Koninklijke Philips has filed a patent for a system and method that automatically verifies the positioning of a medical device in relation to a patient’s anatomy in a medical image. The system detects the position of reference points and the medical device in the image, determines the expected position of the device based on the reference points, and provides a measure of correctness for the device’s positioning. The patent aims to improve the accuracy of medical device placement during procedures. GlobalData’s report on Koninklijke Philips gives a 360-degree view of the company including its patenting strategy. Buy the report here.
According to GlobalData’s company profile on Koninklijke Philips, treatment progress monitoring was a key innovation area identified from patents. Koninklijke Philips's grant share as of September 2023 was 57%. Grant share is based on the ratio of number of grants to total number of patents.
Automatic verification system for positioning medical devices in medical images
A recently filed patent (Publication Number: US20230309936A1) describes a system for automatically verifying the positioning of a medical device in relation to a patient's anatomy in a medical image. The system includes an input for receiving the medical image, a detector for identifying the position of reference points on the patient's anatomy and detecting the presence and position of the medical device in the image. A determiner then calculates the expected position of the medical device based on the reference points and provides a measure of the correctness of the positioning. Finally, an output displays the measure of correctness.
The system utilizes artificial intelligence (AI) modules to enhance its capabilities. The detector includes a neural network that can employ various techniques such as classification, segmentation, region proposal, and pathfinding algorithms to detect the reference points and the medical device. Additionally, a probabilistic modeling module is used by the determiner to determine the expected position of the medical device and provide the measure of correctness. This probabilistic model is derived from a collection of datasets containing medical images of the medical device correctly positioned in relation to the patient's anatomy.
The patent also mentions the inclusion of a second AI module in the system, which is designed to detect complications that may arise from inserting the medical device into the patient. The measure of correctness of the positioning can be represented by a likelihood score and/or the proximity of the actual position of the medical device to the expected position.
In addition to the system, the patent also describes a computer-implemented method for automatic verification of the positioning of a medical device in a medical image. The method follows a similar process as the system, involving the detection of reference points, the presence and position of the medical device, determination of the expected position, and outputting a measure of correctness.
The patent specifies that the method can be applied to various medical images, such as chest X-ray images, and can be used for different types of medical devices, including catheters and tubes. It also highlights the use of the system's AI modules, including the neural network for detection and the probabilistic modeling module for determining the expected position and measure of correctness.
Overall, this patent presents a system and method that utilize AI technology to automatically verify the positioning of a medical device in relation to a patient's anatomy in a medical image. The system's ability to detect reference points, determine expected positions, and provide measures of correctness can potentially enhance the accuracy and efficiency of medical device placement.