Cancerworld Magazine
  • About the Magazine
    • About us
    • Editorial Team
    • Events
    • Archive
    • Contacts
  • Articles
    • Policy
    • Practice Points
    • Delivery of Care
    • Biology basic
    • Medicine
    • Featured
  • Contents
    • News
    • Editorials
    • Interviews to the Expert
    • In the Hot Seat
    • Profiles
    • Obituaries
    • Voices
  • ESCO Corner
SUBSCRIBE FOR FREE
Facebook
Twitter
LinkedIn
Cancerworld Magazine
Cancerworld Magazine
  • About the Magazine
    • About us
    • Editorial Team
    • Events
    • Archive
    • Contacts
  • Articles
    • Policy
    • Practice Points
    • Delivery of Care
    • Biology basic
    • Medicine
    • Featured
  • Contents
    • News
    • Editorials
    • Interviews to the Expert
    • In the Hot Seat
    • Profiles
    • Obituaries
    • Voices
  • ESCO Corner
Cancerworld Magazine > News > Artificial intelligence might help improve the classification of colorectal polyps
  • News

Artificial intelligence might help improve the classification of colorectal polyps

  • 4 May 2020
  • Alessia De Chiara
Visualization of the classifications of the deep neural network model. The first column shows the original image, and the second column shows pathologist annotations of polyps. The third column depicts the model’s detected heat map, where higher confidence predictions are shown in darker color. In the fourth column, the model’s final output is shown, which highlights precancerous lesions that can potentially be used to aid pathologists in clinical practice. With permission of Saeed Hassanpour, PhD.
Artificial intelligence might help improve the classification of colorectal polyps
Total
0
Shares
0
0
0
0
0

Deep neural networks are as good as practicing pathologists in classifying colorectal polyps, according to an experiment by a computer science and clinical research team led by Saeed Hassanpour, from the Dartmouth Cancer Center in Lebanon (New Hampshire). The team trained one such model on data from a single-center, and then checked its abilities in distinguishing the four most common colorectal polyps in imaging coming from 24 institutions in 13 states in the US, observing that its performance was comparable to that of practicing pathologists.

Visualization of the classifications of the deep neural network model. The first column shows the original image, and the second column shows pathologist annotations of polyps. The third column depicts the model’s detected heat map, where higher confidence predictions are shown in darker color. In the fourth column, the model’s final output is shown, which highlights precancerous lesions that can potentially be used to aid pathologists in clinical practice.
With permission of Saeed Hassanpour, PhD.

«To our knowledge, this study is the first to evaluate a deep neural network for colorectal polyp classification on a large multi-institutional data set with comparison with local diagnoses made at the point of care» Saeed Hassanpour and colleagues write in a paper just published in JAMA Network Open. They suggests that if the performance of the model will be confirmed in clinical trials, it could improve efficiency, reproducibility, and accuracy of the colonoscopy, the most common test used for colorectal cancer screening programs. «Early detection of cancer at an early, curable stage and removal of preinvasive adenomas or serrated lesions during this procedure are associated with a reduced mortality rate» the authors explain.

Hassanpour and colleagues used slides from Dartmouth-Hitchcock Medical Center from patients with tubular adenoma, tubulovillous or villous adenoma, hyperplastic polyp, and sessile serrated adenoma to train the deep neural network for their classification. On an internal data set, the mean accuracy of the model observed was 93.5%, compared with that of local pathologists equal to 91.4%. When tested on the external data set from 24 institutions (238 slides for 179 patients), the authors found that «the model performed at a similar level of accuracy, sensitivity, and specificity as local pathologists», (i.e. accuracy was 87.0% and 86.6% respectively). Furthermore, deep neural network and local pathologists had comparable confusion matrixes, which indicate similar misclassifications.

For the authors, the model, implemented in laboratory information systems, could guide pathologists, and «although expert practitioner confirmation of diagnoses will still be required, the model could help triage slides indicating diagnoses that are more likely to be preinvasive for subsequent review by pathologists». Authors want to evaluate their model in a clinical trial and to collect more data to improve its performance.

 

 

Total
0
Shares
Share 0
Tweet 0
Share 0
Share 0
Share 0
Related Topics
  • Artificial intelligence
  • colonoscopy
  • colorectal
  • deep neural network
  • polyps
Alessia De Chiara

Previous Article
  • Articles
  • Featured

Cancer and COVID-19 took the stage at AACR Annual Meeting

  • 30 April 2020
  • Cristina Ferrario
View Post
Next Article
  • Articles
  • Delivery of Care

MDT meetings: why patient care suffers if I’m not there

  • 10 May 2020
  • Janet Fricker
View Post
You May Also Like
View Post
  • News

Personalised neoantigen vaccine for kidney cancer shows promise in phase 1 study

  • Yeva Margaryan
  • 8 May 2025
View Post
  • News
  • Senza categoria

What Caught Our Eye in April: Oncology’s Top Moments

  • Yeva Margaryan
  • 7 May 2025
View Post
  • News

CancerWorld #102 (April 2025)

  • Yeva Margaryan
  • 22 April 2025
View Post
  • News
  • Senza categoria

What Caught Our Eye in March: Oncology’s Top Moments

  • Yeva Margaryan
  • 8 April 2025
View Post
  • News

Ovarian cancer: mechanism conferring resistance to immunotherapy revealed

  • Janet Fricker
  • 21 March 2025
View Post
  • News

Muscular strength and cardiorespiratory fitness improve survival in cancer patients

  • Janet Fricker
  • 20 March 2025
View Post
  • News

CancerWorld #101 (February 2025): The Must-Read Oncology Issue Returns to Print with Exclusive Interviews and Breakthroughs

  • Yeva Margaryan
  • 18 March 2025
View Post
  • News

Low-dose aspirin reduces colorectal cancer recurrence in patients with PI3K alterations

  • Janet Fricker
  • 6 March 2025
search
CancerWorld #101 Download CancerWorld #101 Download CancerWorld #101 Download or search in Cancerworld archive
Newsletter

Subscribe free to
Cancerworld!

We'll keep you informed of the latest features and news with a fortnightly email

Subscribe now
Latest News
  • Personalised neoantigen vaccine for kidney cancer shows promise in phase 1 study
    • 8 May 2025
  • What Caught Our Eye in April: Oncology’s Top Moments
    • 7 May 2025
  • CancerWorld #102 (April 2025)
    • 22 April 2025
  • What Caught Our Eye in March: Oncology’s Top Moments
    • 8 April 2025
  • Ovarian cancer: mechanism conferring resistance to immunotherapy revealed
    • 21 March 2025
Article
  • Miriam Merad and the 2025 Sjöberg Prize: A Celebration of Innovation in Cancer Immunotherapy
    • 6 May 2025
  • Istanbul, Ankara take action on HPV vaccination, as government delays promised national programme
    • 1 April 2025
  • Could this dual approach be the frontier that finally gets immunotherapy to work for MSS colorectal cancer?
    • 31 March 2025
Social

Would you follow us ?

Contents
  • Miriam Merad and the 2025 Sjöberg Prize: A Celebration of Innovation in Cancer Immunotherapy
    • 6 May 2025
  • “I really care about people.” – Philip Kantoff, A Life in Science and Medicine
    • 5 May 2025
  • What If the World’s Leading Prostate Cancer Epidemiologist Opened a Restaurant? A Conversation with Lorelei Mucci- A Harvard Scientist, A Mother, A Leader
    • 23 April 2025
MENU
  • About the Magazine
    • About us
    • Editorial Team
    • Events
    • Archive
    • Contacts
  • Articles
    • Policy
    • Practice Points
    • Delivery of Care
    • Biology basic
    • Medicine
    • Featured
  • Contents
    • News
    • Editorials
    • Interviews to the Expert
    • In the Hot Seat
    • Profiles
    • Obituaries
    • Voices
  • ESCO Corner
Cancerworld Magazine
  • About us
  • Articles
  • Media Corner
  • Privacy Policy
  • Cookie Policy

Cancerworld is published by OncoDaily (P53 Inc.) | Mailing Address: 867 Boylston st, 5th floor, Ste 1094 Boston, MA 02116, United States | [email protected]

Archivio Cancerworld

Input your search keywords and press Enter.