• About
  • Masthead
  • License Content
  • Advertise
  • Submit Press Release
  • RSS/Email List
  • Write for us
  • Contact us
2 Minute Medicine
No Result
View All Result

No products in the cart.

SUBSCRIBE
  • Specialties
    • Cardiology
    • Chronic Disease
    • Dermatology
    • Emergency
    • Endocrinology
    • Gastroenterology
    • Imaging and Intervention
    • Infectious Disease
    • Nephrology
    • Neurology
    • Obstetrics
    • Oncology
    • Ophthalmology
    • Pediatrics
    • Preclinical
    • Psychiatry
    • Public Health
    • Pulmonology
    • Rheumatology
    • Surgery
  • The Scan
  • Wellness
  • Classics™
    • 2MM+ Online Access
    • Paperback and Ebook
  • Rewinds
  • Visual
  • Partners
    • License Content
    • Submit Press Release
    • Advertise with Us
  • AccountLog-in/out
    • Subscribe
    • Sign-in
    • My account
2 Minute Medicine
  • Specialties
    • Cardiology
    • Chronic Disease
    • Dermatology
    • Emergency
    • Endocrinology
    • Gastroenterology
    • Imaging and Intervention
    • Infectious Disease
    • Nephrology
    • Neurology
    • Obstetrics
    • Oncology
    • Ophthalmology
    • Pediatrics
    • Preclinical
    • Psychiatry
    • Public Health
    • Pulmonology
    • Rheumatology
    • Surgery
  • The Scan
  • Wellness
  • Classics™
    • 2MM+ Online Access
    • Paperback and Ebook
  • Rewinds
  • Visual
  • Partners
    • License Content
    • Submit Press Release
    • Advertise with Us
  • AccountLog-in/out
    • Subscribe
    • Sign-in
    • My account
SUBSCRIBE
2 Minute Medicine
Subscribe
Home All Specialties Chronic Disease

Quick Take: Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists

byConstance WuandAliya Ramjaun
December 2, 2018
in Chronic Disease, Emergency, Imaging and Intervention, Pulmonology
Reading Time: 2 mins read
0
Share on FacebookShare on Twitter

RELATED REPORTS

Chest radiograph neural network predicts lung cancer in smokers

Artificial-intelligence, deep-learning algorithm identifies papilledema from fundus photographs

2 Minute Medicine Rewind December 18, 2017

Deep learning approaches have been proposed as a way to facilitate the interpretation of chest radiographs in low resource settings. In this study, investigators developed a convolutional neural network called CheXNeXt and compared its performance on detecting the presence of 14 different pathologies to the performance of 9 radiologists. CheXNeXt was trained and internally validated on a validation set consisting of 420 images of 14 different pathologies such as pneumonia, pleural effusion, pulmonary masses, and nodules. Radiologists included for comparison included 6 board-certified radiologists (average experience 12 years, range 4 to 28 years) and 3 seniors radiology residents from 3 academic institutions. Investigators found that the algorithm had a mean proportion correct for all pathologies of 0.828 (SD 0.12) compared with 0.675 (SD 0.15) for board-certified radiologists and 0.654 (SD 0.16) for residents.  The algorithm had an area under the curve (AUC) of 0.862 (95% CI 0.825 to 0.895) for atelectasis, which was significantly higher than the radiologists’ AUC of 0.808 (95% CI 0.777 to 0.838). Radiologists had statistically significantly higher AUCs for cardiomegaly (AUC 0.888, 95% CI 0.863 to 0.910), emphysema (AUC 0.911, 95% CI 0.866 to 0.947), and hiatal hernia (AUC 0.985, 95% CI 0.974 to 0.991) in comparison to the algorithm (AUC of 0.831 for cardiomegaly, 95% CI 0.790 to 8.70; AUC of 0.704 for emphysema, 95% CI 0.567 to 0.833; AUC of 0.851 for hiatal hernia, 95% CI 0.785 to 0.909). There were no statistically significant differences in AUCs between radiologists and CheXNeXt for the other 10 pathologies. The average time to interpret the 420 images in the validation set was 240 minutes for the radiologists in comparison to 1.5 minutes for CheXNeXt. Taken together, the results from this study indicate that deep learning approaches may be useful for identifying pathologies in chest radiographs in places where radiologists are not readily available.

Click to read the study in PLOS Medicine

Image: PD

©2018 2 Minute Medicine, Inc. All rights reserved. No works may be reproduced without expressed written consent from 2 Minute Medicine, Inc. Inquire about licensing here. No article should be construed as medical advice and is not intended as such by the authors or by 2 Minute Medicine, Inc.

Tags: deep learning
Previous Post

Quick Take: Effect of Pregabalin on Radiotherapy-Related Neuropathic Pain in Patients With Head and Neck Cancer: A Randomized Controlled Trial

Next Post

Quick Take: Association of Prenatal Exposure to Air Pollution with Autism Spectrum Disorder

RelatedReports

Severity of emphysema on pulmonary CT may predict lung cancer location
Imaging and Intervention

Chest radiograph neural network predicts lung cancer in smokers

September 1, 2020
Artificial-intelligence, deep-learning algorithm identifies papilledema from fundus photographs
Emergency

Artificial-intelligence, deep-learning algorithm identifies papilledema from fundus photographs

May 9, 2020
Home scoring system may prevent unnecessary pharyngitis clinic visits
Weekly Rewinds

2 Minute Medicine Rewind December 18, 2017

December 19, 2017
Next Post
Quick Take: Association of Prenatal Exposure to Air Pollution with Autism Spectrum Disorder

Quick Take: Association of Prenatal Exposure to Air Pollution with Autism Spectrum Disorder

Non-invasive prenatal testing linked to decreased diagnostic testing

Interpreting genetic variants in kidney and genitourinary disorders will likely require systematic curation of clinical variant databases

Intensive rehabilitation not superior to traditional therapy for arm function after stroke

2 Minute Medicine Rewind December 4, 2018

License Our Award-Winning Physician-Written Medical News and Visual Abstracts

2 Minute Medicine is the leading authoritative medical news licensing service, and the only with reports written by practicing doctors.

LICENSE CONTENT

2MM+ Premium Access

No ads & unlimited access to all current reports, over 9000 searchable archived reports, visual abstracts, Weekly Rewinds, and the online edition of The Classics Series™ textbook.

Subscription Options
2 Minute Medicine

2 Minute Medicine® is an award winning, physician-run, expert medical media company. Our content is curated, written and edited by practicing health professionals who have clinical and scientific expertise in their field of reporting. Our editorial management team is comprised of highly-trained MD physicians. Join numerous brands, companies, and hospitals who trust our licensed content.

Recent Reports

  • Catheter ablation reduces rates of persistent atrial fibrillation and atrial tachyarrhythmia
  • Deep intronic FGF14 repeat expansion associated with late-onset cerebella ataxia
  • Plant-based diets may be associated with lower risk of aggressive prostate cancer
License Content
Terms of Use | Disclaimer
Cookie Policy
Privacy Statement (EU)
Disclaimer

© 2021 2 Minute Medicine, Inc. - Physician-written medical news.

  • Specialties
    • Cardiology
    • Chronic Disease
    • Dermatology
    • Emergency
    • Endocrinology
    • Gastroenterology
    • Imaging and Intervention
    • Infectious Disease
    • Nephrology
    • Neurology
    • Obstetrics
    • Oncology
    • Ophthalmology
    • Pediatrics
    • Preclinical
    • Psychiatry
    • Public Health
    • Pulmonology
    • Rheumatology
    • Surgery
  • The Scan
  • Wellness
  • Classics™
    • 2MM+ Online Access
    • Paperback and Ebook
  • Rewinds
  • Visual
  • Partners
    • License Content
    • Submit Press Release
    • Advertise with Us
  • Account
    • Subscribe
    • Sign-in
    • My account

© 2021 2 Minute Medicine, Inc. - Physician-written medical news.

Want more physician-written
medical news?

Join over 10 million yearly readers and numerous companies. For healthcare professionals
and the public.

Subscribe for free today!

Subscription options