Search Results

The Ablatherm® Fusion device is indicated for transrectal high intensity focused ultrasound (HIFU) ablation of prostate tissue.

The device is a computer-controlled medical device intended to provide High Intensity Focused Ultrasound (also referred to as HIFU) to ablate prostate tissue. The system consists of the following main sub-assemblies: Therapy Control Module, Endorectal Probe, and consumable Ablapak. HIFU is a unique process of delivering a large amount of heat energy to a confined space in a highly controlled manner. This energy heats the tissue to ablation levels while minimizing the effect on surrounding structures. The ultrasound energy is delivered via an endorectal probe, which includes an imaging system. The ultrasound waves propagate through the rectal wall and are focused on a portion of the prostate, generating intense heat and causing the ablation of tissue within the targeted area. The process is then repeated in a stepwise fashion to destroy the targeted tissues within the prostate. The apex, sphincter and rectum are preserved while prostate tissues are ablated.

The provided text is a 510(k) summary for the Ablatherm® Fusion device, which is an add-on feature, not a standalone AI device. Therefore, a direct response to all requested fields about standalone AI performance or MRMC studies is not fully applicable. However, I will extract the relevant information regarding the performance data provided to support the 510(k) submission for the AblaFusion feature, which allows for elastic fusion between MR images/biopsies locations and ultrasound.

Here's a breakdown of the available information:

1. Table of acceptance criteria and the reported device performance:

The document primarily focuses on demonstrating substantial equivalence to predicate devices and does not explicitly list "acceptance criteria" in a quantitative performance metric format for the AblaFusion feature. Instead, it states that "Fusion accuracy assessment through bench testing" was provided. The key "performance" for the AI/fusion component is the ability to perform elastic fusion accurately.

2. Sample size used for the test set and the data provenance:

The document mentions "bench testing" for fusion accuracy assessment. It does not specify:

• The sample size of cases/images used for this bench testing.
• The data provenance (e.g., country of origin of data).
• Whether the data was retrospective or prospective.

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

The document does not mention the use of experts to establish ground truth for the fusion accuracy assessment. Bench testing typically involves comparison against known physical phantoms or simulated data with precise, known transformations, rather than expert-derived ground truth.

4. Adjudication method for the test set:

Not applicable, as expert-driven ground truth establishment is not mentioned.

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 comparative effectiveness study is mentioned for the AblaFusion feature. The submission focuses on device safety and effectiveness in the context of substantial equivalence, not on quantifying human reader improvement with AI assistance.

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

The "Fusion accuracy assessment through bench testing" could be considered a standalone assessment of the algorithmic component's performance, as it likely evaluates the accuracy of the fusion process itself. However, specific standalone metrics like sensitivity, specificity, or AUC are not provided in this summary.

7. The type of ground truth used:

For the fusion accuracy assessment (bench testing), the ground truth was likely established using physical phantoms or simulated data with known, precise transformations that the fusion algorithm was expected to replicate. The document does not explicitly state "pathology" or "outcomes data" for this specific feature's ground truth.

8. The sample size for the training set:

The document does not provide information on the sample size used for training the AblaFusion software for elastic fusion.

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

The document does not provide information on how the ground truth for the training set was established.

Ask a specific question about this device