Problem: Imagine you are involved in a research project studying the impact of a set of genes on cardiac development. This project has produced a large number of genetically modified chicken embryos - fertilized eggs. Under the study protocol, the eggs are imaged in a Micro-CT scanner, and then a pathologist goes over the resulting 3D images and determines the phenotype of each egg - precisely, the presence and degree of any cardiac abnormalities in each subject. However, it is noted that the pathologist spends most of their time rotating the images so they have a consistent orientation, with the long axis of the heart pointing "upward" as the orientation of the embryos inside the eggs varies. It would save a lot of time and expense if this process could be done automatically.
You have been tasked to find a software solution for this problem. You have access to a broad set of CT images, some of which have already been processed by the pathologist. Assume that you have access to whichever general-purpose numeric computing environment you choose (e.g., MATLAB, Mathematica, R, etc.) as well as any medical-imaging specific toolkit (e.g., Osirix, ITK, MIM, etc.).
Please outline how you would solve this problem. List any assumptions and provide an outline of all algorithms and techniques you would use, as well as any software packages or libraries. Finally, outline a plan to test your solution using matlab is preferred.