Development and validation of CT-based radiomics deep learning signatures to predict lymph node metastasis in non-functional pancreatic neuroendocrine tumors: a multicohort study

Wenchao Gu; Yingli Chen; Haibin Zhu; Haidi Chen; Zongcheng Yang; Shaocong Mo; Hongyue Zhao; Lei Chen; Takahito Nakajima; XianJun Yu; Shunrong Ji; YaJia Gu; Jie Chen; Wei Tang

doi:10.1016/j.eclinm.2023.102269

Development and validation of CT-based radiomics deep learning signatures to predict lymph node metastasis in non-functional pancreatic neuroendocrine tumors: a multicohort study

EClinicalMedicine. 2023 Oct 24:65:102269. doi: 10.1016/j.eclinm.2023.102269. eCollection 2023 Nov.

Authors

Wenchao Gu^{1

2

3}, Yingli Chen^{2

4}, Haibin Zhu⁵, Haidi Chen^{4

6

7

8

9}, Zongcheng Yang¹⁰, Shaocong Mo¹¹, Hongyue Zhao¹², Lei Chen¹³, Takahito Nakajima¹, XianJun Yu^{4

6

7

8

9}, Shunrong Ji^{4

6

7

8

9}, YaJia Gu^{2

4}, Jie Chen^{4

6

14}, Wei Tang^{2

4}

Affiliations

¹ Department of Diagnostic and Interventional Radiology, University of Tsukuba, Faculty of Medicine, Ibaraki, Tsukuba, Japan.
² Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China.
³ Department of Diagnostic Radiology and Nuclear Medicine, Gunma University Graduate School of Medicine, Maebashi, Japan.
⁴ Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China.
⁵ Key Laboratory of Carcinogenesis and Translational Research, Department of Radiology, Peking University Cancer Hospital and Institute, Beijing, China.
⁶ Center for Neuroendocrine Tumors, Fudan University Shanghai Cancer Center, Shanghai, China.
⁷ Department of Pancreatic Surgery, Fudan University Shanghai Cancer Center, Shanghai, China.
⁸ Shanghai Pancreatic Cancer Institute, Shanghai, China.
⁹ Pancreatic Cancer Institute, Fudan University, Shanghai, China.
¹⁰ Department of Stomatology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, PR China.
¹¹ Department of Digestive Diseases, Huashan Hospital, Fudan University, Shanghai, China.
¹² Department of Nuclear Medicine, The First Affiliated Hospital of Harbin Medical University, China.
¹³ Department of Radiology, Minhang Branch, Fudan University Shanghai Cancer Center, Shanghai, China.
¹⁴ Department of Head & Neck Tumors and Neuroendocrine Tumors, Fudan University Shanghai Cancer Center, Shanghai, China.

Abstract

Background: Lymph node status is an important factor for the patients with non-functional pancreatic neuroendocrine tumors (NF-PanNETs) with respect to the surgical methods, prognosis, recurrence. Our aim is to develop and validate a combination model based on contrast-enhanced CT images to predict the lymph node metastasis (LNM) in NF-PanNETs.

Methods: Retrospective data were gathered for 320 patients with NF-PanNETs who underwent curative pancreatic resection and CT imaging at two institutions (Center 1, n = 236 and Center 2, n = 84) between January 2010 and March 2022. RDPs (Radiomics deep learning signature) were developed based on ten machine-learning techniques. These signatures were integrated with the clinicopathological factors into a nomogram for clinical applications. The evaluation of the model's performance was conducted through the metrics of the area under the curve (AUC).

Findings: The RDPs showed excellent performance in both centers with a high AUC for predicting LNM and disease-free survival (DFS) in Center 1 (AUC, 0.88; 95% CI: 0.84-0.92; DFS, p < 0.05) and Center 2 (AUC, 0.91; 95% CI: 0.85-0.97; DFS, p < 0.05). The clinical factors of vascular invasion, perineural invasion, and tumor grade were associated with LNM (p < 0.05). The combination nomogram showed better prediction capability for LNM (AUC, 0.93; 95% CI: 0.89-0.96). Notably, our model maintained a satisfactory predictive ability for tumors at the 2-cm threshold, demonstrating its effectiveness across different tumor sizes in Center 1 (≤2 cm: AUC, 0.90 and >2 cm: AUC, 0.86) and Center 2 (≤2 cm: AUC, 0.93 and >2 cm: AUC, 0.91).

Interpretation: Our RDPs may have the potential to preoperatively predict LNM in NF-PanNETs, address the insufficiency of clinical guidelines concerning the 2-cm threshold for tumor lymph node dissection, and provide precise therapeutic strategies.

Funding: This work was supported by JSPS KAKENHI Grant Number JP22K20814; the Rare Tumor Research Special Project of the National Natural Science Foundation of China (82141104) and Clinical Research Special Project of Shanghai Municipal Health Commission (202340123).

Keywords: CT; Deep learning; Lymph node metastasis; Non-functional pancreatic neuroendocrine tumor; Radiomics.