Deep learning detection of active pulmonary tuberculosis at chest radiography matched the clinical performance of radiologists

S Kazemzadeh, J Yu, S Jamshy, R Pilgrim, Z Nabulsi… - Radiology, 2023 - pubs.rsna.org
… (DLS) to interpret chest radiographs for imaging features of … We designed our study to
model real-world deployment … First, this study was retrospective; prospective validation studies …

A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database

AMR Schilham, B Van Ginneken, M Loog - Medical Image Analysis, 2006 - Elsevier
… A segmentation scheme is deployed that uses the detected blob as a starting point to …
Such a validation requires a carefully executed observer study with several radiologists and …

[HTML][HTML] Key technology considerations in developing and deploying machine learning models in clinical radiology practice

V Kulkarni, M Gawali, A Kharat - JMIR Medical Informatics, 2021 - medinform.jmir.org
… The development, deployment, and eventual adoption of … and bias, and clinical validation.
We describe each consideration and … model to detect pneumonia in chest radiographs: a cross-…

Assessment of radiology artificial intelligence software: a validation and evaluation framework

W Tanguay, P Acar, B Fine, M Abdolell… - Canadian …, 2023 - journals.sagepub.com
… To help guide this growth in AI development and deployment… that have undergone external
validation has shown that only … domain (eg mammography and chest radiograph) and task (…

DeepCOVID-XR: an artificial intelligence algorithm to detect COVID-19 on chest radiographs trained and tested on a large US clinical data set

RM Wehbe, J Sheng, S Dutta, S Chai, A Dravid… - Radiology, 2021 - pubs.rsna.org
… As approximately 5% (44 patients contributing 151 images) of patients in the hold-out test
set also underwent chest radiography at one of the institutions in our training or validation sets …

Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study

JR Zech, MA Badgeley, M Liu, AB Costa… - PLoS …, 2018 - journals.plos.org
… sites using split-sample validation. A total of 158,323 chest radiographs were drawn from three
… give pause to those considering rapid deployment of such systems without first assessing …

Towards large-scale case-finding: training and validation of residual networks for detection of chronic obstructive pulmonary disease using low-dose CT

LYW Tang, HO Coxson, S Lam, J Leipsic… - The Lancet Digital …, 2020 - thelancet.com
validated on a large dataset collected from a separate study. Our results from over 30
independently conducted cross-validation … Because we trained each model and deployed each as …

Human–machine partnership with artificial intelligence for chest radiograph diagnosis

BN Patel, L Rosenberg, G Willcox, D Baltaxe… - NPJ digital …, 2019 - nature.com
… of pneumonia on chest radiographs and compared against … deployment and implementation
strategies in future practice. … of chest radiographs with radiologist level validation and test …

Radiologist-trained AI model for identifying suboptimal chest-radiographs

G Dasegowda, BC Bizzo, RV Gupta, P Kaviani… - Academic …, 2023 - Elsevier
… cross validation with repeated five-fold cross validation … (A, B, C) and validation datasets
from the remaining two sites (… use of differences in the deployed neural networks, training and …

[HTML][HTML] … the diagnostic test accuracy of certified AI products for screening pulmonary tuberculosis in digital chest radiographs: preliminary evidence from a rapid …

D Hua, K Nguyen, NP Conceptualisation… - International Journal of …, 2023 - Elsevier
… and pursue safe, wide-scale deployment. The goal of this research … is because the lack of
validation for negative results can … products are being evaluated in a deployment rather than in-…