PuSH - Publikationsserver des Helmholtz Zentrums München

Sadafi, A. ; Adonkina, O. ; Khakzar, A.* ; Lienemann, P. ; Hehr, M. ; Rueckert, D.* ; Navab, N.* ; Marr, C.

Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images.

In: (Information Processing in Medical Imaging). Berlin [u.a.]: Springer, 2023. 170-182 (Lect. Notes Comput. Sc. ; 13939 LNCS)
DOI
Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making. Multiple instance learning with attention pooling provides instance-level explainability, however for many clinical applications a deeper, pixel-level explanation is desirable, but missing so far. In this work, we investigate the use of four attribution methods to explain a multiple instance learning models: GradCAM, Layer-Wise Relevance Propagation (LRP), Information Bottleneck Attribution (IBA), and InputIBA. With this collection of methods, we can derive pixel-level explanations on for the task of diagnosing blood cancer from patients’ blood smears. We study two datasets of acute myeloid leukemia with over 100 000 single cell images and observe how each attribution method performs on the multiple instance learning architecture focusing on different properties of the white blood single cells. Additionally, we compare attribution maps with the annotations of a medical expert to see how the model’s decision-making differs from the human standard. Our study addresses the challenge of implementing pixel-level explainability in multiple instance learning models and provides insights for clinicians to better understand and trust decisions from computer-aided diagnosis systems.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Schlagwörter Blood Cancer Cytology ; Multiple Instance Learning ; Pixel-level Explainability; Classification
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel Information Processing in Medical Imaging
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 13939 LNCS, Heft: , Seiten: 170-182 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Nichtpatentliteratur Publikationen
Institut(e) Institute of AI for Health (AIH)