Prediction of the Growth Rate of Early-Stage Lung Adenocarcinoma by Radiomics

Tan, Min; Ma, Wenrui; Sun, Yingli; Gao, Pan; Huang, Xuemei; Lu, Jingyu; Chen, Wufei; Wu, Yue; Jin, Liang; Tang, Lin; Kuang, Kaiming; Li, Ming

doi:10.3389/fonc.2021.658138

Cited by 20 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to our study, Tan et al 39 divided pulmonary nodules into the fast-growth group (VDT ≤400 d) and slowgrowth group (VDT > 400 d), and radiography, radiomics, and radiography combined radiomics models were established using the decision tree to predict VDT. The AUC in the test set was 0.727, 0.710, and 0.78, respectively.…”

Section: Discussionsupporting

confidence: 53%

Radiomics-based Machine Learning Methods for Volume Doubling Time Prediction of Pulmonary Ground-glass Nodules With Baseline Chest Computed Tomography

Huang

Zhang

et al. 2023

Journal of Thoracic Imaging

View full text Add to dashboard Cite

Purpose: Reliable prediction of volume doubling time (VDT) is essential for the personalized management of pulmonary ground-glass nodules (GGNs). We aimed to determine the optimal VDT prediction method by comparing different machine learning methods only based on the baseline chest computed tomography (CT) images. Materials and Methods: Seven classical machine learning methods were evaluated in terms of their stability and performance for VDT prediction. The VDT, calculated by the preoperative and baseline CT, was divided into 2 groups with a cutoff value of 400 days. A total of 90 GGNs from 3 hospitals constituted the training set, and 86 GGNs from the fourth hospital served as the external validation set. The training set was used for feature selection and model training, and the validation set was used to evaluate the predictive performance of the model independently. Results: The eXtreme Gradient Boosting showed the highest predictive performance (accuracy: 0.890±0.128 and area under the ROC curve (AUC): 0.896±0.134), followed by the neural network (NNet) (accuracy: 0.865±0.103 and AUC: 0.886±0.097). While regarding stability, the NNet showed the highest robustness against data perturbation (relative SDs [%] of mean AUC: 10.9%). Therefore, the NNet was chosen as the final model, achieving high accuracy of 0.756 in the external validation set. Conclusion: The NNet is a promising machine learning method to predict the VDT of GGNs, which would assist in the personalized follow-up and treatment strategies for GGNs reducing unnecessary follow-up and radiation dose.

show abstract

Section: Discussionsupporting

confidence: 53%

Radiomics-based Machine Learning Methods for Volume Doubling Time Prediction of Pulmonary Ground-glass Nodules With Baseline Chest Computed Tomography

Huang

Zhang

et al. 2023

Journal of Thoracic Imaging

View full text Add to dashboard Cite

show abstract

“…Several studies ( 34 ) have demonstrated that radiomic signatures can differentiate malignant and benign nodules with a sensitivity ranging from 76.2 to 92.9% and a specificity ranging from 72.7 to 96.1%. The combined radiographic factor or supervised machine learning with the radiomics model could achieve better performance ( 34 , 35 ). In the traditional radiomics methods to classify pulmonary nodules ( 11 ), large amounts of labor are required for manual tumor segmentation and feature extraction.…”

Section: Discussionmentioning

confidence: 99%

Deep learning-based growth prediction for sub-solid pulmonary nodules on CT images

Liao

Yan

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

BackgroundEstimating the growth of pulmonary sub-solid nodules (SSNs) is crucial to the successful management of them during follow-up periods. The purpose of this study is to (1) investigate the measurement sensitivity of diameter, volume, and mass of SSNs for identifying growth and (2) seek to establish a deep learning-based model to predict the growth of SSNs.MethodsA total of 2,523 patients underwent at least 2-year examination records retrospectively collected with sub-solid nodules. A total of 2,358 patients with 3,120 SSNs from the NLST dataset were randomly divided into training and validation sets. Patients from the Yibicom Health Management Center and Guangdong Provincial People’s Hospital were collected as an external test set (165 patients with 213 SSN). Trained models based on LUNA16 and Lndb19 datasets were employed to automatically obtain the diameter, volume, and mass of SSNs. Then, the increase rate in measurements between cancer and non-cancer groups was studied to evaluate the most appropriate way to identify growth-associated lung cancer. Further, according to the selected measurement, all SSNs were classified into two groups: growth and non-growth. Based on the data, the deep learning-based model (SiamModel) and radiomics model were developed and verified.ResultsThe double time of diameter, volume, and mass were 711 vs. 963 days (P = 0.20), 552 vs. 621 days (P = 0.04) and 488 vs. 623 days (P< 0.001) in the cancer and non-cancer groups, respectively. Our proposed SiamModel performed better than the radiomics model in both the NLST validation set and external test set, with an AUC of 0.858 (95% CI 0.786–0.921) and 0.760 (95% CI 0.646–0.857) in the validation set and 0.862 (95% CI 0.789–0.927) and 0.681 (95% CI 0.506–0.841) in the external test set, respectively. Furthermore, our SiamModel could use the data from first-time CT to predict the growth of SSNs, with an AUC of 0.855 (95% CI 0.793–0.908) in the NLST validation set and 0.821 (95% CI 0.725–0.904) in the external test set.ConclusionMass increase rate can reflect more sensitively the growth of SSNs associated with lung cancer than diameter and volume increase rates. A deep learning-based model has a great potential to predict the growth of SSNs.

show abstract

“…The enrolled patients were randomly divided into a training set and a validation set at a ratio of 8:2 using SPSS software (version 25.0; IBM Corp., Armonk, NY, USA). This ratio is the one that is commonly used to divide training and validation datasets (20)(21)(22). Univariate analysis was conducted to identify meaningful candidate variables for the model.…”

Section: Construction and Validation Of The Modelmentioning

confidence: 99%

MRI-Based Radiomic Signature Identifying Secondary Loss of Response to Infliximab in Crohn's Disease

Feng

Chen

et al. 2022

Front. Nutr.

View full text Add to dashboard Cite

Up to 50% of patients with Crohn's disease (CD) experience secondary loss of response (SLR) to infliximab. Patients with SLR may show clinical signs of iron deficiency as a result of inflammation despite being iron-replete. The magnetic resonance imaging (MRI)-based radiomic index, R2*, can detect changes in iron metabolism. Therefore, the R2* parameter has considerable potential for detection of SLR to infliximab. The aims of this study were to explore the correlation between R2* and inflammation and to develop a non-invasive nomogram based on R2* to identify SLR to infliximab in patients with CD. Three hundred and twenty-two infliximab-treated patients with CD who underwent magnetic resonance enterography within 2 weeks before or after 54 weeks of infliximab therapy were divided into training and validation datasets at a ratio of 8:2. Point-biserial analysis was conducted to confirm the relationship between R2* and inflammation. A multivariate logistic regression model was created using R2*, CRP and hemoglobin (OR, 1.10, 1.04 and 0.98; P < 0.05). Receiver-operating characteristic curves and the Hosmer-Lemeshow test were used to assess the performance of the model. A correlation between R2* and inflammation was identified. Different trends in R2* and iron status indices were observed between patients with responsive and non-responsive CD, which is worthy of further study. The model was converted to a visualized nomogram that had a good ability to discriminate the outcomes of infliximab therapy with an area under the curve of 0.723 (95% CI, 0.661–0.785) in the training dataset and 0.715 (95% CI, 0.587–0.843) in the validation dataset. We confirmed a correlation between R2* and inflammation in patients with CD. Based on the MRI-based radiomic signature, a novel nomogram was established and validated to facilitate individualized identification of SLR to infliximab in patients with CD.

show abstract

Prediction of the Growth Rate of Early-Stage Lung Adenocarcinoma by Radiomics

Cited by 20 publications

References 34 publications

Radiomics-based Machine Learning Methods for Volume Doubling Time Prediction of Pulmonary Ground-glass Nodules With Baseline Chest Computed Tomography

Radiomics-based Machine Learning Methods for Volume Doubling Time Prediction of Pulmonary Ground-glass Nodules With Baseline Chest Computed Tomography

Deep learning-based growth prediction for sub-solid pulmonary nodules on CT images

MRI-Based Radiomic Signature Identifying Secondary Loss of Response to Infliximab in Crohn's Disease

Contact Info

Product

Resources

About