Regression concept vectors for bidirectional explanations in histopathology

Graziani, Mara (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; University of Geneva (UNIGE), Geneva, Switzerland) ; Andrearczyk, Vincent (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; University of Geneva (UNIGE), Geneva, Switzerland)

Explanations for deep neural network predictions in terms of domain-related concepts can be valuable in medical applications, where justifications are important for confidence in the decision-making. In this work, we propose a methodology to exploit continuous concept measures as Regression Concept Vectors (RCVs) in the activation space of a layer. The directional derivative of the decision function along the RCVs rep- resents the network sensitivity to increasing values of a given concept measure. When applied to breast cancer grading, nuclei texture emerges as a relevant concept in the detection of tumor tissue in breast lymph node samples. We evaluate score robustness and consistency by statisti- cal analysis.


Conference Type:
full paper
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Economie/gestion
Publisher:
Granada, Spain, 16-20 September 2018
Date:
2018-09
Granada, Spain
16-20 September 2018
Pagination:
8 p.
Published in:
Proceedings of the 21st International Conference on MICCAI, 2018
Appears in Collection:



 Record created 2018-11-14, last modified 2019-06-11

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)