IMO this is the weakest course offered by deeplearning.ai. It feels something more our of a medium blog than a full course that someone should pay money for. The good news is that you can sign up for a 7 day free trial and finish it before 7 days are over, so you're not out of any money, just your time. What do you learn? Some new metrics that are specific to medicine (specificity, sensitivity) and the concept of class imbalance (prevalence). The code assignments are designed by someone who understands the concepts well but is unable to teach some of them well (I'm being super critical here, coming from the viewpoint of someone who might spend $49 for a month on this). At the end, I'm unsure what you can say you learned and if you can really demonstrate any concepts in a job interview at a healthcare (adjacent) job. There was some demonstration of segmentation, but a lot of it is really left up to the learner to experiment and learn from. You could talk about these things in a job interview, but a technical round would quickly discover that your knowledge is surface and not really in depth. My 2 cents (stars?). I apologize for being critical, but I've put 3 days into this course and not learned anything I couldn't have from a medium / towards data science blog. I do have higher expectations from courses coming from deeplearning.ai

Too basic, I felt I learnt almost nothing. There are a lot of nice techniques there (for example GradCam), but the exercises focused on implementation details instead of algorithm comprehension. Sincerely, explaining U-NET and segmentation in less than 20 minutes is quite ridicolous, in general it feels a really rushed course, nice if you can finish it for free, but not for long term learning.

It is marketed as a real data course, but actually noone of the problems of real data are actually presented, just quickly talked about in the videos. It feels really substandard compared to the others deeplearning.ai courses

The course is consisted of only 3 weeks which is very little for such a diverse and complex subject. Most exercises were trivial and the automatic grader was working very poorly which made me lose a lot of time thinking my solution was incorrect when it wasn't. Some exercises were poorly written.

Too basic

Hard to say this course teaches a lot of practical or useful topics on AI for Medical Diagnosis. Other than introducing the medical concepts of specificity and sensitivity, the remaining medically oriented topics (such as algos for processing medical images, in particular RMI 3d data) were just glanced over. Concepts such as ROC were poorly explained in practice (I reviewed the content multiple times and couldn't find the answer for the quizz questions, having to resort to research the topic outside the class materials), while spending a lot of time in video and exercises implementing our own U-net, using time that would have been better spend focusing on medical related AI practices.

Perfect! I am a PhD student in neuroscience. I already made my master thesis in machine learning. Now my PhD thesis will also be in the field of AI in medicine. This course is great. It shares so many useful functions and food for thought for my own projects! Definitely not too easy but also not to difficult. Before taking this course make sure to have enough experience with python programming, some understanding of machine learning and best some understanding of typical problems in medicine research.

Complex topics are explained in a simple and straight-forward manner. Really interesting real-life scenarios are used to keep the student interested throughout the whole course. 100% recommend it.

Introduction to the data and problem space in the programming exercises is useful, though there is a ton of boilerplate and a lot of the time will be spent messing around with Python volume manipulation, nothing really to do with medicine at all. Lectures are very brief and not very detailed. One lecture starts out "In this lesson,we'll look at one of the most useful tools to evaluate medical models, the ROC curve." But then doesn't show an example or even define the acronym. The entire video is only 1:44 long. Glad I finished the course during the 1 week free trial...it was worth it.

This was a great practical course overall especially for deep learning models. I admire that proper metrics were used to evaluate the different models that were built into the assignment which is unique compared to other machine learning courses where the standard metric is used.

The programming assignments are pretty engaging and well built as it analyzes MRI and x-rays, the lectures are also short and precise. As the course doesn't require any medical background , if you have general knowledge of machine learning and programming in python, this may be a exciting course for you to explore, learn and apply some wonderful examples of medical diagnosis using machine learning.

Really an outstanding course, very didactic and practical, and above all with cutting-edge material. It really takes you where it matters. It is highly recommended to introduce yourself to medical applications of artificial intelligence, and for anyone who wants to go deeper into artificial intelligence concepts. Thank you very much to the instructors. I really enjoyed it.

This course gave me a good amount of knowledge for a deep understanding of Ai in medical imaging Diagnosis and Segmentation. It gave me a good way to evaluate model performances. I am recommending everyone who wants to do furthermore analysis and work in AI in Medical Imaging. Thanks to every mentor and course creator for such an insightful course. Love you all guys.

A great review of how AI can be applied to the field of diagnostic medicine, with many of the practical issues that must be considered. Some prior experience with deep learning and using python and keras is advised, although the instructor(s) do all of the hard keras model development for you. I'm looking forward to the other courses in the specialization!

It was nice to attend this course, mostly due to clear examples, good visual representation of examples and a lot of practical exercises that served as nice preparation for assignments.

.

Last assignment may be divided into two files... as it is becoming heavy to solve and even upload.

Rest is fine. Congratulation on designing such a pin pointed course in Medical Diagnosis

Excellent. Well structured for beginners, especially with the inclusion of evaluation metrics, methodology and their vast significance in the medical domain of AI.

It was great experience visiting deeplearning.ai course, kudos to the team! Really helpful and a must for AI learner!

Excelent course

Thank you Pranav Rajpurkar and Andrew Ng for this amazing specialization! Thank you deeplearning.ai! Thank you Coursera!This specialization covers application of AI algorithms for: medical diagnosis of patients using chest X-Rays and 3D MRI brain images; prognosis of patients using survival models; and medical treatment recommendation models.The lectures were brief and comprehensive, the quizzes included toy problems to test the grasp over the mathematical formulas, and the assignments were simple and covered implementation of most of the concepts taught in the courses.

Pretty amazing course. The first-ever proper course on Medical Image Processing and modeling. Instructors do an amazing job in explaining the best practices which must be followed while dealing with medical data. Learning tasks like Classification & Segmentation, appropriate loss functions, and performance metrics are explained well. The lab module provides a solid hands-on for the concepts introduced in the theory session. A Highly recommended course and I'm thankful for the whole team for coming up with such solid content.