Automated estimation of midline shift in brain ct images

An apparatus comprising:

• means for receiving a 3D medical image of an anatomical object of a patient;
• means for determining an initial location of landmarks on the anatomical object in the 3D medical image using a first machine learning network;
• means for extracting a 2D slice depicting the initial location of the landmarks from the 3D medical image;
• means for refining the initial location of the landmarks in the 2D slice using a second machine learning network;
• means for quantifying a shift of the anatomical object based on the refined location of the landmarks in the 2D slice;
• and
• means for outputting the quantified shift of the anatomical object.

A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising:

• receiving a 3D medical image of an anatomical object of a patient;
• determining an initial location of landmarks on the anatomical object in the 3D medical image using a first machine learning network;
• extracting a 2D slice depicting the initial location of the landmarks from the 3D medical image;
• refining the initial location of the landmarks in the 2D slice using a second machine learning network;
• quantifying a shift of the anatomical object based on the refined location of the landmarks in the 2D slice;
• and
• outputting the quantified shift of the anatomical object.