One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images

One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images

One Map Does Not Fit All: Evaluating Multi-Modal Medical Image Explanation 1. Propose the problem of multi-modal medical image explanation. 2. Propose the evaluation metric MSFI and conducted experiments to evaluate saliency maps regarding their abilities to fulfill clinical requirements for multi-modal medical image explanation. Talk on ICML 2021 workshop Interpretable Machine Learning in Healthcare Paper: https://arxiv.org/abs/2107.05047 Project website (paper, poster, slides): http://weina.me/one-map-not-fit-all

One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images
One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images
ACR AI-LAB: Saliency Maps
DBCE : A Saliency Method for Medical Deep Learning Through Anatomically-Consistent Free-Form Deform
miccai2020_presentation
Analysis of patient triage with saliency maps using deep learning
Transparency
Medical Imaging Tutorial 2020 - Ch4 - Incorrect Feature Attribution
Class Saliency Maps | Lecture 20 (Part 2) | Applied Deep Learning (Supplementary)
Explainable machine learning #3: Saliency Maps
Saliency Inference
Graphical Perception of Saliency-based Model Explanations
video3: ChainerRL Visualizer demo3: Saliency map
ROS visual saliency map with VOCUS2
End-To-End Saliency Mapping via Probability Distribution Prediction
ITBIO05 - Supervised Saliency Map Driven Segmentation of Lesions in Dermoscopic Images
DS-GA 1011 (Fall 2021) - Lecture 12 Multimodal learning by Aishwarya Kamath
Explainable Machine Learning, Saliency maps, GRAD-CAM implementation in keras and tensorflow
MIDL 2020, S256, Kuzina et al. Short presentation
Saliency-based Lesion Segmentation via Background Detection in Dermoscopic Images