scholarly journals Machine learning to differentiate small round cell malignant tumors and non-small round cell malignant tumors of the nasal and paranasal sinuses using apparent diffusion coefficient values

2022 ◽  
Author(s):  
Chen Chen ◽  
Yuhui Qin ◽  
Haotian Chen ◽  
Junying Cheng ◽  
Bo He ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Diffusion Coefficient ◽  
Apparent Diffusion Coefficient ◽  
Paranasal Sinuses ◽  
Malignant Tumors ◽  
Round Cell ◽  
Machine Learning Classifiers ◽  
Small Round Cell ◽  
Apparent Diffusion

Abstract Objective We used radiomics feature–based machine learning classifiers of apparent diffusion coefficient (ADC) maps to differentiate small round cell malignant tumors (SRCMTs) and non-SRCMTs of the nasal and paranasal sinuses. Materials A total of 267 features were extracted from each region of interest (ROI). Datasets were randomized into two sets, a training set (∼70%) and a test set (∼30%). We performed dimensional reductions using the Pearson correlation coefficient and feature selection analyses (analysis of variance [ANOVA], relief, recursive feature elimination [RFE]) and classifications using 10 machine learning classifiers. Results were evaluated with a leave-one-out cross-validation analysis. Results We compared the AUC for all the pipelines in the validation dataset using FeAture Explorer (FAE) software. The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUCs with ten features. When the “one-standard error” rule was used, FAE produced a simpler model with eight features, including Perc.01%, Perc.10%, Perc.90%, Perc.99%, S(1,0) SumAverg, S(5,5) AngScMom, S(5,5) Correlat, and WavEnLH_s-2. The AUCs of the training, validation, and test datasets achieved 0.995, 0.902, and 0.710, respectively. For ANOVA, the pipeline with the auto-encoder classifier yielded the highest AUC using only one feature, Perc.10% (training/validation/test datasets: 0.886/0.895/0.809, respectively). For the relief, the AUCs of the training, validation, and test datasets that used the LRLasso classifier using five features (Perc.01%, Perc.10%, S(4,4) Correlat, S(5,0) SumAverg, S(5,0) Contrast) were 0.892, 0.886, and 0.787, respectively. Compared with the RFE and relief, the results of all algorithms of ANOVA feature selection were more stable with the AUC values higher than 0.800. Conclusions We demonstrated the feasibility of combining artificial intelligence with the radiomics from ADC values in the differential diagnosis of SRCMTs and non-SRCMTs and the potential of this non-invasive approach for clinical applications. Key Points • The parameter with the best diagnostic performance in differentiating SRCMTs from non-SRCMTs was the Perc.10% ADC value. • Results of all the algorithms of ANOVA feature selection were more stable and the AUCs were higher than 0.800, as compared with RFE and relief. • The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUC.

scholarly journals The histogram analysis of apparent diffusion coefficient in differential diagnosis of parotid tumor

2020 ◽  
Vol 49 (5) ◽  
pp. 20190420 ◽  
Author(s):  
Peiqian Chen ◽  
Bing Dong ◽  
Chunye Zhang ◽  
Xiaofeng Tao ◽  
Pingzhong Wang ◽  
...  
Keyword(s):  
Diffusion Coefficient ◽  
Apparent Diffusion Coefficient ◽  
Pleomorphic Adenoma ◽  
Area Under Curve ◽  
Malignant Tumors ◽  
Basal Cell Adenoma ◽  
Cell Adenoma ◽  
Apparent Diffusion ◽  
Subgroup Classification

Objectives: Use apparent diffusion coefficient (ADC) histogram to investigate whether the parameters of ADC histogram can distinguish between benign and malignant tumors and further differentiate the tumor subgroups. Methods and materials: This study retrospectively enrolls 161 patients with parotid gland tumors. Histogram parameters including mean, inhomogeneity, skewness, kurtosis and 10th, 25th, 50th, 75th, 90th percentiles are derived from ADC mono-exponential model. Mann–Whitney U test is used to compare the differences between benign and malignant groups. Kruskal–Wallis test with post-hoc Dunn–Bonferroni method is used for subgroup classification, then receiver operating characteristic curve analysis is performed in mean ADC value to obtain the appropriate cutoff values. Results: Except for kurtosis and 90th percentile, there are significant differences in all other ADC parameters between benign and malignant groups. In subgroup classification of benign tumors, there are significant differences in all ADC parameters between pleomorphic adenoma and Warthin’s tumor (area under curve 0.988; sensitivity 93.8%; specificity 94.7%; all ps < 0.05). Pleomorphic adenoma has high value in mean than basal cell adenoma (area under curve 0.819; sensitivity 76.9%; specificity 76.9%; p < 0.05). Basal cell adenoma has high values in mean (area under curve 0.897; sensitivity 92.3%; specificity 78.9%; all ps < 0.05) and 10th, 25th, 50th percentiles than Warthin’s tumor. In subgroup classification of malignant tumors, low-risk parotid carcinomas have higher values than hematolymphoid tumors in mean (area under curve 0.912; sensitivity 84.6%; specificity 100%, all ps < 0.05) and 10th, 25th percentiles. Conclusion: ADC histogram parameters, especially mean and 10th, 25th percentiles, can potentially be an effective indicator for identifying and classifying parotid tumors.

scholarly journals Predictive Role of the Apparent Diffusion Coefficient and MRI Morphologic Features on IDH Status in Patients With Diffuse Glioma: A Retrospective Cross-Sectional Study

2021 ◽  
Vol 11 ◽  
Author(s):  
Jun Zhang ◽  
Hong Peng ◽  
Yu-Lin Wang ◽  
Hua-Feng Xiao ◽  
Yuan-Yuan Cui ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Diffusion Coefficient ◽  
Apparent Diffusion Coefficient ◽  
Image Feature ◽  
Support Vector ◽  
Who Grade ◽  
Test Set ◽  
Apparent Diffusion ◽  
Grade Ii

PurposeTo evaluate isocitrate dehydrogenase (IDH) status in clinically diagnosed grade II~IV glioma patients using the 2016 World Health Organization (WHO) classification based on MRI parameters.Materials and MethodsOne hundred and seventy-six patients with confirmed WHO grade II~IV glioma were retrospectively investigated as the study set, including lower-grade glioma (WHO grade II, n = 64; WHO grade III, n = 38) and glioblastoma (WHO grade IV, n = 74). The minimum apparent diffusion coefficient (ADCmin) in the tumor and the contralateral normal-appearing white matter (ADCn) and the rADC (ADCmin to ADCn ratio) were defined and calculated. Intraclass correlation coefficient (ICC) analysis was carried out to evaluate interobserver and intraobserver agreement for the ADC measurements. Interobserver agreement for the morphologic categories was evaluated by Cohen’s kappa analysis. The nonparametric Kruskal-Wallis test was used to determine whether the ADC measurements and glioma subtypes were related. By univariable analysis, if the differences in a variable were significant (P&lt;0.05) or an image feature had high consistency (ICC &gt;0.8; κ &gt;0.6), then it was chosen as a predictor variable. The performance of the area under the receiver operating characteristic curve (AUC) was evaluated using several machine learning models, including logistic regression, support vector machine, Naive Bayes and Ensemble. Five evaluation indicators were adopted to compare the models. The optimal model was developed as the final model to predict IDH status in 40 patients with glioma as the subsequent test set. DeLong analysis was used to compare significant differences in the AUCs.ResultsIn the study set, six measured variables (rADC, age, enhancement, calcification, hemorrhage, and cystic change) were selected for the machine learning model. Logistic regression had better performance than other models. Two predictive models, model 1 (including all predictor variables) and model 2 (excluding calcification), correctly classified IDH status with an AUC of 0.897 and 0.890, respectively. The test set performed equally well in prediction, indicating the effectiveness of the trained classifier. The subgroup analysis revealed that the model predicted IDH status of LGG and GBM with accuracy of 84.3% (AUC = 0.873) and 85.1% (AUC = 0.862) in the study set, and with the accuracy of 70.0% (AUC = 0.762) and 70.0% (AUC = 0.833) in the test set, respectively.ConclusionThrough the use of machine-learning algorithms, the accurate prediction of IDH-mutant versus IDH-wildtype was achieved for adult diffuse gliomas via noninvasive MR imaging characteristics, including ADC values and tumor morphologic features, which are considered widely available in most clinical workstations.

scholarly journals Prediction of Pathological Upgrading at Radical Prostatectomy in Prostate Cancer Eligible for Active Surveillance: A Texture Features and Machine Learning-Based Analysis of Apparent Diffusion Coefficient Maps

2021 ◽  
Vol 10 ◽  
Author(s):  
Jinke Xie ◽  
Basen Li ◽  
Xiangde Min ◽  
Peipei Zhang ◽  
Chanyuan Fan ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Diffusion Coefficient ◽  
Radical Prostatectomy ◽  
Apparent Diffusion Coefficient ◽  
Texture Features ◽  
Training Cohort ◽  
Machine Learning Methods ◽  
Significant Difference ◽  
Apparent Diffusion

ObjectiveTo evaluate a combination of texture features and machine learning-based analysis of apparent diffusion coefficient (ADC) maps for the prediction of Grade Group (GG) upgrading in Gleason score (GS) ≤6 prostate cancer (PCa) (GG1) and GS 3 + 4 PCa (GG2).Materials and methodsFifty-nine patients who were biopsy-proven to have GG1 or GG2 and underwent MRI examination with the same MRI scanner prior to transrectal ultrasound (TRUS)-guided systemic biopsy were included. All these patients received radical prostatectomy to confirm the final GG. Patients were divided into training cohort and test cohort. 94 texture features were extracted from ADC maps for each patient. The independent sample t-test or Mann−Whitney U test was used to identify the texture features with statistically significant differences between GG upgrading group and GG non-upgrading group. Texture features of GG1 and GG2 were compared based on the final pathology of radical prostatectomy. We used the least absolute shrinkage and selection operator (LASSO) algorithm to filter features. Four supervised machine learning methods were employed. The prediction performance of each model was evaluated by area under the receiver operating characteristic curve (AUC). The statistical comparison between AUCs was performed.ResultsSix texture features were selected for the machine learning models building. These texture features were significantly different between GG upgrading group and GG non-upgrading group (P &lt; 0.05). The six features had no significant difference between GG1 and GG2 based on the final pathology of radical prostatectomy. All machine learning methods had satisfactory predictive efficacy. The diagnostic performance of nearest neighbor algorithm (NNA) and support vector machine (SVM) was better than random forests (RF) in the training cohort. The AUC, sensitivity, and specificity of NNA were 0.872 (95% CI: 0.750−0.994), 0.967, and 0.778, respectively. The AUC, sensitivity, and specificity of SVM were 0.861 (95%CI: 0.732−0.991), 1.000, and 0.722, respectively. There had no significant difference between AUCs in the test cohort.ConclusionA combination of texture features and machine learning-based analysis of ADC maps could predict PCa GG upgrading from biopsy to radical prostatectomy non-invasively with satisfactory predictive efficacy.

scholarly journals [OA047] Robust radiomic feature selection in magnetic resonance apparent diffusion coefficient maps of rectal cancer

2018 ◽  
Vol 52 ◽  
pp. 20
Author(s):  
Leonard Wee ◽  
Alberto Traverso ◽  
Michal Kazmierski ◽  
Petros Kalendralis ◽  
Henrik Dahl Nissen ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Feature Selection ◽  
Diffusion Coefficient ◽  
Magnetic Resonance ◽  
Apparent Diffusion Coefficient ◽  
Apparent Diffusion ◽  
Apparent Diffusion Coefficient Maps
Sign in / Sign up

Export Citation Format

Share Document