Dataset Information

An integrated model incorporating deep learning, hand-crafted radiomics and clinical and US features to diagnose central lymph node metastasis in patients with papillary thyroid cancer.

ABSTRACT:

Objective

To evaluate the value of an integrated model incorporating deep learning (DL), hand-crafted radiomics and clinical and US imaging features for diagnosing central lymph node metastasis (CLNM) in patients with papillary thyroid cancer (PTC).

Methods

This retrospective study reviewed 613 patients with clinicopathologically confirmed PTC from two institutions. The DL model and hand-crafted radiomics model were developed using primary lesion images and then integrated with clinical and US features selected by multivariate analysis to generate an integrated model. The performance was compared with junior and senior radiologists on the independent test set. SHapley Additive exPlanations (SHAP) plot and Gradient-weighted Class Activation Mapping (Grad-CAM) were used for the visualized explanation of the model.

Results

The integrated model yielded the best performance with an AUC of 0.841. surpassing that of the hand-crafted radiomics model (0.706, p < 0.001) and the DL model (0.819, p = 0.26). Compared to junior and senior radiologists, the integrated model reduced the missed CLNM rate from 57.89% and 44.74-27.63%, and decreased the rate of unnecessary central lymph node dissection (CLND) from 29.87% and 27.27-18.18%, respectively. SHAP analysis revealed that the DL features played a primary role in the diagnosis of CLNM, while clinical and US features (such as extrathyroidal extension, tumour size, age, gender, and multifocality) provided additional support. Grad-CAM indicated that the model exhibited a stronger focus on thyroid capsule in patients with CLNM.

Conclusion

Integrated model can effectively decrease the incidence of missed CLNM and unnecessary CLND. The application of the integrated model can help improve the acceptance of AI-assisted US diagnosis among radiologists.

SUBMITTER: Gao Y

PROVIDER: S-EPMC10787418 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An integrated model incorporating deep learning, hand-crafted radiomics and clinical and US features to diagnose central lymph node metastasis in patients with papillary thyroid cancer.

Gao Yang Y Wang Weizhen W Yang Yuan Y Xu Ziting Z Lin Yue Y Lang Ting T Lei Shangtong S Xiao Yisheng Y Yang Wei W Huang Weijun W Li Yingjia Y

BMC cancer 20240112 1

<h4>Objective</h4>To evaluate the value of an integrated model incorporating deep learning (DL), hand-crafted radiomics and clinical and US imaging features for diagnosing central lymph node metastasis (CLNM) in patients with papillary thyroid cancer (PTC).<h4>Methods</h4>This retrospective study reviewed 613 patients with clinicopathologically confirmed PTC from two institutions. The DL model and hand-crafted radiomics model were developed using primary lesion images and then integrated with cl ...[more]

PMID: 38216936

Similar Datasets

Project description:BackgroundThyroid cancer is prone to early lymph node metastasis (LNM), and patients with large volume LNM (LVLNM) tend to have a poorer prognosis. The aim of this study was to predict LVLNM in before surgery based on radiomics and deep learning (DL).MethodsA multicenter retrospective study was performed, including 854 papillary thyroid carcinoma (PTC) patients from three centers. Radiomics features were extracted. Logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), multi-layer perceptron (MLP), random forest (RF), ExtraTrees, extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) algorithms were used to construct radiomics models. AlexNet, DenseNet121, inception_v3, ResNet50, and transformer algorithms were used to construct DL models. The receiver operating characteristic (ROC) curve was employed to select the better-performing model. A combined model was then created by merging radiomics features and DL features. The least absolute shrinkage and selection operator (LASSO) method was utilized to identify metabolites and radiomics features with non-zero coefficients. The performance of the models was evaluated using area under the curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), and F1-score.ResultsA total of 1,357 radiomics features were extracted. Among the radiomics models, the ExtraTrees model demonstrated the optimal diagnostic capabilities with an AUC of 0.787 [95% confidence interval (CI): 0.715-0.858], and DenseNet121 DL model demonstrated the optimal diagnostic capabilities with an AUC of 0.766 (95% CI: 0.683-0.848). Furthermore, the combined model, named the Thy-DL-Radiomics model, exhibited an AUC of 0.839 (95% CI: 0.758-0.920) in the internal validation set and 0.789 (95% CI: 0.718-0.859) in the external validation set.ConclusionsA radiomics-DL features integrated model can predict LVLNM in PTC patients and provide guidance for personalized treatment.

Project description:ObjectiveTo assess the utility of predictive models using ultrasound radiomic features to predict cervical lymph node metastasis (CLNM) in solitary papillary thyroid carcinoma (PTC) patients.MethodsA total of 570 PTC patients were included (456 patients in the training set and 114 in the testing set). Pyradiomics was employed to extract radiomic features from preoperative ultrasound images. After dimensionality reduction and meticulous selection, we developed radiomics models using various machine learning algorithms. Univariate and multivariate logistic regressions were conducted to identify independent risk factors for CLNM. We established clinical models using these risk factors. Finally, we integrated radiomic and clinical models to create a combined nomogram. We plotted ROC curves to assess diagnostic performance and used calibration curves to evaluate alignment between predicted and observed probabilities.ResultsA total of 1561 radiomics features were extracted from preoperative ultrasound images. After dimensionality reduction and feature selection, 16 radiomics features were identified. Among radiomics models, the logistic regression (LR) model exhibited higher predictive efficiency. Univariate and multivariate logistic regression results revealed that patient age, tumor size, gender, suspicious cervical lymph node metastasis, and capsule contact were independent predictors of CLNM (all P < 0.05). By constructing a clinical model, the LR model demonstrated favorable diagnostic performance. The combined model showed superior diagnostic efficacy, with an AUC of 0.758 (95% CI: 0.712-0.803) in the training set and 0.759 (95% CI: 0.669-0.849) in the testing set. In the training dataset, the AUC value of the nomogram was higher than that of the clinical and radiomics models (P = 0.027 and 0.002, respectively). In the testing dataset, the AUC value of the nomogram model was also greater than that of the radiomics models (P = 0.012). However, there was no significant statistical difference between the nomogram and the clinical model (P = 0.928). The calibration curve indicated a good fit of the combined model.ConclusionUltrasound radiomics technology offers a quantitative and objective method for predicting CLNM in PTC patients. Nonetheless, the clinical indicators persists as irreplaceable.

Dataset Information

An integrated model incorporating deep learning, hand-crafted radiomics and clinical and US features to diagnose central lymph node metastasis in patients with papillary thyroid cancer.

Objective

Methods

Results

Conclusion

Publications

An integrated model incorporating deep learning, hand-crafted radiomics and clinical and US features to diagnose central lymph node metastasis in patients with papillary thyroid cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets