Estimate treatment effects using data from randomized control trials
Professional CertificateIntermediate
AI for Medicine
Instructor: Pranav Rajpurkar
DeepLearning.AI
Enroll Now
Also available on Coursera
- Intermediate
- 137 Video Lessons
- 29 Code Examples
- Instructor: Pranav Rajpurkar
What you'll learn
Explore methods to interpret diagnostic and prognostic models
Apply natural language processing to extract information from unstructured medical data
AI is transforming the practice of medicine. It’s helping doctors diagnose patients more accurately, make predictions about patients’ future health, and recommend better treatments. In this Specialization, you’ll gain practical experience applying machine learning to concrete problems in medicine. You’ll learn how to:
- Diagnose diseases from x-rays and 3D MRI brain images
- Predict patient survival rates more accurately using tree-based models
- Estimate treatment effects on patients using data from randomized trials
- Automate the task of labeling medical datasets using natural language processing
Course Outline
AI for Medical Diagnosis
This course is part of AI for Medicine
Week 1: Disease Detection with Computer Vision
- Building and Training a Model for Medical DiagnosisVideo・2 mins
- Training, Prediction, and LossVideo・1 min
- Image Classification and Class ImbalanceVideo・1 min
- Binary Cross Entropy Loss FunctionVideo・3 mins
- Impact of Class Imbalance on Loss CalculationVideo・3 mins
- Counting Labels and Weighted Loss FunctionCode Example・1 hour
- Resampling to Achieve Balanced ClassesVideo・1 min
- Multi-TaskVideo・1 min
- Multi-task Loss, Dataset size, and CNN ArchitecturesVideo・2 mins
- DensenetCode Example・1 hour
- Working with a Small Training SetVideo・2 mins
- Generating More SamplesVideo・3 mins
Welcome to the AI for Medicine Specialization
Applications of Computer Vision to Medical Diagnosis
Handling Class Imbalance and Small Training Sets
Checking your Model Performance
Programming Assignment: Chest X-Ray Medical Diagnosis with Deep Learning
Week 2: Evaluating Models
Key Evaluation Metrics
Threshold and Evaluation Metrics
Interpreting Confidence Intervals Correctly
Programming Assignment: Evaluation of Diagnostic Models
Week 3: Image Segmentation on MRI Images
- MRI Data and Image RegistrationVideo・3 mins
- SegmentationVideo・3 mins
- Extract a Sub SectionCode Example・1 hour
- Convolutional Neural networksReading・10 mins
- 2D U-Net and 3D U-NetVideo・2 mins
- More about U-Net (Optional)Reading・10 mins
- U-Net ModelCode Example・1 hour
- Data Augmentation for SegmentationVideo・2 mins
- Loss Function for Image SegmentationVideo・3 mins
Image Segmentation
Practical Considerations
End of access to Lab Notebooks
Programming Assignment: Brain Tumor Auto-Segmentation for Magnetic Resonance Imaging (MRI)
Summary of AI for Medical Diagnosis
Instructor
Frequently Asked Questions
Who is this Specialization for?
The AI For Medicine Specialization is for anyone who has a basic understanding of deep learning and wants to apply AI to the medicine space. After taking the Specialization, you could go on to pursue a career in the medical industry as a data scientist, machine learning engineer, innovation officer, or business analyst.
What will I learn in this Specialization?
In Course 1, you’ll learn how AI can help doctors make better medical diagnoses. In Course 2, you’ll learn how AI can improve predictions of patients’ future health. In Course 3, you’ll learn how AI can make better treatment recommendations based on individual patients’ health data.
Are there any prerequisites?
We recommend taking the Deep Learning Specialization first, but it’s not required. You should be able to code in Python and understand statistics and probability.
How do I take the Specialization?
You can enroll in the Specialization on Coursera’s platform. You will watch videos and complete assignments on Coursera as well.
How long is the Specialization?
It typically takes 3-4 weeks, 4-6 hours per week to complete each course. There will be three courses in the Specialization.
How much does the Specialization cost?
You can take this Specialization on the DeepLearning.AI platform. A DeepLearning.AI Pro subscription costs $30/month, and gives you access to all courses by DeepLearning.AI.
The Specialization is also available on Coursera. A Coursera subscription costs $49/month.
Can I preview the Specialization?
Yes! You can preview the course for free by accessing the entire first module at no cost. This allows you to explore the learning experience before deciding if you’d like to continue. If you want full access to all modules, assessments, and the certificate of completion, you’ll need to upgrade to the paid version.
Can I apply for financial aid?
Yes, Coursera provides financial aid to learners who cannot afford the fee. You can apply for it by going to the Coursera course page and clicking on the Financial Aid link beneath the “Enroll” button on the left.
Will I receive a certificate at the end of the Specialization?
You will receive a certificate at the end of each course if you pay for the courses and complete the programming assignments. There is a limit of 180 days of certificate eligibility, after which you would have to repurchase the course. If you audit the course for free, you will not receive a certificate.
Once all three courses in the Specialization are released and you are subscribed to the Specialization, you will also receive a certificate for the Specialization if you complete all three courses.
Is this a stand-alone course or a Specialization?
This is a deeplearning.ai Specialization made up of multiple courses. You can take the first two courses now on Coursera. Course 3 will be released by the end of May 2020.
Sign Up
Be notified of new courses