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

Autor: Adrian Saftoiu, Gabriel Gruionu, Irina M. Cazacu, Carmen Popescu, Lucian Gheorghe Gruionu, Daniela E. Burtea, Bogdan Silviu Ungureanu, Ștefan Udriștoiu, Mădălin Ionuț Costache, Alina Constantin, Andreea Valentina Iacob, Anca Loredana Udriștoiu
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Endoscopic ultrasound
Computer science
Pilot Projects
Endosonography
Diagnostic Radiology
Machine Learning
0302 clinical medicine
Ultrasound Imaging
Medicine and Health Sciences
Diagnosis
Computer-Assisted
Multidisciplinary
Artificial neural network
medicine.diagnostic_test
Radiology and Imaging
Fine-needle aspiration
Oncology
030220 oncology & carcinogenesis
Medicine
030211 gastroenterology & hepatology
Radiology
Elastography
Research Article
medicine.medical_specialty
Computer and Information Sciences
Imaging Techniques
Science
Surgical and Invasive Medical Procedures
Adenocarcinoma
Research and Analysis Methods
Sensitivity and Specificity
Doppler Imaging
Diagnosis
Differential
03 medical and health sciences
Pancreatic Cancer
Deep Learning
Diagnostic Medicine
Artificial Intelligence
Pancreatic cancer
Gastrointestinal Tumors
parasitic diseases
medicine
Cancer Detection and Diagnosis
Humans
Endoscopic Ultrasound-Guided Fine Needle Aspiration
Pancreas
business.industry
Deep learning
Carcinoma
Cancers and Neoplasms
Endoscopy
medicine.disease
Pancreatic Neoplasms
Computer-aided diagnosis
Artificial intelligence
Neural Networks
Computer
Differential diagnosis
business
Zdroj: PLoS ONE, Vol 16, Iss 6, p e0251701 (2021)
PLoS ONE
ISSN: 1932-6203
Popis: 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.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje