Systems, methods, and media for selectively presenting images captured by confocal laser endomicroscopy

A system, comprising:

• a confocal laser endomicroscopy (CLE) device, comprising:
• a rigid probe;
• and
• a light source, wherein the confocal laser endomicroscopy device is configured to generate image data representing brain tissue during brain surgery;
• and
• a computing device comprising:
• a hardware processor;
• and
• memory storing computer-executable instructions that, when executed by the processor, cause the processor to:
• receive, from the CLE device, a first image captured during a brain surgery;
• provide the first image to a convolution neural network trained using at least a plurality of images, wherein each of the plurality of images is an image of brain tissue that was captured using CLE techniques, and is labeled as either a diagnostic image or a non-diagnostic image, wherein images labeled as diagnostic provide at least a threshold level of identifiable histological features and images labeled as non-diagnostic do not provide the threshold level of identifiable histological features;
• receive an indication, based on a first output of the convolution neural network, of a first likelihood that the first image is a diagnostic image;
• determine, based on the first likelihood, that the first image is a diagnostic image;
• and
• in response to determining that the first image is a diagnostic image, present the first image during the brain surgery.

A method for selectively presenting images captured by a confocal laser endomicroscopy (CLE) device, comprising:

• receiving an image captured by a CLE device during brain surgery;
• providing the first image to a plurality of convolution neural networks trained using at least a subset of images from a plurality of images,
• wherein the plurality of images are images of brain tissue captured using CLE techniques and labeled as either a diagnostic image or a non-diagnostic image,
• wherein images labeled as diagnostic provide at least a threshold level of identifiable histological features and images labeled as non-diagnostic do not provide the threshold level of identifiable histological features, and
• wherein each of the plurality of convolutional neural networks was trained with a validation subset from the plurality of images that is different than the validation subset used to train each of the other convolution neural networks in the plurality of convolutional neural networks;
• receiving an indication, based on first outputs of the plurality of convolution neural networks, of a first likelihood that the first image is a diagnostic image;
• determining, based on the first likelihood, that the first image is a diagnostic image;
• and
• in response to determining that the first image is a diagnostic image, causing the first image to be presented during the brain surgery.