At my consulting company Big Vision, we recently started working on a new medical diagnostic problem that utilizes X-ray photographs.
The spectacular growth of AI means that the knowledge we acquired just a year back is now outdated. So, we continuously learn, and before embarking on a new problem, we do an extensive survey of state of the art in the industry.
Today's blog post distills the knowledge we refreshed about Transfer Learning applied to medical data.
You will learn if it is good to use ImageNet architectures to solve medical image classification problems. Which architectures are the best and the most popular? We discuss whether we should use ImageNet pretrained weights.
There is no accompanying code with this post.
The literature on medical image analysis is vast, and we have just scratched the surface. If I have missed something essential in the above post, please feel free to point it out in the comments section. If possible, provide a reference paper I can check out.
Our goal is to present the best information to the readers.
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.