(33 days)
The Tractus TissueMapper Image Recording System is intended to provide physicians with tools for electromagnetic tracking of instruments with respect to image data.
The TissueMapper Image Recording System is an electronic image recording and storage system. The device is an accessory to standard ultrasound systems and allows the digital recording images from those standard ultrasound devices, along with the spatial position coordinates of the recorded images. The images are recorded from the video out port of the standard ultrasound device. The images are recorded as output from the video output of the standard ultrasound imaging device. Brightness, contrast, and gamma are not adjusted by the program. lmages are recorded using Video Graphics Array (VGA) or Digital Video Interface (DVI) video output formats. Images are displayed and saved as uncompressed, 8-bit grayscale images. No loss of data occurs with this image format. The Imaging probe location is monitored and location identifiers are stored with each recorded image. Magnetic location sensors are attached to the hand-held ultrasound imaging probe via a clip.
1. A table of acceptance criteria and the reported device performance
The acceptance criteria for the Tractus TissueMapper Image Recording System are primarily related to its accuracy in locating regions of interest and its ability to identify masses in phantoms.
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Absolute location of a region of interest: Within one-half of the width of the ultrasound probe. | The device is intended to allow identification of a region of interest in a subsequent review and allow accurate placement of an ultrasound probe in another, subsequent, diagnostic ultrasound procedure. The absolute location of the probe is accurate within one-half of the width of the ultrasound probe. For the Ultrasonix L141-5W/60 60mm linear transducer, this is within 3 cm. |
| Image location relative to a previously recorded image: Within 1 mm. | Image location, relative to the previously recorded image is accurate to within 1 mm. |
| Registration accuracy: Similar to or better than the Civco predicate device. | Registration accuracy tests were performed, and the results demonstrated that the selected target location based on the registration calculation is within the same tolerance range or better than the Civco predicate device. |
| Mass identification in breast phantoms: All masses successfully identified. | System Validation Testing was performed on 2 breast phantoms with 11 masses total randomly positioned. All 11 of the masses were successfully identified. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The test set for the "mass identification in breast phantoms" criterion involved 2 breast phantoms with 11 masses total. The data provenance is internal testing conducted in-house by trained personnel in a simulated work-environment, using phantoms. This suggests it's a prospective test of the device's performance in a controlled setting. The country of origin of the data is not explicitly stated.
For the other accuracy criteria (absolute and relative image location, registration accuracy), the document mentions that "testing was conducted in-house by trained personnel in a simulated work-environment using phantoms." It does not specify a distinct "test set" sample size in terms of number of phantoms or measurements for these individual criteria, but implies these were evaluated as part of the overall performance, verification, and validation testing.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document does not explicitly state the number of experts used or their qualifications for establishing the ground truth of the test set (the phantoms). It only mentions that testing was conducted "in-house by trained personnel." Given that phantoms were used, the "ground truth" would likely be the known, engineered positions of the masses or regions within the phantoms, rather than clinical expert interpretation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
No adjudication method is described for the test set. The ground truth for the test set (phantoms) would be the precisely known physical properties and locations within the phantoms,
eliminating the need for expert adjudication.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
No multi-reader multi-case (MRMC) comparative effectiveness study was reported. This device is an image recording device with spatial tracking capabilities, not an AI-assisted diagnostic tool for human readers. Therefore, an MRMC study comparing human readers with and without AI assistance is not applicable to the device described.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a form of standalone performance testing was done. The performance data focuses on the intrinsic accuracy and functionality of the device itself (the "algorithm only" in terms of its spatial tracking and image recording). The "System Validation Testing of the Tractus TissueMapper Image Recording System was performed on 2 breast phantoms with 11 masses total randomly positioned. All 11 of the masses were successfully identified" is an example of standalone performance relative to a known ground truth. The device's ability to accurately locate a region of interest within a specified tolerance also describes its standalone performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The type of ground truth used for the performance testing was phantom-based ground truth. The document explicitly states that testing was performed "using phantoms." This implies that the locations of masses and reference points within these phantoms were precisely known and served as the absolute ground truth against which the device's measurements were compared.
8. The sample size for the training set
The document does not mention a training set nor any machine learning or AI components that would require a training set. The device is described as an "electronic image recording and storage system" and an "accessory to standard ultrasound systems" that tracks spatial position coordinates. Its functionality relies on electromagnetic tracking and digital image recording, not on learned parameters from a training dataset.
9. How the ground truth for the training set was established
As no training set is mentioned or implied by the device's described functionality,
there is no information on how its ground truth would have been established.
§ 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.