Dear guest, welcome to this publication database. As an anonymous user, you will probably not have edit rights. Also, the collapse status of the topic tree will not be persistent. If you like to have these and other options enabled, you might ask Admin (Ivan Eggel) for a login account.
 [BibTeX] [RIS]
Regression Concept Vectors for Bidirectional Explanations in Histopathology
Type of publication: Article
Citation:
Journal: Lecture Notes in Computer Science
Volume: Workshop on Interpretability of Machine Intelligence in Medical Image Computing at MICCAI 2018
Year: 2018
Pages: 8
Note: Source code: https://github.com/medgift/iMIMIC-RCVs
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 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.
Keywords: concept vectors, Deep convolutional neural network, Deep Learning, Histopathology, interpretability
Authors Graziani, Mara
Andrearczyk, Vincent
Müller, Henning
Added by: []
Total mark: 0
Attachments
  • rcv_cameraready.pdf
       (paper)
Notes
  • []: Best paper award
Topics