TY  - JOUR
T1  - Regression Concept Vectors for Bidirectional Explanations in Histopathology
A1  - Graziani, Mara
A1  - Andrearczyk, Vincent
A1  - Müller, Henning
JA  - Lecture Notes in Computer Science
Y1  - 2018
VL  - Workshop on Interpretability of Machine Intelligence in Medical Image Computing at MICCAI 2018
SP  - 8
N1  - Source code: https://github.com/medgift/iMIMIC-RCVs
KW  - concept vectors
KW  - Deep convolutional neural network
KW  - Deep Learning
KW  - Histopathology
KW  - interpretability
N2  - 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.
ER  -