Regression Concept Vectors for Bidirectional Explanations in Histopathology
| Art der Publikation: | Artikel |
| Zitat: | |
| Zeitschrift: | Lecture Notes in Computer Science |
| Band: | Workshop on Interpretability of Machine Intelligence in Medical Image Computing at MICCAI 2018 |
| Jahr: | 2018 |
| Seiten: | 8 |
| Notiz: | Source code: https://github.com/medgift/iMIMIC-RCVs |
| Abriss: | 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. |
| Schlagworte: | concept vectors, Deep convolutional neural network, Deep Learning, Histopathology, interpretability |
| Autoren | |
| Hinzugefügt von: | [] |
| Gesamtbewertung: | 0 |
|
Anhänge
|
|
|
|
|
Notizen
|
|
|
|
|
Themen
|
|
|
|
|
