(286 days)
The QT Ultrasound Breast Scanner-1 is for use as an ultrasonic imaging system to provide reflection-mode and transmission-mode images of a patient's breast. The device is not intended to be used as a replacement for screening mammography.
Diagnostic ultrasound imaging or fluid flow analysis of the human body as follows:
Small Organ (Breast) - Reflection, Transmission (Speed of Sound)
QT Ultrasound Breast Scanner-1 is intended for ultrasonic breast exams
The QT Ultrasound Breast Scanner-1 is an automated software-controlled ultrasonic imaging system that performs a standardized scan of the whole breast. The OT Ultrasound Breast Scanner-1 is comprised of a Patient Scanning System, Operator Console and Viewer Console.
The Patient Scanning System consists of a patient support table, scan tank, water management system, ultrasound transducer arrays and all associated image processing electronics. The scan tank is centered below a patient's breast and contains the ultrasound transducer arrays. The transducer arrays include a set of three reflection transducers that transmit pulsed ultrasound plane waves into targeted tissues using the water bath in the scan tank as coupling medium. An additional transmitter and receiver array pair collect the ultrasound energy to provide speed of sound values.
During scanning, a patient lies prone on the examination table with the breast suspended in a warm water bath maintained near skin temperature. Images are automatically acquired on a pendant breast positioned with the nipple as a point of reference. The transducer arrays rotate about a vertical axis to circle the breast in the coronal plane. The array is then translated vertically and the scanning process is repeated until the entire breast is scanned, allowing B-scan images to be constructively combined into tomographic, speed of sound and reflection ultrasound images.
The QT Ultrasound Breast Scanner-1 outputs the images to the QTviewer which allows the images to be stored until they are reviewed on a Viewer Console. Coronal, axial and sagittal images are generated for review by the radiologist. Speed of sound images may be queried by the Probe and Region of Interest (ROI) tools provided in the Viewer Console. These tools provide speed of sound values in meters/sec. to aid in diagnostic evaluation of the breast.
Here's a breakdown of the acceptance criteria and study details for the QT Ultrasound Breast Scanner-1, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't explicitly state "acceptance criteria" in a numerical or pass/fail format per se for performance. Instead, it describes comparative evaluation results against predicate devices (X-ray Mammography and Handheld Ultrasound) to demonstrate "clinical usefulness" and "equivalent or better" image quality. The criteria effectively revolve around demonstrating that the QT Ultrasound Breast Scanner-1 images provide diagnostic information comparable to or superior to existing modalities for visualizing breast anatomy.
Since a numerical acceptance criterion table with specific targets isn't present, I'll describe the performance findings based on the Visual Grading Assessment (VGA) studies conducted.
| Acceptance Criteria (Implied/Demonstrative) | Reported Device Performance (QT Ultrasound Breast Scanner-1) |
|---|---|
| Clinical Usefulness for Visualizing Breast Anatomy (vs. XRM) | For QT Ultrasound vs. XRM: The analysis demonstrated that the QT Ultrasound Breast Scanner-1 produces clinically-useful depictions of patient anatomy. Readers scored the image quality on the QT Ultrasound images as equivalent to or better than on XRM for each feature in more than 90% of breasts. |
| Image Quality for Breast Anatomy Visualization (vs. HHUS) | For QT Ultrasound vs. HHUS: Except for epidermis and pectoralis muscle, readers scored the image quality on the QT Scan as equivalent or better than HHUS on each feature in more than 80% of breasts. Readers scored the image quality of epidermis and muscle as better on the QT Scan in more than 70% of breasts. The findings suggest that QT images are at least equivalent or better in defining the anatomical components of the breast than HHUS. |
| Safety - Acoustic Output | Meets all Track 1 acoustic output requirements. Examples: Max. Mechanical Index (MI) of 0.145-1.186 (vs. 1.9 limit), Max. ISPTA (mW/cm²) of 0.79-1.63 (vs. 94 mW/cm² limit). All reported as "Pass". |
| Safety - Electrical, EMC, Usability, Biocompatibility, Cleaning, Software | All applicable testing conducted, requirements met, and no new issues of safety or effectiveness compared to the predicate device were raised. |
| Performance - System Verification (Measurement Range/Accuracy, Spatial/Contrast Resolution, SoS Uniformity/Accuracy) | System verification testing conducted to ensure design requirements were met. All requirements were met and no new issues of safety or effectiveness compared to the predicate device were raised. |
2. Sample Sizes Used for the Test Set and Data Provenance
- Test Set (VGA Review with QT Ultrasound vs. X-ray Mammography - XRM):
- Sample Size: 22 cases from 20 subjects.
- Data Provenance: Not explicitly stated, but given the context of FDA submission, it refers to clinical data used for evaluation. The "QT Library cases" mention suggests historical/retrospective data. No country of origin is specified.
- Test Set (VGA Review with QT Ultrasound vs. HandHeld Ultrasound - HHUS):
- Sample Size: 17 cases.
- Data Provenance: Not explicitly stated, but also likely retrospective/historical "QT Library cases." No country of origin is specified.
- Representative Clinical Cases (No Grading):
- Sample Size: 16 clinical cases.
- Data Provenance: Not explicitly stated, but implied to be from the clinical setting. "Historical QT Library cases" are mentioned for the VGA studies, suggesting a retrospective collection.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
The document describes "readers" who performed the image quality assessment, not necessarily those establishing "ground truth" for disease state.
- VGA Review with QT Ultrasound vs. XRM:
- Number of Readers: 4
- Qualifications: "independent board-certified radiology readers."
- VGA Review with QT Ultrasound vs. HHUS:
- Number of Readers: 5
- Qualifications: "independent board-certified radiology readers."
- Representative Clinical Cases:
- Number of Reviewers: 1 (Dr. Elaine Iuanow, M.D.)
- Qualifications: "board certified radiologist, Dr. Elaine Iuanow, M.D. and Chief Medical Officer." This review was for demonstration, not graded assessment.
4. Adjudication Method for the Test Set
The studies described are Visual Grading Assessments (VGAs).
- The document states, "The four readers independently scored the image quality" and similarly for the HHUS comparison, "The five readers independently scored the image quality."
- Statistical analysis was then performed on these independent scores (e.g., median image quality score, proportion of breasts rated better/equivalent).
- There is no mention of an adjudication method (e.g., 2+1, 3+1 consensus) for establishing a single 'ground truth' score for image quality from the readers. The analysis appears to aggregate or summarize the independent reader scores.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size
- Type of Study: The VGA studies described are MRMC studies focused on image quality comparison, not necessarily diagnostic accuracy or human reader improvement with AI assistance. They compare the inherent image quality of QT Ultrasound to XRM and HHUS.
- Effect Size of Human Readers Improvement with AI vs. Without AI Assistance:
- Not Applicable. This device is an imaging system (QT Ultrasound Breast Scanner-1) generating images, not an AI interpretative software providing assistance to human readers. Therefore, the study design does not involve comparing human reader performance with and without AI assistance from this device. The focus is on the device's image quality compared to other imaging modalities.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- This is an imaging device, not an algorithm for diagnosis. The "performance" in this context is primarily related to image quality and safety/technical specifications.
- The document describes non-clinical testing which can be considered "standalone" in the sense that it evaluates the device's technical performance (e.g., electrical safety, acoustic output, software verification, system verification like spatial resolution, contrast resolution, speed of sound uniformity). These tests are not "human-in-the-loop" studies but validate the device's operational characteristics.
7. The Type of Ground Truth Used
- For Image Quality Assessment (VGA studies): The "ground truth" for image quality was based on the subjective assessment of board-certified radiologists. They scored the visibility of various anatomical features using an ordinal scale (1=Excellent to 5=Poor).
- For Lesion Type in Representative Clinical Cases (demonstrative, not graded):
- Solid Benign and Solid Malignant Lesions: Ground truth was determined by histology.
- Cyst Lesions: Ground truth was determined by appearance on handheld ultrasound (HHUS).
- Breast density was determined by visual inspection on the QT Ultrasound images.
- Clinical history, previous biopsies, and other imaging studies were also used to confirm identification, size, and location of lesions (a form of clinical ground truth/consensus).
8. The Sample Size for the Training Set
- The document does not provide information on the sample size of a training set. This is expected as the submission is for a medical imaging device (hardware and software for image acquisition), not a specific AI diagnostic algorithm that requires a "training set" in the machine learning sense for its primary function. The images generated by the scanner are for human interpretation.
9. How the Ground Truth for the Training Set Was Established
- Not Applicable. As no training set data for an AI algorithm (in the context of image interpretation) is mentioned, the method for establishing its ground truth is not provided. The development and verification of the device's imaging capabilities were performed through engineering design and standard medical device verification and validation processes (e.g., non-clinical testing listed in Table 2-2).
§ 892.1560 Ultrasonic pulsed echo imaging system.
(a)
Identification. An ultrasonic pulsed echo imaging system is a device intended to project a pulsed sound beam into body tissue to determine the depth or location of the tissue interfaces and to measure the duration of an acoustic pulse from the transmitter to the tissue interface and back to the receiver. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). A biopsy needle guide kit intended for use with an ultrasonic pulsed echo imaging system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.