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

PLoS One. 2021 Jun 28;16(6):e0251701. doi: 10.1371/journal.pone.0251701. eCollection 2021.

Abstract

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.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adenocarcinoma / diagnosis
  • Adenocarcinoma / pathology
  • Diagnosis, Computer-Assisted / methods
  • Diagnosis, Differential
  • Endoscopic Ultrasound-Guided Fine Needle Aspiration / methods
  • Endosonography / methods
  • Humans
  • Neural Networks, Computer
  • Pancreas / pathology*
  • Pancreatic Neoplasms / diagnosis*
  • Pancreatic Neoplasms / pathology
  • Pilot Projects
  • Sensitivity and Specificity

Grants and funding

This study was primarily supported by the Executive Unit for the Financing of Higher Education, Research, Development and Innovation (UEFISCDI) of the Ministry of National Education via the Norwegian Financial Mechanism 2014-2021 (project RO-NO-2019-0138, 19/2020 “Improving Cancer Diagnostics in Flexible Endoscopy using Artificial Intelligence and Medical Robotics” IDEAR, Contract No. 19/2020) to authors ALU, IC, LGG, GG, AVI, SU and AS, and partially by the Executive Unit for the Financing of Higher Education, Research, Development and Innovation (UEFISCDI) of the Ministry of National Education, (project "PREdictive Machine Learning Algorithm for the Dynamic Evaluation of Pancreatic Cancer during Therapy Multimodal Therapy” - PREDYCT, code PN-III-P4-ID-PCE2020-0884 within PNCDI III) to authors DEB, BSU, MIC, AC, CFP and AS. No additional external funding was received for this study. The funders had no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.