Imaging features and deep learning for prediction of pulmonary epithelioid hemangioendothelioma in CT images

Junfeng Huang; Shuojia Xie; Junjie Huang; Ziwen Zheng; Zikai Lin; Jinsheng Lin; Kailun Tang; Mingqiang Meng; Yulin Zhao; Wanzhe Liao; Chunping Liu; Yingying Gu; Shiyue Li; Huai Chen; Ruchong Chen

doi:10.21037/jtd-23-455

Imaging features and deep learning for prediction of pulmonary epithelioid hemangioendothelioma in CT images

J Thorac Dis. 2024 Feb 29;16(2):935-947. doi: 10.21037/jtd-23-455. Epub 2024 Feb 23.

Authors

Junfeng Huang^#¹, Shuojia Xie^#^{1

2}, Junjie Huang^#^{3

4}, Ziwen Zheng¹, Zikai Lin^{1

2}, Jinsheng Lin¹, Kailun Tang^{1

5}, Mingqiang Meng^{6

7}, Yulin Zhao², Wanzhe Liao², Chunping Liu¹, Yingying Gu¹, Shiyue Li¹, Huai Chen⁸, Ruchong Chen¹

Affiliations

¹ Department of Allergy and Clinical Immunology, National Center for Respiratory Medicine, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
² Nanshan School of Medicine, Guangzhou Medical University, Guangzhou, China.
³ Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
⁴ Department of Medical Imaging, Foshan Hospital of Traditional Chinese Medicine, Foshan, China.
⁵ Clinical Medical College of Henan University, Kaifeng, China.
⁶ The School of Biomedical Engineering, Southern Medical University, Guangzhou, China.
⁷ Guangdong Artificial Intelligence and Digital Economy Laboratory (Guangzhou), Guangzhou, China.
⁸ Department of Radiology, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.

^# Contributed equally.

Abstract

Background: Pulmonary epithelioid hemangioendothelioma (PEH) is a rare vascular tumour, and its early diagnosis remains challenging. This study aims to comprehensively analyse the imaging features of PEH and develop a model for predicting PEH.

Methods: Retrospective and pooled analyses of imaging findings were performed in PEH patients at our center (n=25) and in published cases (n=71), respectively. Relevant computed tomography (CT) images were extracted and used to build a deep learning model for PEH identification and differentiation from other diseases.

Results: In this study, bilateral multiple nodules/masses (n=19) appeared to be more common with most nodules less than 2 cm. In addition to the common types and features, the pattern of mixed type (n=4) and isolated nodules (n=4), punctate calcifications (5/25) and lymph node enlargement were also observed (10/25). The presence of pleural effusion is associated with a poor prognosis in PEH. The deep learning model, with an area under the receiver operating characteristic curve (AUC) of 0.71 [95% confidence interval (CI): 0.69-0.72], has a differentiation accuracy of 100% and 74% for the training and test sets respectively.

Conclusions: This study confirmed the heterogeneity of the imaging findings in PEH and showed several previously undescribed types and features. The current deep learning model based on CT has potential for clinical application and needs to be further explored in the future.

Keywords: Pulmonary epithelioid hemangioendothelioma (PEH); computed tomography (CT); deep learning; imaging features.