Optical Voice Activity Detection in MRI Systems

Solution Overview

Problem

Current magnetic resonance imaging (MRI) systems rely on squeeze bulbs for patient communication, which can be difficult for children and elderly patients to handle, and may lead to panic or motion artifacts if dropped, necessitating an alternative method for real-time patient feedback.

Innovation Solution

A video-based system that captures facial images to detect voice activity using a video-based voice activity detection module, providing a voice activity signal to initiate communication between the patient and operator, potentially replacing traditional squeeze bulbs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a squeeze bulb is provided for patient communication, then the operator can receive patient feedback, but the patient may inadvertently drop the bulb and panic or move, creating motion artifacts

Engineering Contradiction:

Improvecommunication reliabilityVSAvoidmotion artifacts

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the mechanical squeeze bulb system with an optical detection system that monitors facial movements and voice activity. Cameras capture video of the patient's face, and algorithms detect mouth movements and voice signals to determine when the patient wants to communicate, eliminating the need for manual mechanical interaction with the squeeze bulb.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables patients to communicate automatically through their natural facial expressions and voice without requiring manual operation of external devices. The automated detection system interprets patient intent from passive observation of facial region video, allowing patients to communicate without physical interaction that could cause motion.

Inventive Principle:

Principle #25Self-service

2Reliability

If a squeeze bulb is provided for patient communication, then the operator can receive patient feedback, but holding onto the squeeze bulb may be difficult for children or elderly persons

Engineering Contradiction:

Improvecommunication reliabilityVSAvoidease of operation

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent replaces the mechanical squeeze bulb system with an optical detection system that monitors facial movements and voice activity. Cameras capture video of the patient's face, and algorithms detect mouth movements and voice signals to determine when the patient wants to communicate, eliminating the need for manual operation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables patients to communicate automatically through their natural facial expressions and voice without requiring manual operation of external devices. The automated detection system interprets patient intent from passive observation of facial region video, allowing patients to communicate without physical interaction that could be difficult for children or elderly persons.

Inventive Principle:

Principle #25Self-service

3Manufacturing precision

If the subject remains motionless for minutes during data acquisition, then image quality is improved, but the subject may experience discomfort or panic due to noise and confined space

Engineering Contradiction:

Improveimage qualityVSAvoidpatient discomfort

Core Design Contradiction:

Manufacturing precisionVSObject-affected harmful factors

Solution Approach 1:

The system continuously monitors the patient's facial region video and voice activity throughout the scan, providing real-time feedback about patient comfort. When the automated system detects communication intent through facial movements or voice, it immediately alerts the operator, enabling timely intervention to address discomfort or panic.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system proactively detects patient discomfort or communication needs before the patient can physically react or move. By continuously analyzing facial expressions and voice activity, the system can alert the operator to potential issues before they escalate into panic or significant motion that would degrade image quality.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentEP3803421B1Optical detection of a communication request by a subject being imaged in a magnetic resonance imaging system

Publication Date: 2023.07.19 KONINKLIJKE PHILIPS NV

Figure 1
Figure 2
Figure 3

AI summary

The invention provides for a magnetic resonance imaging system (100, 300, 500). The magnetic resonance imaging system comprises a video system (122, 122', 122'') configured for providing video images (146) of a facial region (119) of a subject (118) during acquisition of the magnetic resonance imaging data (144). The magnetic resonance imaging system further comprises a memory (134) for storing machine executable instructions (140) and pulse sequence commands (142). Execution of the machine executable instructions causes a processor (130)to: control (200) the magnetic resonance imaging system with the pulse sequence commands to acquire the magnetic resonance imaging data; receive (202) the video images from the video system during execution of the pulse sequence commands; determine (204) a voice activity state (150) in real time for the video images by inputting the video images into a video-based voice activity detection module, wherein the voice activity state indicates a talking state of the subject or a non-talking state of the subject; and provide (206) a voice activity signal (152) if the voice activity state indicates the talking state.