JMIR Publications

ABSTRACT

Background:

Radiomics can improves the accuracy of traditional image diagnosis to evaluate extrahepatic cholangiocarcinoma (ECC), however, this is limited by variation across radiologists, subjective evaluation, and restricted data. A radiomics-based particle swarm optimization and support vector machine (PSO-SVM) model may provide more accurate auxiliary diagnosis for assessing differentiation degree (DD) and lymph node metastases (LNM) of ECC.

Objective:

To develop a PSO-SVM radiomics model for predicting DD and LNM of ECC.

Methods:

For this retrospective study, the MRI data of 110 patients with ECC, who were diagnosed from January 2011 to October 2019, were used to construct radiomics prediction model. Radiomics features were extracted from T1-precontrast (T1WI), T2-weighted imaging (T2WI) and diffusion weighted imaging (DWI) by MaZda software. we performed dimension reduction to obtain 30 optimal features of each sequence, respectively. A PSO-SVM radiomics model was developed to predict DD and LNM of ECC by incorporating radiomics features and apparent diffusion coefficient (ADC) values. We randomly divided the 110 cases into training group (80%) and testing group (20%). The performance of the model is evaluated by analyzing the area under the curve (AUC) on receiver operating characteristic (ROC) curve.

Results:

A radiomics model based on PSO-SVM was developed by using 110 patients with ECC, this model produced average AUCs of 0.8905 and 0.8461 respectively for DD in training and testing groups of ECC. Meanwhile, the average AUCs of the LNM in training and testing groups of ECC were 0.9036 and 0.8889, respectively. For the 110 patients, this model has high predictive performance. The classification accuracy of this model was 82.6% and 83.6%, respectively.

Conclusions:

The MRI based PSO-SVM radiomics model might be useful for auxiliary clinical diagnosis and decision-making, which has great potential for clinical application in DD and LNM of ECC.