Lecture image placeholder

Premium content

Access to this content requires a subscription. You must be a premium user to view this content.

Need help?
Contact us
Lecture placeholder background
VIDEO DOI: https://doi.org/10.48448/9rvw-3816

technical paper

AMA Research Challenge 2022

October 21, 2022

Virtual, United States

AI-Powered Fully automated Early Detection of Pancreatic Ductal Adenocarcinoma on Standard-of-care CT Scans.

Speakers

Garima
Garima Suman

Resident or Fellow @ Mayo Clinic

Please log in to leave a comment

Venkata Suresh Patthipati

over 2 years ago

This is an excellent study. Good sample size. Well Presented research. Significant advancement to a science of machine learning in medicine. Hopefully, more predictive models including risk factors will prove to be useful especially with the prognostication purpose

0
Garima Suman

Alexandra Kunz

over 2 years ago

Impressively important work!!

0
Garima Suman

Falgun Gosai

over 2 years ago

This could present a breakthrough for the screening of Pancreatic duct adenocarcinoma!

0
Garima Suman

Preston Seaberg

over 2 years ago

The potential of the model to predict subsequent development of pancreatic cancer is exciting. Thank you for showing the rates of error of the model in the other two cohorts. The misclassification combines both false positives and false negatives. Which error did the model tend to produce: false positives, false negatives, or an equal distribution of the two?

1
Garima Suman
Vaani Shah

Vaani Shah

over 2 years ago

Medical student

Great presentation- it is awesome that your model showed such high accuracy for diagnosing such a rapid and aggressive form of cancer! What platform or software was used for the CNN?

0
Garima Suman