Cargando…

Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected r...

Descripción completa

Detalles Bibliográficos
Autores principales: Nguon, Leang Sim, Seo, Kangwon, Lim, Jung-Hyun, Song, Tae-Jun, Cho, Sung-Hyun, Park, Jin-Seok, Park, Suhyun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8229855/
https://www.ncbi.nlm.nih.gov/pubmed/34201066
http://dx.doi.org/10.3390/diagnostics11061052
_version_ 1783713069345538048
author Nguon, Leang Sim
Seo, Kangwon
Lim, Jung-Hyun
Song, Tae-Jun
Cho, Sung-Hyun
Park, Jin-Seok
Park, Suhyun
author_facet Nguon, Leang Sim
Seo, Kangwon
Lim, Jung-Hyun
Song, Tae-Jun
Cho, Sung-Hyun
Park, Jin-Seok
Park, Suhyun
author_sort Nguon, Leang Sim
collection PubMed
description Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected retrospectively from 59 MCN and 49 SCN patients from two different hospitals. Data augmentation was used to enhance the size and quality of training datasets. Fine-tuning training approaches were utilized by adopting the pre-trained model from transfer learning while training selected layers. Testing of the network was conducted by varying the endoscopic ultrasonography (EUS) image sizes and positions to evaluate the network performance for differentiation. The proposed network model achieved up to 82.75% accuracy and a 0.88 (95% CI: 0.817–0.930) area under curve (AUC) score. The performance of the implemented deep learning networks in decision-making using only EUS images is comparable to that of traditional manual decision-making using EUS images along with supporting clinical information. Gradient-weighted class activation mapping (Grad-CAM) confirmed that the network model learned the features from the cyst region accurately. This study proves the feasibility of diagnosing MCN and SCN using a deep learning network model. Further improvement using more datasets is needed.
format Online
Article
Text
id pubmed-8229855
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82298552021-06-26 Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography Nguon, Leang Sim Seo, Kangwon Lim, Jung-Hyun Song, Tae-Jun Cho, Sung-Hyun Park, Jin-Seok Park, Suhyun Diagnostics (Basel) Article Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected retrospectively from 59 MCN and 49 SCN patients from two different hospitals. Data augmentation was used to enhance the size and quality of training datasets. Fine-tuning training approaches were utilized by adopting the pre-trained model from transfer learning while training selected layers. Testing of the network was conducted by varying the endoscopic ultrasonography (EUS) image sizes and positions to evaluate the network performance for differentiation. The proposed network model achieved up to 82.75% accuracy and a 0.88 (95% CI: 0.817–0.930) area under curve (AUC) score. The performance of the implemented deep learning networks in decision-making using only EUS images is comparable to that of traditional manual decision-making using EUS images along with supporting clinical information. Gradient-weighted class activation mapping (Grad-CAM) confirmed that the network model learned the features from the cyst region accurately. This study proves the feasibility of diagnosing MCN and SCN using a deep learning network model. Further improvement using more datasets is needed. MDPI 2021-06-08 /pmc/articles/PMC8229855/ /pubmed/34201066 http://dx.doi.org/10.3390/diagnostics11061052 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Nguon, Leang Sim
Seo, Kangwon
Lim, Jung-Hyun
Song, Tae-Jun
Cho, Sung-Hyun
Park, Jin-Seok
Park, Suhyun
Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography
title Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography
title_full Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography
title_fullStr Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography
title_full_unstemmed Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography
title_short Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography
title_sort deep learning-based differentiation between mucinous cystic neoplasm and serous cystic neoplasm in the pancreas using endoscopic ultrasonography
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8229855/
https://www.ncbi.nlm.nih.gov/pubmed/34201066
http://dx.doi.org/10.3390/diagnostics11061052
work_keys_str_mv AT nguonleangsim deeplearningbaseddifferentiationbetweenmucinouscysticneoplasmandserouscysticneoplasminthepancreasusingendoscopicultrasonography
AT seokangwon deeplearningbaseddifferentiationbetweenmucinouscysticneoplasmandserouscysticneoplasminthepancreasusingendoscopicultrasonography
AT limjunghyun deeplearningbaseddifferentiationbetweenmucinouscysticneoplasmandserouscysticneoplasminthepancreasusingendoscopicultrasonography
AT songtaejun deeplearningbaseddifferentiationbetweenmucinouscysticneoplasmandserouscysticneoplasminthepancreasusingendoscopicultrasonography
AT chosunghyun deeplearningbaseddifferentiationbetweenmucinouscysticneoplasmandserouscysticneoplasminthepancreasusingendoscopicultrasonography
AT parkjinseok deeplearningbaseddifferentiationbetweenmucinouscysticneoplasmandserouscysticneoplasminthepancreasusingendoscopicultrasonography
AT parksuhyun deeplearningbaseddifferentiationbetweenmucinouscysticneoplasmandserouscysticneoplasminthepancreasusingendoscopicultrasonography