CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network

Rong Yang,Guo Sa,Haigen Hu,Qiu Guan,Yizhou Chen,Feng Chen,Kangjie Li,Jie Zhou

doi:10.1007/s00261-021-03230-5

Abstract

BackgroundAt present, numerous challenges exist in the diagnosis of pancreatic SCNs and MCNs. After the emergence of artificial intelligence (AI), many radiomics research methods have been applied to the identification of pancreatic SCNs and MCNs.PurposeA deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRF-ResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs).Materials and methodsThis study is a retrospective analysis of pancreatic unenhanced and enhanced CT images in 63 patients with pancreatic SCNs and 47 patients with MCNs (3 of which were mucinous cystadenocarcinoma) confirmed by pathology from December 2010 to August 2016. Different image segmented methods (single-channel manual outline ROI image and multi-channel image), feature extraction methods (wavelet, LBP, HOG, GLCM, Gabor, ResNet, and AlexNet) and classifiers (KNN, Softmax, Bayes, random forest classifier, and Majority Voting rule method) are used to classify the nature of the lesion in each CT image (SCNs/MCNs). Then, the comparisons of classification results were made based on sensitivity, specificity, precision, accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), with pathological results serving as the gold standard.ResultsMulti-channel-ResNet (AUC 0.98) was superior to Manual-ResNet (AUC 0.91).CT image characteristics of lesions extracted by ResNet are more representative than wavelet, LBP, HOG, GLCM, Gabor, and AlexNet. Compared to the use of three classifiers alone and Majority Voting rule method, the use of the MMRF-ResNet model exhibits a better evaluation effect (AUC 0.96) for the classification of the pancreatic SCNs and MCNs.ConclusionThe CT image classification model MMRF-ResNet is an effective method to distinguish between pancreatic SCNs and MCNs.Graphic abstract

Highlights

Pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs) are rare types of pancreatic tumors
Numerous challenges exist in the diagnosis and treatment of pancreatic SCNs and MCNs, such as the rational selection of imaging evaluation methods, the key points of correct imaging diagnosis, and conservative observation or surgical resection
MCNs have the potential to develop into pancreatic cancer, a recent review of 90 resected MCNs found that 10% of them contained either high-grade dysplasia or pancreatic cancer [12]

Summary

Introduction

Pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs) are rare types of pancreatic tumors. The classification probabilities of three single classifiers (KNN classifier, Softmax classifier, and Bayes classifier) were integrated using the random forest classifier to distinguish between pancreatic SCNs and MCNs. The purpose of this study was to analyze the CT features of pancreatic SCNs and MCNs using the MMRF-ResNet model (The structure of MMRF-ResNet model is shown in Fig. 1) and to provide a better non-invasive imaging evaluation model for the identification of pancreatic SCNs and MCNs. At present, numerous challenges exist in the diagnosis of pancreatic SCNs and MCNs. After the emergence of artificial intelligence (AI), many radiomics research methods have been applied to the identification of pancreatic SCNs and MCNs. Purpose A deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRFResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs). Different image segmented methods (single-channel manual outline ROI image and multi-channel image), feature extraction methods (wavelet, LBP, HOG, GLCM, Gabor, ResNet, and AlexNet) and classifiers (KNN, Softmax, Bayes, random forest classifier, and Majority Voting rule method) are used to classify the nature of the lesion in each CT image (SCNs/MCNs).

Objectives

Methods

Results

Conclusion