(131 days)
The SmartTarget device is intended as an accessory for image-guided interventional and diagnostic procedures involving the prostate gland, and to be used by physicians for enhanced visualization of two-dimensional (2D) transrectal ultrasound TRUS images of the prostate in clinic and hospital settings. It allows the user to segment medical images and it performs three-dimensional (3D) reconstruction of digitized TRUS video images to form a 3D TRUS volume. The SmartTarget software provides 2D and 3D image visualization features, including the ability to review images, generate multi-planar views, annotate images, and identify and record the locations of instruments inserted during the procedure.
The device is intended to be used in diagnostic and treatment procedures in a clinical setting in which a needle or other instrument is inserted into the prostate through the perineum or urethra, or instruments that are positiond externally to the prostate so that treatment can be delivered to prostate insue, or diagnostic information obtained from prostate tissue.
Example procedures include, but are not limited to: needle biopsy in which tissue samples are removed from the prostate; in situ diagnostic techniques, such as those based on optical sensing; thermal tissue ablation using radiofrequency, microwave, laser, cryotherapy, or high-intensity focused ultrasound; photodynamic therapy; irreversible electroporation; radioactive source implantation (brachy-injected drug therapies
The SmartTarget software is designed for the fusion/registration of transrectal ultrasound (TRUS) images of the prostate with three-dimensional (3D) images, such as a magnetic resonance image (MRI) or x-ray computed tomography (CT) image etcetera, during procedures for which TRUS is used to provide real-time imaging of the prostate, nearby anatomical structures, and instruments inserted into the prostate to guide instrument placement. The software supports the following tasks: computer-assisted surgical planning, allowing target regions to be defined within the prostate in a diagnostic/planning image and TRUS images; reconstruction of 3D TRUS images from multiple US video frames, captured at pre-set intervals as the TRUS probe is translated or rotated; and image fusion/registration wherein the spatial relationship between prostate in the diagnostic/planning image and TRUS images is calculated. The system software reproduces and supplements the visual information provided by real-time TRUS images, and superimposes a graphical representation of one or more target regions on to the reproduced TRUS images. The target region(s) may represent a tumor, another tissue structure visible in the diagnostic/planning image, or a location of clinical relevance (such as a region from which tissue samples are to be removed).Displayed target regions provide additional information to the TRUS image, enabling the operating clinician to direct instruments to these regions.
Here's a breakdown of the acceptance criteria and study details for the SmartTarget device, based on the provided FDA 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Measured Performance) | Reported Device Performance (SmartTarget) |
|---|---|
| Image alignment error (linear distance between image-visible target after registering ultrasound and MRI volumes) | 2.0 mm |
| Overall needle-tip placement error | 2.9 mm |
2. Sample Size and Data Provenance for Test Set
The document does not explicitly state a specific "test set" in the context of clinical images or patient data. The performance claims are based on "careful laboratory experiments" using "Test phantoms incorporating synthetic prostates."
- Sample Size: Not specified for the phantoms, but implied to be sufficient for "careful laboratory experiments."
- Data Provenance: Synthetic prostates within test phantoms. No specific country of origin or retrospective/prospective nature is applicable as it's a bench test.
3. Number of Experts and Qualifications for Ground Truth of Test Set
Not applicable. The ground truth for the bench testing was established through precise measurements within the controlled environment of laboratory experiments using phantoms. No human experts were involved in establishing the ground truth for these phantom tests.
4. Adjudication Method for Test Set
Not applicable. As the ground truth was established through physical measurements on phantoms, there was no need for expert adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No. The document describes non-clinical/bench testing. It does not mention any MRMC study comparing human readers with and without AI assistance. The SmartTarget device is an accessory for visualization and guidance, rather than an AI diagnostic tool that directly impacts human reader performance.
6. Standalone (Algorithm Only) Performance
Yes, in essence. The reported performance metrics (image alignment error and needle-tip placement error) are derived from the device's algorithmic and mechanical accuracy during bench testing. This represents the standalone performance of the system in a controlled environment, demonstrating its precision in rendering and guiding.
7. Type of Ground Truth Used
Physical measurements within phantoms/laboratory experiments. The document states: "Test phantoms incorporating synthetic prostates were used to verify the accuracy of both the image registration/fusion functionality and physical instrument placement error during guided needle insertion."
8. Sample Size for Training Set
Not specified. The document primarily focuses on the device's functionality, comparison to predicates, and non-clinical performance testing. It does not provide details about a training set for machine learning models, as the device's core functionality appears to be image processing, registration, and visualization rather than a machine learning-based diagnostic algorithm requiring extensive training data.
9. How Ground Truth for Training Set Was Established
Not applicable. As no training set information is provided, the method for establishing its ground truth is also not mentioned.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).