Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Can machines be trusted? Robustification of deep learning for medical imaging

Award Number: R01LM013151
ORGANIZATION: NATIONAL LIBRARY OF MEDICINE
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 07/02/2020
PERIOD OF PERFORMANCE END DATE: 03/31/2024

Group Awards By:

View Award Description

Can machines be trusted? Robustification of deep learning for medical imaging - Machine learning algorithms have become increasing popular in medical imaging, where highly functional algorithms have been trained to recognize patterns or features within image data sets and perform clinically relevant tasks such as tumor segmentation and disease diagnosis. In recent years, an approach known as deep learning has revolutionized the field of machine learning, by leveraging massive datasets and immense computing power to extract features from data. Deep learning is ideally suited for problems in medical imaging, and has enjoyed success in diverse tasks such as segmenting cardiac structures, tumors, and tissues. However, research in machine learning has also shown that deep learning is fragile in the sense that carefully designed perturbations to an image can cause the algorithm to fail. These perturbations can be designed to be imperceptible by humans, so that a trained radiologist would not make the same mistakes. As deep learning approaches gain acceptance and move toward clinical implementation, it is therefore crucial to develop a better understanding of the performance of neural networks. Specifically, it is critical to understand the limits of deep learning when presented with noisy or imperfect data. The goal of this project is to explore these questions in the context of medical imaging—to better identify strengths, weaknesses, and failure points of deep learning algorithms. We posit that malicious perturbations, of the type studied in theoretical machine learning, may not be representative of the sort of noise encountered in medical images. Although noise is inevitable in a physical system, the noise arising from sources such as subject motion, operator error, or instrument malfunction may have less deleterious effects on a deep learning algorithm. We propose to characterize the effect of these perturbations on the performance of deep learning algorithms. Furthermore, we will study the effect of random labeling error introduced into the data set, as might arise due to honest human error. We will also develop new methods for making deep learning algorithms more robust to the types of clinically relevant perturbations described above. In summary, although the susceptibility of neural networks to small errors in the inputs is widely recognized in the deep learning community, our work will investigate these general phenomena in the specific case of medical imaging tasks, and also conduct the first study of average-case errors that could realistically arise in clinical studies. Furthermore, we will produce novel recommendations for how to quantify and improve the resiliency of deep learning approaches in medical imaging.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2024 ( Subtotal = -$26,238 )
2024	2023	UNIVERSITY OF WISCONSIN SYSTEM	21 N PARK ST STE 6301	MADISON	WI	53715	DANE	USA	Medical Library Assistance	000	4	8/15/2024	NON-COMPETING CONTINUATION	-$26,238
														Subtotal = -$26,238

Issue Date FY: 2023 ( Subtotal = $319,116 )
2023	2023	UNIVERSITY OF WISCONSIN SYSTEM	21 N PARK ST STE 6301	MADISON	WI	53715	DANE	USA	Medical Library Assistance	000	4	3/6/2023	NON-COMPETING CONTINUATION	$319,116
														Subtotal = $319,116

Issue Date FY: 2022 ( Subtotal = $319,116 )
2022	2022	UNIVERSITY OF WISCONSIN SYSTEM	21 N PARK ST STE 6301	MADISON	WI	53715	DANE	USA	Medical Library Assistance	000	3	6/7/2022	NON-COMPETING CONTINUATION	$319,116
														Subtotal = $319,116

Issue Date FY: 2021 ( Subtotal = $318,876 )
2021	2021	UNIVERSITY OF WISCONSIN SYSTEM	21 N PARK ST STE 6401	MADISON	WI	53715	DANE	USA	Medical Library Assistance	002	2	5/14/2021	NON-COMPETING CONTINUATION	$15,945
2021	2021	UNIVERSITY OF WISCONSIN SYSTEM	21 N PARK ST STE 6401	MADISON	WI	53715	DANE	USA	Medical Library Assistance	001	2	3/12/2021	NON-COMPETING CONTINUATION	$302,931
2021	2020	UNIVERSITY OF WISCONSIN SYSTEM	21 N PARK ST STE 6401	MADISON	WI	53715	DANE	USA	Medical Library Assistance	000	1	2/3/2021	NEW	$0
														Subtotal = $318,876

Issue Date FY: 2020 ( Subtotal = $318,155 )
2020	2020	UNIVERSITY OF WISCONSIN SYSTEM	21 N PARK ST STE 6401	MADISON	WI	53715	DANE	USA	Medical Library Assistance	000	1	7/2/2020	NEW	$318,155
														Subtotal = $318,155

Grand Total All Awards = $1,249,025

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Can machines be trusted? Robustification of deep learning for medical imaging

Award Number: R01LM013151

ORGANIZATION: NATIONAL LIBRARY OF MEDICINE

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)

PERIOD OF PERFORMANCE START DATE: 07/02/2020

PERIOD OF PERFORMANCE END DATE: 03/31/2024

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer