CT-Based Radiomics Signatures for Predicting the Risk Categorization of Thymic Epithelial Tumors.

Jin Liu,Sicong Wang,Ping Yin,Tao Liu,Nan Hong,Chao Sun

doi:10.3389/fonc.2021.628534

Abstract

ObjectivesThis study aims to assess the performance of radiomics approaches based on 3D computed tomography (CT), clinical and semantic features in predicting the pathological classification of thymic epithelial tumors (TETs).MethodsA total of 190 patients who underwent surgical resection and had pathologically confirmed TETs were enrolled in this retrospective study. All patients underwent non-contrast-enhanced CT (NECT) scans and contrast-enhanced CT (CECT) scans before treatment. A total of 396 hand-crafted radiomics features of each patient were extracted from the volume of interest in NECT and CECT images. We compared three clinical features and six semantic features (observed radiological traits) between patients with TETs. Two triple-classification radiomics models (RMs), two corresponding clinical RMs, and two corresponding clinical-semantic RMs were built to identify the types of the TETs. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) were useful to evaluate the different models.ResultsOf the 190 patients, 83 had low-risk thymoma, 58 had high-risk thymoma, and 49 had thymic carcinoma. Clinical features (Age) and semantic features (mediastinal fat infiltration, mediastinal lymph node enlargement, and pleural effusion) were significantly different among the groups(P < 0.001). In the validation set, the NECT-based clinical RM (AUC = 0.770 for low-risk thymoma, 0.689 for high-risk thymoma, and 0.783 for thymic carcinoma; ACC = 0.569) performed better than the CECT-based clinical-semantic RM (AUC = 0.785 for low-risk thymoma, 0.576 for high-risk thymoma, and 0.774 for thymic carcinoma; ACC = 0.483).ConclusionsNECT-based and CECT-based RMs may provide a non-invasive method to distinguish low-risk thymoma, high-risk thymoma, and thymic carcinoma, and NECT-based RMs performed better.Advances in KnowledgeRadiomics models may be used for the preoperative prediction of the pathological classification of TETs.

Highlights

Thymic epithelial tumors (TETs) originate from thymic epithelial cells and are the most common tumors in the anterior mediastinum, accounting for 47% of mediastinal neoplasms [1]
This study aims to assess the performance of radiomics approaches based on 3D computed tomography (CT), clinical and semantic features in predicting the pathological classification of thymic epithelial tumors (TETs)
Advances in Knowledge: Radiomics models may be used for the preoperative prediction of the pathological classification of TETs

Summary

Introduction

Thymic epithelial tumors (TETs) originate from thymic epithelial cells and are the most common tumors in the anterior mediastinum, accounting for 47% of mediastinal neoplasms [1]. Before 1980, TET classification was based on the morphological features of tumor cells and was divided into spindle cell, lymphocyte dominant, epithelial cell, and lymphoepithelial types. Based on the consensus of the international thymic malignancy interest group on thymic tumors, the 2015 WHO classification of TETs modified the view of thymoma as a benign tumor, except for nodule-type thymoma and micro thymoma with lymphoid stroma. Patients with types B2 and B3 thymomas had higher tumor recurrence rates and mortality rates than those with other types [5]. The potential for complete resection and the overall and disease-free survival outcomes were closely related to the thymoma stage. Both the histotype and stage correlated with disease-free survival. Accurate preoperative classification can help develop individualized treatment methods for TET patients and improve prognosis [8, 9]

Objectives

Methods

Results

Conclusion