An XAI Approach to Deep Learning Models in the Detection of DCIS
Michele La Ferla, Matthew Montebello, Dylan Seychell
TL;DR
This paper explores the use of explainable AI (XAI) techniques to improve understanding and trust in deep learning models for detecting DCIS, aiming to facilitate clinical adoption.
Contribution
It demonstrates the potential of XAI methods as a foundational step towards integrating AI assistive tools in clinical settings for DCIS detection.
Findings
XAI can serve as proof of concept for clinical AI implementation
XAI enhances interpretability of deep learning models in medical diagnosis
Supports discussions on AI integration in healthcare
Abstract
The results showed that XAI could indeed be used as a proof of concept to begin discussions on the implementation of assistive AI systems within the clinical community.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning in Healthcare
Methods*Communicated@Fast*How Do I Communicate to Expedia? · 1x1 Convolution · Average Pooling · Batch Normalization · Residual Connection · Max Pooling · Global Average Pooling · Bottleneck Residual Block · Residual Block · Kaiming Initialization