Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.

Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis rem...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Anca Loredana Udriștoiu, Irina Mihaela Cazacu, Lucian Gheorghe Gruionu, Gabriel Gruionu, Andreea Valentina Iacob, Daniela Elena Burtea, Bogdan Silviu Ungureanu, Mădălin Ionuț Costache, Alina Constantin, Carmen Florina Popescu, Ștefan Udriștoiu, Adrian Săftoiu
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/15fd473252e0407a8d6f34c3979ad484
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:15fd473252e0407a8d6f34c3979ad484
record_format	dspace
spelling	oai:doaj.org-article:15fd473252e0407a8d6f34c3979ad4842021-12-02T20:03:49ZReal-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.1932-620310.1371/journal.pone.0251701https://doaj.org/article/15fd473252e0407a8d6f34c3979ad4842021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0251701https://doaj.org/toc/1932-6203Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.Anca Loredana UdriștoiuIrina Mihaela CazacuLucian Gheorghe GruionuGabriel GruionuAndreea Valentina IacobDaniela Elena BurteaBogdan Silviu UngureanuMădălin Ionuț CostacheAlina ConstantinCarmen Florina PopescuȘtefan UdriștoiuAdrian SăftoiuPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0251701 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Anca Loredana Udriștoiu Irina Mihaela Cazacu Lucian Gheorghe Gruionu Gabriel Gruionu Andreea Valentina Iacob Daniela Elena Burtea Bogdan Silviu Ungureanu Mădălin Ionuț Costache Alina Constantin Carmen Florina Popescu Ștefan Udriștoiu Adrian Săftoiu Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.
description	Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.
format	article
author	Anca Loredana Udriștoiu Irina Mihaela Cazacu Lucian Gheorghe Gruionu Gabriel Gruionu Andreea Valentina Iacob Daniela Elena Burtea Bogdan Silviu Ungureanu Mădălin Ionuț Costache Alina Constantin Carmen Florina Popescu Ștefan Udriștoiu Adrian Săftoiu
author_facet	Anca Loredana Udriștoiu Irina Mihaela Cazacu Lucian Gheorghe Gruionu Gabriel Gruionu Andreea Valentina Iacob Daniela Elena Burtea Bogdan Silviu Ungureanu Mădălin Ionuț Costache Alina Constantin Carmen Florina Popescu Ștefan Udriștoiu Adrian Săftoiu
author_sort	Anca Loredana Udriștoiu
title	Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.
title_short	Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.
title_full	Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.
title_fullStr	Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.
title_full_unstemmed	Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.
title_sort	real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/15fd473252e0407a8d6f34c3979ad484
work_keys_str_mv	AT ancaloredanaudristoiu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT irinamihaelacazacu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT luciangheorghegruionu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT gabrielgruionu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT andreeavalentinaiacob realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT danielaelenaburtea realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT bogdansilviuungureanu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT madalinionutcostache realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT alinaconstantin realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT carmenflorinapopescu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT stefanudristoiu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel AT adriansaftoiu realtimecomputeraideddiagnosisoffocalpancreaticmassesfromendoscopicultrasoundimagingbasedonahybridconvolutionalandlongshorttermmemoryneuralnetworkmodel
_version_	1718375645230137344

Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.

Ejemplares similares