Literature DB >> 29898829

Machine learning "red dot": open-source, cloud, deep convolutional neural networks in chest radiograph binary normality classification.

E J Yates1, L C Yates2, H Harvey3.   

Abstract

AIM: To develop a machine learning-based model for the binary classification of chest radiography abnormalities, to serve as a retrospective tool in guiding clinician reporting prioritisation.
MATERIALS AND METHODS: The open-source machine learning library, Tensorflow, was used to retrain a final layer of the deep convolutional neural network, Inception, to perform binary normality classification on two, anonymised, public image datasets. Re-training was performed on 47,644 images using commodity hardware, with validation testing on 5,505 previously unseen radiographs. Confusion matrix analysis was performed to derive diagnostic utility metrics.
RESULTS: A final model accuracy of 94.6% (95% confidence interval [CI]: 94.3-94.7%) based on an unseen testing subset (n=5,505) was obtained, yielding a sensitivity of 94.6% (95% CI: 94.4-94.7%) and a specificity of 93.4% (95% CI: 87.2-96.9%) with a positive predictive value (PPV) of 99.8% (95% CI: 99.7-99.9%) and area under the curve (AUC) of 0.98 (95% CI: 0.97-0.99).
CONCLUSION: This study demonstrates the application of a machine learning-based approach to classify chest radiographs as normal or abnormal. Its application to real-world datasets may be warranted in optimising clinician workload.
Copyright © 2018 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

Mesh:

Year:  2018        PMID: 29898829     DOI: 10.1016/j.crad.2018.05.015

Source DB:  PubMed          Journal:  Clin Radiol        ISSN: 0009-9260            Impact factor:   2.350


  7 in total

1.  Automatic multi-class intertrochanteric femur fracture detection from CT images based on AO/OTA classification using faster R-CNN-BO method.

Authors:  Sun-Jung Yoon; Tae Hyong Kim; Su-Bin Joo; Seung Eel Oh
Journal:  J Appl Biomed       Date:  2020-09-22       Impact factor: 1.797

2.  COVID-19 open source data sets: a comprehensive survey.

Authors:  Junaid Shuja; Eisa Alanazi; Waleed Alasmary; Abdulaziz Alashaikh
Journal:  Appl Intell (Dordr)       Date:  2020-09-21       Impact factor: 5.086

3.  The Desire of Medical Students to Integrate Artificial Intelligence Into Medical Education: An Opinion Article.

Authors:  Timothy C Frommeyer; Reid M Fursmidt; Michael M Gilbert; Ean S Bett
Journal:  Front Digit Health       Date:  2022-05-13

Review 4.  Artificial intelligence in paediatric radiology: Future opportunities.

Authors:  Natasha Davendralingam; Neil J Sebire; Owen J Arthurs; Susan C Shelmerdine
Journal:  Br J Radiol       Date:  2020-09-17       Impact factor: 3.039

5.  Automated abnormality classification of chest radiographs using deep convolutional neural networks.

Authors:  Yu-Xing Tang; You-Bao Tang; Yifan Peng; Ke Yan; Mohammadhadi Bagheri; Bernadette A Redd; Catherine J Brandon; Zhiyong Lu; Mei Han; Jing Xiao; Ronald M Summers
Journal:  NPJ Digit Med       Date:  2020-05-14

6.  3D Analysis of Upper Limbs Motion during Rehabilitation Exercises Using the KinectTM Sensor: Development, Laboratory Validation and Clinical Application.

Authors:  Bruno Bonnechère; Victor Sholukha; Lubos Omelina; Serge Van Sint Jan; Bart Jansen
Journal:  Sensors (Basel)       Date:  2018-07-10       Impact factor: 3.576

7.  Artificial intelligence abstracts from the European Congress of Radiology: analysis of topics and compliance with the STARD for abstracts checklist.

Authors:  Thomas Dratsch; Liliana Caldeira; David Maintz; Daniel Pinto Dos Santos
Journal:  Insights Imaging       Date:  2020-04-25
  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.