Search Results

The Smart Finder is intended to be used for mammographic procedures requiring stereotactic guidance, such as fine needle aspiration, needle biopsy and guide wire placement.

Not Found

This document, K203509, is a 510(k) clearance letter for a mammographic x-ray system called "SMART FINDER." It primarily covers the administrative aspects of the device's clearance for marketing. It does not contain information regarding detailed acceptance criteria, study methodologies, performance metrics (such as sensitivity, specificity, AUC), sample sizes for test or training sets, expert qualifications, or ground truth establishment relevant to an AI/CAD device.

The "SMART FINDER" device, as described, is intended for "mammographic procedures requiring stereotactic guidance, such as fine needle aspiration, needle biopsy and guide wire placement." This suggests it's a hardware device used for image-guided procedures, not an AI or CAD software that analyzes images for diagnostic aid.

Therefore,Based on the provided text, I cannot provide the requested information about device acceptance criteria and the study proving it meets them. The document is a 510(k) clearance letter for a medical device called "SMART FINDER," which is described as a "mammographic x-ray system" used for stereotactic guidance in procedures like fine needle aspiration and biopsy.

This document does NOT contain the following information:

• A table of acceptance criteria and reported device performance: This letter is an administrative clearance, not a technical report on performance.
• Sample sizes used for the test set and data provenance: No study details are provided.
• Number of experts used to establish ground truth and their qualifications: No study details are provided.
• Adjudication method for the test set: No study details are provided.
• If a multi-reader multi-case (MRMC) comparative effectiveness study was done, or its effect size: No study details are provided.
• If a standalone (algorithm only) performance study was done: No study details are provided.
• The type of ground truth used: No study details are provided.
• The sample size for the training set: No study details are provided.
• How the ground truth for the training set was established: No study details are provided.

The document indicates that the device is "substantially equivalent" to legally marketed predicate devices, which is the basis for 510(k) clearance. However, the details of the studies and data used to demonstrate this substantial equivalence are not included in this administrative letter.

Ask a specific question about this device

Affirm® Contrast Biopsy is indicated as an optional accessory for the Selenia Dimensions 2D Full Field Digital Mammography System and 3Dimensions system. It is designed to allow the accurate location of lesions in the breast in three dimensions, using information extracted from stereotactic pairs of two-dimensional images. It is intended to provide guidance for interventional purposes (such as biopsy, pre-surgical localization or treatment devices). Contrast Enhanced Digital Mammography (CEDM) is an extension of the existing indication for diagnostic mammography with the Selenia Dimensions system. Biopsy targeting can be done on captured contrast enhanced images (scout and stereo pair). The CEDM application shall enable contrast imaging using a dual energy technique. This imaging technique can be used as an adjunct following mammography and/or ultrasound exams to localize a known or suspected lesion. Affirm® Contrast Biopsy is intended for patients recommended for biopsy who have had a suspicious finding on previous contrast enhanced imaging or have lesions that may be occult under other modalities.

The proposed Affirm® Contrast Biopsy is a licensable software for the Selenia Dimensions and 3Dimensions system platforms (P010025 and P08003, respectively). The proposed software option will be used with the Affirm® Breast Biopsy Guidance System (K103512). The proposed software is a stereotactic lesion localization system option for the Dimensions systems. It allows clinicians to perform biopsy targeting on captured contrast enhanced images. Affirm® Contrast Biopsy uses the same workflow as stereotactic biopsy, substituting standard scout and stereo pair views with contrast enhanced views captured at the associated angles. The proposed device is compatible with the standard vertical biopsy approach as well as the right or left lateral approach.

Affirm® Contrast Biopsy introduces new software and labeling. There are no changes to the Dimensions platform and Affirm® Breast Biopsy Guidance System hardware, platform software architecture, or stereotactic function as a result of the proposed software.

The provided text is a 510(k) Summary for the Hologic Affirm® Contrast Biopsy system. It primarily focuses on demonstrating substantial equivalence to a predicate device for regulatory clearance, rather than presenting a performance study against specific acceptance criteria for AI/ML device performance.

Therefore, the document does not contain the detailed information required to answer the specific questions about acceptance criteria and a study proving the device meets them, especially in the context of an AI/ML system's performance. The device described appears to be a hardware/software system for guiding biopsies using contrast-enhanced imaging, not an AI/ML algorithm that requires performance metrics like sensitivity, specificity, or reader studies.

Specifically, the document states: "Non-clinical bench testing demonstrates the Affirm® Contrast Biopsy is substantially equivalent to the predicate and reference device with regards to the indication for use, software, technology, and performance. Design verification testing demonstrates the proposed device complies with design specifications. The software, and performance showed that the overall system demonstrated equivalent performance and equivalent safety and effectiveness as the predicate..." This indicates that bench testing and design verification were conducted to show equivalence, typical for traditional medical devices, not a study focused on AI/ML performance.

Here's a breakdown of why the requested information cannot be extracted from the provided text:

1. A table of acceptance criteria and the reported device performance: Not provided. The document discusses "design specifications" and "equivalent performance" but no specific quantitative acceptance criteria or results are listed.
2. Sample size used for the test set and the data provenance: Not mentioned. There is no description of a clinical test set or data origins.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable based on the provided text, as no clinical test set for performance evaluation (e.g., sensitivity/specificity) is described using expert ground truth.
4. Adjudication method: 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 interpretation device in the traditional sense, but rather a biopsy guidance system. No MRMC study is mentioned.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The device is described as a system for guidance, not a standalone diagnostic algorithm.
7. The type of ground truth used: Not applicable. No ground truth for performance evaluation (e.g., pathology, expert consensus) is described.
8. The sample size for the training set: Not applicable. This document does not describe an AI/ML model that would have a training set.
9. How the ground truth for the training set was established: Not applicable.

In summary, the provided FDA 510(k) clearance letter and summary are for a biopsy guidance system that uses contrast-enhanced images, which is cleared based on substantial equivalence to existing predicate devices through bench testing and design verification, rather than a clinical performance study with specific AI/ML acceptance criteria and human-in-the-loop evaluations.

Ask a specific question about this device

The FUJIFILM Biopsy Positioner (FDR-2000BPY) is an optional accessory for the Aspire Cristalle (FDR MS-3500) digital mammography system. It is designed to allow for accurate determination of three dimensional lesion locations in the breast using information extracted from stereotactic pairs of two-dimensional images and/or Digital Breast Tomosynthesis (DBT) images. It is intended to provide guidance for interventional purposes (such as biopsy, pre-surgical localization or treatment devices).

The Biopsy Positioner (FDR-2000BPY) is an optional accessory for the Digital Mammography system. It is designed for positioning the needle when performing Stereotactic and/or Tomosynthesis Biopsies, fine needle aspirations, core needle, and vacuum assisted biopsies in an upright position. The Biopsy Positioner uses a Stereo pair of images and/or Tomosynthesis images. The position of the three coordinates (X, Y, and Z) is computed using the position of the object on each of the images, as indicated by the operator, and the known geometry of the system.

FDR-2000BPY is mainly composed of the following elements:

• The Positioner that supports and positions the needle .
• The Positioner Control Cabinet which supplies power to the positioned .
• The Operation panel which displays the distance between the compression plate and . target pathology, the distance between the target pathology and the needle, and also electrically drives the positioner in the X, Y and Z directions.

The subject of this Special 510(k) premarket notification is addinq use of Digital Breast Tomosynthesis (DBT) images for extracting information to determine three dimensional lesion locations in the breast.

This document describes the Biopsy Positioner (FDR-2000BPY) for determining 3D lesion locations in the breast for interventional purposes using stereotactic and/or Digital Breast Tomosynthesis (DBT) images.

There is no information in the provided text regarding a study on "AI" performance or human reader improvement with AI assistance. The device described is a biopsy positioner and not an AI algorithm for image interpretation.

Here's the information that can be extracted based on the provided text, focusing on the device itself and its performance:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document states "Bench testing was performed... to evaluate the stereotactic and tomosynthesis biopsy needle positioning accuracy." It does not specify a numerical sample size for this bench testing.

• Data Provenance: Bench testing, so it is synthetic/physical testing, not patient data. No country of origin is specified for the bench testing.

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

• This device is a biopsy positioner, not an image interpretation or diagnostic AI device. Therefore, the concept of "experts establishing ground truth for a test set" in the context of diagnostic performance is not directly applicable.
• The accuracy of the device (e.g., needle positioning) would be verified against physical measurements or established calibration standards during bench testing. No human experts are mentioned for establishing ground truth in this context.

4. Adjudication Method for the Test Set

• Not applicable as the testing involves physical performance metrics (e.g., positioning accuracy) rather than subjective interpretation requiring adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• No, an MRMC comparative effectiveness study was not done. The device is a biopsy positioner accessory, not an image reader or an AI diagnostic tool. There is no mention of human readers or AI assistance in the document.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• This question is built on the premise that the device is an "algorithm." The FDR-2000BPY is a physical "Biopsy Positioner," an accessory to a mammography system. While it has software and computes 3D coordinates, it is not described as a standalone diagnostic algorithm. Its performance is integrated with the mammography system and involves human operation for marking targets.
• The "performance data" section focuses on hardware-related compliance (EMC, radiation safety) and "needle positioning accuracy" via bench testing, not autonomous algorithmic performance.

7. The Type of Ground Truth Used

• For the needle positioning accuracy, the ground truth would likely be physical measurements against known target coordinates or established calibration standards in a bench test environment. It is not expert consensus, pathology, or outcomes data, as these relate to diagnostic accuracy, not the accuracy of a physical positioning system itself.

8. The Sample Size for the Training Set

• Not applicable. This device is a physical accessory with integrated software for coordinate calculation, not a machine learning model that requires a "training set" in the conventional sense. The "training" for such a system would involve engineering and calibration, not data-driven model training.

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

• Not applicable, as there is no "training set" for an AI model. For the device's development and calibration, ground truth would be established through engineering specifications, precise physical measurements, and system calibration procedures.

Ask a specific question about this device

The Affirm Breast Biopsy Guidance System is an optional accessory for the Selenia Dimensions Mammography System. It is designed to allow the accurate localization of lesions in three dimensions. It is intended to provide guidance for interventional purposes (such as biopsy, pre-surgical localization or treatment devices).

This submission introduces the optional Affirm Lateral Arm Upright Biopsy Accessory which attaches to the Affirm Breast Biopsy Guidance System used with the Selenia Dimensions 2D/3D Mammography System, software version 1.8.4 and higher.

The optional Affirm Lateral Arm Upright Biopsy Accessory attaches to the Affirm Biopsy Guidance Module (BGM) to enable lateral needle approach procedures. The Lateral Arm can only be used when the Selenia Dimensions C-arm is positioned at 0 degrees. When using the Lateral Arm, the X- Y- and Z-axis movement is the same as for the Affirm standard (upright) needle approach. For the lateral approach, the biopsy needle is manually advanced into the breast along its own X-axis, referred to as "Lat X".

When performing lateral approach biopsies, the biopsy device is installed onto the lateral arm in the same manner as when performing standard (upright biopsies).

New components used with the Affirm Lateral Arm Upright Biopsy Accessory include: lateral biopsy paddle, lateral arm stand, case, and QC phantom specifically to be used for Lateral approach biopsies.

The document provided describes the Affirm Lateral Arm Upright Biopsy Accessory, an optional accessory for the Selenia Dimensions Mammography System. This device is intended to provide guidance for interventional purposes (such as biopsy, pre-surgical localization, or treatment devices) with a lateral needle approach.

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance:

The primary acceptance criterion for this device appears to be its targeting accuracy, which is compared to existing predicate devices.

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

• Sample Size: Not explicitly stated as a number of patient cases or images. The testing focused on functional and performance characteristics using test reports.
• Data Provenance: Not applicable, as no clinical studies were performed. The testing was non-clinical.

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

• Number of Experts: Not applicable. Ground truth was established through physical measurements and engineering tests.
• Qualifications of Experts: Not applicable.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable. The testing described is primarily engineering and performance verification, not an interpretation of medical findings requiring adjudication.

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

• MRMC Study Done? No. The document explicitly states: "No clinical studies were performed. Substantial equivalence has been demonstrated by nonclinical testing." Therefore, no MRMC study comparing human readers with and without AI assistance was conducted.

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

• Standalone Study Done? Yes, in essence, the "Lateral Arm Targeting Accuracy Test" and "Default Needle Parameter Validation Test Report" represent standalone performance tests of the device's mechanical and software accuracy without direct human intervention in the targeting process during the test. The device provides guidance, but the testing assesses the accuracy of that guidance mechanism itself.

7. Type of Ground Truth Used:

• Type of Ground Truth: Physical measurement and engineering specifications. For target accuracy, this would involve precise measurements of the actual needle tip position relative to the intended target point within a phantom or test setup.

8. Sample Size for the Training Set:

• Sample Size: Not applicable. The device is a mechanical accessory with integrated software for guidance. It does not appear to use machine learning or AI models that require a "training set" in the conventional sense. Its function is based on pre-programmed algorithms and physical calibration.

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

• Ground Truth for Training Set: Not applicable, as there is no "training set" for an AI model. The system's accuracy and functionality were verified through engineering tests and validation against established standards.

Summary of Testing:

The document highlights that the device underwent system design control verification and validation tests, conforming to FDA's Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (moderate level of concern).

Specific tests included:

• Lateral Arm Targeting Accuracy Test: This directly addresses the core function of the device to accurately guide interventions.
• Default Needle Parameter Validation Test Report: Ensures correct operation with needle parameters.
• Updated Affirm CB test report (including Lateral Arm Accessory): Likely refers to a comprehensive test suite for the combined system.
• Third-party testing on:
  • Tensile Safety Factor (IEC 60601-1, Clause 9.8.2)
  • Strength of Compression Plates (IEC 60601-2-45, Subclause 203.8.5.4.102.5)
  • Biopsy Needle Positioning Accuracy of Mammographic Stereotactic Devices (IEC 60601-2-45, Subclause 201.9.2.1013 a,b,c)

The conclusion states that substantial equivalence was demonstrated by nonclinical testing, and no clinical studies were performed. The device's design, operation, construction, and materials were deemed substantially equivalent to the predicate and reference devices.

Ask a specific question about this device

The indications for use of the product is to remove the cold from the bucky by placing this sheet between patient's breast and the image receptor plate allowing the patient to feel more comfortable and less cold without interfering with image quality.

Comfort Cover is a single-use disposable cover placed between the patient's breast and the image receptor plate during mammography. The purpose of this product is to allow the patient to feel more comfortable and less cold during the mammographic examination without interfering with image quality. Comfort Cover will allow for artifact-free images in both Field Digital Mammography (FFDM) and Digital Breast Tomosynthesis (DBT), patient radiation dose is equivalent to that when using no Comfort Cover and the Image quality is equivalent to images exposed without Comfort Cover.

Comfort Cover is designed to fit small and large image receptor plates of all leading mammographic equipments. The product is constructed of a fabric material with a purple printed design and has adhesive backing with a paper liner. Both the material and adhesive backing of the product do not affect imaging.

The product is directly applied wrinkle free to the image receptor plate of the mammographic machine by the adhesive backing exposed by peeling off the liner. After the patient's mammogram, the product is peeled off the image receptor plate and disposed. As the product removes cleanly without leaving behind any residue, the image receptor plate does not need to be cleaned between Comfort Covers nor between patients.

The provided document, a 510(k) Premarket Notification for the "Comfort Cover," describes the device, its intended use, and comparative testing against a predicate device. However, it does not contain the level of detail typically found in a clinical study report or a regulatory submission for a device involving AI or complex performance metrics. The Comfort Cover is a disposable cover for mammography plates to enhance patient comfort without affecting image quality.

Below is an attempt to extract and synthesize the requested information based on the document, noting where specific details are not provided or are not applicable to this type of device.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance
The document does not provide specific sample sizes (e.g., number of covers, images, or participants) for the test sets. It states that "a number of non-clinical performance tests" were completed.

• Biocompatibility: Testing was conducted per ISO 10993-5 and ISO 10993-10 on the subject device.
• Mechanical Testing: Performed on "both the subject and the predicate devices."
• Radiological Studies: Phantom image testing was performed "as per MQSA regulations and with relevant International Electro technical Commission (IEC) standards (62220-1-2:2007 and 61223-3-2)." This implies the use of standardized phantoms, not patient data.
• Usability Studies: Included "radiologists, radiology technologists and patients." The number of each group is not specified.

Data provenance (country of origin, retrospective/prospective) is not specified, but given the nature of the tests (lab-based, phantom studies, usability feedback), it is likely all internal data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided. For the usability studies, "radiologists" and "radiology technologists" were involved, but their number and specific qualifications (e.g., years of experience) are not detailed. For radiological studies, phantom images were used, implying objective measurements rather than expert human interpretation for ground truth.

4. Adjudication method for the test set
Not applicable or not described. The tests are primarily objective measurements (e.g., passing a specific ISO standard, conforming to ASTM methods, measuring radiation dose, image quality metrics from phantom images). For usability, it simply states that user needs were fulfilled, but no adjudication method for consensus is 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 study was done, nor is this device related to Artificial Intelligence (AI). The Comfort Cover is a physical accessory for patient comfort during mammography.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
Not applicable. This device is not an algorithm or AI.

7. The type of ground truth used

• Biocompatibility: In-vitro and in-vivo (skin irritation/sensitization) test results against ISO standards.
• Mechanical Testing: Objective measurements (e.g., ASTM standards, in-house developed test for residue).
• Radiological Studies: Objective measurements from phantom images (e.g., presence/absence of artifacts, radiation dose measurements, image quality metrics) compared to baselines (without Comfort Cover) and regulatory/IEC standards.
• Usability Studies: User feedback (radiologists, technologists, patients) on comfort and impact on positioning.

8. The sample size for the training set
Not applicable. This device is not an AI/machine learning model and does not have a "training set."

9. How the ground truth for the training set was established
Not applicable.

Ask a specific question about this device

The Affirm Prone Biopsy System combines the function of a standard x-ray mammography unit with that of a lesion localization system to produce a device that has specific application in first accurately localizing lesions in the breast in two and/or three dimensions, and then providing guidance for interventional purposes (such as biopsy, pre-surgical localization or treatment devices) for lesions determined to be suspicious through prior mammographic examination.

It is intended for lesion location for biopsy while the patient is in the prone position to provide guidance for interventional purposes (such as biopsy, presurgical localization or treatment devices).

The Affirm Prone Biopsy Table is a mammographic x-ray system intended for lesion location while the patient is in the prone position. The subject device will be capable of both 2D and 3D imaging methods to calculate the target location. The system localizes suspicious lesions, as determined through prior mammographic examinations, using either stereotactic or tomosynthesis techniques. The system then affords a physician the capacity of performing vacuum assisted or needle core biopsy, or wire localization of the lesion.

Localization can be accomplished either via conventional 2D stereotactic imaging, or by use of a 3D data set. With the 3D data set, the image plane or "slice" most fully containing the suspected lesion is chosen by the physician from the data set to compute the lesion depth within the breast.

Here's an analysis of the provided text to extract information about acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance:

Based on the provided document, specific quantitative acceptance criteria or a direct performance table are not explicitly stated or presented. The document focuses on regulatory compliance and substantial equivalence to predicate devices.

However, the "Performance Testing" section (Page 4, Section 7) indirectly points to an acceptance criterion:

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

The document does not specify a sample size for a test set in the context of clinical performance or diagnostic accuracy. The testing mentioned appears to be primarily engineering verification and validation against safety and quality standards.

The data provenance (e.g., country of origin, retrospective/prospective) related to any clinical test set is not mentioned.

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

This information is not provided in the document. The type of testing described (compliance with IEC standards, design control) does not typically involve expert-established ground truth in the same way a clinical performance study would.

4. Adjudication Method for the Test Set:

An adjudication method (e.g., 2+1, 3+1) for a clinical test set is not mentioned because a clinical test set for diagnostic performance is not described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:

No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance is not mentioned in this document. The device is a "Biopsy System" for guidance, not a diagnostic AI interpretation tool.

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

The document describes the "Affirm Prone Biopsy System" as a physical mammographic x-ray system that provides guidance for interventional procedures. While it utilizes "2D and 3D imaging methods to calculate the target location" (Page 4, Section 4), it is fundamentally a system that aids a physician. Therefore, a standalone (algorithm only) performance, separate from human operation or decision-making, is not described or implied. The device's function is to guide a human operator.

7. The Type of Ground Truth Used:

The document focuses on engineering and regulatory ground truth:

• Compliance with IEC 60601-2-45 standards: This implies meeting established technical specifications and safety requirements.
• Compliance with 21 CFR Part 820 (Design Controls): This refers to documented evidence that the device design meets user needs and intended uses.
• Equivalence to Predicate Devices: The "ground truth" for its performance is its demonstrated similarity in technology, operation, and functional performance to previously cleared devices.

There is no mention of clinical ground truth such as pathology, expert consensus on lesions, or outcomes data for a diagnostic or interventional accuracy claim. The device's purpose is localization and guidance, not diagnostic interpretation.

8. The Sample Size for the Training Set:

The document does not mention a training set size. This is consistent with the nature of the device being an imaging and guidance system, rather than a machine learning or AI algorithm requiring a training set for feature learning. The image processing for 2D/3D localization would be based on established algorithms, not necessarily a trained machine learning model.

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

Since a training set is not mentioned, the method for establishing its ground truth is also not applicable/provided.

Ask a specific question about this device

MammoGRIP aids in positioning during radiologic visualization of the breast.

MammoGRIP™ is a non-medicated, 0.1% benzalkonium chloride foam solution intended to be used during mammography to facilitate breast positioning. When MammoGRIP is applied to the technician's hands, it imparts a slightly tacky or sticky surface while it is still damp, thereby allowing the technician to have a better grip of the dry breast tissue for optimal positioning in the field of view of the mammography machine. MammoGRIP is intended to be used with standard mammogram positioning techniques.

The provided text is a 510(k) summary for the MammoGRIP device. It does not describe a study involving an AI algorithm or its performance. Instead, it describes a device that aids in breast positioning during mammography by making a technician's hands slightly tacky. The acceptance criteria and "study" mentioned refer to biocompatibility tests and verification of physical characteristics for this accessory, not an AI performance study.

Therefore, most of the requested information regarding AI device performance, sample sizes, ground truth establishment, expert adjudication, and MRMC studies is not applicable to this document.

Here's what can be extracted based on the provided text, interpreted in the context of the device:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance
The text describes biocompatibility tests (assays) and quality control verifications for the physical characteristics of the device. These are not "test sets" in the context of clinical performance data for an AI system. The sample size for these tests is not specified in the document, nor is the data provenance in terms of country of origin or retrospective/prospective nature, as these are typically laboratory tests.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not applicable. The "ground truth" here would relate to the outcome of biological responses to the material (biocompatibility) or the physical/chemical properties of the product. These are assessed by laboratory procedures, not by expert interpretation of clinical data in the way an AI would be evaluated.

4. Adjudication method for the test set
Not applicable. Adjudication methods like "2+1" are used for expert consensus on clinical findings. For biocompatibility tests, results are typically determined by standardized laboratory protocols.

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. This is not an AI device, and no MRMC study was conducted or is relevant for this type of accessory.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
No. This is not an AI algorithm.

7. The type of ground truth used
For biocompatibility, the ground truth is established by the biological response observed in standardized assays. For physical characteristics, the ground truth is the measured physicochemical properties of the formulation.

8. The sample size for the training set
Not applicable. This is not an AI device that requires a training set.

9. How the ground truth for the training set was established
Not applicable. This is not an AI device.

Ask a specific question about this device

SPECBOARD JR is intended to be used as an accessory to a mammographic x-ray system. The SPECBOARD JR is used to contain the mammographic specimen from the patient when transported to the x-ray device and then accompany the x-ray image to the pathology laboratory.

The SPECBOARD is a medical device that allows for accurate localization of suspect lesions in breast tissue. The SPECBOARD JR is comprised of a foam core base coupled with a tape hinge along one edge to a thick cardboard cover. On the base foam core piece there is a centrally located piece of absorbent blotter paper. Along two joining edges of the blotter are two radio-opaque nickel stencils, one marked with alpha characters and the other with numerical characters. The SPECBOARD JR is used in the operating room where the surgeon will remove a suspect portion of the breast tissue and place it on the blotter portion of the SPECBOARD JR. The cover is then closed, sandwiching the breast specimen between the cover and the base. The cover is then secured with the Velcro latch and an x-ray is taken of the specimen inside the SPECBOARD JR. The resulting x-ray image will show the perpendicular stencils along the border of the blotter paper and the specimen on the blotter paper. Any lesions will show up within the specimen and the pathologist then has a reference of where to cut into the specimen to withdrawal a piece for analysis.

The provided text is a 510(k) summary for the SPECBOARD JR, which is a specimen transport and identification device used as an accessory to a mammographic x-ray system. The filing asserts substantial equivalence to a predicate device, the SPECBOARD (K891090).

Based on the provided information, there is no detailed study described that establishes acceptance criteria for device performance or provides data from such a study. The 510(k) summary focuses entirely on demonstrating substantial equivalence to the predicate device, not on proving clinical performance or meeting specific acceptance criteria through a performance study.

Here's an analysis based on the structure of your request and the information available:

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

• Acceptance Criteria: Not explicitly stated or provided in the document.
• Reported Device Performance: Not explicitly stated or provided in the document in terms of quantitative performance metrics. The filing claims the device "is expected to have the same safety record as the predicate SPECBOARD product, no failures reports." This is a statement of expectation rather than reported performance from a specific study.

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 applicable. No test set or performance study data is described.
• Data Provenance: Not applicable.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

• Number of Experts: Not applicable. No performance study requiring expert adjudication is described.
• Qualifications of Experts: Not applicable.

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

• Adjudication Method: Not applicable. No performance study requiring adjudication is described.

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

• MRMC Study: No. This device is a passive accessory and does not involve AI or human readers for diagnostic interpretation in the way an AI-driven imaging CAD system would. Its function is to hold a specimen for X-ray and provide reference markers.

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

• Standalone Performance: Not applicable. This is a physical device, not an algorithm.

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

• Ground Truth: Not applicable. No performance study is described that would require a ground truth for evaluation. The device's primary function is to aid in localization for pathology, not to diagnose.

8. The sample size for the training set

• Training Set Sample Size: Not applicable. This is a physical device, not an AI algorithm requiring a training set.

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

• Ground Truth for Training Set: Not applicable.

Summary of the 510(k) Approach for SPECBOARD JR:

The 510(k) for SPECBOARD JR is a design modification submission, leveraging the substantial equivalence pathway based on predicate device K891090 (SPECBOARD). The core argument for safety and effectiveness is that:

• The SPECBOARD JR is smaller than the predicate SPECBOARD.
• It uses the same materials as the predicate.
• It has the same design elements and packages them into a smaller form factor.
• It performs the same function (containing specimens for X-ray and providing reference markers for pathology).
• The predicate device has a long history of safe use ("in worldwide use since 1989" with "no failures reports").

Because the changes are minimal and do not alter the fundamental technological characteristics or intended use, a dedicated performance study with acceptance criteria was not deemed necessary by the FDA. The FDA's decision summary explicitly states, "The information in the 510(k) is complete and supports a substantial equivalence (SE) determination." This indicates that the comparison to the predicate, demonstrating that the device is "the difference being in size," was sufficient for clearance.

Ask a specific question about this device

The Affirm breast biopsy guidance system is an optional accessory for the Selenia Dimensions Mammography System. It is designed to allow the accurate localization of lesions in the breast in three dimensions. It is intended to provide guidance for interventional purposes (such as biopsy, pre-surgical localization or treatment devices).

The Affirm Breast Biopsy Guidance System is used with Selenia Dimensions 2D or with Selenia Dimensions 3D tomosynthesis. Lesion location can be obtained from either 2D stereotactic or 3D tomosynthesis image acquisition. Both stereotactic and 3D localization calculate a three dimensional location for percutaneous placement for biopsy, pre-surgical localization or treatment devices. Safety Features include: Automatic detection of mounting, latching, and connection of biopsy guidance module; C-arm motion disabled if biopsy guidance module is not locked in place; Automatic compression release disabled when biopsy guidance module installed; Motorized movement of biopsy device only under user control; Audible alert if biopsy device motion could result in mechanical interference.

The provided text describes a Special 510(k) Premarket Notification for the "Modified Affirm Breast Biopsy Guidance System." However, it does not contain the detailed acceptance criteria or the specifics of a study proving the device meets those criteria in the format requested.

The document states that the device "meets IEC 60601-2-45 Medical Electrical Equipment - Safety of Mammographic X-ray Equipment and Mammographic Stereotactic Devices" and that "Hologic successfully performed design control verification and validation tests in accordance with 21 CFR Part 820." It also mentions that "Accuracy can be verified during the biopsy process."

The core of this 510(k) submission is to demonstrate substantial equivalence to a predicate device (K103512), specifically regarding a software change that enables the use of 3D tomosynthesis calculations for lesion localization, in addition to the existing 2D stereotactic capabilities. The manufacturer asserts that the "3D tomosynthesis lesion location is substantially equivalent to and as safe and effective as the cleared Affirm Breast Biopsy Guidance System and poses no additional risks or hazards."

Without explicit reported device performance metrics or a detailed study description in the provided text, I cannot populate most of the requested table.

Here's a breakdown of what can and cannot be answered based on the input:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Not specified in the provided text. The document refers to "design control verification and validation tests," but does not detail the specific test set size or data provenance (e.g., country of origin, retrospective/prospective nature).

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

• Not specified in the provided text.

4. Adjudication method for the test set:

• Not specified in the provided text.

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 is mentioned. The device is a guidance system for biopsy, not an AI-assisted diagnostic tool for human readers in the classical sense of an MRMC study. The "AI" component would be the 3D tomosynthesis calculations for localization, but the text focuses on its equivalence rather than reader improvement.

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

• The document implies that the "3D tomosynthesis lesion location" calculation itself was evaluated for "accuracy" and "substantial equivalence." This suggests an evaluation of the algorithm's output (lesion coordinates) as a standalone function, separate from a human interpreting images. However, specific details of such a standalone study (e.g., methodology, metrics, and number of cases) are not provided.

7. The type of ground truth used:

• The document states "Accuracy can be verified during the biopsy process." This strongly suggests that the ground truth for localization accuracy would be based on biopsy results or confirmation during the interventional procedure. However, it is not explicitly stated how this ground truth was used in specific verification or validation tests mentioned.

8. The sample size for the training set:

• Not specified in the provided text. This document is for a modified version of an already cleared device, primarily focusing on a software change. Details of the original device's training are not provided, nor are details of any specific training done for the 3D tomosynthesis algorithm.

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

• Not specified in the provided text.

Ask a specific question about this device

The Biopsy Digit S and SL are intended to be used for mammographic procedures requiring stereotactic guidance, such as fine needle aspiration, needle biopsy and guide wire placement.

The Biopsy Digit S and Biopsy Digit SL are modifications to the Biopsy Digit AM needle guidance system. previously cleared as #K062039. and supplied as an accessory to the Giotto Image 3D/DL mammography system. The CMOS digital camera used on the Biopsy Digit AM is not used on the Biopsy Digit S/SL. Rather a 65mm (high) X 80mm (wide) portion of the full field amorphous selenium detector of the Giotto Image 3D/DL is used to acquire the mammographic, targeting, image data. The mechanics, cleanable surfaces, on-board electronics, and user interface software are all the same as on the biopsy Digit AM. The Biopsy Digit S/SL receives power from the Giotto Image 3D/DL. The Biopsy Digit S/SL in conjunction with the Giotto Image 3D/DL, take two exposures at separate angles ± 22.6° from the perpendicular of the digital detector centerline. The x-ray tube is driven first to one side of center and then to the other by an electro-mechanical mechanism, which is an integral part of the Giotto Image 3D/3DL, so that a stereo pair of images can be acquired. The two views provide two separate 2dimensional projections of the subject anatomy. The two views are stored in the computer system, and can be retrieved and viewed on the computer monitor. The operator, using a mouse, identifies the region of interest on the monitor. The computer then calculates of the region of interest in three dimensions, using trigonometry, and then transfers the coordinates to the needle-positioning unit. The software algorithm used for the calculation is identical to that used by the Biopsy Digit AM (#K062039). The needle-positioning unit then drives the needle holder to the required location so that the operator can insert the needle or locating wire into the exact coordinates necessary.

The provided 510(k) summary for the Giotto Biopsy Digit S/SL does not contain explicit acceptance criteria or a detailed study description with specific performance metrics and statistical analyses typically associated with proving a device meets acceptance criteria.

The document describes the device as a modification of a previously cleared device (Biopsy Digit AM) and focuses on demonstrating substantial equivalence through non-clinical testing. It highlights changes in the detector technology (from CMOS to an amorphous selenium detector) and confirms that the mechanics and software algorithms remain the same.

However, based on the information provided, here's what can be inferred and what is explicitly missing:

1. Table of Acceptance Criteria and Reported Device Performance

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

This information is not provided in the document. There is no mention of the number of images, cases, or subjects used in any of the described tests. The provenance of any data (e.g., country of origin, retrospective/prospective) is also not stated.

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

This information is not provided. The document mentions "end user validation testing," but does not specify how many users participated, their qualifications, or how any "ground truth" for this validation was established. For stereotactic accuracy testing, the "ground truth" would likely be derived from physical measurements against a known standard, not expert consensus.

4. Adjudication Method for the Test Set

This information is not provided. Given the nature of the testing described (comparative image parameters, stereotactic accuracy, end-user validation), an adjudication method (like 2+1 or 3+1 expert consensus) is unlikely to be directly applicable in the way it would be for diagnostic AI performance. For end-user validation, feedback mechanisms would be used, but the specific method is not detailed.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed or described in this 510(k) submission. The device is a needle guidance system, not a diagnostic AI intended to assist human readers in interpretation. Therefore, assessing how human readers improve with or without AI assistance is not relevant to this device's function as described.

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

Standalone performance, especially for the "software algorithm used for the calculation" of the region of interest in three dimensions, was implicitly tested. The document states:

• "Stereotactic accuracy testing for both biopsy systems in compliance with IEC Standard 60601-2-45"
  This testing would assess the accuracy of the system (including the algorithm) in guiding the needle, independent of a specific human operator's interpretation. However, specific results of this standalone accuracy are not provided. The document emphasizes that "The software algorithm used for the calculation is identical to that used by the Biopsy Digit AM (#K062039)," relying on the previous clearance for the algorithm's validation.

7. The Type of Ground Truth Used

• For Image Parameter Testing: Likely objective measures derived from test phantoms or calibrated imaging standards.
• For Stereotactic Accuracy Testing: Established through physical measurements against known targets or a gold standard measurement device, as per IEC Standard 60601-2-45.
• For End User Validation: Likely user feedback and possibly a demonstration of successful task completion based on the device's intended use.
• For Compliance with Standards: Objective verification against the requirements of the specified IEC standards.

The document does not explicitly state the exact nature of the ground truth for each test, but it can be inferred from the type of testing.

8. The Sample Size for the Training Set

This information is not applicable / not provided. The device is an accessory for stereotactic guidance, not a machine learning or AI algorithm that requires a training set in the conventional sense. The "software algorithm" for coordinate calculation is stated to be "identical" to the predicate device, implying it was developed and validated previously, not "trained" in this submission.

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

This information is not applicable / not provided for the same reasons as #8. If the "software algorithm" for coordinate calculation was developed using any form of historical data or training, those details are not within this 510(k) submission. The submission relies on the previous clearance (K062039) for the validation of this specific algorithm.

Ask a specific question about this device