Search Results

The SCOUT MD Reflector is intended to be placed percutaneously in soft tissue (>30 days) to mark a biopsy site or a soft tissue site intended for surgical removal. Using imaging guidance (such as ultrasound, MRI, or radiography) or aided by non-imaging guidance (SCOUT MD System) the SCOUT MD Reflector is located and surgically removed with the target tissue. The SCOUT MD System is intended only for the non-imaging detection and localization of the SCOUT MD Reflector that has been implanted in a soft tissue biopsy site or a soft tissue site intended for surgical removal.

The SCOUT MD Delivery System is used to implant the preassembled SCOUT MD Reflector. The needle of the Delivery System is percutaneously advanced into tissue to the site to be marked for biopsy or surgical removal. Needle placement is confirmed under imaging technique (radiographic, ultrasound). The Reflector (tissue marker) is deployed at the target site and the Delivery Device is removed from the patient and discarded. The Reflector, a passive implant, remains in situ and, if surgical removal of the target tissue is necessary, the Reflector is located at the time of surgery (intraoperatively) by the SCOUT MD Surgical Guidance System. The SCOUT MD Guide/Handpiece connected to the SCOUT MD Console is used to detect the SCOUT MD Reflector but it does not contact tissue. SCOUT MD Guides are always used while inside the SCOUT Guide Sheath. When the SCOUT MD System detects the Reflector, the Console emits audible feedback that increases in cadence as the Guide is placed closer to the Reflector. The distance between the distal end of the Guide and the detected Reflector, in millimeters, is displayed on the Console. If necessary, the Reflector is removed from the patient during a subsequent surgical procedure along with the tissue of interest or the Reflector can be left in-situ.

The provided text is a 510(k) Premarket Notification for the SCOUT MD Surgical Guidance System. It aims to demonstrate substantial equivalence to a predicate device, the SAVI Scout Reflector and SAVI Scout System.

However, the document does not contain the detailed performance data, acceptance criteria, or study methodologies that would typically be described in a clinical study report for proving a device meets specific acceptance criteria. Instead, it lists the types of tests performed to support substantial equivalence.

Therefore, I cannot extract answers to many of your specific questions regarding acceptance criteria, sample sizes for test/training sets, ground truth establishment, expert roles, and MRMC studies, as this information is not present in the provided text.

The document implicitly "proves" the device meets acceptance criteria by stating that the results of safety and performance tests demonstrate the device is substantially equivalent to the predicate, and that any differences do not raise new questions of safety and effectiveness. This is the core argument for a 510(k) submission.

Here's an attempt to answer what can be inferred or directly stated from the provided text, with clear indications where the information is not available.

Acceptance Criteria and Device Performance (Inferred/Stated)

While explicit numerical acceptance criteria are not detailed, the summary implies that the device performance met the standards for demonstrating substantial equivalence to the predicate. The performance "tests" enumerated are implicitly the method by which acceptance was determined.

Study Details (Information from the Text):

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

   • Sample Size: Not specified. The document lists types of performance tests, but not the sample sizes used for those tests (e.g., number of devices tested, number of simulated deployments, or any human subject data).
   • Data Provenance: Not specified. The document does not mention the country of origin of any data or whether the studies were retrospective or prospective. Given the nature of the tests listed (e.g., integrity, functional, electrical safety, biocompatibility, simulated use), these are typically bench or lab-based engineering verification and validation activities, not clinical studies with human subjects in the traditional sense for AI/imaging devices.

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

   • This information is not provided. The listed tests are primarily engineering and bench testing, not clinical performance studies requiring expert ground truth establishment in the context of diagnostic accuracy. If "Simulated Use" involved expert assessment, it's not detailed.

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

   • Not applicable / Not provided. This typically refers to clinical image interpretation studies, which are not detailed here.

4. 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 evidence of an MRMC study. This device (SCOUT MD Surgical Guidance System) is an implantable marker and a localization system. It does not appear to be an AI-powered diagnostic imaging device that would assist human readers in interpreting images. Its function is to non-imaging detect and localize an implanted reflector.

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

   • The "SCOUT MD System is intended only for the non-imaging detection and localization of the SCOUT MD Reflector." The functional and performance tests mentioned (deployment, detection, accuracy) would constitute standalone performance evaluation of the algorithm and system components. The specific details of how thoroughly this was tested are not explicitly described beyond listing the types of tests.

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

   • For the engineering and functional tests described (e.g., dimensional accuracy, detection range accuracy, material properties), the "ground truth" would be engineering specifications, physical measurements, and established scientific standards (e.g., ISO, ASTM standards for materials, sterilization, electrical safety). There is no mention of expert consensus, pathology, or outcomes data as ground truth, as these tests are not related to diagnostic accuracy.

7. The sample size for the training set:

   • Not applicable / Not provided. The document describes a "Surgical Guidance System" that non-imaging detects an implanted marker. There is no indication that this system uses machine learning or requires a 'training set' in the context of AI model development. The principle of operation is described as measuring the relative strength of RF reflective energy.

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

   • Not applicable / Not provided. As there's no mention of a traditional 'training set' for an AI model, this question is not relevant to the information provided.

Ask a specific question about this device

The Sirius Pintuition Seed is intended to be placed Percutaneously in soft tissue to mark (>30 days) a biopsy site or a soft tissue site intended for surgical removal. Using imaging guidance (such as ultrasound or radiography) or aided by nonimaging guidance (Sirius Pintuition Detector) the Sirius Pintuition Seed is located and surgically removed with the target tissue.

The Sirius Pintuition Detector is intended only for the non-imaging detection of the Sirius Pintuition Seed that has been implanted in a soft tissue biopsy site or a soft tissue site intended for surgical removal.

The Sirius Pintuition Seed and Sirius Pintuition Detector (consisting of Base Unit and Probe) are part of the Sirius Pintuition Localization System.

The Sirius Pintuition Seed is a small (1.65 x 5mm) Titanium tissue marker that is indicated for use to radiographically mark soft tissue during a surgical procedure or for future surgical procedures. The device is supplied single-use, sterile and pre-loaded within its delivery needle (7cm, 12cm or 20cm length variants).

The Pintuition Detector is designed to detect the presence and proximity of the implanted Pintuition Seed. It consists of a mains-powered, table-top Pintuition Base Unit, and a cableconnected, reusable Pintuition Probe. Using the Pintuition Probe, a user may use the Pintuition Detector prior to and during surgery to plan the surgical approach and quide surgery. The location of the seed is fed back to the user using audible and visual cues (distance in mm).

The principle of operation is magnetism, the Pintuition Seed is associated with a magnetic field which the Pintuition Detector utilizes to determine the location of the Pintuition Seed.

Here's a summary of the acceptance criteria and study information for the Sirius Pintuition Seed, Sirius Pintuition Probe, and Sirius Pintuition Base Unit, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific quantitative acceptance criteria for performance (e.g., a specific accuracy threshold or a certain rate of successful localization). Instead, it lists various pre-clinical tests and a clinical evaluation to demonstrate safety and performance.

However, based on the Summary of Technological Characteristics and the Summary of Non-Clinical Performance Data, we can infer the aspects that were evaluated to ensure the device performs as intended:

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

The document states: "An analysis of available data was conducted to evaluate and characterize the clinical safety and performance of the Sirius Pintuition Localization System. The clinical data support the safety and performance of the device: Clinical Evaluation, including clinical safety and performance data with the actual device, a previous version of the device and an extensive evaluation of available literature data pertaining to the previous version device, the predicate device and additional benchmark devices in various soft tissue types."

• Sample Size: The document does not specify a numerical sample size for the test set of the clinical evaluation. It refers to "available data," "clinical safety and performance data," and "extensive evaluation of available literature data."
• Data Provenance: The data provenance is described as a combination of:
  • Data from the "actual device" (implying prospective or recent retrospective studies specific to this version).
  • Data from a "previous version of the device."
  • "Extensive evaluation of available literature data pertaining to the previous version device, the predicate device and additional benchmark devices." This indicates that the provenance is varied and includes retrospective literature reviews.
  • Country of Origin: The country of origin for the clinical data is not specified in the provided text.

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

The document does not provide information on the number of experts used to establish ground truth or their specific qualifications (e.g., radiologist with 10 years of experience). The clinical evaluation is broad and references existing clinical data and literature.

4. Adjudication Method for the Test Set

The document does not specify any adjudication method (e.g., 2+1, 3+1, none) for the test set.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study and therefore does not provide an effect size for human readers with vs. without AI assistance. The device in question (Sirius Pintuition) is a localization system, not an AI software intended to assist human readers in image interpretation.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The Sirius Pintuition system is designed to be used by a human operator ("Using the Pintuition Probe, a user may use the Pintuition Detector prior to and during surgery to plan the surgical approach and guidesurgery. The location of the seed is fed back to the user using audible and visual cues (distance in mm)").

Therefore, a standalone performance study without human-in-the-loop would not be applicable or relevant to its intended use, and the document does not describe such a study. The "System accuracy and range verification" under non-clinical data would assess the device's inherent capability, but always within the context of a user interacting with it.

7. Type of Ground Truth Used

Based on the description of the device's function (locating and surgically removing the target tissue along with the implanted seed), the ground truth for clinical evaluation would likely involve:

• Pathology: To confirm whether the resected tissue contained the target lesion and the implanted seed.
• Surgical Confirmation: Direct visual or palpation confirmation during surgery of successful seed and lesion removal.
• Imaging Confirmation: Post-operative imaging (e.g., X-ray, ultrasound) to confirm removal of the seed and, if applicable, the target lesion.

The document does not explicitly state "pathology" or "outcome data" as ground truth, but given the indication for surgical removal, these are the most logical forms of truth. The clinical evaluation supported "safety and performance," which inherently relies on such confirmation.

8. Sample Size for the Training Set

The Sirius Pintuition system is a hardware device for localization based on magnetic principles, not a machine learning or AI algorithm in the context of image analysis that typically requires a "training set." Therefore, the concept of a "training set" in the context of an algorithm or AI is not applicable to this device as described.

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

As the concept of a "training set" doesn't apply to this type of device, this question is not relevant to the information provided.

Ask a specific question about this device

The MOLLI Marker is intended to be placed percutaneously in soft tissue to temporarily mark a surgical site intended for surgical removal. The MOLLI Marker can only be implanted for less than 30 days. Using imaging guidance (such as ultrasound or radiography) or aided by non-imaging guidance (MOLLI System), the MOLLI Marker is located and surgically removed with the target tissue.

The MOLLI System is intended only for the non-imaging detection and localization of the MOLLI Marker that has been implanted in a site intended for surgical removal.

MOLLI is a precision surgical marking and guidance system for locating non-palpable lesions during surgery. MOLLI consists of a temporary marker (MOLLI Marker), a marker delivery system (MOLLI Introducer), a detection wand (MOLLI Wand), and a visualization tablet (MOLLI Tablet). The MOLLI Marker is preloaded in the MOLLI Introducer. The MOLLI Wand and the MOLLI Tablet constitute the MOLLI System. The MOLLI System is intended for the non-imaging detection and localization of the MOLLI Marker that has been implanted in a site intended for surgical removal.

This document is a 510(k) premarket notification from the FDA, and as such, it primarily focuses on demonstrating substantial equivalence to predicate devices based on non-clinical testing. It does not contain information about a clinical study involving human subjects to prove the device meets specific acceptance criteria based on performance metrics like accuracy, sensitivity, or specificity.

Therefore, I cannot provide the information requested in your prompt regarding acceptance criteria and a study proving device performance in a clinical context (e.g., sample size, expert ground truth, MRMC study, effect size of human reader improvement with AI, standalone performance, training set details).

Here's a breakdown of what can be extracted from the provided text, and what cannot:

Information NOT available in the document (and why):

• Acceptance Criteria Table with Reported Performance: This document describes non-clinical bench testing and safety standards, not clinical performance metrics with pre-defined acceptance criteria.
• Sample size used for the test set and data provenance: No clinical test set involving device performance on human subjects is described. The "test set" mentioned in this context refers to non-clinical bench testing.
• Number of experts used to establish the ground truth for the test set and qualifications of those experts: There is no clinical data from human subjects requiring expert ground truth for performance evaluation.
• Adjudication method for the test set: Not applicable as there's no clinical test set requiring adjudication.
• 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: This is a non-AI device (an implantable marker and detection system), and no clinical MRMC study is mentioned.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable for this device type.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable for clinical performance as no clinical study is described. Ground truth for non-clinical tests would be established by physical measurements and engineering specifications.
• The sample size for the training set: Not applicable as this is not an AI/machine learning device.
• How the ground truth for the training set was established: Not applicable.

What the document does describe (relevant to your prompt but not directly answering all parts):

The document focuses on non-clinical testing to demonstrate the device's safety and effectiveness compared to predicate devices. This includes:

• Summary of Non-Clinical Testing:
  • Biocompatibility testing per ISO 10993-1
  • Packaging validation testing per ISO 11607-1 and ASTM D4169-19
  • EO sterilization validation per ISO 14937 and ISO 10993-7
  • Software testing per IEC 62304
  • Electrical safety testing per IEC 60601-1
  • EMC testing per IEC 60601-1-2:2014
  • MRI compatibility testing per ASTM standards F2052-15, F2119-07, F2182-11, and F2213-17.
  • Non-clinical performance bench testing including V&V testing, MOLLI Marker displacement testing, tissue performance testing, and needle penetration testing (per ISO 7864)
  • Human factor validation testing

The document concludes that "Based on the testing performed... it can be concluded that the subject device does not raise new issues of safety or effectiveness compared to the predicate device." This is the core of a 510(k) submission: demonstrating substantial equivalence, often without the need for large-scale clinical trials if non-clinical data is sufficient to address safety and effectiveness concerns.

Ask a specific question about this device

The Tag of the RFLS is intended for percutaneous placement in the breast to mark (>30 days) a lesion intended for surgical removal. Using image guidance (such as ultrasound or radiography) or aided by non-imaging guidance (RFLS), the RFID Tag is located and surgically removed with the target tissue. The RFLS is intended only for the non-imaging detection and localization of the Tag that has been implanted in a lesion intended for surgical removal.

The proposed RFID Localization System is a marker-with-detector localization device that employs miniature RFID tags as markers and a hand-held reader that can measure distance to the tag. The RFLS is comprised of a Tag, Tag Applicator/Tag Applicator S, LOCalizer Reader) and LOCalizer Surgical Probe (Surgical Probe). The Tag, when used in conjunction with the Reader and Surgical Probe, can be used as a guide for the surgeon to refer to in the excision of tissue. The RFLS is a prescription device meant only for use by trained professionals.

Since the provided text is a 510(k) summary for a medical device (RFID Localization System), and not a study report for a diagnostic AI/ML device, much of the requested information regarding acceptance criteria for AI/ML performance, sample sizes for AI test/training sets, expert ground truth establishment, and MRMC studies is not directly applicable or present in this document.

The document discusses performance data related to the physical device's function, safety, and compatibility, rather than the performance of an AI model in a diagnostic context. The "RFID Localization System" is a marker-with-detector device, not an AI-powered diagnostic system.

However, I can extract the acceptance criteria and performance data as described for this physical device, along with other relevant information that is present.

Here's the closest possible interpretation of your request based on the provided text, focusing on the device validation rather than AI performance:

Device: RFID Localization System (RFLS)
Intended Use: Percutaneous placement in the breast to mark a lesion intended for surgical removal. Aids in non-imaging detection and localization of the implanted Tag for surgical removal.

1. Table of Acceptance Criteria and Reported Device Performance

For a physical device like the RFLS, "acceptance criteria" relate more to meeting design specifications and safety/performance standards. The document states that the RFLS met the applicable design and performance requirements. The "performance" is demonstrated by passing the various tests listed, affirming its functionality and safety.

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

The document does not specify a "test set sample size" in the context of an AI/ML model. Instead, it refers to various engineering and biological validation tests. For many tests, it explicitly states that the performance was "previously established" through prior 510(k) clearances (e.g., K190932, K181692, K163667, DEN040007/K033440). This indicates that the current submission relies on historical test data and validations, with some additional testing (e.g., multiple tags, updated packaging/shipping in K190932, and the explicitly mentioned electrosurgery and MRI compatibility for K163667, and the current submission's specific software and electrical safety/EMC testing).

• Data Provenance: The document doesn't specify the country of origin for the underlying test data, but it refers to FDA-cleared predicate and reference devices, implying compliance with US regulatory standards. All validations appear to be retrospective or performed as part of device development and previous submissions.

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

This information is not applicable. This is a physical medical device, not an AI/ML diagnostic algorithm requiring expert "ground truth" for interpretations of medical images or data. The "ground truth" for the device's performance would be established by objective measurements against engineering specifications and validated medical standards.

4. Adjudication Method for the Test Set:

Not applicable. This concept applies to human reader studies often used for AI/ML validation, not the direct performance testing of a physical medical device.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

Not applicable. This type of study is for evaluating observer performance with or without AI assistance, which is not the subject of this 510(k). The device is a physical marker and localization system, not a diagnostic AI.

6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance:

Not applicable. This device is not an algorithm; it's a marker-with-detector system that a human surgeon uses. Its performance is inherent in its physical properties and functionality.

7. Type of Ground Truth Used:

The "ground truth" for this device's validation is based on:

• Engineering specifications and design requirements.
• Objective measurements (e.g., distance readings, physical stability, electrical safety parameters).
• Compliance with established international and ASTM standards (e.g., ISO 11607-1, ASTM D4169-09, ISO 10993-1, IEC 60601-1).
• Biocompatibility assessments of materials.
• Validation of sterilization processes.

8. Sample Size for the Training Set:

Not applicable. This device does not use an AI/ML model that requires training data in the conventional sense.

9. How the Ground Truth for the Training Set was Established:

Not applicable, as there is no AI/ML training set. The "ground truth" for the device's design and manufacturing is established through scientific principles, engineering validated methods, and adherence to medical device regulatory standards and best practices.

Ask a specific question about this device