Page 74 - Read Online

Page 32 McGivern et al. Art Int Surg 2023;3:27-47 https://dx.doi.org/10.20517/ais.2022.39

Table 1. Summary of included studies focusing on diagnostic uses of AI in HPB surgery
Year of AI
Authors Location Organ Aim Method Data
publication method
[13]
Saftoiu et al. 2012 Romania P DL/CV Assessed accuracy of real-time Prospective, EUS images
EUS elastography in pancreatic blinded,
lesions using artificial neural multicentric
network analysis study
[14]
Kaizhi et al. 2014 Japan L DL/CV Proposes automatic classification Case series CEUS images
method based on deep learning in
contrast-enhanced
ultrasonography (CEUS) of focal
liver lesions
[15]
Gatos et al. 2015 Greece L ML/CV Design and implementation of a Retrospective MRI images
computer-based image analysis study
system employing the support
vector machine system for the
classification of liver lesions
Roch et al [16] 2015 USA P NLP Implement an automated Natural Single institution Patient records
Language Processing based prospective pilot
pancreatic cyst identification study
system
[17]
Sada et al. 2016 USA L NLP Evaluated whether natural Retrospective Pathology/radiology
language processing document study reports
classification improves HCC
identification
[18]
Kondo et al. 2017 Japan L ML/CV Proposes automatic classification Single institution CEUS images
method based on machine pilot study
learning in CEUS of focal liver
lesions
[19]
Yang et al. 2017 China L NLP Assess gene expression in HCC Description of Gene library/
using combined data from The experiment published literature
Cancer Genome Atlas and NLP
identified genes
Kuwahara et al. [20] 2019 Japan P DL Investigate whether a deep Retrospective EUS images
learning algorithm using EUS study
images of IPMN could predict the
diagnosis of malignancy
Shen et al. [21] 2019 China P ML Establish and validate a radiomics Retrospective CT images
diagnosis model for the study
classification of three subtypes of
pancreatic lesion
Lei Xu et al. [22] 2019 China/ G ML/CV Develop and validate a prediction Retrospective MRI images
USA model for preoperative LN status study
evaluation in ICC patients
[23]
Brown et al. 2019 Canada L NLP/ML Explore natural language Retrospective Radiology reports
processing to predict downstream study
radiology resource utilization in
patients undergoing surveillance
for HCC
[24]
Watson et al. 2020 USA P DL Use CT-guided deep learning Retrospective CT images
techniques to predict malignancy pilot study
of PCNs
Liu et al. [25] 2020 China L NLP/DL Designed an NLP pipeline for the Retrospective Radiology reports
direct extraction of clinically study
relevant features of liver cancer
from radiology reports
[26]
Mao et al. 2021 China L ML Investigate the performance of an Retrospective US images
ultrasound-based radiomics study
approach to differentiate primary
liver cancer from metastatic liver
cancer
Jang et al. [27] 2021 South G DL/CV Evaluate the diagnostic Retrospective EUS images
Korea performance of AI in study
differentiating biliary lesions using
EUS images
[28]
Dongyan et al. 2021 China G DL/CV Assessed duodenoscopy assisted Pilot study ERCP/