Report formatting for automated or assisted analysis of medical imaging data and medical diagnosis

A medical device for analysis of medical imaging data to diagnose abnormalities, the medical device comprising:

• a processor and memory configured to implement the steps of:
• receiving imaging data relating to a body part of a human patient;
• classifying by machine learning the imaging data into a normal or an abnormal class;
• for the abnormal class, spatially localizing an abnormality within the imaging data of the body part, and categorizing by machine learning the abnormality within a category to provide a categorized abnormality for diagnostic purposes;
• grouping taxonomies into broad categories that relate to a particular physiology;
• and
• implementing computer code of a convolutional neural network (CNN), the CNN comprising a plurality of layers in a sequence, each layer comprising a plurality of nodes,
• wherein:
• each node of each layer is connected to at least one other node of a subsequent or preceding layer in the sequence;
• each node accepts an input value and outputs an output value;
• the classifying, spatially localizing and categorizing are performed by the CNN;
• the CNN is trained by deep supervision based on known anatomy of the body part;
• the category is derived from a taxonomy created by a physician;
• the medical imaging data comprises at least one of X-ray slides, computerized tomography, magnetic-resonance (MR), diffusion-tensor (DT), functional MR, gene-expression data, dermatological images, and optical imaging of tissue slices;
• the category has a normal or abnormal flag;
• the processor and memory are further configured to implement the step of compiling a human readable report based on the imaging data and the normal or abnormal flag, the step of compiling using a lookup table by selecting pre-formatted text based on the category and the normal or abnormal flag;
• and
• the pre-formatted text includes quantitative descriptions for the abnormality.