Title: How can we explain medical image segmentation models?


Explainability is a crucial field of AI, and in medical image analysis in particular, to ensure building trust with the clinicians. In computer vision, most of the explainability works have historically focused on image classification, notably to produce saliency maps that highlight the pixels that most contributed to the decision. Why and how we can produce explainability methods for medical image segmentation are open questions. From the viewpoint of a practitioner, it can be argued that an explanation is less useful, because the prediction is in the image domain, directly understandable by humans through visual analysis. However, existing literature suggests that explainability methods for segmentation models offer other benefits, including providing insights into models, detecting dataset biases, creating counterfactual examples, estimating segmentation-related uncertainties, and identifying pixel contributions to specific regions in an image. Insights from explainable models can also help in transferring knowledge to other tasks and understanding model generalizability.

In this talk, we will present a review of the literature on explainability for image segmentation, spanning from the earliest works published in 2019, and make some proposals on how to generate specific heatmaps that can be useful to assess the reliability of the segmentation model.

Speaker Bio:

Caroline Petitjean is a Full Professor at the Université de Rouen Normandie, France, in data science and computer science. Her research interests include deep learning for medical image segmentation, with an emphasis on explainability, modeling prior knowledge for segmentation, and hybridizing deep models and variational models. She is currently serving as an Associate Editor for IEEE Transactions on Medical Imaging and Computer Vision and Image Understanding.


Date: Friday, May 17th 2024

Time: 09:00 PST | 17:00 West Africa Time | 16:00 UTC

Zoom Meeting Link: To be sent to only registered participants

Contact Information


View recordings of previous sessions on our YouTube channel https://www.youtube.com/@COMPASS-nn5or 






Leave a Reply

Your email address will not be published. Required fields are marked *