A Framework for Interpretability in Machine Learning for Medical Imaging
IEEE Access · 2024 · 12 · 53277-53292
DOI: 10.1109/access.2024.3387702 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Alan Q Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Computer Engineering, Cornell University-Cornell Tech, New York City, NY 10044, USA. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 160 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIA NIH HHS, NLM NIH HHS, NIGMS NIH HHS.
Abstract (Originalsprache)
Interpretability for machine learning models in medical imaging (MLMI) is an important direction of research. However, there is a general sense of murkiness in what interpretability means. Why does the need for interpretability in MLMI arise? What goals does one actually seek to address when interpretability is needed? To answer these questions, we identify a need to formalize the goals and elements of interpretability in MLMI. By reasoning about real-world tasks and goals common in both medical image analysis and its intersection with machine learning, we identify five core elements of interpretability: localization, visual recognizability, physical attribution, model transparency, and actionability. From this, we arrive at a framework for interpretability in MLMI, which serves as a step-by-step guide to approaching interpretability in this context. Overall, this paper formalizes interpretability needs in the context of medical imaging, and our applied perspective clarifies concrete MLMI-specific goals and considerations in order to guide method design and improve real-world usage. Our goal is to provide practical and didactic information for model designers and practitioners, inspire developers of models in the medical imaging field to reason more deeply about what interpretability is achieving, and suggest future directions of interpretability research.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical and Computer Engineering, Cornell University-Cornell Tech, New York City, NY 10044, USA.
- Department of Radiology, Weill Cornell Medical School, New York City, NY 10065, USA.
- Weill Cornell/Rockefeller/Sloan Kettering Tri-Institutional M.D.-Ph.D. Program, New York City, NY 10065, USA.
- Martinos Center for Biomedical Imaging, Harvard Medical School, Boston, MA 02129, USA.
- Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, MA 02139, USA.
ORCID-Profile: Alan Q Wang, Batuhan K Karaman, Heejong Kim, Jacob Rosenthal, Sean I Young
Förderung
- NIA NIH HHS
- NLM NIH HHS
- NIGMS NIH HHS
- NIH
- NSF CAREER
Zitieren
APA
Wang, A. Q., Karaman, B. K., Kim, H., Rosenthal, J., Saluja, R., Young, S. I., & Sabuncu, M. R. (2024). A Framework for Interpretability in Machine Learning for Medical Imaging. IEEE Access, 12, 53277-53292. https://doi.org/10.1109/access.2024.3387702
Vancouver
Wang AQ, Karaman BK, Kim H, Rosenthal J, Saluja R, Young SI, et al. A Framework for Interpretability in Machine Learning for Medical Imaging. IEEE Access. 2024;12:53277-53292. doi:10.1109/access.2024.3387702
BibTeX
@article{Wang2024,
author = {Wang, Alan Q and Karaman, Batuhan K and Kim, Heejong and Rosenthal, Jacob and Saluja, Rachit and Young, Sean I and Sabuncu, Mert R},
title = {A Framework for Interpretability in Machine Learning for Medical Imaging},
journal = {IEEE Access},
year = {2024},
volume = {12},
pages = {53277--53292},
doi = {10.1109/access.2024.3387702}
}
EUVIMED