Click here to learn about the course. The new course of Medical imaging AI (AI for Medicine) is recommended

Welcome to artificial Intelligence in Medicine. If you have completed a deep learning specialization or machine learning course, and you are looking for a deeper grasp of the applied field of ARTIFICIAL intelligence, this is a good specialization to learn.

One of the most important things to do to be truly good machine learning is to practice applying machine learning to multiple use cases.

Specialization will allow you to leapfrog through multiple use cases to the most important applications of ARTIFICIAL intelligence in medicine. Such as:

  • Given an image from a chest X-ray, then unstructured image data, can you train a neural network to diagnose if a patient has pneumonia? You learn to do that in this major.
  • Given structural data, such as a patient’s laboratory results, can you train a decision tree to estimate heart attack risk? You have to learn to do the same.

By addressing these specific problems, you can also see many practical aspects of machine learning, from how to deal with lopsided data sets to how to deal with missing data to choosing the right evaluation metrics.

In machine learning, we usually default to classification accuracy as a measure. But for many applications, this is not the right metric.

So how to choose a more suitable one? Even if you don’t work in medicine now, I think you’ll find the application scenarios and the practice of those application scenarios very useful, and maybe specialization will convince you to be more interested in medicine.

If you are interested in medicine, then this is a good specialized course. Medical artificial intelligence is booming around the world.

So it’s a great time to jump in and try to make a big impact. You could invent something that could save a patient’s life. Let’s get started.

I am glad that this major will be organized byinaudibleThe professor explained that I (Ng) and he had the honor to collaborate on artificial intelligence medical research for several years.

This is a three-course professional course,

  • In the first course, you learned how to build machine learning models for diagnostics.

Diagnosis is the identification of disease. In the first lesson, you will build an algorithm that will examine a chest X-ray and determine if it contains disease. You’re also going to build another algorithm that can look at brain MRIs and determine the location of tumors in those brain MRIs. So the first lesson is diagnosing or identifying diseases,

  • The second lesson is predicting patients

Future health, this is called prognosis.

In the second course, you will learn how to work with structured data. Let’s say you have a patient’s lab values and their demographics, and you use that to predict the risk of an event, like their risk of dying or having a heart attack.

  • In the third lesson, you learned about artificial intelligence therapy.

That is, for medical procedures and information extraction, information is obtained from medical texts. In course 2, you will learn how to use machine learning models to estimate the impact of specific treatments on patients. You’ll also learn about the use of ARTIFICIAL intelligence in text, for example, answering questions and extracting labels from radiology reports.

You do not need any medical background for this and other specialized courses. However, I recommend that you meet three prerequisites before taking this course and any other specialized courses.

  • First, this course assumes that you know the basics of deep learning. For example, you should understand the basics of supervised learning, convolutional neural networks, and loss functions.
  • Second, being able to code in Python should be pretty comfortable, because in the assignments for these three courses, you’ll use Python to process data and build machine learning models.
  • Third, class concepts will assume some knowledge of probability. For example, when we say the probability of a given B, you should be able to recognize that this is a conditional probability. With these three prerequisites, you’re ready to get started.

This is the first week of lesson 1, where you will learn how to build and evaluate a deep learning model for detecting disease from medical images.

  • In the first week, you build a deep learning model that can interpret chest X-rays to classify different causes of disease.
  • In the second week, you will implement an evaluation method to assess the quality of the model.
  • In week three, you will use image segmentation to determine the location and boundary of a brain tumor on an MRI scan.

After this explanation, please read the next content ~~

The article continues to be updated, you can follow the wechat public account [Medical image Artificial Intelligence Field Camp] to get the latest developments, a public account focusing on the frontier technology in the field of medical image processing. Adhere to the practice of the main, hand in hand to take you to do projects, play games, write papers. All original articles provide theoretical explanation, experimental code, experimental data. Only practice can grow faster, pay attention to us, learn and progress together ~

I’m Tina and I’ll see you next time

I work all day and write all night

If you think it’s written well, then finally, == Get likes, comments, favorites. Or one button three times equals equals