Search Results

Fusion Bx is intended for use by physicians for enhanced visualization of ultrasound imaging of the prostate in clinic and hospital settings. It provides 2D and 3D image visualization including review, manipulation, and analysis tools. Additional features include patient data management, multiplanar reconstruction, 3D image registration, segmentation, image annotation, and to record the biopsies were acquired during the procedure.

Fusion Bx is designed to display the 2D live video received from commercially available ultrasound machines and use this 2D video to reconstruct a 3D ultrasound image volume. The system is designed to work with clinicians' existing ultrasound machines, transrectal ultrasound (TRUS) probes, commercially available needles, needle guides/templates and needle qun combination. Additional software features include patient data management, multi-planar reconstruction, segmentation, image measurements and 3D image registration. The device will assist clinicians in planning and performing image-guided interventional procedures such as biopsies and placing instruments in the prostate for adult men with suspected prostate cancer.

Fusion Bx is comprised of a laptop-based workstation and a hardware assembly. The included hardware consists of a frame grabber, encoder converter, hardware arm (comprising of a swing arm, counterbalance, tracker and stepper), and stand. The stepper holds the ultrasound probe and measures probe position while the physician performs a normal ultrasound imaging procedure of the subject prostate. Encoders in the stepper and tracker send joint movement procedure of the computer workstation which tracks probe position and orientation. Control of imontation to the oomputer wonetation tem is done manually by the physician, just as it would the altrasound probo and all.recome eyer, by tracking the position and orientation of the be in the absento of Pacion and in a video image, the workstation is able to reconstruct and ultiasound probe while capturing the nace integor ... o the prostate and to display the live image position within the prostate.

The computer workstation is connected to the ultrasound system via a cable and hardware The computer workstation to connected to a stream 2D ultrasound image into a format that is device that converts the rour time track can be marked up with gland readable by T dolon DX. The roometrations in ages of the patient's prostate can be Segmentation of other manch in the principle that features of the prostate can be visualized consistently with a number of imaging modalities.

The physician may attach a commercially available biopsy needle guide to the TRUS probe and The privsician may uttain a sommercially at the prostate biopsy procedure. During the biopsy use the probe and blopsy noodio to personn are process visible on the Fusion Bx display. This procedure this roar time == an be marked up to record the locations where the biopsies were acquired during the procedure. As the probe and needle guide are maneuvered by the acquired duling the probe is tracked. Needle tracked. Needle trajectory is estimated by physion, the poolion and onehative to the 3D image stack. This information is provided so the physician can assess prostate abnormalities, plan and implement biopsy procedures.

Supported imaging modalities include DICOM images and real-time 2D ultrasound images. Oupportou imaging modulars received through CD, USB memory stick, or over a network DICOM-compliant miages are roomed throught be processed. This includes images that have connection. Images that are oompressed in hossless, such as JPEG2000, compression been compressed adming roosy, cash an encessed to perform volume estimations of the methous. The UD integoriation of interest (ROIs). Length measurements are also available.

Data, notes and images are stored in the patient file for later retrieval. Images are stored as Data, notes and intaged are stored in are stored in DICOM format with the same image size unchanged onginals: mago mark ups are in place to place to protect against data loss. and onemallon as the transfer where data loss is evaluated upon receipt and/or reading of data.

In summary, Fusion Bx offers the physician additional 3D information for assessing prostate n summally, I dolon DX onero the procedures. The additional image processing abliomalities, prairing and implomenting are of probe-based procedures, and leatures are generated with minimal onanges to the live prostate assessment or the prysician always had adoooo to the existing workflow by connecting to standard ultrasound equipment. This system will not prevent the clinician from using the standard ultrasound equipment.

The provided text describes the Fusion Bx device and its predicate device, the Eigen 3-D Imaging Workstation (K081093). It outlines the device's intended use and technological characteristics, and briefly mentions testing and performance data. However, the document does not contain a detailed study design with specific acceptance criteria, sample sizes, expert qualifications, or ground truth establishment methods in the format requested.

The information relevant to the acceptance criteria and performance is very limited and is primarily found in the "Testing and Performance Data" section.

Here's a summary of the available information and a breakdown of what's missing:

1. Table of Acceptance Criteria and Reported Device Performance:

Missing Information/Cannot Determine from Text:

• Detailed acceptance criteria for all features mentioned (2D/3D visualization, patient data management, multiplanar reconstruction, 3D image registration, segmentation, image annotation, biopsy recording).
• Any quantitative metrics for the "enhanced visualization" claim.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

• Sample Size: Not specified. The document states "Test phantoms incorporating simulated prostates were used to verify system performance". The number of phantoms or trials is not mentioned.
• Data Provenance: The test data came from "test phantoms incorporating simulated prostates." This implies synthetic or laboratory-generated data, not human patient data. The origin of the phantoms or where the testing was conducted (country) is not specified. It is laboratory-based testing, not clinical.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not specified. Given the use of "test phantoms," the ground truth would likely be based on the known physical properties and measurements of the phantoms themselves, rather than expert interpretation.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Not specified. Adjudication methods are typically relevant for human reader studies or when establishing ground truth from multiple expert opinions, neither of which is indicated here.

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 MRMC study was done or reported. The testing described focuses on the device's technical specifications and performance with phantoms, not its impact on human reader performance.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

• The testing described is for the device's technical performance in reconstructing images and measuring errors, which could be considered a form of standalone testing in a controlled environment (phantoms). However, it's not explicitly framed as an "algorithm-only" performance study in a clinical context. The device itself is an image processing workstation that assists physicians.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

• The ground truth was established by the known physical properties and measurements of the "test phantoms incorporating simulated prostates."

8. The sample size for the training set:

• Not specified. The document does not discuss the training of any AI/ML models. The Fusion Bx is described as an "image processing workstation system" providing visualization and analysis tools, implying traditional software engineering and image processing rather than a machine learning approach requiring a training set in the typical sense.

9. How the ground truth for the training set was established:

• Not applicable/Not specified. As there's no mention of an AI/ML training set, the establishment of ground truth for such a set is not discussed.

Ask a specific question about this device