papers AI Learner
The Github is limit! Click to go to the new site.

Regression Concept Vectors for Bidirectional Explanations in Histopathology

2019-04-09
Mara Graziani, Vincent Andrearczyk, Henning Müller

Abstract

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 represents 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 statistical analysis.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.04520

PDF

http://arxiv.org/pdf/1904.04520


Similar Posts

Comments