Dataset Information

Identifying sarcopenia in advanced non-small cell lung cancer patients using skeletal muscle CT radiomics and machine learning.

ABSTRACT: BACKGROUND:Sarcopenia has been confirmed as a poor prognostic indicator of lung cancer. However, the lack of abdominal computed tomography (CT) hindered the application to assess the status of sarcopenia. The purpose of this study was to assess the ability of chest CT radiomics combined with machine learning classifiers to identify sarcopenia in advanced non-small cell lung cancer (NSCLC) patients. METHODS:This study retrospectively analyzed CT images of 99 patients with NSCLC. Skeletal muscle radiomics were extracted from a single axial slice of the chest CT scan at the 12th thoracic vertebrae level. In total, 854 radiomic and clinical features were obtained from each patient. Feature selection was conducted with FeatureSelector module, optimal key features were fed into the lightGBM classifier for model construction, and Bayesian optimization was adopted to tune hyperparameters. The model's performance was evaluated by specificity, sensitivity, accuracy, precision, F1-score, Matthew's correlation coefficient (MCC), Cohen's kappa coefficient (Kappa), and AUC. RESULTS:A total of 40 patients were found to have sarcopenia. Five optimal features were selected. In the base lightGBM model, the specificity, sensitivity, accuracy, precision, F1-score, AUC, MCC, Kappa of validation set were 0.889, 0.750, 0.833, 0.818, 0.783, 0.819, 0.649, 0.648, respectively. After Bayesian hyperparameter tuning, the optimized lightGBM model achieved better prediction performance, and the corresponding values were 0.944, 0.833, 0.900, 0.909, 0.870, 0.889, 0.791, 0.789, respectively. CONCLUSIONS:Chest CT-based radiomics has the potential to identify sarcopenia in NSCLC patients with the lightGBM classifier, and the optimal lightGBM model via Bayesian hyperparameter tuning demonstrated better performance. KEY POINTS:SIGNIFICANT FINDINGS OF THE STUDY: Our study demonstrates that chest CT-based radiomics combined with lightGBM classifier has the ability to identify sarcopenia in NSCLC patients. WHAT THIS STUDY ADDS:Skeletal muscle radiomics would be a potential biomarker for sarcopenia identity in NSCLC patients.

SUBMITTER: Dong X

PROVIDER: S-EPMC7471037 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying sarcopenia in advanced non-small cell lung cancer patients using skeletal muscle CT radiomics and machine learning.

Dong Xing X Dan Xu X Yawen Ao A Haibo Xu X Huan Li L Mengqi Tu T Linglong Chen C Zhao Ruan R

Thoracic cancer 20200806 9

<h4>Background</h4>Sarcopenia has been confirmed as a poor prognostic indicator of lung cancer. However, the lack of abdominal computed tomography (CT) hindered the application to assess the status of sarcopenia. The purpose of this study was to assess the ability of chest CT radiomics combined with machine learning classifiers to identify sarcopenia in advanced non-small cell lung cancer (NSCLC) patients.<h4>Methods</h4>This study retrospectively analyzed CT images of 99 patients with NSCLC. Sk ...[more]

PMID: 32767522

Similar Datasets

Project description:Measurements of skeletal muscle cross-sectional area (SMA) at the level of the third lumbar (L3) vertebra derived from clinical computed tomography (CT) scans are commonly used in assessments of sarcopenia, the loss of skeletal muscle mass and function associated with aging. As SMA is correlated with height and Body Mass Index (BMI), body size adjustment is necessary to fairly assess sarcopenic low muscle mass in individuals of different height and BMI. The skeletal muscle index, a widely used measure, adjusts for height as [Formula: see text] but uses no BMI adjustment. There is no agreed upon standard for body size adjustment. We extracted L3 SMA using non-contrast-enhanced CT scans from healthy adults, split into 'Under-40' and 'Over-40' cohorts. Sex-specific allometric analysis showed that height to the power of one was the optimal integer coefficient for height adjusted SMA in both males and females. We computed two height-adjusted measures [Formula: see text] and [Formula: see text], comparing their Pearson correlations versus age, height, weight, and BMI separately by sex and cohort. Finally, in the 'Under-40' cohort, we used linear regression to convert each height-adjusted measure into a z-score ([Formula: see text], [Formula: see text]) adjusted for BMI. [Formula: see text] was less correlated with height in both males and females ([Formula: see text], [Formula: see text] and [Formula: see text], [Formula: see text]) than [Formula: see text] ([Formula: see text] and [Formula: see text], [Formula: see text]). [Formula: see text] was uncorrelated with BMI and weight, and minimally correlated with height in males and females ([Formula: see text], [Formula: see text] and [Formula: see text], [Formula: see text]). The final [Formula: see text] equation was: [Formula: see text], where [Formula: see text], [Formula: see text], [Formula: see text], and sex = 1 if male, 0 if female. We propose [Formula: see text] for optimal height adjustment and the [Formula: see text] score for optimal height and BMI adjustment. By minimizing correlations with height and BMI, the [Formula: see text] score produces unbiased assessments of relative L3 skeletal muscle area across the full range of body sizes.

Project description:BackgroundSarcopenia is generally diagnosed by the total area of skeletal muscle in the CT axial slice located in the third lumbar (L3) vertebra. However, patients with severe liver cirrhosis cannot accurately obtain the corresponding total skeletal muscle because their abdominal muscles are squeezed, which affects the diagnosis of sarcopenia.PurposeThis study proposes a novel lumbar skeletal muscle network to automatically segment multi-regional skeletal muscle from CT images, and explores the relationship between cirrhotic sarcopenia and each skeletal muscle region.MethodsThis study utilizes the skeletal muscle characteristics of different spatial regions to improve the 2.5D U-Net enhanced by residual structure. Specifically, a 3D texture attention enhancement block is proposed to tackle the issue of blurred edges with similar intensities and poor segmentation between different skeletal muscle regions, which contains skeletal muscle shape and muscle fibre texture to spatially constrain the integrity of skeletal muscle region and alleviate the difficulty of identifying muscle boundaries in axial slices. Subsequentially, a 3D encoding branch is constructed in conjunction with a 2.5D U-Net, which segments the lumbar skeletal muscle in multiple L3-related axial CT slices into four regions. Furthermore, the diagnostic cut-off values of the L3 skeletal muscle index (L3SMI) are investigated for identifying cirrhotic sarcopenia in four muscle regions segmented from CT images of 98 patients with liver cirrhosis.ResultsOur method is evaluated on 317 CT images using the five-fold cross-validation method. For the four skeletal muscle regions segmented in the images from the independent test set, the avg. DSC is 0.937 and the avg. surface distance is 0.558 mm. For sarcopenia diagnosis in 98 patients with liver cirrhosis, the cut-off values of Rectus Abdominis, Right Psoas, Left Psoas, and Paravertebral are 16.67, 4.14, 3.76, and 13.20 cm2/m2 in females, and 22.51, 5.84, 6.10, and 17.28 cm2/m2 in males, respectively.ConclusionThe proposed method can segment four skeletal muscle regions related to the L3 vertebra with high accuracy. Furthermore, the analysis shows that the Rectus Abdominis region can be used to assist in the diagnosis of sarcopenia when the total muscle is not available.

Project description:Object To evaluate the difference between multiple primary lung adenocarcinoma (MPLA) and solitary primary lung adenocarcinoma (SPLA) by delta-radiomics based machine learning algorithms in CT images. Methods A total of 1094 patients containing 268 MPLAs and 826 SPLAs were recruited for this retrospective study between 2014 to 2020. After the segmentation of volume of interest, the radiomic features were automatically calculated. The patients were categorized into the training set and testing set by a random proportion of 7:3. After feature selection, the relevant classifiers were constructed by the machine learning algorithms of Bayes, forest, k-nearest neighbor, logistic regression, support vector machine, and decision tree. The relative standard deviation (RSD) was calculated and the classification model with minimal RSD was chosen for delta-radiomics analysis to explore the variation of tumor during follow-up surveillance in the cohort of 225 MPLAs and 320 SPLAs. According to the different follow-up duration, it was divided into group A (3–12 months), group B (13–24 months), and group C (25–48 months). Then the corresponding delta-radiomics classifiers were developed to predict MPLAs. The area under the receiver operator characteristic curve (AUC) with 95% confidence interval (CI) was quantified to evaluate the efficiency of the model. Results To radiomics analysis, the forest classifier (FC-radio) with the minimal RSD showed the better stability with AUCs of 0.840 (95%CI, 0.810–0.867) and 0.670 (95%CI, 0.611–0.724) in the training and testing set. The AUCs of the forest classifier based on delta-radiomics (FC-delta) were higher than those of FC-radio. In addition, with the extension of follow-up duration, the performance of FC-delta in Group C were the best with AUCs of 0.998 (95%CI, 0.993–1.000) in the training set and 0.853 (95%CI, 0.752–0.940) in the testing set. Conclusions The machine-learning approach based on radiomics and delta-radiomics helped to differentiate SPLAs from MPLAs. The FC-delta with a longer follow-up duration could better distinguish between SPLAs and MPLAs. Supplementary Information The online version contains supplementary material available at 10.1186/s12885-022-10036-1.

Project description:Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.

Project description:PurposeMYCN amplification plays a critical role in defining high-risk subgroup of patients with neuroblastoma. We aimed to develop and validate the CT-based machine learning models for predicting MYCN amplification in pediatric abdominal neuroblastoma.MethodsA total of 172 patients with MYCN amplified (n = 47) and non-amplified (n = 125) were enrolled. The cohort was randomly stratified sampling into training and testing groups. Clinicopathological parameters and radiographic features were selected to construct the clinical predictive model. The regions of interest (ROIs) were segmented on three-phrase CT images to extract first-, second- and higher-order radiomics features. The ICCs, mRMR and LASSO methods were used for dimensionality reduction. The selected features from the training group were used to establish radiomics models using Logistic regression, Support Vector Machine (SVM), Bayes and Random Forest methods. The performance of four different radiomics models was evaluated according to the area under the receiver operator characteristic (ROC) curve (AUC), and then compared by Delong test. The nomogram incorporated of clinicopathological parameters, radiographic features and radiomics signature was developed through multivariate logistic regression. Finally, the predictive performance of the clinical model, radiomics models, and nomogram was evaluated in both training and testing groups.ResultsIn total, 1,218 radiomics features were extracted from the ROIs on three-phrase CT images, and then 14 optimal features, including one original first-order feature and eight wavelet-transformed features and five LoG-transformed features, were identified and selected to construct the radiomics models. In the training group, the AUC of the Logistic, SVM, Bayes and Random Forest model was 0.940, 0.940, 0.780 and 0.927, respectively, and the corresponding AUC in the testing group was 0.909, 0.909, 0.729, 0.851, respectively. There was no significant difference among the Logistic, SVM and Random Forest model, but all better than the Bayes model (p <0.005). The predictive performance of the Logistic radiomics model based on three-phrase is similar to nomogram, but both better than the clinical model and radiomics model based on single venous phase.ConclusionThe CT-based radiomics signature is able to predict MYCN amplification of pediatric abdominal NB with high accuracy based on SVM, Logistic and Random Forest classifiers, while Bayes classifier yields lower predictive performance. When combined with clinical and radiographic qualitative features, the clinics-radiomics nomogram can improve the performance of predicting MYCN amplification.

Dataset Information

Identifying sarcopenia in advanced non-small cell lung cancer patients using skeletal muscle CT radiomics and machine learning.

Publications

Identifying sarcopenia in advanced non-small cell lung cancer patients using skeletal muscle CT radiomics and machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets