Envisioning MedCLIP: A Deep Dive into Explainability for Medical Vision-Language Models
This work provides insights into explainability for safety-critical medical imaging models, though it is incremental in nature.
The authors analyzed the performance of explainable AI methods on the medical vision-language model MedCLIP to address the gap between model development and safe deployment, proposing a simple methodology to overcome existing shortcomings.
Explaining Deep Learning models is becoming increasingly important in the face of daily emerging multimodal models, particularly in safety-critical domains like medical imaging. However, the lack of detailed investigations into the performance of explainability methods on these models is widening the gap between their development and safe deployment. In this work, we analyze the performance of various explainable AI methods on a vision-language model, MedCLIP, to demystify its inner workings. We also provide a simple methodology to overcome the shortcomings of these methods. Our work offers a different new perspective on the explainability of a recent well-known VLM in the medical domain and our assessment method is generalizable to other current and possible future VLMs.