I am working on a project in medical image analysis - Breast cancer detection. And since I am the one who has proposed this project I was wondering, what would be the (data science) steps its development?
In my opinion, we need to:
- Identify the problem that we would like to solve - this has been done (Breast cancer detection)
- Talk about available data - see which data is publicly available and what we need to do to acquire it if we find it useful for the purpose of our project, also, see with what amount of data our medical center can supply us with
- Research various algorithms used to solve the exact or similar problem, pick and possibly tweak one of them.
- Find a base solution to which we will compare the performance of our previously picked model.
- Determine metrics used for evaluation
- See how the model applies in clinical practice by forming a group of the radiologist that is willing to go toe to toe with the model in order to see if there are any statistical differences between their analysis and the models.
The above is my view of how this project should proceed. I just want to know if there are any suggestions, if I am forgetting something, or any relative readings you could refer me to so that I can educate myself further.
Thank you so much!