Search Results

The Senographe Pristina system is intended to be used in the same clinical applications as traditional mammographic film/ screen systems. It generates digital mammographic images which can be used for screening and diagnosis of breast cancer.

eContrast is an image post-processing algorithm applied to the DICOM "for processing" images in order to generate “for presentation" images. It consists in optimizing the local contrasts while reducing the overall dynamic range. This submission is proposing a software modification consisting of a new version of eContrast algorithm for Senographe Pristina platform to allow more flexibility for proposing different levels preserving/enhancing the visibility of the different structures present in the breast image. The first version of the eContrast image processing was previously cleared for Senographe Essential platform in the 510(k)# K131885. Then it was cleared with Senographe Pristina platform in the 510(k) # K162268. This design change is a software and labeling only option, compatible with Senographe Pristina installed base and does not require any hardware modification on the Senographe Pristina platform.

Here's a breakdown of the acceptance criteria and study information for the Senographe Pristina with the new version of eContrast, based on the provided document:

1. Acceptance Criteria and Reported Device Performance

The provided document describes a change to an existing cleared device (Senographe Pristina with eContrast K162268), specifically a new version of the eContrast post-processing algorithm. The core acceptance criteria revolve around demonstrating that the new version is substantially equivalent to the predicate device and does not raise new questions of safety or effectiveness.

2. Sample Size and Data Provenance for Test Set (Clinical Data)

• Sample Size: Not explicitly stated for the clinical image review. The document mentions "clinical image review by radiologists" but does not specify the number of images or cases reviewed.
• Data Provenance: Not explicitly stated. It's likely retrospective as it involves reviewing existing images, but this is not confirmed. The country of origin is not mentioned.

3. Number of Experts and Qualifications for Ground Truth (Clinical Data)

• Number of Experts: "radiologists" (plural), but the exact number is not specified.
• Qualifications: "radiologists." Specific years of experience or sub-specialty are not provided.

4. Adjudication Method for Test Set (Clinical Data)

• Adjudication Method: Not explicitly stated. The document mentions "clinical image review by radiologists, with objective criteria defined," but does not detail how disagreements among radiologists, if any, were resolved.

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

• No MRMC Study was done. The study's purpose was to demonstrate substantial equivalence of a new version of an image processing algorithm, not to show improvement of human readers with AI assistance. It aimed to show that the new algorithm's output was "acceptable" and "same quality" as the previous version.

6. Standalone Performance Study (Algorithm Only)

• Yes, a standalone performance study was implicitly done through the "Non-Clinical Data – Image Quality and Dose test." This test would assess the direct output of the algorithm (image quality) without human intervention, comparing it to the previous version's output. The document states this test "demonstrates that images acquired with Senographe Pristina with the new version of eContrast are of same quality as images acquired with Senographe Pristina with eContrast as cleared in K162268 at similar dose levels."

7. Type of Ground Truth Used

• Non-Clinical Data (Image Quality): The ground truth for image quality comparison would likely be based on established image quality metrics, possibly evaluated against images from the predicate device as a reference standard. These are objective measures rather than expert consensus on disease.
• Clinical Data (Clinical Image Acceptability): The ground truth for clinical image acceptability was established via "objective criteria defined" by radiologists. This suggests a form of expert consensus or adherence to predefined quality standards for clinical interpretation, rather than pathology or outcomes data related to disease detection.

8. Sample Size for the Training Set

• Not applicable / Not disclosed. The document describes a modification to an existing algorithm (eContrast) rather than the development of a wholly new AI model that typically requires a separate training set. The new version of eContrast is an "extension of the current algorithm." If any internal parameter tuning or retraining occurred, the details of a training set are not provided. It's more of an algorithm update than a de novo AI model.

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

• Not applicable / Not disclosed. As noted above, this appears to be an algorithm update rather than a new AI model requiring a separate training set with specific ground truth for learning.

Ask a specific question about this device

The Pristina Serena option provides the three-dimensional locations, using information obtained from stereotactic pairs of two-dimensional X-ray images. This information provides guidance for a variety of minimally invasive or interventional procedures in the breast such as: vacuum assisted biopsy, core biopsy, pre-surgical localization (e.g. hookwire), and fine needle aspirations (FNA).

Pristina Serena is a hardware and software add-on to the Senographe Pristina mammography platform (cleared in K162268).
Pristina Serena uses the Stereotaxy principle to determine the three-dimensional (3D) location (X, Y and Z coordinates) of a region of interest in the breast (such as a suspicious lesion).
The stereotaxy biopsy process uses a stereo pair of +/-15° angulated 2D low-dose X-ray images of the compressed breast. The user identifies the point of interest in each image of the stereo pair, Pristina Serena computes the three dimensions coordinates (X,Y,Z) of the user-specified location in the stereo pair.
Pristina Serena uses the target lesion 3D coordinates and information on the geometry of the biopsy device to compute the position of a biopsy device holder that will allow intervention in the breast at the targeted position (biopsy of sample tissue or placement of a hookwire for guidance of surgical interventions).
The Pristina Serena add-on includes the following items:
Hardware: a Biopsy Positioner (BP) the main hardware component of the Pristina Serena option. It can be mounted on the Senographe Pristina in lieu of the Imaging Bucky. The purpose of the BP is to allows breast positioning and mechanical guidance to the target lesion for Biopsy medical application; dedicated breast compression paddles for Biopsy application; mechanical adaptors: pieces of hardware to allow mounting of several kind of biopsy devices on the Biopsy positioner arm.
Software: A new software version for the Senographe Pristina platform which includes software to manage the Pristina Serena option. Labeling for the Biopsy Medical application.
Pristina Serena option is compatible with previously installed Senographe Pristina systems. Pristina Serena does not require any hardware modification on the Senographe Pristina platform.

Here's an analysis of the provided text to extract information about the acceptance criteria and the study proving the device meets them, specifically for the GE Healthcare Pristina Serena.

It's important to note that the provided text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than a full clinical trial report or a detailed performance validation study. Therefore, some information, particularly regarding specifics of human reader studies (MRMC), detailed ground truth methodologies for large datasets, and training set information, may not be explicitly present or fully elaborated upon as one might find in a peer-reviewed publication or a more comprehensive FDA submission. The focus here is on bench performance testing for accuracy and engineering validation for safety and proper function.

Acceptance Criteria and Device Performance for Pristina Serena (K173576)

The primary acceptance criteria mentioned for the Pristina Serena are related to its biopsy accuracy and image quality/dose performance, demonstrating equivalence to its predicate device (Senographe Stereo) and reference predicate (Senographe Pristina).

1. Table of Acceptance Criteria and Reported Device Performance

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

The text does not specify numerical sample sizes for the "biopsy accuracy testing" or "image quality and dose performance testing."

Regarding data provenance:

• The tests described ("engineering bench performance testing") are laboratory-based and simulation-based.
• The device is manufactured by GE Healthcare in France (283 RUE DE LA MINIERE, 78530 BUC - FRANCE).
• The nature of the testing implies these are prospective bench tests performed during device development and validation.
• The data used for these engineering tests would typically be generated in a controlled lab environment rather than being retrospective patient data from a specific country, as these are tests of the device's technical specifications.

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

For the engineering bench tests described (biopsy accuracy, image quality/dose), the concept of "experts establishing ground truth for a test set" in the context of human interpretation of medical images (like for an AI algorithm's diagnostic performance) is not directly applicable.

• Ground truth for biopsy accuracy: This would be established by precise metrology and physical measurements of the needle tip's position relative to a target in a phantom using the device. This is a technical measurement, not an expert interpretation.
• Ground truth for image quality/dose: This would be established by physical measurements (e.g., dose meters) and standardized image quality metrics (e.g., contrast, spatial resolution) using phantoms, not by human experts.

Therefore, the text does not mention human experts for establishing ground truth for these specific performance tests.

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

Given that the performance evaluation relies on "engineering bench performance testing" and technical measurements/verification, adjudication methods as typically used in human reader studies (like 2+1 or 3+1 consensus for ambiguous cases) are not applicable or mentioned in this context. The determination of accuracy and image quality is based on objective, quantifiable metrics following established engineering 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 MRMC comparative effectiveness study is mentioned in this 510(k) summary. The Pristina Serena device is a stereotactic biopsy guidance system, not an AI-assisted diagnostic tool for image interpretation. Its function is to guide physical interventions, not to interpret images for diagnosis alongside human readers. Therefore, there is no discussion of human reader improvement with or without AI assistance.

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

This device is not an AI algorithm for image interpretation. It's a hardware and software add-on that uses stereotaxy principles to calculate 3D coordinates based on user-identified points in 2D images.

• The "standalone" performance here refers to the system's ability to accurately calculate the 3D coordinates and guide the biopsy device. This was addressed by the "Biopsy accuracy testing."
• The user is "human-in-the-loop" by identifying the initial point of interest in the images, but the calculation itself is algorithmic/systemic. The tests confirm the accuracy of the system's output (3D coordinates and guidance).

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

For the "Biopsy accuracy testing":

• The ground truth is established by physical measurement of the actual position of the biopsy needle tip (or needle notch) relative to a known target in a phantom. This is a highly precise engineering measurement.
• It is not based on expert consensus, pathology, or outcomes data, as those are typically used for diagnostic or prognostic AI systems evaluated on patient data.

For "Image quality and dose performance testing":

• The ground truth is established by physical measurements using phantoms and adherence to established image quality metrics.

8. The sample size for the training set

The text does not mention a training set sample size. This is expected because the Pristina Serena is a stereotactic guidance system, not a machine learning or deep learning AI model that requires a vast training dataset of medical images. Its core function is based on principles of geometry and X-ray physics to calculate 3D coordinates from 2D images.

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

As no training set (in the context of machine learning) is mentioned or implied for this device, the question of how its ground truth was established is not applicable. The device's operation relies on established physical and mathematical principles, which do not typically involve a "training" phase with ground-truth labels in the way AI/ML algorithms do. The development involved traditional software development lifecycle testing, verification, and validation against engineering specifications.

Ask a specific question about this device

SenoBright HD is an extension of the existing indication for diagnostic mammography with Senographe Pristina. The SenoBright HD application shall enable contrast enhanced breast imaging a dual energy technique. This imaging technique can be used as an adjunct following mammography and ultrasound exams to help localize a known or suspected lesion.

The subject of this submission is a modification of Senographe Pristina FFDM system (cleared in K162268) that will introduce a new imaging option called SenoBright HD. This imaging option has been previously cleared for Senographe Essential FFDM system in K103485,marketed as SenoBright Contrast Enhanced Spectral Mammography (CESM). The dual energy exposures will be done following an iodine based contrast injection of the patient and with a single breast compression. The new mode of operation for Senographe Pristina system is referred to as SenoBright HD Contrast Enhanced Spectral Mammography (CESM) due to the nature of taking an exposure with the x-ray spectrum optimized for general mammographic imaging and a second exposure with the x-ray spectrum optimized for the iodine based contrast image. The main modification of the Senographe Pristina system is the addition of software feature to control the low and high energy images and post processing and recombination of those images to create FFDM like image and recombined image. These two images allow the visualization of the breast tissue in a way that is typical and familiar for mammographic imaging and the x-ray contrast enhancement in the breast at the same time.

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

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

The document does not explicitly state quantitative acceptance criteria in a table format, nor does it provide specific reported device performance metrics against such criteria. Instead, it makes a general statement about "appropriate performance" and "good" image quality.

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

• Test Set Sample Size: The document only mentions a "Clinical image evaluation was performed" without specifying the number of images or cases in the test set.
• Data Provenance: Not specified (e.g., country of origin, retrospective or prospective).

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: "expert radiologists" (plural) were used, but the exact number is not specified.
• Qualifications of Experts: Only "expert radiologists" is stated, without details on their specific experience (e.g., years of experience, board certifications).

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

The document does not specify an adjudication method for the test set. It only mentions that an evaluation was performed by "expert radiologists."

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

A multi-reader multi-case (MRMC) comparative effectiveness study focusing on human readers improving with AI vs. without AI assistance was not done. The device description explicitly states: "The SenoBright HD application shall enable contrast enhanced breast imaging a dual energy technique. This imaging technique can be used as an adjunct following mammography and ultrasound exams to help localize a known or suspected lesion." This implies it is a diagnostic imaging tool, not an AI-assisted reader tool.

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

The device itself is an imaging system (Full-field digital mammography system with contrast enhancement), not an algorithm. Therefore, a "standalone algorithm only" performance study is not directly applicable in the way it would be for an AI-CAD device. The "Clinical image evaluation" mentioned was likely to assess the quality and utility of the images produced by the device, which would then be interpreted by human readers.

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

The document states "A Clinical image evaluation was performed showing that image quality of SenoBright HD in a clinical setting is good as assessed by expert radiologists." This implies that the ground truth for the image quality assessment was expert radiologist assessment/consensus. It does not mention pathology or outcomes data as ground truth for this specific evaluation, as the evaluation focused on image quality rather than diagnostic accuracy against a definitive truth for lesions.

8. The sample size for the training set

The document does not provide any information about a specific "training set" or its size. The device is a modification of an existing FFDM system, introducing new software features for image acquisition and processing. This suggests that the development likely involved engineering and image processing adjustments rather than deep learning model training in the conventional sense that would require a distinct "training set."

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

As no training set is mentioned for an AI model, this question is not applicable based on the provided text. The "ground truth" for the development of the image processing might have involved phantom studies and clinical images used for optimization, but these are not described as a formal "training set" with established ground truth in the context of machine learning.

Ask a specific question about this device