Search Results

The TULSA-PRO ® is indicated for transurethral ultrasound ablation (TULSA) of prostate tissue.

Not Found

I apologize, but the provided text from the FDA 510(k) clearance letter for the "Tulsa Pro System (Pad-105)" does not contain any information regarding acceptance criteria, device performance studies, or the methodologies used to prove the device meets acceptance criteria.

The letter is a regulatory document confirming substantial equivalence of the device to legally marketed predicate devices, allowing it to be marketed. It discusses:

• The FDA's determination of substantial equivalence.
• Regulatory requirements and general controls (annual registration, listing, GMP, labeling, etc.).
• Links to guidance documents for changes requiring new premarket notifications.
• Information about the Quality System (QS) regulation.
• Advice on adverse event reporting and other regulatory information.
• The product's indications for use.

To answer your detailed questions about acceptance criteria and study design, you would typically need to refer to:

• The actual 510(k) submission itself: This document would contain the detailed study protocols, results, and acceptance criteria presented to the FDA.
• Clinical trial publications: If the device underwent clinical trials, the scientific papers would provide this information.
• The device's Instruction for Use (IFU) or technical manual: Some performance claims and supporting data might be summarized here.

Without that specific documentation, I cannot create the table or provide the detailed answers you requested.

Therefore, I cannot fulfill your request based on the provided text.

Ask a specific question about this device

The TULSA-PRO is indicated for transurethral ultrasound ablation (TULSA) of prostate tissue.

The TULSA-PRO system combines real-time Magnetic Resonance (MR) imaging and MR thermometry with transurethral directional ultrasound and closed-loop process control software to deliver precise thermal ablation of physician prescribed prostate tissue. The system consists of both hardware and software components. The subject device includes a modification to the device software that is described below. The hardware components and treatment workflow description are identical to the predicate device.

The physician inserts two catheters, one transurethral and another transrectal, into the patient before he is moved into the MR bore. The transurethral catheter consists of an Ultrasound Applicator (UA) which delivers energy from within the prostate tissue, heating it to thermal coagulation. The transrectal catheter is an Endorectal Cooling Device (ECD) which does not emit any energy and cools the rectal wall adjacent to the prostate. Both catheters have fluid flowing inside throughout the treatment.

The physician uses the TULSA-PRO console to robotically position the Ultrasound Applicator in the prostate and plan the treatment by contouring the prescribed tissue intended for ablation on real-time high-resolution cross-sectional MR images of the prostate. These features provide the physician with the ability and the control to customize the treatment plan to minimize thermal impact to critical structures surrounding the prostate including the external urethral sphincter, rectum and neurovascular bundles.

The treatment begins based upon the physician starting the thermal ablation in the software. The TULSA-PRO closed-loop process control software reads real-time MR thermometry measurements and adjusts automatically and dynamically the frequency and power of ultrasound provided by each ultrasound transducer, and rotation rate of the Ultrasound Applicator, to deliver precise ablation of the prescribed prostate tissue defined by the physician in the treatment plan.

Software Modification: An optional feature called Thermal Boost is available in the software during the treatment delivery phase of the treatment workflow. The Thermal Boost feature is useful when the prostate is large and the treatment radius is >15mm for any active ultrasound element. In such cases, heat may not reach the prostate boundary due to prostate size or if tissue perfusion is preventing the heat from reaching the target boundary. The physician has a choice to use the Thermal Boost feature on the corresponding ultrasound transducer. When this feature is turned on, the treatment boundary temperature can reach ≤63 degrees or ≤65 degrees depending on the treatment radius. Thermal Boost does not change the ablation plan prescribed by the physician. Whether Thermal Boost is turned on or off, the tissue heating and monitoring principle of operation of the TDC software do not change.

Following completion of the ablation process, the two catheters are removed from the natural orifices of the patient.

The provided text describes modifications to the TULSA-PRO System, specifically a software update introducing an optional feature called "Thermal Boost." The document is a 510(k) summary, aimed at demonstrating substantial equivalence to a previously cleared predicate device rather than presenting a novel device that requires a full, de-novo clinical trial with extensive acceptance criteria.

Therefore, the acceptance criteria and study detailed here are focused on demonstrating that the modification (Thermal Boost feature) does not adversely impact the safety and effectiveness of the existing, cleared TULSA-PRO system. It's not a study to establish the device's efficacy from scratch, but rather to show that the new feature maintains the established safety and performance profile.

Here's an analysis based on the provided text:

Key Takeaway: The "acceptance criteria" for this 510(k) submission are implicitly about demonstrating that the software modification (Thermal Boost) does not introduce new safety or effectiveness concerns compared to the predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

Based on the document, the "acceptance criteria" are not explicitly defined as pass/fail thresholds for specific metrics in a table format for the Thermal Boost feature itself in a clinical comparative study. Instead, the focus is on showing that the modified device's performance, particularly in terms of safety and technical metrics, is consistent with or better than the predicate device.

The document highlights the following evaluation points for the Thermal Boost feature:

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size for Clinical Performance (Test Set): 71 adult male patients.
• Data Provenance: Clinical performance data were collected from patients presumably treated with the commercially available TULSA-PRO system with Thermal Boost applied. The location of the clinical study is not explicitly stated, but the company is based in Canada. Given it's a 510(k) for a known device, it's likely a prospective collection of data on patients treated with the modified system in a clinical setting. It is not explicitly stated if it was retrospective or prospective, but the phrasing "Clinical performance data were collected from 71 adult male patients treated..." implies prospective data collection tailored to assess the new feature's impact.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

The document does not specify the number of experts or their qualifications involved in establishing "ground truth" for the clinical test set concerning the Thermal Boost feature. The assessment appears to rely on:

• Treating Physician's Determination: The area of prostate requiring Thermal Boost was determined by the treating physician.
• Adverse Event Assessment: Adverse events were assessed by the treating physician for a six-month period post-treatment.
• Technical Performance: Evaluation was via comparison of physician-defined ablation plan to temperature maps measured during ablation delivery by the software. This implies the software's ability to monitor and report accurate temperature data serves as a form of "ground truth" for real-time ablation monitoring, validated by physical phantom testing.
• Usability Questionnaire: Administered to physicians who used the system.

Given the nature of the submission (510(k) for a software modification to an already cleared device), the "ground truth" is primarily whether the software controls maintained their accuracy and if clinical outcomes (adverse events, usability) remained comparable to the cleared predicate, as reported by the treating physicians and the device's own monitoring systems.

4. Adjudication Method for the Test Set

The document does not explicitly state an adjudication method (e.g., 2+1, 3+1 consensus) for the clinical data. Adverse events were assessed by the treating physician. Technical performance was automatically evaluated by the system comparing its plan to measured temperature maps. Usability was through a questionnaire. This implies no external, multi-expert adjudication process beyond the primary treating physicians' reports and the device's internal technical metrics.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No, an MRMC comparative effectiveness study was not explicitly stated or implied for this submission.
  • This type of study is more common for AI-driven diagnostic or interpretative tools where human reader performance (with vs. without AI) is a direct measure of the AI's clinical utility.
  • The TULSA-PRO System is an ablation device with a software control modification. Its "effectiveness" is primarily a measure of its ability to ablate tissue safely and accurately, not an interpretative aid. The efficacy of the TULSA-PRO system itself was established in previous clearances (K191200 onward). This 510(k) focuses on the safety and performance impact of a new control feature.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study was Done

• Yes, in a non-clinical context.
  • "Technical performance of the software with Thermal Boost enabled was compared to the predicate software during simulated prostate ablation in a tissue-mimicking gel phantom."
  • This phantom study effectively tested the algorithm's performance in a standalone, controlled environment, measuring temperature profiles and confirming its targeting statistics. This demonstrates the algorithm's behavior independent of human intervention, although the "Thermal Boost" is a user-enabled feature.

7. The Type of Ground Truth Used

The "ground truth" depends on the evaluation aspect:

• Safety: The ground truth for safety was based on clinically reported adverse events identified by the treating physicians and classified using MedDRA and Clavien-Dindo.
• Technical Performance: The ground truth was the real-time MR thermometry measurements during ablation delivery, compared against the physician-defined ablation plan. This implies the MR thermometry is considered the benchmark for actual temperature distribution, while the physician's plan is the target.
• Usability: The ground truth for usability was the direct subjective feedback from physicians via a questionnaire.
• Non-clinical (Software V&V): For the phantom study, the ground truth was MR thermometry measurements within the tissue-mimicking gel.

8. The Sample Size for the Training Set

The document does not specify a training set sample size. This is because the submission describes a software modification for an existing device, not a de novo AI/ML model that requires a new, explicit training phase for this specific submission. The "Thermal Boost" feature appears to be a modification to the control algorithm of an existing system, likely developed based on engineering principles and potentially internal performance data, rather than a separate, newly trained AI model.

9. How the Ground Truth for the Training Set Was Established

As no specific "training set" for a new AI/ML model linked to this specific software feature is mentioned, the method for establishing its ground truth is not detailed. The software verification and validation activities are described as being performed in accordance with FDA guidance, comparing the modified software's performance to the predicate device. This implies that the "ground truth" for verifying the software's behavior would stem from its expected performance parameters, likely established during the original device development (K191200) and confirmed during the modification through non-clinical testing.

Ask a specific question about this device

The TULSA-PRO® is indicated for transurethral ultrasound ablation (TULSA) of prostate tissue.

The TULSA-PRO system combines real-time Magnetic Resonance (MR) imaging and MR thermometry with transurethral directional ultrasound and closed-loop process control software to deliver precise thermal ablation of physician prescribed prostate tissue. The system consists of both hardware and software components. The transurethral ultrasound ablation (TULSA) treatment is delivered completely within the MR bore. A real-time MRI interface is used by closed-loop features of the TULSA-PRO system: real-time MRI prostate temperature measurements are processed by TULSA-PRO software which communicates with TULSA-PRO hardware, thereby controlling frequency, power and rotation rate of ultrasound to ablate physician prescribed prostate tissue with a high degree of precision. The physician inserts two catheters, one transurethral and another transrectal, into the patient before he is moved into the MR bore. The transurethral catheter consists of an Ultrasound Applicator (UA) which delivers energy from within the prostate tissue, heating it to thermal coagulation. The transrectal catheter is an Endorectal Cooling Device (ECD) which does not emit any energy and cools the rectal wall adjacent to the prostate. The modified ECD component provides users with a rectal bubble removing feature, and is manufactured using a 3-D printed technology. Both catheters have fluid flowing inside throughout the treatment to thermally protect the urethra and rectum, in order to minimize the potential of any thermal damage to either the urinary or rectal pathways. The physician uses the TULSA-PRO console that was cleared under K191200 to robotically position the Ultrasound Applicator in the prostate and plan the treatment by contouring the prescribed tissue on real-time high-resolution crosssectional MR images of the prostate. These cleared features provide the physician with the ability and the control to customize the treatment plan to minimize thermal impact to critical structures surrounding the prostate including the external urethral sphincter, rectum and neurovascular bundles. The treatment begins based upon the physician's instructions by enabling the software to initiate thermal ablation. The TULSA-PRO closed-loop process control software reads real-time MR thermometry measurements and adjusts automatically and dynamically the frequency, power and rotation rate of ultrasound provided by each UA transducer, to deliver precise ablation of the prescribed prostate tissue. The software controls automated. continuous and robotic rotation of the transurethral UA by 360 degrees in sync with the process-controlled delivery of thermal heating to all the required regions of the prostate. Following completion of the ablation process, the two catheters are removed from the natural orifices of the patients.

The provided text is an FDA 510(k) summary for the TULSA-PRO® System, which is a medical device for prostate tissue ablation. The document primarily focuses on demonstrating substantial equivalence to a previously cleared predicate device, rather than providing the detailed acceptance criteria and study results typically found for a novel AI/ML-based medical device.

Therefore, many of the requested details regarding acceptance criteria, study design for proving performance (especially for AI/ML models), expert ground truth establishment, MRMC studies, and sample sizes for training/test sets are not present in the provided document, as this submission is for a modification to an existing device.

The submission states: "Clinical testing was not required to demonstrate the substantial equivalence to the predicate devices. Non-clinical bench testing was sufficient to establish the substantial equivalence of the modifications." This explicitly indicates that no clinical study (which would typically involve test sets, ground truth establishment, expert readers, etc.) was performed for this specific submission to prove device performance in a clinical setting. The "performance" being assessed here is the equivalence of the modified (and slightly different manufacturing process for the ECD component) to the previously cleared version.

However, based on the information available in the document, here's what can be inferred or stated:

1. A table of acceptance criteria and the reported device performance:

Since no clinical study data is presented, acceptance criteria for performance metrics (like sensitivity, specificity, accuracy for an AI model) are not relevant or provided. The "performance" here is demonstrating that the modified device is as safe and effective as the predicate device through bench testing.

Regarding points 2-9:

These points are primarily relevant for submissions involving new AI/ML device performance claims or significant changes requiring clinical validation/testing. As stated in the document, "Clinical testing was not required to demonstrate the substantial equivalence to the predicate devices. Non-clinical bench testing was sufficient to establish the substantial equivalence of the modifications." Therefore, the following information is not applicable or not provided in this specific 510(k) summary:

2. Sample sized used for the test set and the data provenance: Not applicable, as no clinical test set for AI performance was used. The testing was bench-based.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth establishment for image interpretation by experts is not described, as there was no clinical study.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.
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: Not applicable. This is not an AI-assisted diagnostic device submission requiring such a study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is not a standalone AI diagnostic algorithm. The TULSA-PRO system has software with closed-loop process control, but this submission pertains to mechanical/material modifications to a component (ECD) and expanded MR scanner compatibility, not a new or significantly altered AI component requiring standalone validation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable, as detailed clinical performance validation with ground truth is not the subject of this 510(k). The ground truth for their bench testing would be engineering measurements and material specifications.
8. The sample size for the training set: Not applicable. This document does not describe the development or training of a new AI model. The software exists and controls the ablation process, but no new AI training is discussed.
9. How the ground truth for the training set was established: Not applicable.

In summary: The provided document is a 510(k) submission for demonstrating substantial equivalence of a modified version of an already cleared device, primarily through non-clinical bench testing of hardware/material changes (specifically to the Endorectal Cooling Device and expanded MR compatibility). It does not contain the detailed clinical study data, AI model performance metrics, or ground truth establishment processes that would be typically found for a novel AI/ML device or a significant software upgrade requiring clinical validation. The "study" mentioned here refers to the bench testing conducted to ensure the modified device retains its safety and effectiveness compared to the predicate.

Ask a specific question about this device

The TULSA-PRO® is indicated for transurethral ultrasound ablation (TULSA) of prostate tissue.

The TULSA-PRO® system combines real-time Magnetic Resonance (MR) imaging and MR thermometry with transurethral directional ultrasound and closed-loop process control software to deliver precise thermal ablation of a customized volume of physician prescribed prostate tissue. The system consists of both hardware and software components.

Transurethral ultrasound ablation (TULSA) treatment ablates prostate tissue using inbore real-time MRI treatment planning, monitoring, visualization, and active temperature feedback control. The closed-loop features of the TULSA-PRO® software use a real-time MRI interface to process MRI prostate temperature measurements, and communicate with the TULSA-PRO® hardware, thereby controlling frequency, power and rotation rate of ultrasound to ablate physician prescribed prostate tissue with a high degree of precision.

The physician inserts two catheters, one transurethral and another transrectal, into the patient before he is moved into the MR bore. The transurethral catheter consists of an Ultrasound Applicator (UA) which delivers energy from the urethra outwards into the prostate tissue, heating it to thermal coagulation. The transrectal catheter is an Endorectal Cooling Device (ECD) which does not emit any energy and cools the rectal wall adjacent to the prostate. Both catheters have fluid flowing inside throughout the treatment to thermally protect the urethra and rectum, in order to minimize the potential of any thermal damage to either the urinary or rectal pathways. The physician uses the TULSA-PRO® console to robotically position the UA in the prostate and plan the treatment by contouring the prescribed tissue on real time high-resolution crosssectional MR images of the prostate. These features provide the physician with the ability and the control to customize the treatment plan to minimize thermal impact to critical structures surrounding the prostate including the external urethral sphincter, rectum and neurovascular bundles. The treatment begins based upon the physician's instructions by enabling the software to initiate thermal ablation. The TULSA-PRO® closed-loop process control software reads real-time MR thermometry measurements and adjusts automatically and dynamically the frequency, power and rotation rate of ultrasound provided by each UA transducer, to deliver precise ablation of the prescribed prostate tissue. The software controls automated, continuous and robotic rotation of the transurethral UA by 360 degrees in sync with the process-controlled delivery of thermal heating to all the intended regions of the prostate. Following completion of the ablation process, the two catheters are removed from the natural orifices of the patients.

This document is a 510(k) Premarket Notification from the FDA regarding the TULSA-PRO System. It primarily addresses the substantial equivalence of an updated version of the TULSA-PRO System (K202286) to a previously cleared version (K191200).

The provided text does not contain acceptance criteria for device performance or a study demonstrating the device meets those criteria in the typical sense of a clinical trial or performance study with defined endpoints/metrics.

Instead, this 510(k) submission is a "Special 510(k)" application, which means the manufacturer is asserting that the changes made to the device do not affect its safety or effectiveness and that the modified device remains substantially equivalent to the cleared predicate device.

Therefore, many of the requested details about acceptance criteria, sample sizes for test sets, expert ground truth, MRMC studies, and standalone performance studies are not present in this document. The focus here is on demonstrating that the modifications made do not necessitate new clinical data or performance studies.

Based on the document, here's what can be extracted and what cannot:

1. A table of acceptance criteria and the reported device performance:

• Not provided in the document. The document focuses on showing the modified device is "the same" or has minor, non-impactful changes compared to the predicate. There are no performance acceptance criteria explicitly stated for the device's function (e.g., ablation efficacy, precision of tissue removal) in this submission.

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

• Not applicable/Not mentioned. This submission is not based on a new test set of clinical data for performance evaluation. It relies on non-clinical testing (bench performance, software validation, EMC, packaging) demonstrating that the minor changes (e.g., software version upgrade, packaging modifications) do not alter the established safety and effectiveness of the predicate device.
• The document explicitly states: "The modifications of TULSA-PRO® System does not require additional clinical data to demonstrate substantial equivalence."

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

• Not applicable/Not mentioned. No new clinical test set with human-established ground truth was used for this Special 510(k) submission.

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

• Not applicable/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:

• Not applicable/Not mentioned. This device (TULSA-PRO System) is an ultrasound ablation system, not an AI-assisted diagnostic device typically evaluated with MRMC studies.

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

• Not applicable/Not mentioned in the context of clinical performance. The "algorithm" here is the closed-loop process control software for ablation. Its performance is validated through bench testing and system validation in a simulated-use environment, not typically as an "algorithm-only" clinical performance study.

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

• Not applicable for clinical performance. For the non-clinical testing mentioned:
  • Bench Performance Testing: Verification against "design specifications" (internal standards).
  • Software Information: Validation in accordance with FDA guidance for software in medical devices.
  • EMC/Packaging/Biocompatibility/Sterilization/Electrical Safety: Conformance to recognized standards and previous testing from K191200.
  • Animal Studies: Explicitly stated that this submission "does not rely on the assessment of animal data."

8. The sample size for the training set:

• Not applicable/Not mentioned. There's no indication that a machine learning or AI model, requiring a "training set," was developed or updated as part of this submission. The "software" refers to control and processing software, not typically a learning algorithm.

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

• Not applicable/Not mentioned.

Summary of what the document DOES state regarding "performance" and "meeting criteria":

The "acceptance criteria" here are effectively demonstrating substantial equivalence to the predicate device (K191200) despite minor modifications. The "study" proving this is a series of non-clinical tests and comparisons, rather than new clinical trials.

The document claims the device "meets the acceptance criteria" in the following ways:

• Bench Performance testing: "All design specifications for components of TULSA-PRO® system are verified either by design or by test and are traceable to a verification report or other document." Also, "All the performance testing performed on the subject device remains the same when compared with the cleared device K191200." The system as a whole is "validated in a simulated-use environment."
• Software Information: "Software validation activities were performed in accordance with the FDA Guidance..." (for "TDC software version has been upgraded from V2.8 to V2.9").
• Electromagnetic Compatibility: "Changes to PSIB have been tested to conform with Electromagnetic test requirements by Nationally Recognized Testing Laboratory."
• Packaging: "The packaging meets the transit performance test requirements of ASTM D4169."
• Biocompatibility, Sterilization, Electrical Safety: "No change from K191200," implying they still meet prior criteria.

In essence, the "study" proving the device meets the (implied) acceptance criteria is the demonstration that the modifications are minor and do not alter the established safety and effectiveness of the predicate device, confirmed through documented non-clinical testing and adherence to relevant standards.

Ask a specific question about this device

The TULSA-PRO System is indicated for transurethral ultrasound ablation (TULSA) of prostate tissue.

The TULSA-PRO system combines real-time Magnetic Resonance (MR) imaging and MR thermometry with transurethral directional ultrasound and closed-loop process control software to deliver precise thermal ablation of a customized volume of physician prescribed prostate tissue. The system consists of both hardware and software components.

Transurethral ultrasound ablation (TULSA) treatment ablates prostate tissue using in-bore real-time MRI treatment planning, monitoring, visualization, and active temperature feedback control. The closed-loop features of the TULSA-PRO software use a real-time MRI interface to process MRI prostate temperature measurements, and communicate with the TULSA-PRO hardware, thereby controlling frequency, power and rotation rate of ultrasound to ablate physician prescribed prostate tissue with a high degree of precision.

The physician inserts two catheters, one transurethral and another transrectal, into the patient before he is moved into the MR bore. The transurethral catheter consists of an Ultrasound Applicator (UA) which delivers energy from the urethra outwards into the prostate tissue, heating it to thermal coagulation. The transrectal catheter is an Endorectal Cooling Device (ECD) which does not emit any energy, and cools the rectal wall adjacent to the prostate. Both catheters have fluid flowing inside throughout the treatment to thermally protect the urethra and rectum, in order to minimize the potential of any thermal damage to either the urinary or rectal pathways. The physician uses the TULSA-PRO console to robotically position the UA in the prostate and plan the treatment by contouring the prescribed tissue on realtime high-resolution cross-sectional MR images of the prostate. These features provide the physician with the ability and the control to customize the treatment plan to minimize thermal impact to critical structures surrounding the prostate including the external urethral sphincter, rectum and neurovascular bundles. The treatment begins based upon the physician's instructions by enabling the software to initiate thermal ablation. The TULSA-PRO closed-loop process control software reads real-time MR thermometry measurements and adjusts automatically and dynamically the frequency, power and rotation rate of ultrasound provided by each UA transducer, to deliver precise ablation of the prescribed prostate tissue. The software controls automated, continuous and robotic rotation of the transurethral UA by 360 degrees in sync with the process controlled delivery of thermal heating to all the intended regions of the prostate. Following completion of the ablation process, the two catheters are removed from the natural orifices of the patients.

The provided document, K191200, is a 510(k) Premarket Notification for the TULSA-PRO System. It details the device's intended use, non-clinical and clinical testing, and its substantial equivalence to a predicate device.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly present a table of "acceptance criteria" with pass/fail metrics for a specific algorithm's performance in the way one might see for an AI/ML device. Instead, the "acceptance criteria" are implied by the primary and secondary endpoints of the clinical study, which demonstrate the safety and effectiveness of the device (a high-intensity ultrasound system for prostate tissue ablation), not specifically an AI algorithm's performance. The "reported device performance" refers to the outcomes of the clinical trial for the TULSA-PRO System.

• Mean (95% confidence interval) PSA reduction to nadir was 92% (90 – 94%).
• Median (IQR) PSA reduction was 95% (91 – 98%) to nadir of 0.34 (0.12 – 0.56) ng/ml.
• Median (IQR) PSA decreased from 6.26 (4.65 - 7.95) ng/ml to 0.53 (0.30 - 1.19) ng/ml at 1 month, remaining stable to 0.53 (0.28 – 1.25) ng/ml at 12 months. |
  | Primary Safety Endpoint: | |
  | - Frequency and severity of all adverse events graded according to CTCAE. | - No rectal injury or fistula.
• No severe urinary incontinence or erectile dysfunction.
• No Grade 4 or higher AE related or possibly related to TULSA-PRO.
• 12 attributable Grade 3 AEs in 9 patients (7.8%), all resolved by 12 months.
• Majority of attributable events were acute Grade 1 and 2, resolving within 3 months of treatment, mostly genitourinary.
• Urethral stenosis in 3 subjects (one Grade 2 and two Grade 3, all resolved).
• Urinary tract infections common, resolved with antibiotics.
• Urinary retention in 9 attributable Grade 2 events (7%) and 2 attributable Grade 3 events (1.7%), all resolved with medication/catheterization up to 3 months.
• Attributable gastrointestinal AEs limited to acute Grade 1 and 7 acute Grade 2 events: pain/discomfort (3.5%), nausea (1.7%), constipation (0.9%), all resolved within one month.
• Erectile dysfunction: 49 (42.6%) assessed as attributable, with 41 (35.7%) ongoing at 12 months (12.2% mild, 23.5% moderate, 0% severe).
• Urinary incontinence: 26 (22.6%) assessed as attributable, with 12 (10.4%) ongoing at 12 months (7.8% mild, 2.6% moderate, 0% severe).
• Ongoing attributable moderate (Grade 2) AEs at 12 months included ejaculatory disorder (2.6%), weak urinary stream (2.6%), urinary tract infection (1.7%), and disrupted urethra (0.9%). |
  | Secondary Endpoints: | |
  | - Prostate volume reduction. | - Median (IQR) perfused prostate volume decreased 91.4% from 37.3 (27.2 – 47.6) cc pre-treatment to 2.8 (1.7 – 4.7) cc at 12 months on MRI.
• Mean and 95% CI of prostate volume reduction was 89% (87 – 91%). |
  | - Proportion of patients with negative biopsy. | - 72 of 115 (63%) patients had a complete histological response with no evidence of any cancer (95% CI: 54 – 71%) using an intent-to-treat analysis (4 patients who refused follow-up biopsy considered "positive"). |
  | - Patient reported changes in quality of life (erectile, urinary and bowel function). | (Specific details on patient reported QoL changes beyond AE reporting are not fully detailed in the provided summary, but AEs related to these functions are reported under safety). |
  | - Evaluation of multiparametric prostate MRI. | - Median of 97.6% of the prescribed prostate volume was heated to an ablative thermal dose with spatial ablation precision of ±1.4 mm measured on MRI thermometry during treatment.
• Central radiology core lab used for prostate volume measurements. |

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

• Sample Size (Test Set): 115 patients.
• Data Provenance:
  • Country of Origin: United States, Canada, and Europe.
  • Retrospective or Prospective: Prospective clinical trials (specifically, the TACT Pivotal Study).

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

The document states that a "central radiology core lab" was employed to measure prostate volume prior to and after TULSA treatment. This suggests expert involvement in evaluating imaging data. However, the exact number of experts and their specific qualifications (e.g., years of experience) are not specified in this summary. The mention of "central radiology core lab" implies qualified radiologists performing these assessments to ensure consistent methodology and reduce inter-observer variability.

For the adverse events (AEs), they were "evaluated according to the Common Terminology Criteria for Adverse Events (CTCAE) developed by the NCI" and "standardized to medical terminology using the Medical Dictionary for Regulatory Activities (MedDRA)." This process involves trained medical professionals, but not specifically "experts" establishing a ground truth in the same manner as diagnostic imaging interpretation.

For prostate biopsy, the ground truth for "complete histological response with no evidence of any cancer" would be established by pathologists. The number of pathologists and their specific qualifications are not detailed.

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

The document notes that the "central radiology core lab" provided consistent methodology and reduced inter-observer variability for prostate volume measurements. While this implies a standardized process, no specific adjudication method like "2+1" or "3+1" is explicitly mentioned for any part of the test set (e.g., imaging interpretation or biopsy slides). Adverse events were "evaluated" and "standardized" but not described as adjudicated by multiple experts.

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 was conducted or reported. The TULSA-PRO System itself is a therapeutic device that combines MR imaging, MR thermometry, and closed-loop process control software for tissue ablation. It is not an AI assistance tool for human readers interpreting images, but rather a system that uses real-time MR data for treatment delivery. Therefore, there is no mention of human readers improving with or without AI assistance as part of this submission.

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

The "software" component of the TULSA-PRO System is described as "closed-loop process control software" that "uses a real-time MRI interface to process MRI prostate temperature measurements, and communicate with the TULSA-PRO hardware, thereby controlling frequency, power and rotation rate of ultrasound to ablate physician prescribed prostate tissue." This software is integral to the device's function, performing automated adjustments.

While the device has software that acts in a "standalone" fashion to control the ablation based on real-time MRI feedback, it's not a standalone diagnostic algorithm being evaluated for its interpretive performance. Instead, it's a control system part of a larger therapeutic device. Therefore, a "standalone (algorithm only without human-in-the-loop performance)" study in the context of diagnostic AI performance (e.g., sensitivity/specificity) was not performed or described in this document. The entire system's performance (including the software's control function) is validated through the clinical study outcomes.

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

The ground truth for evaluating the effectiveness of the TULSA-PRO System was established using a combination of methods:

• Outcomes Data:
  • Prostate Volume Reduction: Measured by a central radiology core lab on MRI images (implies expert interpretation).
  • PSA Reduction: Biochemical marker, directly measured.
  • Adverse Events: Documented clinical outcomes, graded by CTCAE.
  • Patient Reported Outcomes (QoL): Implied, though specific data not detailed.
• Pathology:
  • Prostate Biopsy at 12 months: Histological response evaluated through 10-core prostate biopsy, providing definitive evidence of cancer presence/absence.

Therefore, the ground truth was a combination of imaging measurements by experts, biochemical markers, documented adverse events (clinical outcomes), and pathology results.

8. The sample size for the training set

The document describes the clinical study (TACT Pivotal Study) as the evaluation of the device. This study enrolled 115 patients. The software component mentioned (closed-loop process control software) is part of the operational system. This document does not describe the development or training of a separate AI/ML algorithm that would typically have a distinct "training set." The TULSA-PRO System's "software" appears to be more of a deterministic control system rather than a machine learning model that learns from a large training dataset. Therefore, a "training set" in the context of AI model development is not applicable or mentioned in this submission.

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

As there is no explicit training set for a distinct AI/ML algorithm described in this document (the software is a process control system), the concept of "ground truth for the training set" is not applicable. The device's overall design and control logic would have been developed based on scientific principles, engineering, and potentially pre-clinical (animal) studies, which are mentioned as having been "conducted on a canine prostate model."

Ask a specific question about this device