profile

Machine Learning for Medical Imaging

How to animate kids drawings with ML

Published about 1 year ago • 2 min read

Hello Reader,

Welcome to another edition of PYCAD newsletter where we cover interesting topics in Machine Learning and Computer Vision applied to Medical Imaging. The goal of this newsletter is to help you stay up-to-date and learn important concepts in this amazing field! I've got some cool insights for you below ↓

How to animate kids drawings using deep learning

With all the attention that ChatGPT and LLMs have been having lately. Some incredible advancements in computer vision have been overlooked.
​
Here's a new technique to animate kids drawings using a single image!
​
The Facebook AI Research team has developed a groundbreaking system for generating animated characters from single images.
​
They've structured the task as a series of sub-tasks: human figure detection, segmentation, pose estimation, and animation.
​
This system is perfect for creating diverse and dynamic characters in a fast-paced, high-stakes industry.
​
The first step involves identifying the human figure and predicting a bounding box that tightly encompasses it.
​
From there, segmentation is used to separate the human figure from the background and identify skeletal joints for pose estimation.
​
With this information, a character rig suitable for animation is generated, which can be easily modified.
​
To showcase the power of this system, the Facebook AI Research team has released the Animated Drawings Demo, which allows users to play around with different images, poses, and animations.
​
They've also provided examples of common failures and how to avoid them, ensuring that even novice animators can use the system to its fullest potential.
​
This system has the potential to revolutionize the world of animation and design, and I'm excited to see what the community will do with it.

You can find out more about this technique here. To to try it for yourself, check the github repo.

How to use ChatGPT Plus from your browser and cheaper!

If you've been following the last editions of the AIFEE newsletter, then you've noticed that I'm working on a Chrome extension that allows you to use ChatGPT straight from your browser.

When most people have been using ChatGPT Plus for 20$/month, developers have been using the ChatGPT API for 0.001$/token!

So if you're able to use the ChatGPT API (through code), you'll be only paying for your usage, which would generally be a lot cheaper than the ChatGPT Plus subscription.

As a developer, I've been using this ChatGPT API.

Now, it's possible for you to use it as well with my new Chrome extension called Remchee.

Here's how you can use it:

  1. Install the extension through this link.
  2. Sign up for an account using an email and a password.
  3. Set up billing and get your OpenAI credentials from the OpenAI website.
  4. Copy your OpenAI credentials and paste them in the corresponding fields in Remchee.
  5. Start chatting with ChatGPT!

​

Here are the benefits you'll get from using Remchee:

  • Using the pro version of ChatGPT but on a per use basis.
  • Accessing ChatGPT straight from your browser (no need to go to OpenAI website each time you want to use it).
  • I'm open to any new suggestions or feature requests that can help make your use of ChatGPT as optimal as possible.

You can get the extension here.

Machine Learning for Medical Imaging

by Nour Islam Mokhtari from pycad.co

👉 Learn how to build AI systems for medical imaging domain by leveraging tools and techniques that I share with you! | 💡 The newsletter is read by people from: Nvidia, Baker Hughes, Harvard, NYU, Columbia University, University of Toronto and more!

Read more from Machine Learning for Medical Imaging

Hi Reader,, Welcome to the PYCAD newsletter, where every week you receive doses of machine learning and computer vision techniques and tools to help you learn how to build AI solutions to empower the most vulnerable members of our society, patients. TotalSegmentator : Whole Body Segmentation at your Fingertips This free tool available online can do full body segmentation, it's called TotalSegmentator. I have already mentioned this tool in a previous edition of the newsletter, but in this...

9 days ago • 3 min read

Hello Reader, Welcome to another edition of PYCAD newsletter where we cover interesting topics in Machine Learning and Computer Vision applied to Medical Imaging. The goal of this newsletter is to help you stay up-to-date and learn important concepts in this amazing field! I've got some cool insights for you below ↓ A Medical Imaging Expert Told Me This Recently I saw a post on LinkedIn where a medical imaging expert showcased his work of segmenting the lungs and its bronchial trees. You can...

16 days ago • 2 min read

Hello Reader, Welcome to another edition of PYCAD newsletter where we cover interesting topics in Machine Learning and Computer Vision applied to Medical Imaging. The goal of this newsletter is to help you stay up-to-date and learn important concepts in this amazing field! I've got some cool insights for you below ↓ How we helped accelerate inference time for a client's AI product Below is a screenshot of a benchmark we did for a client of ours. The goal was to accelerate inference time. This...

22 days ago • 3 min read
Share this post