Open-source tool for model performance analysis for subpopulations

Stijn Vandewiele; Jonas De Vylder; Bart Diricx; Edward Sandra; Tom Kimpe

doi:10.1117/12.2653453

7 April 2023 Open-source tool for model performance analysis for subpopulations

Stijn Vandewiele, Jonas De Vylder, Bart Diricx, Edward Sandra, Tom Kimpe

Proceedings Volume 12465, Medical Imaging 2023: Computer-Aided Diagnosis; 1246521 (2023) https://doi.org/10.1117/12.2653453
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

When a CAD-AI network is created and employed, both safety and effectiveness need to be guaranteed for all subgroups of the target population. We present a novel toolbox for automatic slicing and performance assessment in a generic and modular approach, helping to find the subpopulations where cautiousness is warranted, and the model may need improvement. In a first step slices are generated and saved for further analysis inspired by the existing ‘Slice Finder’ algorithm. Depending on the type of AI task (classification, object detection, segmentation, instance segmentation...) multiple metrics are evaluated. Both labeled (specificity, sensitivity...), unlabeled (outlier score, confidence score...) and user-defined metrics can be included. Optionally, the confidence interval (CI) is calculated. In a last step, the metric values and CI are used to rank the slices to quickly find the slices of interest. Custom ranking methods can be added, keeping the full process from slice generation up to and including visualization modular and customizable. We illustrate the toolbox with a dermatology classification and object detection use-case. First a single model is evaluated down to crosses of three slices where slices of interest are detected on degree three which would be difficult to find if not automated. Additionally, the usage of unlabeled metrics such as outlier score is illustrated to automatically find slices of interest.

Citation Download Citation

Stijn Vandewiele, Jonas De Vylder, Bart Diricx, Edward Sandra, and Tom Kimpe "Open-source tool for model performance analysis for subpopulations", Proc. SPIE 12465, Medical Imaging 2023: Computer-Aided Diagnosis, 1246521 (7 April 2023); https://doi.org/10.1117/12.2653453

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available