USPTO Patent Application: Image Processing for Monitoring Inserted Objects

ChangeBridge: Patent Apps - Prosthetics (A61F)

Published March 19th, 2026

Detected March 23rd, 2026

Summary

The USPTO has published a patent application detailing a system for monitoring objects inserted into a patient's body using image processing and machine learning. The application, filed by Gabriel Fine and Nathan Silberman, describes a method for training models on annotated images to determine the spatial information of inserted objects within a patient.

View original document View source feed page

What changed

This document is a USPTO patent application (US20260080315A1) for a system and method that uses image processing and machine learning to monitor objects inserted into a patient's body. The system involves training a model on annotated images of the object with spatial information, then using an imaging computer system to receive images from an external device and determine the object's current spatial information within the patient. The output includes the images and the object's spatial data.

This patent application does not impose any new regulatory requirements or compliance obligations on regulated entities. It represents a novel technological development in the medical field, potentially impacting future medical device design and patient monitoring practices. Compliance officers should note this as a development in medical technology rather than an immediate regulatory change requiring action.

Source document (simplified)

← USPTO Patent Applications

SYSTEM FOR MONITORING OBJECT INSERTED INTO PATIENT'S BODY VIA IMAGE PROCESSING

Application US20260080315A1 Kind: A1 Mar 19, 2026

Inventors

Gabriel FINE, Nathan SILBERMAN

Abstract

A system and method for image-based monitoring of an object inserted into a patient is disclosed. A model can be trained for an object configured to be inserted into a patient as part of a medical procedure, the trained model being generated from one or more machine learning algorithms that are trained on annotated images of the object with spatial information of the object. An imaging computer system can receive one or more images of the object inserted within the patient captured by an imaging device positioned external to the patient. The imaging computer system can further determine, based on applying the trained model to the one or more images of the object, current spatial information of the object within the patient. A display can output the one or more images and the current spatial information of the object.

CPC Classifications

G06N 20/00 A61B 34/10 A61B 34/20 G06F 18/2414 G06N 3/044 G06N 3/045 G06N 3/08 G06T 7/0016 G06T 7/70 G06T 7/75 G06V 10/82 G06V 30/19173 G06V 30/194 G16H 30/20 G16H 30/40 G16H 40/63 G16H 50/50 A61B 2034/102 A61B 2034/2051 A61B 2034/2065 A61B 2090/367 A61B 2090/376 A61F 2/01 A61F 2/0105 G06T 2207/10072 G06T 2207/10081 G06T 2207/10088 G06T 2207/10116 G06T 2207/10121 G06T 2207/10132 G06T 2207/20084 G06T 2207/30021