Generating abnormality data for a medical scan via a generic model and a fine-tuned model

A multi-model medical scan analysis system, comprising:

• at least one processor;
• and
• a memory that stores operational instructions that, when executed by the at least one processor, cause the multi-model medical scan analysis system to:
• receive, via a receiver, a plurality of medical scans, wherein each of the plurality of medical scans includes corresponding labeling data indicating whether each of a plurality of abnormality types are present in the each of the plurality of medical scans;
• generate a generic model by performing a training step on image data of the plurality of medical scans and the corresponding labeling data;
• generate a plurality of fine-tuned models, wherein each of the plurality of fine-tuned models is generated by performing a fine-tuning step on the generic model, and wherein each of the plurality of fine-tuned models corresponds to one of the plurality of abnormality types;
• receive, via a receiver, a new medical scan;
• generate abnormality detection data for the new medical scan by performing a generic inference function on image data of the new medical scan, wherein the generic inference function utilizes the generic model, and wherein the abnormality detection data indicates a plurality of probability values that each indicate a probability that a corresponding one of the plurality of abnormality types is present in the new medical scan;
• determine a first one of the plurality of abnormality types that is detected in the new medical scan by determining a corresponding one of the plurality of probability values compares favorably to a detection threshold;
• select one of the plurality of fine-tuned models that corresponds to the first one of the plurality of abnormality types;
• generate additional abnormality data for the new medical scan by performing a fine-tuned inference function on the image data of the new medical scan, wherein the fine-tuned inference function utilizes the one of the plurality of fine-tuned models;
• and
• transmit the additional abnormality data to a client device for display via a display device.