Self-supervised training at scale with weakly-supervised latent space structure

An apparatus comprising:

• means for receiving input medical data;
• means for performing a medical analysis task using a trained machine learning based task network based on the input medical data;
• and
• means for outputting results of the medical analysis task,
• wherein the trained machine learning based task network is trained by:
• receiving unannotated training medical data;
• generating weakly-supervised labels for the unannotated training medical data using one or more trained machine learning based supervised learning networks, wherein generating weakly-supervised labels for the unannotated training medical data using one or more trained machine learning based supervised learning networks comprises:
• generating initial labels using the one or more trained machine learning based supervised learning networks, and
• filtering the initial labels using one or more out-of-domain probability distribution models to result in labels generated from input data that is in-domain of the one or more trained machine learning based supervised learning networks as the weakly-supervised labels;
• training the machine learning based task network for performing the medical analysis task based on 1) the unannotated training medical data, 2) self-supervised labels for the unannotated training medical data learned via self-supervised learning, and 3) the generated weakly-supervised labels for the unannotated training medical data, wherein training the machine learning based task network for performing the medical analysis task comprises:
• extracting latent features from the unannotated training medical data using an encoder of the machine learning based task network,
• assigning the generated weakly-supervised labels to the extracted latent features, and
• training the machine learning based task network based on the generated weakly-supervised labels assigned to the extracted latent features;
• and
• outputting the trained machine learning based task network.

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 input medical data;
• performing a medical analysis task using a trained machine learning based task network based on the input medical data;
• and
• outputting results of the medical analysis task,
• wherein the trained machine learning based task network is trained by:
• receiving unannotated training medical data;
• generating weakly-supervised labels for the unannotated training medical data using one or more trained machine learning based supervised learning networks, wherein generating weakly-supervised labels for the unannotated training medical data using one or more trained machine learning based supervised learning networks comprises:
• generating initial labels using the one or more trained machine learning based supervised learning networks, and
• filtering the initial labels using one or more out-of-domain probability distribution models to result in labels generated from input data that is in-domain of the one or more trained machine learning based supervised learning networks as the weakly-supervised labels;
• training the machine learning based task network for performing the medical analysis task based on 1) the unannotated training medical data, 2) self-supervised labels for the unannotated training medical data learned via self-supervised learning, and 3) the generated weakly-supervised labels for the unannotated training medical data, wherein training the machine learning based task network for performing the medical analysis task comprises:
• extracting latent features from the unannotated training medical data using an encoder of the machine learning based task network,
• assigning the generated weakly-supervised labels to the extracted latent features, and
• training the machine learning based task network based on the generated weakly-supervised labels assigned to the extracted latent features;
• and
• outputting the trained machine learning based task network.

A computer-implemented method comprising:

• receiving unannotated training medical data;
• generating weakly-supervised labels for the unannotated training medical data using one or more trained machine learning based supervised learning networks, wherein generating weakly-supervised labels for the unannotated training medical data using one or more trained machine learning based supervised learning networks comprises:
• generating initial labels using the one or more trained machine learning based supervised learning networks, and
• filtering the initial labels using one or more out-of-domain probability distribution models to result in labels generated from input data that is in-domain of the one or more trained machine learning based supervised learning networks as the weakly-supervised labels;
• training a machine learning based task network for performing a medical analysis task based on 1) the unannotated training medical data, 2) self-supervised labels for the unannotated training medical data learned via self-supervised learning, and 3) the generated weakly-supervised labels for the unannotated training medical data, wherein training the machine learning based task network for performing the medical analysis task comprises:
• extracting latent features from the unannotated training medical data using an encoder of the machine learning based task network,
• assigning the generated weakly-supervised labels to the extracted latent features, and
• training the machine learning based task network based on the generated weakly-supervised labels assigned to the extracted latent features;
• and
• outputting the trained machine learning based task network.