Development and Validation of a Nomogram for Preoperative Prediction of Lymph Node Metastasis in Lung Adenocarcinoma Based on Radiomics Signature and Deep Learning Signature

PurposeThis study aims to uncover and validate an MRI-based radiomics nomogram for detecting lymph node metastasis (LNM) in pancreatic ductal adenocarcinoma (PDAC) patients prior to surgery.Materials and MethodsWe retrospectively collected 141 patients with pathologically confirmed PDAC who underwent preoperative T2-weighted imaging (T2WI) and portal venous phase (PVP) contrast-enhanced T1-weighted imaging (T1WI) scans between January 2017 and December 2021. The patients were randomly divided into training (n = 98) and validation (n = 43) cohorts at a ratio of 7:3. For each sequence, 1037 radiomics features were extracted and analyzed. After applying the gradient-boosting decision tree (GBDT), the key MRI radiomics features were selected. Three radiomics scores (rad-score 1 for PVP, rad-score 2 for T2WI, and rad-score 3 for T2WI combined with PVP) were calculated. Rad-score 3 and clinical independent risk factors were combined to construct a nomogram for the prediction of LNM of PDAC by multivariable logistic regression analysis. The predictive performances of the rad-scores and the nomogram were assessed by the area under the operating characteristic curve (AUC), and the clinical utility of the radiomics nomogram was assessed by decision curve analysis (DCA).ResultsSix radiomics features of T2WI, eight radiomics features of PVP and ten radiomics features of T2WI combined with PVP were found to be associated with LNM. Multivariate logistic regression analysis showed that rad-score 3 and MRI-reported LN status were independent predictors. In the training and validation cohorts, the AUCs of rad-score 1, rad-score 2 and rad-score 3 were 0.769 and 0.751, 0.807 and 0.784, and 0.834 and 0.807, respectively. The predictive value of rad-score 3 was similar to that of rad-score 1 and rad-score 2 in both the training and validation cohorts (P > 0.05). The radiomics nomogram constructed by rad-score 3 and MRI-reported LN status showed encouraging clinical benefit, with an AUC of 0.845 for the training cohort and 0.816 for the validation cohort.ConclusionsThe radiomics nomogram derived from the rad-score based on MRI features and MRI-reported lymph status showed outstanding performance for the preoperative prediction of LNM of PDAC.

Section: Discussionsupporting

confidence: 90%

Section: Discussionmentioning

confidence: 99%

Preoperative Prediction of Lymph Node Metastasis of Pancreatic Ductal Adenocarcinoma Based on a Radiomics Nomogram of Dual-Parametric MRI Imaging

Shi

Wei³

et al. 2022

“…By integrating DL and radiomics analysis, pattern classification was able to achieve a high prediction in the benign and malignant pathology of gastrointestinal stromal tumors ( 42 ). Combining radiomics and DL signatures can be used to accurately predict lymph node metastasis in lung adenocarcinoma ( 43 ). However, the ensemble performances of five different cML models (such as SVM, GBM, and RF) in combination with DL have never been reported, and our study is the first to evaluate these performances in HCC patients receiving TACE therapy.…”

Section: Discussionmentioning

confidence: 99%

Predicting the Initial Treatment Response to Transarterial Chemoembolization in Intermediate-Stage Hepatocellular Carcinoma by the Integration of Radiomics and Deep Learning

Peng

Huang

et al. 2021

ObjectivesWe aimed to develop radiology-based models for the preoperative prediction of the initial treatment response to transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) since the integration of radiomics and deep learning (DL) has not been reported for TACE.MethodsThree hundred and ten intermediate-stage HCC patients who underwent TACE were recruited from three independent medical centers. Based on computed tomography (CT) images, recursive feature elimination (RFE) was used to select the most useful radiomics features. Five radiomics conventional machine learning (cML) models and a DL model were used for training and validation. Mutual correlations between each model were analyzed. The accuracies of integrating clinical variables, cML, and DL models were then evaluated.ResultsGood predictive accuracies were showed across the two cohorts in the five cML models, especially the random forest algorithm (AUC = 0.967 and 0.964, respectively). DL showed high accuracies in the training and validation cohorts (AUC = 0.981 and 0.972, respectively). Significant mutual correlations were revealed between tumor size and the five cML models and DL model (each P < 0.001). The highest accuracies were achieved by integrating DL and the random forest algorithm in the training and validation cohorts (AUC = 0.995 and 0.994, respectively).ConclusionThe radiomics cML models and DL model showed notable accuracy for predicting the initial response to TACE treatment. Moreover, the integrated model could serve as a novel and accurate method for prediction in intermediate-stage HCC.

“…Radiomics features are artificially defined features, while deep learning features are extracted by a convolutional neural network (CNN). A model combining radiomics signature and deep learning signature was reported to be promising to predict LN metastasis in lung cancer ( 20 ). However, few studies used both radiomics and deep learning to predict ALN metastasis in breast cancer ( 16 ).…”

Section: Introductionmentioning

confidence: 99%

A nomogram based on radiomics signature and deep-learning signature for preoperative prediction of axillary lymph node metastasis in breast cancer

Wang

Hu²,

Zhan³

et al. 2022

PurposeTo develop a nomogram based on radiomics signature and deep-learning signature for predicting the axillary lymph node (ALN) metastasis in breast cancer.MethodsA total of 151 patients were assigned to a training cohort (n = 106) and a test cohort (n = 45) in this study. Radiomics features were extracted from DCE-MRI images, and deep-learning features were extracted by VGG-16 algorithm. Seven machine learning models were built using the selected features to evaluate the predictive value of radiomics or deep-learning features for the ALN metastasis in breast cancer. A nomogram was then constructed based on the multivariate logistic regression model incorporating radiomics signature, deep-learning signature, and clinical risk factors.ResultsFive radiomics features and two deep-learning features were selected for machine learning model construction. In the test cohort, the AUC was above 0.80 for most of the radiomics models except DecisionTree and ExtraTrees. In addition, the K-nearest neighbor (KNN), XGBoost, and LightGBM models using deep-learning features had AUCs above 0.80 in the test cohort. The nomogram, which incorporated the radiomics signature, deep-learning signature, and MRI-reported LN status, showed good calibration and performance with the AUC of 0.90 (0.85-0.96) in the training cohort and 0.90 (0.80-0.99) in the test cohort. The DCA showed that the nomogram could offer more net benefit than radiomics signature or deep-learning signature.ConclusionsBoth radiomics and deep-learning features are diagnostic for predicting ALN metastasis in breast cancer. The nomogram incorporating radiomics and deep-learning signatures can achieve better prediction performance than every signature used alone.