Version 1
: Received: 9 September 2024 / Approved: 9 September 2024 / Online: 10 September 2024 (07:35:50 CEST)
How to cite:
De Santi, L. A.; Piparo, F. I.; Bargagna, F.; Santarelli, M. F.; Celi, S.; Positano, V. Part-Prototypes Models in Medical Imaging: Applications and Current Challenges. Preprints2024, 2024090771. https://doi.org/10.20944/preprints202409.0771.v1
De Santi, L. A.; Piparo, F. I.; Bargagna, F.; Santarelli, M. F.; Celi, S.; Positano, V. Part-Prototypes Models in Medical Imaging: Applications and Current Challenges. Preprints 2024, 2024090771. https://doi.org/10.20944/preprints202409.0771.v1
De Santi, L. A.; Piparo, F. I.; Bargagna, F.; Santarelli, M. F.; Celi, S.; Positano, V. Part-Prototypes Models in Medical Imaging: Applications and Current Challenges. Preprints2024, 2024090771. https://doi.org/10.20944/preprints202409.0771.v1
APA Style
De Santi, L. A., Piparo, F. I., Bargagna, F., Santarelli, M. F., Celi, S., & Positano, V. (2024). Part-Prototypes Models in Medical Imaging: Applications and Current Challenges. Preprints. https://doi.org/10.20944/preprints202409.0771.v1
Chicago/Turabian Style
De Santi, L. A., Simona Celi and Vincenzo Positano. 2024 "Part-Prototypes Models in Medical Imaging: Applications and Current Challenges" Preprints. https://doi.org/10.20944/preprints202409.0771.v1
Abstract
The last wave of Artificial Intelligence is dedicating particular emphasis to the line of
explainability research. The potential of Explainable Artificial Intelligence (XAI) in producing
trustworthy computer-aided-diagnosis systems and its usage for knowledge discovery are collecting
interest in the Medical Imaging (MI) community to support the diagnostic process and the discovery
of image biomarkers. Most of the existing XAI applications in MI were focused on interpreting
the predictions returned by deep neural networks, typically including attribution techniques with
saliency map approaches and other feature visualization methods. However, these are often criticized
for providing incorrect and incomplete representations of the black-box models’ behaviour. This
raises the attention in proposing models intentionally designed to be self-explanatory. In particular,
part-prototype (PP) models are interpretable-by-design computer vision (CV) models that base their
decision process in learning and identifying representative prototypical parts from the input images,
and they are collecting increasing interest and results in MI applications. This narrative review
provides a summary of existing PP networks, their application in MI analysis and current challenges.
Keywords
Deep Learning; XAI; Interpretability-by-Design; Part-prototypes Models; Medical Imaging
Subject
Engineering, Bioengineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.