Dual-Energy CT Texture Analysis With Machine Learning for the Evaluation and Characterization of Cervical Lymphadenopathy

Seidler, Matthew; Forghani, Behzad; Reinhold, Caroline; Lara, Almudena Pérez; Romero-Sánchez, Griselda; Muthukrishnan, N. Moorthy; Wichmann, Julian L.; Melki, Gabriel; Yu, Eugene; Forghani, Reza

doi:10.1016/j.csbj.2019.07.004

Cited by 73 publications

(65 citation statements)

References 46 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Texture analysis refers to an objective and quantitative set of metrics calculated for quantifying the textural patterns of images. Previous studies have showed radiomics features were associated with nodal involvement in oncologic imaging [7,12]. Herein, we studied primary tumor texture features of PDAC at preoperative CT by automatically extracting several quantitative parameters, which were compared according to the nodal involvement status.…”

Section: Discussionmentioning

confidence: 99%

“…Dual-energy CT has been widely used recently [6]. Quantitative parameters derived from dual-energy CT data have proven to be useful for the diagnosis and nodal staging in several types of tumors [7][8][9][10]. However, the value of quantitative parameters from dual-energy CT in the preoperative diagnosis of LN metastasis in patients with pancreatic cancer remains elusive.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Resectable pancreatic ductal adenocarcinoma: association between preoperative CT texture features and metastatic nodal involvement

Fang

Zhu

et al. 2020

Cancer Imaging

View full text Add to dashboard Cite

Background: To explore the relationship between the lymph node status and preoperative computed tomography images texture features in pancreatic cancer. Methods: A total of 155 operable pancreatic cancer patients (104 men, 51 women; mean age 63.8 ± 9.6 years), who had undergone contrast-enhanced computed tomography in the arterial and portal venous phases, were enrolled in this retrospective study. There were 73 patients with lymph node metastases and 82 patients without nodal involvement. Four different data sets, with thin (1.25 mm) and thick (5 mm) slices (at arterial phase and portal venous phase) were analysed. Texture analysis was performed by using MaZda software. A combination of feature selection algorithms was used to determine 30 texture features with the optimal discriminative performance for differentiation between lymph node positive and negative groups. The prediction performance of the selected feature was evaluated by receiver operating characteristic (ROC) curve analysis. Results: There were 10 texture features with significant differences between two groups and significance in ROC analysis were identified. They were WavEnLH_s-2(wavelet energy with rows and columns are filtered with low pass and high pass frequency bands with scale factors 2) from wavelet-based features, 135dr_LngREmph (long run emphasis in 135 direction) and 135dr_Fraction (fraction of image in runs in 135 direction) from run length matrix-based features, and seven variables of sum average from coocurrence matrix-based features (SumAverg). The ideal cutoff value for predicting lymph node metastases was 270 for WavEnLH_s-2 (positive likelihood ratio 2.08). In addition, 135dr_ LngREmph and 135dr_Fraction were correlated with the ratio of metastatic to examined lymph nodes. Conclusions:Preoperative computed tomography high order texture features provide a useful imaging signature for the prediction of nodal involvement in pancreatic cancer.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Resectable pancreatic ductal adenocarcinoma: association between preoperative CT texture features and metastatic nodal involvement

Fang

Zhu

et al. 2020

Cancer Imaging

View full text Add to dashboard Cite

show abstract

“…an accuracy of up to 93% and 80% for distinguishing lymphoma and inflammatory from normal nodes, respectively, and of 92% for distinguishing benign and malignant lymph nodes [54]. However, the abovementioned studies focused on the differentiation between benign and malignant lesions; reports on the use of radiomics for differentiating between different types of malignant lesions are rare [31][32][33].…”

Section: Contrast Media and Molecular Imagingmentioning

confidence: 99%

“…e current trends in texture research involve the use of machine learning/deep learning to avoid the tedious process of manual operation and the accompanying uncertainty. Texture analysis based on dual-energy CT, full-field digital mammography, dual time 18 F-FDG PET/CT, and biparametric MRI can identify benign and malignant diseases with high efficiency (AUC fluctuates between 0.84-0.96 depending on the disease and analysis method) in studies using machine learning/deep learning [52][53][54][55]. e AUC in these studies did not significantly differ from that in our study, but the abovementioned studies focused on distinguishing between benign and malignant tumors.…”

mentioning

confidence: 99%

Distinguishing Lymphomatous and Cancerous Lymph Nodes in 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography by Radiomics Analysis

Zheng

Zhao

et al. 2020

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Background. The National Comprehensive Cancer Network guidelines recommend excisional biopsies for the diagnosis of lymphomas. However, resection biopsies in all patients who are suspected of having malignant lymph nodes may cause unnecessary injury and increase medical costs. We investigated the usefulness of 18F-fluorodeoxyglucose positron emission/computed tomography- (18F-FDG-PET/CT-) based radiomics analysis for differentiating between lymphomatous lymph nodes (LLNs) and cancerous lymph nodes (CLNs). Methods. Using texture analysis, radiomic parameters from the 18F-FDG-PET/CT images of 492 lymph nodes (373 lymphomatous lymph nodes and 119 cancerous lymph nodes) were extracted with the LIFEx package. Predictive models were generated from the six parameters with the largest area under the receiver operating characteristics curve (AUC) in PET or CT images in the training set (70% of the data), using binary logistic regression. These models were applied to the test set to calculate predictive variables, including the combination of PET and CT predictive variables (PREcombination). The AUC, sensitivity, specificity, and accuracy were used to compare the differentiating ability of the predictive variables. Results. Compared with the pathological diagnosis of the patient’s primary tumor, the AUC, sensitivity, specificity, and accuracy of PREcombination in differentiating between LLNs and CLNs were 0.95, 91.67%, 94.29%, and 92.96%, respectively. Moreover, PREcombination could effectively distinguish LLNs caused by various lymphoma subtypes (Hodgkin’s lymphoma and non-Hodgkin’s lymphoma) from CLNs, with the AUC, sensitivity, specificity, and accuracy being 0.85 and 0.90, 77.78% and 77.14%, 97.22% and 88.89%, and 90.74% and 83.10%, respectively. Conclusions. Radiomics analysis of 18F-FDG-PET/CT images may provide a noninvasive, effective method to distinguish LLN and CLN and inform the choice between fine-needle aspiration and excision biopsy for sampling suspected lymphomatous lymph nodes.

show abstract

“…In the study, the morphological features of the lesions were excluded. An analysis was made only about the texture features of the lesions (21).…”

Section: Voi Segmentation and Radiomic Feature Acquisitionmentioning

confidence: 99%

Radiomics Based on CECT in Differentiating Kimura Disease From Lymph Node Metastases in Head and Neck: A Non-Invasive and Reliable Method

Zhang

et al. 2020

Front. Oncol.

View full text Add to dashboard Cite

Background: Kimura disease may be easily misdiagnosed as malignant tumors such as lymph node metastases based on imaging and clinical symptoms. The aim of this article is to investigate whether the radiomic features and the model based on the features on venous-phase contrast-enhanced CT (CECT) images can distinguish Kimura disease from lymph node metastases in the head and neck. Methods: A retrospective analysis of 14 patients of head and neck Kimura disease (a total of 38 enlarged lymph nodes) and 39 patients with head and neck lymph node metastases (a total of 39 enlarged lymph nodes), confirmed by biopsy or surgery resection, was conducted. All patients accepted CECT within 10 days before biopsy or surgery resection. Radiomic features based on venous-phase CECT were generated automatically from Artificial-Intelligence Kit (AK) software. All lymph nodes were randomly divided into the training set (n = 54) and testing set (n = 23) in a ratio of 7:3. ANOVA + Mann-Whitney, Spearman correlation, least absolute shrinkage and selection operator, and Gradient Descent were introduced for the reduction of the highly redundant features. Binary logistic regression model was constructed based on the selected features. Receiver operating characteristic was used to evaluate the diagnostic performance of the features and the model. Finally, a nomogram was established for model application. Results : Seven features were screened out at the end. Significant difference was found between the two groups for all the features with area under the curves (AUCs) ranging from 0.759 to 0.915. The AUC of the model's identification performance was 0.970 in the training group and 0.977 in the testing group. The disease discrimination efficiency of the model was better than that of any single feature. Conclusions : The radiomic features and the model based on these features on venous-phase CECT images had very good performance for the discrimination between Kimura disease and lymph node metastases in the head and neck.

show abstract

Dual-Energy CT Texture Analysis With Machine Learning for the Evaluation and Characterization of Cervical Lymphadenopathy

Cited by 73 publications

References 46 publications

Resectable pancreatic ductal adenocarcinoma: association between preoperative CT texture features and metastatic nodal involvement

Resectable pancreatic ductal adenocarcinoma: association between preoperative CT texture features and metastatic nodal involvement

Distinguishing Lymphomatous and Cancerous Lymph Nodes in 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography by Radiomics Analysis

Radiomics Based on CECT in Differentiating Kimura Disease From Lymph Node Metastases in Head and Neck: A Non-Invasive and Reliable Method

Contact Info

Product

Resources

About