Systems, methods, and apparatuses for the use of transferable visual words for ai models through self-supervised learning in the absence of manual labeling for the processing of medical imaging

Non-transitory computer-readable storage media having instructions stored thereupon that, when executed by a system having at least a processor and a memory therein and being specially configured to perform self-supervised learning for an AI model in the absence of manually labeled input, the instructions cause the system to perform operations including:

• executing instructions via the processor for performing a self-discovery operation which crops 2D patches or crops 3D cubes from similar patient scans received at the system as input;
• executing instructions via the processor for transforming each anatomical pattern represented within the cropped 2D patches or the cropped 3D cubes to generate transformed 2D anatomical patterns or transformed 3D anatomical patterns;
• performing a self-classification operation of the transformed anatomical patterns by formulating a C-way multi-class classification task for representation learning;
• performing a self-restoration operation by recovering original anatomical patterns from the transformed 2D patches or transformed 3D cubes having transformed anatomical patterns embedded therein to learn different sets of visual representation;
• and
• providing a semantics-enriched pre-trained AI model having a trained encoder-decoder structure with skip connections in between based on the performance of the self-discovery operation, the self-classification operation, and the self-restoration operation.

A method performed by a system having at least a processor and a memory therein to execute instructions and being specially configured to perform self-supervised learning for an AI model in the absence of manually labeled input, wherein the method comprises:

• executing instructions via the processor for performing a self-discovery operation which crops 2D patches or crops 3D cubes from similar patient scans received at the system as input;
• executing instructions via the processor for transforming each anatomical pattern represented within the cropped 2D patches or the cropped 3D cubes to generate transformed 2D anatomical patterns or transformed 3D anatomical patterns;
• performing a self-classification operation of the transformed anatomical patterns by formulating a C-way multi-class classification task for representation learning;
• performing a self-restoration operation by recovering original anatomical patterns from the transformed 2D patches or transformed 3D cubes having transformed anatomical patterns embedded therein to learn different sets of visual representation;
• and
• providing a semantics-enriched pre-trained AI model having a trained encoder-decoder structure with skip connections in between based on the performance of the self-discovery operation, the self-classification operation, and the self-restoration operation.