Computer-implemented method and associated device for modelling a joint of a patient

A computer-implemented method for modelling a joint of a patient for real-time assistance in creating at least one bone tunnel by arthroscopy or during open surgery in said joint, comprising:

• receiving at least one of a stream of monocular or binocular intraoperative two-dimensional images obtained using an imaging device, each of the monocular or binocular intraoperative two-dimensional images being obtained at a time t and comprising at least a portion of interest of the joint;
• for each monocular or binocular intraoperative two-dimensional image, calculating a depth map associated with the time t, by implementing a first previously trained learning model, said first learning model configured to receive as input at least said monocular or binocular intraoperative two-dimensional image obtained at the time t;
• and
• calculating a current partial three-dimensional model of the joint of the patient associated with a current time tc, on the basis of at least one depth map associated with the current time tc and at least one depth map associated with a previous time (tc−Δt), and the location information of the imaging device.

A device for modelling a joint of a patient for real-time assistance in creating at least one bone tunnel by arthroscopy or during open surgery in said joint, said device comprising:

• at least one input configured to receive at least one of a stream of monocular or binocular intraoperative two-dimensional images obtained using an imaging device, each of the monocular or binocular intraoperative two-dimensional images being obtained at a time t and comprising at least a portion of interest of the joint;
• at least one processor configured to:
• for each monocular or binocular intraoperative two-dimensional image, calculate a depth map associated with the time t, by implementing a first previously trained learning model, said first learning model being configured to receive as input at least said monocular or binocular intraoperative two-dimensional image obtained at the time t;
• calculate a current partial three-dimensional model of the joint of the patient associated with a current time tc, on the basis of at least one depth map associated with the current time tc and of at least one depth map associated with a previous time (tc−Δt), and location information of the imaging device;
• and
• at least one output configured to provide said current partial three-dimensional model of the joint of the patient associated with a current time tc.