Preoperative Prediction of Pancreatic Neuroendocrine Neoplasms Grading Based on Enhanced Computed Tomography Imaging: Validation of Deep Learning with a Convolutional Neural Network

Yanji Luo; Xin Chen; Jie Chen; Chenyu Song; Jingxian Shen; Huanhui Xiao; Minhu Chen; Zi-Ping Li; Bingsheng Huang; Shi-Ting Feng

doi:10.1159/000503291

Preoperative Prediction of Pancreatic Neuroendocrine Neoplasms Grading Based on Enhanced Computed Tomography Imaging: Validation of Deep Learning with a Convolutional Neural Network

Neuroendocrinology. 2020;110(5):338-350. doi: 10.1159/000503291. Epub 2019 Sep 13.

Authors

Yanji Luo¹, Xin Chen², Jie Chen³, Chenyu Song¹, Jingxian Shen⁴, Huanhui Xiao², Minhu Chen³, Zi-Ping Li¹, Bingsheng Huang⁵, Shi-Ting Feng¹

Affiliations

¹ Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China.
² School of Biomedical Engineering, Health Science Center, Shenzhen University, Block A2, Xili Campus of Shenzhen University, Shenzhen, China.
³ Department of Gastroenterology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China.
⁴ Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, China.
⁵ School of Biomedical Engineering, Health Science Center, Shenzhen University, Block A2, Xili Campus of Shenzhen University, Shenzhen, China, huangb@szu.edu.cn.

PMID: 31525737
DOI: 10.1159/000503291

Abstract

Introduction: The pathological grading of pancreatic neuroendocrine neoplasms (pNENs) is an independent predictor of survival and indicator for treatment. Deep learning (DL) with a convolutional neural network (CNN) may improve the preoperative prediction of pNEN grading.

Methods: Ninety-three pNEN patients with preoperative contrast-enhanced computed tomography (CECT) from Hospital I were retrospectively enrolled. A CNN-based DL algorithm was applied to the CECT images to obtain 3 models (arterial, venous, and arterial/venous models), the performances of which were evaluated via an eightfold cross-validation technique. The CECT images of the optimal phase were used for comparing the DL and traditional machine learning (TML) models in predicting the pathological grading of pNENs. The performance of radiologists by using qualitative and quantitative computed tomography findings was also evaluated. The best DL model from the eightfold cross-validation was evaluated on an independent testing set of 19 patients from Hospital II who were scanned on a different scanner. The Kaplan-Meier (KM) analysis was employed for survival analysis.

Results: The area under the curve (AUC; 0.81) of arterial phase in validation set was significantly higher than those of venous (AUC 0.57, p = 0.03) and arterial/venous phase (AUC 0.70, p = 0.03) in predicting the pathological grading of pNENs. Compared with the TML models, the DL model gave a higher (although insignificantly) AUC. The highest OR was achieved for the p ratio <0.9, the AUC and accuracy for diagnosing G3 pNENs were 0.80 and 79.1% respectively. The DL algorithm achieved an AUC of 0.82 and an accuracy of 88.1% for the independent testing set. The KM analysis showed a statistical significant difference between the predicted G1/2 and G3 groups in the progression-free survival (p = 0.001) and overall survival (p < 0.001).

Conclusion: The CNN-based DL method showed a relatively robust performance in predicting pathological grading of pNENs from CECT images.

Keywords: Deep learning; Neoplasm grading; Neuroendocrine tumors; Pancreatic neoplasms; Tomography, spiral computed.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adult
Aged
Deep Learning
Female
Humans
Image Interpretation, Computer-Assisted / methods*
Image Interpretation, Computer-Assisted / standards
Machine Learning*
Male
Middle Aged
Neoplasm Grading / methods*
Neoplasm Grading / standards
Neural Networks, Computer*
Neuroendocrine Tumors / diagnostic imaging*
Pancreatic Neoplasms / diagnostic imaging*
Retrospective Studies
Tomography, Spiral Computed*