Search: onr:"swepub:oai:DiVA.org:uu-457241" >
Quantifying Explain...
Quantifying Explainers of Graph Neural Networks in Computational Pathology
-
Jaume, Guillaume (author)
-
Pati, Pushpak (author)
-
Bozorgtabar, Behzad (author)
-
show more...
-
Foncubierta, Antonio (author)
-
Anniciello, Anna Maria (author)
-
Feroce, Florinda (author)
-
Rau, Tilman (author)
-
Thiran, Jean-Philippe (author)
-
Gabrani, Maria (author)
-
- Göksel, Orcun (author)
- Uppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion,ETH Zurich,Computer-assisted Applications in Medicine
-
show less...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2021
- 2021
- English.
-
In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781665445092 - 9781665445108 ; , s. 8102-8112
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Explainability of deep learning methods is imperative to facilitate their clinical adoption in digital pathology. However, popular deep learning methods and explainability techniques (explainers) based on pixel-wise processing disregard biological entities' notion, thus complicating comprehension by pathologists. In this work, we address this by adopting biological entity-based graph processing and graph explainers enabling explanations accessible to pathologists. In this context, a major challenge becomes to discern meaningful explainers, particularly in a standardized and quantifiable fashion. To this end, we propose herein a set of novel quantitative metrics based on statistics of class separability using pathologically measurable concepts to characterize graph explainers. We employ the proposed metrics to evaluate three types of graph explainers, namely the layer-wise relevance propagation, gradient-based saliency, and graph pruning approaches, to explain Cell-Graph representations for Breast Cancer Subtyping. The proposed metrics are also applicable in other domains by using domain-specific intuitive concepts. We validate the qualitative and quantitative findings on the BRACS dataset, a large cohort of breast cancer RoIs, by expert pathologists.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Cancer och onkologi (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Cancer and Oncology (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Systemvetenskap, informationssystem och informatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Information Systems (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database
- By the author/editor
-
Jaume, Guillaume
-
Pati, Pushpak
-
Bozorgtabar, Beh ...
-
Foncubierta, Ant ...
-
Anniciello, Anna ...
-
Feroce, Florinda
-
show more...
-
Rau, Tilman
-
Thiran, Jean-Phi ...
-
Gabrani, Maria
-
Göksel, Orcun
-
show less...
- About the subject
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
and Computer Vision ...
-
- MEDICAL AND HEALTH SCIENCES
-
MEDICAL AND HEAL ...
-
and Clinical Medicin ...
-
and Cancer and Oncol ...
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
and Information Syst ...
- Articles in the publication
-
2021 IEEE/CVF Co ...
- By the university
-
Uppsala University