Deep Learning Radiomics to Predict Regional Lymph Node Staging for Hilar Cholangiocarcinoma

Yubizhuo Wang; Jiayuan Shao; Pan Wang; Lintao Chen; Mingliang Ying; Siyuan Chai; Shijian Ruan; Wuwei Tian; Yongna Cheng; Hongbin Zhang; Xiuming Zhang; Xiangming Wang; Yong Ding; Wenjie Liang; Liming Wu

doi:10.3389/fonc.2021.721460

Deep Learning Radiomics to Predict Regional Lymph Node Staging for Hilar Cholangiocarcinoma

Front Oncol. 2021 Oct 26:11:721460. doi: 10.3389/fonc.2021.721460. eCollection 2021.

Authors

Yubizhuo Wang^{1

2}, Jiayuan Shao³, Pan Wang², Lintao Chen¹, Mingliang Ying⁴, Siyuan Chai⁵, Shijian Ruan⁶, Wuwei Tian⁶, Yongna Cheng¹, Hongbin Zhang¹, Xiuming Zhang⁷, Xiangming Wang¹, Yong Ding⁶, Wenjie Liang², Liming Wu⁵

Affiliations

¹ Department of Radiology, Yiwu Central Hospital, Yiwu, China.
² Department of Radiology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China.
³ Polytechnic Institute, Zhejiang University, Hangzhou, China.
⁴ Department of Radiology, Jinhua Municipal Central Hospital, Jinhua, China.
⁵ Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
⁶ College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, China.
⁷ Department of Pathology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China.

Abstract

Background: Our aim was to establish a deep learning radiomics method to preoperatively evaluate regional lymph node (LN) staging for hilar cholangiocarcinoma (HC) patients.

Methods and materials: Of the 179 enrolled HC patients, 90 were pathologically diagnosed with lymph node metastasis. Quantitative radiomic features and deep learning features were extracted. An LN metastasis status classifier was developed through integrating support vector machine, high-performance deep learning radiomics signature, and three clinical characteristics. An LN metastasis stratification classifier (N1 vs. N2) was also proposed with subgroup analysis.

Results: The average areas under the receiver operating characteristic curve (AUCs) of the LN metastasis status classifier reached 0.866 in the training cohort and 0.870 in the external test cohorts. Meanwhile, the LN metastasis stratification classifier performed well in predicting the risk of LN metastasis, with an average AUC of 0.946.

Conclusions: Two classifiers derived from computed tomography images performed well in predicting LN staging in HC and will be reliable evaluation tools to improve decision-making.

Keywords: computed tomography; deep learning; hilar cholangiocarcinoma; lymph node; radiomics.