PMID- 34636931
OWN - NLM
STAT- MEDLINE
DCOM- 20220308
LR  - 20221005
IS  - 2366-0058 (Electronic)
IS  - 2366-004X (Print)
VI  - 47
IP  - 1
DP  - 2022 Jan
TI  - CT classification model of pancreatic serous cystic neoplasms and mucinous cystic 
      neoplasms based on a deep neural network.
PG  - 232-241
LID - 10.1007/s00261-021-03230-5 [doi]
AB  - BACKGROUND: 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 (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 METHODS: This 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. RESULTS: Multi-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. CONCLUSION: The CT image 
      classification model MMRF-ResNet is an effective method to distinguish between 
      pancreatic SCNs and MCNs.
CI  - (c) 2021. The Author(s).
FAU - Yang, Rong
AU  - Yang R
AD  - Department of Radiology, The First Affiliated Hospital, Zhejiang University 
      School of Medicine, #79 Qingchun Road, Hangzhou, 310003, Zhejiang Province, P.R. 
      China.
FAU - Chen, Yizhou
AU  - Chen Y
AD  - College of Computer Science and Technology, Zhejiang University of Technology, 
      #288 Liuhe Road, Hangzhou, 310023, Zhejiang Province, P.R. China.
FAU - Sa, Guo
AU  - Sa G
AD  - Department of Radiology, The First Affiliated Hospital, Zhejiang University 
      School of Medicine, #79 Qingchun Road, Hangzhou, 310003, Zhejiang Province, P.R. 
      China.
FAU - Li, Kangjie
AU  - Li K
AD  - College of Computer Science and Technology, Zhejiang University of Technology, 
      #288 Liuhe Road, Hangzhou, 310023, Zhejiang Province, P.R. China.
FAU - Hu, Haigen
AU  - Hu H
AD  - College of Computer Science and Technology, Zhejiang University of Technology, 
      #288 Liuhe Road, Hangzhou, 310023, Zhejiang Province, P.R. China.
FAU - Zhou, Jie
AU  - Zhou J
AD  - Department of Pathology, The First Affiliated Hospital, Zhejiang University 
      School of Medicine, #79 Qingchun Road, Hangzhou, 310003, Zhejiang Province, P.R. 
      China.
FAU - Guan, Qiu
AU  - Guan Q
AD  - College of Computer Science and Technology, Zhejiang University of Technology, 
      #288 Liuhe Road, Hangzhou, 310023, Zhejiang Province, P.R. China. gq@zjut.edu.cn.
FAU - Chen, Feng
AU  - Chen F
AUID- ORCID: 0000-0003-4402-4955
AD  - Department of Radiology, The First Affiliated Hospital, Zhejiang University 
      School of Medicine, #79 Qingchun Road, Hangzhou, 310003, Zhejiang Province, P.R. 
      China. chenfenghz@zju.edu.cn.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20211012
PL  - United States
TA  - Abdom Radiol (NY)
JT  - Abdominal radiology (New York)
JID - 101674571
SB  - IM
MH  - *Artificial Intelligence
MH  - Bayes Theorem
MH  - Diagnosis, Differential
MH  - Humans
MH  - Neural Networks, Computer
MH  - *Pancreatic Neoplasms/diagnostic imaging/pathology
MH  - Retrospective Studies
MH  - Tomography, X-Ray Computed
PMC - PMC8776667
OTO - NOTNLM
OT  - Computed tomography
OT  - Deep neural network
OT  - MCNs
OT  - Pancreas
OT  - SCNs
EDAT- 2021/10/13 06:00
MHDA- 2022/03/09 06:00
PMCR- 2021/10/12
CRDT- 2021/10/12 12:56
PHST- 2021/03/23 00:00 [received]
PHST- 2021/07/26 00:00 [accepted]
PHST- 2021/07/25 00:00 [revised]
PHST- 2021/10/13 06:00 [pubmed]
PHST- 2022/03/09 06:00 [medline]
PHST- 2021/10/12 12:56 [entrez]
PHST- 2021/10/12 00:00 [pmc-release]
AID - 10.1007/s00261-021-03230-5 [pii]
AID - 3230 [pii]
AID - 10.1007/s00261-021-03230-5 [doi]
PST - ppublish
SO  - Abdom Radiol (NY). 2022 Jan;47(1):232-241. doi: 10.1007/s00261-021-03230-5. Epub 
      2021 Oct 12.