%, respectively. When SUVmax = 4.56, its sensitivity and specificity were 81.33% and 76.18%, respectively. The SUVmax of group B was much lower ( P < 0.01 ). It indicated that the established method could realize higher classification accuracy on TN and was of great significance in the evaluation of the PPIR of RLN.

scholarly journals Research on Recognition of Motor Imagination Based on Connectivity Features of Brain Functional Network

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Zhizeng Luo ◽  
Ronghang Jin ◽  
Hongfei Shi ◽  
Xianju Lu
Keyword(s):  
Feature Extraction ◽  
Cerebral Cortex ◽  
Pearson Correlation ◽  
Three Dimensional ◽  
Movement Patterns ◽  
Classification Performance ◽  
Functional Network ◽  
Support Vector ◽  
Mu Rhythm ◽  
Feature Extraction Method

Feature extraction is essential for classifying different motor imagery (MI) tasks in a brain-computer interface. To improve classification accuracy, we propose a novel feature extraction method in which the connectivity increment rate (CIR) of the brain function network (BFN) is extracted. First, the BFN is constructed on the basis of the threshold matrix of the Pearson correlation coefficient of the mu rhythm among the channels. In addition, a weighted BFN is constructed and expressed by the sum of the existing edge weights to characterize the cerebral cortex activation degree in different movement patterns. Then, on the basis of the topological structures of seven mental tasks, three regional networks centered on the C3, C4, and Cz channels are constructed, which are consistent with correspondence between limb movement patterns and cerebral cortex in neurophysiology. Furthermore, the CIR of each regional functional network is calculated to form three-dimensional vectors. Finally, we use the support vector machine to learn a classifier for multiclass MI tasks. Experimental results show a significant improvement and demonstrate the success of the extracted feature CIR in dealing with MI classification. Specifically, the average classification performance reaches 88.67% which is higher than other competing methods, indicating that the extracted CIR is effective for MI classification.

Sign in / Sign up

Export Citation Format

Share Document