Odiosoft MamAcoustic

MamAcoustic is an AI-assisted assessment tool that uses the smartphone's speaker to deliver a mechanical vibration (chirp) to breast tissue, and records the tissue's mechanical response via the device microphone and accelerometer.

The tissue's mechanical response is decomposed into frequency-domain (FFT) parameters such as resonance frequency, Q-factor, bandwidth and damping. These parameters provide numerical information about breast tissue stiffness, viscoelastic balance and mechanical transmission.

Core Capabilities

• Non-invasive, contactless-contact mechanical stimulus + response recording
• FFT extraction of resonance, Q-factor, damping, stiffness, viscoelastic, transmission
• Right-left breast comparison and asymmetry detection
• Longitudinal trend and recording history

The platform uses the device's built-in speaker as the mechanical source, the microphone as the acoustic receiver and the accelerometer as the motion sensor. It is hardware-independent; no extra medical device required.

Processing Flow

• Calibration: reference spectrum baseline
• Breast side selection: right/left
• Contact check: real-time microphone + accelerometer monitoring
• Auto measurement: sustained good contact → chirp signal + recording
• FFT analysis: transfer function + mechanical parameters
• AI clinical commentary: scenario match score

Software-Centric Architecture

MamAcoustic measurement uses all of the phone's microphone, accelerometer, gyroscope, speaker and audio engine (AudioContext) sensors. The Device Suitability Test checks whether your device has these sensors and they are working before starting the measurement.

The test checks each sensor in sequence: detects the device type, verifies microphone permission and stream, checks that accelerometer and gyroscope data is received, tests the speaker presence, and confirms the audio engine can be initialized.

Critical sensors are microphone, accelerometer and audio engine. If any of these fail, the device is not suitable for measurement. If the gyroscope is missing, measurement can proceed with the stability check disabled. Desktop computers lack an accelerometer, so measurement is not possible.

Checked Sensors

How to Perform

• 1. Start Test: Press the 'Run Test' button
• 2. Grant Permissions: Approve microphone and motion sensor permissions
• 3. Wait: Each sensor is tested in sequence (~5 seconds)
• 4. Review Results: Green = pass, red = fail, yellow = warning
• 5. Proceed if Suitable: If all critical sensors are green, you can measure

Result Interpretation

Calibration establishes the baseline of the device's speaker and sensors. Measurements are normalized against this reference, so accurate calibration is a prerequisite for accurate results.

Place the phone with the speaker (bottom edge) contacting a hard, flat reference surface (glass table, granite, or a hard book). Do NOT contact breast tissue — calibration is done in an empty reference environment.

The system generates a chirp (frequency sweep) signal: the speaker sweeps from low to high frequency. Simultaneously, the microphone and accelerometer record the mechanical response of that stimulus through the device/surface.

From the recorded signal, the transfer function is extracted via FFT. The reference resonance frequency and acceleration RMS are stored as the baseline. All subsequent measurements are normalized against this reference (stiffness index = measured resonance / reference resonance).

Calibration Steps

Mechanical parameters extracted from the FFT spectrum provide information about breast tissue stiffness, elasticity and fluid content.

Output Format

• Per measurement: resonance, Q-factor, bandwidth, damping, stiffness, viscoelastic, transmission
• Transfer function spectrum ({f, db} array)
• AI clinical commentary (in user language)
• Right-left comparison + longitudinal trend chart

Each clinical scenario defines the expected mechanical profile of the breast tissue. The AI compares measured parameters against this profile to produce a match score.

Safety Architecture

• AI output is not a diagnosis; it supports the physician's assessment
• Experimental technology; not validated
• Does not replace mammography/ultrasound/biopsy
• Per-patient data isolation (RLS) and KVKK/GDPR compliance

The platform supports breast health clinical workflows as a screening and monitoring tool. Mechanical parameter mapping and the scenario match score provide structured, comparable data to the physician.

Safety (Human-in-the-loop)

• AI output is not a diagnosis
• Experimental technology; unvalidated
• Does not replace mammography/ultrasound/biopsy
• KVKK/GDPR-aligned sensitive-data approach

Integration Scenarios

The software-centric architecture aligns with EU carbon-reduction and ESG goals. Hardware independence brings medical consumable use close to zero.

Roadmap

The following studies establish the clinical validity and methodological foundations of vibroacoustic and mechanical tissue analysis. Our platform draws inspiration from this literature but does not replace these methods.