Course concept good. In fact one of the first courses with direct practical application of AI.

This and other 2 courses expect beginners knowledge of deep learning hence newcomers may find it tough. However sorely miss in depth theory of U Net and other advanced Algorithms . Videos are crisp, smart but inadequate.

going to take the next 2 courses and complete them

I learned a lot from this course. Each lab, assignments, and weekly quizzes enabled me to take a deeper dive into how these models and image processing work on medical images. It made me wear my thinking cap and think deeply into each parameters and features and what mathematical-statistical models are used for prediction and classification analysis!

It was a nice course. Though it covers basics. A follow-up advanced specilization can be made. Overall, it's sufficient for beginner for an engineer trying to learn application of AI for medical field

Throughout this course, I was able to understand the different medical and deep learning terminology used. Definitely a good course to understand the basic of image classification and segmentation!

It's a wonderful intro to the medical diagnosis using DL technologies and this course provides the detailed application in the lab session, which helps a lot to the understanding of the theory.

I am a Radiation Oncologist and I found this Course really interesting and satisfactory as far as my professional area is concerned. Unfortunately, my limited competence in applied informatics prevented me from successfully trying and performing the 3 informatics labs graded tests . Therefore I understand that I cannot receive the Passing Certificate relative to this course. So, my review could have been 5 stars if I could attend and pass a Course more shaped with a clinical approach. My 3 stars score is due to the fact that I could not complete the course.

It was not covering the preprocessing and in-depth hands-on but was mainly focused on the beginner material and being able to run the code or evaluate the model rather actual preprocessing of the data or the modeling part.

There is no reply or response to discussion forums from the instructors and assessment of the assignments are always zero so I can not pass to week two even my assignment's outputs are matched with the correct ones .

A far too brief overview of AI applications in medical diagnosis - only really covers image analysis and even then is cursory at best. Disappointing as I have found the other deeplearning.ai courses quite helpful.

Very basic, and the assignments are basically NumPy arrays manipulation rather than actually using ai on real-world data to get predictions.

Not useful. Probability distributions are not intuitive mostly.

This course relays on "add one line" code too often.

The course was quite shallow, and the actual challenges of model selection, training or building appropriate augmentation steps were pre-built and not discussed in any detail.

The coding challenges were using badly outdated package versions, for which documentation does not exist anymore and which do not represent best practice usage of the libraries involved.

On top of that, the coding challenges expect a very specific solution, while not considering equivalent implementations as correct (case in point: In the week 3 coding challenge, I used np.transpose where the challenge used np.moveaxis. I prefer transpose since it clearly and explicitly states where _all_ the other axis go, while moveaxis makes that change of state implicitly.)

Finally, the grading of the last coding challenge does not respect the special cases that are explicitly mentioned in the excercise itself. The "standardize" function to be implemented explicitly mentions the possibility of a slice having a zero standard deviation and the pre-coded framework handles this special case correctly. However, if one changes the selection of the slice in the cell before, which the user is encouraged to do, it is possible to obtain an empty slice. The grader expects a unit standard deviation though, without checking this edge case.

The shallow content and lackluster excercises, as well as the common mistakes in the presentation videos (sometimes corrected by a "question" popup during playback) do not give the impression this course was prepared well.

I have done several of AI courses including the TensorFlow. While the TensorFlow course, gives you a neat and excellent hands on on how to build a network from scratch or implement easily a CNN such as Inception V3, this course make you confused as what sort of aim it follows. Overall confusing and not useful. Though you find some good stuff in the videos but the design and strategy of the course is meaningless.

Lectures are short, mainly focused on programming details (how to subsample and image or how to calculate an error). The assignments do not help understand the AI part of the medical diagnosis. It can be considered as an intro course for the AI for MD.

You provide no means of starting over in a lab. Critical design flaws prevent me from completing my assignment and completing the course(!!!)

No for medical students. Terrible time loosing

Very basic

This course was excellent! I previously did the Machine Learning course from Andrew Ng and the CS50 AI course on Edx, and I've been trying to work on ML projects since. Specifically, I've been trying to do a lot of work on medical applications of ML, stuff like brain tumor detectors. I wanted to do this course to learn about things like U-Nets and how to evaluate my models, and this course really helped with that! I don't think I'll be completing the entire specialization since winter break is almost over and I probably won't have time, but I definitely feel very satisfied with the information I've gained so far! My one complaint is that I felt the assignments were very "hand-holdy", as in they didn't let you implement a lot of the stuff yourself. There are functions you implement, but that's mostly just really simple stuff. I think the assignments are very cool, but I think I would have preferred assignments that were less complicated but you had to do most of the work yourself so that it truly feels like you built it.

This is the best course of the specialization. The instructor created one of the best models for chest X-ray diagnosis that was the first model that beat human radiologists in detecting pneumonia (now with COVID-19 that's more important than ever). The original CheXNet model is flawlessly and simply explained so that anyone could understand it with all details served literally on a plate requiring no additional work. This is my favorite course of all DeepLearning.ai specializations! Thanks Pranav & Andrew!

Amazing course if you are interested in learning about the applications of AI in the field of Medical Diagnosis. Learned the meaning of a lot of medical terms and concepts required in this field. It was a perfect combination of interesting and challenging tasks that kept me hooked in the course from beginning all the way till the end. Highly recommended for anyone interested in this particular field of study for their research or education.

Wonderfully structured course. Dr Pranav's approach, knowledge & passion for the subject are worth emulating. It has put me on a path to seek more knowledge about disease conditions, radiology and applying AI to a clinical settings. Lots more to learn, practice and validate. The foundations are strong. Thank you Dr Pranav & Dr Andrew Ng.

I enjoyed this course! Having taken the deep learning specialization, I wanted to understand how various techniques can be applied to medical applications. The topics covered were delivered well and the labs, assignments were quite helpful. The final assignment however was quite challenging since it was my first time working with 3D data.

This was the most easy to understand course I think due to how it was presented and broken down into various sections. The exercies and assignements helped to clear the concept. The coding assignment could add some more information so that it would be easier to visulize 4D arrays and what to slice etc, may be add few more lines to Hint?

The course is excellent in its content. However, I would suggest a bit more rigorous setting like letting the students write the function on their own just by providing them with hints. Also, I would like to suggest that some of the utilfunctions that were provided can be given as assignments say for honors purposes.