Dataset Information

A radiomics model can distinguish solitary pulmonary capillary haemangioma from lung adenocarcinoma.

ABSTRACT:

Objectives

Solitary pulmonary capillary haemangioma (SPCH) is a benign lung tumour that presents as ground-glass nodules on computed tomography (CT) images and mimics lepidic-predominant adenocarcinoma. This study aimed to establish a discriminant model using a radiomic feature analysis to distinguish SPCH from lepidic-predominant adenocarcinoma.

Methods

In the adenocarcinoma group, all tumours were of the lepidic-predominant subtype with high purity (>70%). A classification model was proposed based on a two-level decision tree and 26 radiomic features extracted from each segmented lesion. For comparison, a baseline model was built with the same 26 features using a support vector machine as the classifier. Both models were assessed by the leave-one-out cross-validation method.

Results

This study included 13 and 49 patients who underwent complete resection for SPCH and adenocarcinoma, respectively. Two sets of features were identified for discrimination between the 2 different histology types. The first set included 2 principal components corresponding to the 2 largest eigenvalues for the root node of the two-level decision tree. The second set comprised 4 selected radiomic features. The area under the receiver operating characteristic curve, accuracy, sensitivity, specificity were 0.954, 91.9%, 92.3% and 91.8% in the proposed classification model, and were 0.805, 85.5%, 61.5% and 91.8% in the baseline model, respectively. The proposed classification model significantly outperformed the baseline model (P < 0.05).

Conclusions

The proposed model could differentiate the 2 different histology types on CT images, and this may help surgeons to preoperatively discriminate SPCH from adenocarcinoma.

SUBMITTER: Wang HJ

PROVIDER: S-EPMC8860424 | biostudies-literature | 2022 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A radiomics model can distinguish solitary pulmonary capillary haemangioma from lung adenocarcinoma.

Wang Hao-Jen HJ Lin Mong-Wei MW Chen Yi-Chang YC Chen Li-Wei LW Hsieh Min-Shu MS Yang Shun-Mao SM Chen Ho-Feng HF Wang Chuan-Wei CW Chen Jin-Shing JS Chang Yeun-Chung YC Chen Chung-Ming CM

Interactive cardiovascular and thoracic surgery 20220201 3

<h4>Objectives</h4>Solitary pulmonary capillary haemangioma (SPCH) is a benign lung tumour that presents as ground-glass nodules on computed tomography (CT) images and mimics lepidic-predominant adenocarcinoma. This study aimed to establish a discriminant model using a radiomic feature analysis to distinguish SPCH from lepidic-predominant adenocarcinoma.<h4>Methods</h4>In the adenocarcinoma group, all tumours were of the lepidic-predominant subtype with high purity (>70%). A classification model ...[more]

PMID: 34648631

Similar Datasets

Project description:ObjectiveTo develop and validate predictive models using clinical parameters, radiomic features and a combination of both for preoperative differentiation of pulmonary nodular mucinous adenocarcinoma (PNMA) from pulmonary tuberculoma (PTB).MethodA total of 124 and 53 patients with PNMA and PTB, respectively, were retrospectively analyzed from January 2017 to November 2022 in The Fourth Affiliated Hospital of Hebei Medical University (Ligang et al., A machine learning model based on CT and clinical features to distinguish pulmonary nodular mucinous adenocarcinoma from tuberculoma, 2023). A total of 1037 radiomic features were extracted from contrast-enhanced computed tomography (CT). The patients were randomly divided into a training group and a test group at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) algorithm was used for radiomic feature selection. Three radiomics prediction models were applied: logistic regression (LR), support vector machine (SVM) and random forest (RF). The best performing model was adopted, and the radiomics score (Radscore) was then computed. The clinical model was developed using logistic regression. Finally, a combined model was established based on clinical factors and radiomics features. We externally validated the three models in a group of 68 patients (46 and 22 patients with PNMA and PTB, respectively) from Xing Tai People's Hospital (30 and 14 patients with PNMA and PTB, respectively) and The First Hospital of Xing Tai (16 and 8 patients with PNMA and PTB, respectively). The area under the receiver operating characteristic (ROC) curve (AUC) value and decision curve analysis were used to evaluate the predictive value of the developed models.ResultsThe combined model established by the logistic regression method had the best performance. The ROC-AUC (also a decision curve analysis) of the combined model was 0.940, 0.990 and 0.960 in the training group, test group and external validation group, respectively, and the combined model showed good predictive performance for the differentiation of PNMA from PTB. The Brier scores of the combined model were 0.132 and 0.068 in the training group and test group, respectively.ConclusionThe combined model incorporating radiomics features and clinical parameters may have potential value for the preoperative differentiation of PNMA from PTB.

Project description:ObjectiveTo evaluate the performance of 2D and 3D radiomics features with different machine learning approaches to classify SPLs based on magnetic resonance(MR) T2 weighted imaging (T2WI).Material and methodsA total of 132 patients with pathologically confirmed SPLs were examined and randomly divided into training (n = 92) and test datasets (n = 40). A total of 1692 3D and 1231 2D radiomics features per patient were extracted. Both radiomics features and clinical data were evaluated. A total of 1260 classification models, comprising 3 normalization methods, 2 dimension reduction algorithms, 3 feature selection methods, and 10 classifiers with 7 different feature numbers (confined to 3-9), were compared. The ten-fold cross-validation on the training dataset was applied to choose the candidate final model. The area under the receiver operating characteristic curve (AUC), precision-recall plot, and Matthews Correlation Coefficient were used to evaluate the performance of machine learning approaches.ResultsThe 3D features were significantly superior to 2D features, showing much more machine learning combinations with AUC greater than 0.7 in both validation and test groups (129 vs. 11). The feature selection method Analysis of Variance(ANOVA), Recursive Feature Elimination(RFE) and the classifier Logistic Regression(LR), Linear Discriminant Analysis(LDA), Support Vector Machine(SVM), Gaussian Process(GP) had relatively better performance. The best performance of 3D radiomics features in the test dataset (AUC = 0.824, AUC-PR = 0.927, MCC = 0.514) was higher than that of 2D features (AUC = 0.740, AUC-PR = 0.846, MCC = 0.404). The joint 3D and 2D features (AUC=0.813, AUC-PR = 0.926, MCC = 0.563) showed similar results as 3D features. Incorporating clinical features with 3D and 2D radiomics features slightly improved the AUC to 0.836 (AUC-PR = 0.918, MCC = 0.620) and 0.780 (AUC-PR = 0.900, MCC = 0.574), respectively.ConclusionsAfter algorithm optimization, 2D feature-based radiomics models yield favorable results in differentiating malignant and benign SPLs, but 3D features are still preferred because of the availability of more machine learning algorithmic combinations with better performance. Feature selection methods ANOVA and RFE, and classifier LR, LDA, SVM and GP are more likely to demonstrate better diagnostic performance for 3D features in the current study.

Project description:BackgroundThis study proposed a precise diagnostic model for malignant solitary pulmonary nodules (SPNs). This model can be used to identify objective and quantifiable image features and guide the clinical treatment strategy adopted for SPNs. This model will help clinicians optimize management strategies for SPN.MethodsIn this retrospective study, the clinical data of 455 patients of SPN with defined pathological diagnosis between September 2016 and August 2019 were collected and analyzed. The data included pathological diagnosis, preoperative computed tomography (CT) diagnosis, gender, age, smoking history, family history of tumor, previous history, and contact history data. The quantitative image features and radiomic information of the SPNs were provided using computer-aided detection (CAD) "digital lung" software. The Chi-squared test was used to assess the accuracy between CAD and conventional CT in the diagnosis of SPNs. The diagnostic model for benign or malignant SPNs was developed using a multivariate logistic regression analysis that comprises 6 radiomic factors (irregularity, average diameter, COPD910, proportion of emphysema, proportion of fat, and average density of related blood vessels). The area under the receiver operating characteristic curve was used to evaluate the performance of the model in determining SPN risk of malignancy.ResultsThere was a statistical difference in the accuracy of CAD and conventional CT in diagnosing SPNs. According to the golden standard pathological diagnosis, the diagnostic accuracy of CAD (81%) was higher than that of conventional CT (63.7%) (P<0.05). Six variables (i.e., irregularity, the mean diameter, COPD910, the proportion of emphysema, the proportion of fat, and the vascular density) were identified using multivariable logistic regression to establish the diagnostic model for distinguish benign or malignant SPNs. The area under the receiver operating characteristic (ROC) curve (AUC) of the diagnostic model was 0.876 (95% CI: 0.8445-0.9076), and its sensitivity and specificity were 81.25% and 82.56% respectively.ConclusionsThe proposed diagnostic model, which comprises 6 radiomic factors, is accurate and effective at diagnosing benign or malignant SPNs.

Project description:BackgroundChest computed tomography (CT) is a critical tool in the diagnosis of pulmonary cryptococcosis as approximately 30% of normal immunity individuals may not exhibit any significant symptoms or laboratory findings. Pulmonary cryptococcosis granuloma and lung adenocarcinoma can appear similar on noncontrast chest CT. This study evaluates the use of an integrated model that was developed based on radiomic features combined with demographic and radiological features to differentiate pulmonary cryptococcosis nodules from lung adenocarcinomas.MethodsPreoperative chest CT images for 215 patients with solid pulmonary nodules with histopathologically confirmed lung adenocarcinoma and cryptococcosis infection were collected from two clinical centers (108 cases in the training set and 107 cases in the test set divided by the different hospitals). Radiomics models were constructed based on nodular lesion volume (LV), 5-mm extended lesion volume (ELV), and perilesion volume (PLV). A demoradiological model was constructed using logistic regression based on demographic information (age, sex) and 12 radiological features (location, number, shape and specific imaging signs). Both models were used to build an integrated model, the performance of which was assessed using the test set. A junior and a senior radiologist evaluated the nodules. Receiver operating characteristic (ROC) curve analysis was conducted, and areas under the curve (AUCs), sensitivity (SEN), and specificity (SPE) of the models were calculated and compared.ResultsAmong the radiomics models, AUCs of the LV, ELV, and PLV were 0.558, 0.757, and 0.470, respectively. Age, lesion number, and lobular sign were identified as independent discriminative features providing an AUC of 0.77 in the demoradiological model (SEN 0.815, SPE 0.642). The integrated model achieved the highest AUC of 0.801 (SEN 0.759, SPE 0.755), which was significantly higher than that obtained by a junior radiologist (AUC =0.689, P=0.024) but showed no significant difference from that of the senior radiologist (AUC =0.784, P=0.388).ConclusionsAn integrated model with radiomics and demoradiological features improves discrimination of cryptococcosis granulomas from solid adenocarcinomas on noncontrast CT. This model may be an effective strategy for machine complementation to discrimination by radiologists, and whole-lung automated recognition methods might dominate in the future.

Project description:BackgroundAs a rare subtype of lung adenocarcinoma, the diagnosis of pulmonary enteric adenocarcinoma (PEAC) remains challenging due to overlapping morphologic spectrum with lung metastatic colorectal cancer (lmCRC). However, the molecular features of PEAC as a separate lung cancer entity are poorly understood.MethodsWe performed whole-exome sequencing and targeted bisulfite sequencing of 32 PEAC and 30 lmCRC to improve differential molecular characterization of the two diseases. We used machine learning methods to select key markers and developed a diagnostic classifier. In addition, we validated the classifier in the internal test cohort and an independently recruited external validation cohort with 17 PEAC and 7 lmCRC.FindingsOur results showed that EGFR was the key driver mutation in PEAC but at a lower prevalence compared to typical lung adenocarcinomas, whereas ERBB2 and KRAS were more frequently observed in PEAC. By contrast, we observed significant enrichment of KRAS and APC mutations in lmCRC compared with PEAC. At the chromosome arm level, copy number variations in 13q, 14q, and 18p were the major chromosomal differences observed between PEAC and lmCRC. Furthermore, by comparing differentially methylated regions (DMRs), we established a neat DNA methylation-based classifier consisting of eight DMRs. This classifier correctly classified all samples in the training cohort and 95% of the samples in the internal test cohort. An external validation cohort of 24 cases recruited from multiple centers in China also reliably agreed with pathological diagnosis.InterpretationThese results provide solid evidence of PEAC-specific genomic characteristics and demonstrate the potential utility of DNA methylation markers for auxiliary diagnosis of PEAC and lmCRC.FundingThis work was supported by National key research and development project 2019YFC1315700, CAMS Key Laboratory of Translational Research on Lung Cancer (2018PT31035), and Beijing Natural Science Foundation (7222144).

Dataset Information

A radiomics model can distinguish solitary pulmonary capillary haemangioma from lung adenocarcinoma.

Objectives

Methods

Results

Conclusions

Publications

A radiomics model can distinguish solitary pulmonary capillary haemangioma from lung adenocarcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets