Markerless anatomical object tracking during an image-guided medical procedure

An image guidance system for treatment provided by a medical device comprising:

• an imaging system arranged to generate a succession of images of a target area for directing the treatment provided by the medical device;
• a control system configured to:
• receive images from the imaging system;
• analyse the images with a patient-specific, individually trained artificial neural network during the treatment to:
• determine the position of the target area;
• and
• adjust the medical device using the determined positions to direct the treatment to the target area.

A computer software product comprising a sequence of instructions storable on one or more computer-readable storage media, said instructions when executed by one or more processors, cause the processor to:

• receive an image, from an imaging system, of a target area for directing treatment by a medical device;
• analyse the image with a patient-specific, individually trained artificial neural network to determine the position of one or more anatomical objects of interest present in the target area;
• and
• output the position of the one or more anatomical objects of interest to the medical device.

A method of monitoring movement of an organ or portion of an organ or surrogates of the organ during treatment, comprising:

• directing treatment to at least a portion of an organ in a body part or human or animal subject;
• imaging multiple two-dimensional images of the organ or surrogates of the organ from varying positions and angles relative to the body part;
• digitally processing at least a plurality of the multiple two-dimensional images using a one or more computers with a software application executing patient-specific, individually trained artificial neural network;
• and
• displaying estimated three-dimensional motion of the organ or portion of the organ in the body part based on output from the digital processing.

A method of training a conditional Generative Adversarial Network (cGAN) for determining the position of one or more anatomical objects of interest present in the target area of an image of a patient, the method comprising:

• generating a training dataset using Direct Radiograph Rendering (DRRs) from CT images and associated contours at multiple imaging angles at high angular resolution of the patient;
• training a generator network of the cGAN using the training set, where the generator network generates synthetic images of the target area;
• training a discriminator network of the cGAN to evaluate smaller patches of the synthetic image generated by the generator network, where each evaluation results in a score determining whether the patch is real or fake;
• calculating an averaged score of all patches evaluated by the discriminator network for each synthetic image;
• adjusting the generator network based on feedback from the discriminator network to enhance the realism of generated synthetic images;
• and
• continually optimising both the generator and discriminator networks until no further improvement can be achieved in one network without compromising the performance of the other network.

An image guidance method for treatment of a predetermined type of organ by a medical device, comprising:

• imaging a target area to which the treatment is to be delivered;
• during the interventional procedure, analysing an image from the imaging with a population-based trained conditional Generative Adversarial Network (cGAN) to determine the position of the predetermined type of organ present in the target area;
• and
• outputting the determined position(s).