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

Sample Imaging for Senographe Pristina™ with Pristina Serena™ biopsy option is intended to provide digital X-ray images of the biopsy excised breast tissues while the patient is still under compression, to allow rapid verification that the correct tissue has been excised during the biopsy procedure.

Sample Imaging for Senographe Pristina is an additional option that builds upon the Pristina Serena Stereotaxy biopsy device cleared on May 14, 2018 (K173576). The Sample Imaging option enables the imaging of breast tissue samples collected during biopsy medical application. In other words, the Sample Imaging option provides the capability to image, within the same examination, and while the patient is still under compression, the breast tissue samples collected during biopsy procedures performed with any biopsy medical application available on the system. The acquisition of such images is done with dose to the patient limited to scatter radiation from the samples.

The provided text describes a 510(k) submission for "Sample Imaging for Senographe Pristina" by GE Healthcare. The purpose of this device is to provide X-ray images of excised breast tissues during biopsy procedures for rapid verification.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided document:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the safety and performance claims made and the comparative testing against a predicate device and a reference device. The primary performance claim is regarding image quality and dose.

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

The document does not specify the sample size for the test set used in the performance evaluation.
The data provenance is also not explicitly stated in terms of country of origin or whether it was retrospective or prospective patient data. The tests appear to be pre-clinical bench testing ("Image Quality test," "Patient Radiation Dose Testing," "MTF was measured") rather than studies on a patient cohort. The "ACR mini stereotactic breast biopsy accreditation phantom" was used, indicating phantom-based testing.

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

The document does not mention any human experts being used to establish a ground truth for the test set. The evaluation relies on objective technical measurements (image quality, MTF, dose) using a phantom, rather than human expert interpretation of images.

4. Adjudication Method for the Test Set

Since no human experts were involved in evaluating images for ground truth, there was no adjudication method described. The tests were objective, technical measurements.

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

No MRMC comparative effectiveness study was done as described in the provided text. The evaluation focuses on technical performance metrics (image quality, MTF, dose) of the device itself, rather than assessing human reader performance with or without the device.

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

The device itself is an "imaging option" that provides digital X-ray images. The "performance" described is about the quality of these images and the dose produced. This is inherently a "standalone" or "algorithm only" performance since it refers to the image acquisition and processing capabilities of the system (e.g., "FineView" processing, MTF measurements, image quality on a phantom). It's not an AI algorithm but a hardware/software imaging feature.

7. The Type of Ground Truth Used

The ground truth for the performance testing was established by technical metrics and a standardized phantom.

• ACR mini stereotactic breast biopsy accreditation phantom: Used for Image Quality assessment.
• MTF measurements: Optical/technical property of image sharpness.
• Air Kerma measurements: Objective radiation dose measurement.
  This is not expert consensus, pathology, or outcomes data, but rather a phantom-based, objective technical evaluation.

8. The Sample Size for the Training Set

The document does not refer to a "training set" in the context of machine learning or AI models. This device is an imaging system component, not an AI algorithm that requires a training set of data. The development process mentions "development under GE Healthcare's quality management system and design controls" and "full verification testing and additional engineering bench performance testing."

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

As there is no mention of a "training set" for an AI/ML component, this question is not applicable based on the provided information. The device functions as an imaging system, and its performance verification appears to be based on engineering and quality control procedures, rather than a data-driven training/validation paradigm.

Ask a specific question about this device

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.

Patient-assisted compression (Self-Compression) is an option of the Senographe Pristina Full Field Digital Mammography system. It consists of a handheld wireless remote control to allow patient to adjust the compression force during breast positioning. The remote transmits the compression command to the Senographe Pristina. Senographe Pristina executes the command by raising or lowering the compression paddle, if conditions for motion are met.

Patient-assisted compression is designed to minimize patients perceived pain and discomfort by giving them an active role in the application of compression. The technologist positions the patient and initiates compression. The technologist then guides the patient while she operates the remote to gradually increase compression until she reaches adequate compression.

The provided text describes the Senographe Pristina Full-Field Digital Mammography System and an optional patient-assisted compression feature. However, the text does not contain acceptance criteria or a detailed study that proves the device meets specific performance criteria related to the image quality or diagnostic accuracy of the mammography system itself.

The "Performance Testing" section primarily focuses on the patient-assisted compression option and its impact on image quality compared to technologist-applied compression. It states that patient-assisted compression produced images of similar quality.

Here's an attempt to answer your questions based only on the provided text, acknowledging that many questions cannot be fully answered due to limited information:

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

The document does not explicitly state quantitative acceptance criteria for the mammography device's diagnostic performance (e.g., sensitivity, specificity for cancer detection). The performance testing described is for the patient-assisted compression feature, not the core mammography system's diagnostic ability.

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

• Test Set Sample Size: 30 patients.
• Data Provenance: Not explicitly stated (e.g., country of origin). It's implied to be prospective as it's a "clinical evaluation."

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

• The text states "MQSA qualified radiologists" assessed image quality. It does not specify the number of radiologists or their years of experience.
• Ground Truth for Image Quality: Radiologist assessment of image quality based on criteria set in the "Guidance for Industry and FDA Staff - Class II Special Controls Guidance Document: Full Field Digital Mammography System." This is an expert opinion/consensus on image quality, not disease presence.

4. Adjudication method for the test set

Not specified. The text only mentions "Image quality was assessed by MQSA qualified radiologists." It does not indicate if multiple radiologists assessed each image and how disagreements were resolved.

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 document does not mention an MRMC study or any AI assistance. The "performance testing" was a clinical evaluation of the patient-assisted compression feature, comparing image quality between two compression methods.

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

No. This is a medical imaging device, not an algorithm being tested in standalone mode.

7. The type of ground truth used

For the patient-assisted compression clinical evaluation, the "ground truth" was expert assessment/opinion of image quality by MQSA qualified radiologists. It was not pathology, outcomes data, or expert consensus on disease diagnosis.

8. The sample size for the training set

Not applicable/mentioned. The document describes a medical device, not a machine learning algorithm that requires a training set in the typical sense. If the "design and test" phase involved iterative development, the "training" would be part of the engineering and testing process rather than a distinct dataset for an algorithm.

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

Not applicable/mentioned. See answer to question 8.

Ask a specific question about this device

Senographe Pristina generates digital mammographic images that can be used for screening and in the diagnosis of breast cancer. Senographe Pristina is intended to be used in the same clinical applications as traditional mammographic screenfilm systems.

Senographe Pristina is a new Full Field Digital Mammography (FFDM) system. The system consists of an X-ray image acquisition system dedicated to breast imaging and of a control station for image acquisition, processing and display. The image acquisition system includes a Cesium lodine digital detector, x-ray tube, integrated high voltage generator, compression paddles. The control station provides a touch-screen user interface to control image acquisition, image processing, and image transfer.

The provided text describes GE Healthcare's Senographe Pristina, a full-field digital mammography system, and its FDA 510(k) clearance (K162268). The document summarizes the device, its indications for use, comparison to a predicate device (Senographe Essential), and the studies conducted to demonstrate substantial equivalence.

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

1. Table of Acceptance Criteria and Reported Device Performance:

The document mentions a "Clinical image evaluation was performed showing that image quality of Senographe Pristina in a clinical setting is good as assessed by expert radiologists." However, specific quantitative acceptance criteria or numerical performance metrics for this clinical image evaluation are not explicitly stated in the provided text. The statement "showing appropriate performance" in the context of "Complete Image Quality Bench Performance testing" also lacks specific metrics.

Therefore, a table of acceptance criteria and reported device performance cannot be fully constructed from the provided text in a quantitative sense. The acceptance criterion appears to be a qualitative assessment by expert radiologists that the image quality is "good."

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

The provided text does not explicitly state the sample size used for the clinical image evaluation (test set) or the data provenance (e.g., country of origin, retrospective/prospective). It only mentions "a clinical setting."

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

The text states that image quality was "assessed by expert radiologists." However, the number of experts and their specific qualifications (e.g., years of experience) are not specified in the provided document.

4. Adjudication method for the test set:

The adjudication method used for the clinical image evaluation is not specified in the provided text. It only mentions assessment 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:

The provided document describes the Senographe Pristina as a full-field digital mammography system for image acquisition, not an AI-driven image analysis or CAD device. Therefore, an MRMC comparative effectiveness study regarding "human readers improve with AI vs without AI assistance" would not be applicable for this device as described. The focus is on demonstrating equivalent image quality to a predicate device.

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

Similar to point 5, the Senographe Pristina is an image acquisition system, not an AI algorithm for diagnosis. Therefore, a standalone performance study of an algorithm without human-in-the-loop performance is not applicable in this context. The "Clinical image evaluation" mentioned appears to involve human radiologists assessing the quality of images produced by the device.

7. The type of ground truth used:

For the clinical image evaluation, the "ground truth" for image quality appears to be the qualitative assessment of "good" image quality by expert radiologists. This is based on visual assessment of factors like clarity, contrast, and resolution relevant for screening and diagnosis, implying a form of expert consensus on image interpretability, rather than a definitive "truth" like pathology or outcomes data.

8. The sample size for the training set:

As the Senographe Pristina is a hardware device (mammography system) and not an AI algorithm directly, the concept of a "training set" in the context of machine learning is not directly applicable to the device itself.
The "Complete Image Quality Bench Performance testing" and "Clinical image evaluation" are more akin to validation steps for the device's imaging capabilities, rather than training data for an AI model.

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

Since a traditional "training set" for an AI algorithm is not explicitly discussed for this device, the question of how its ground truth was established is not applicable in the context of the provided document. The development and testing of the device focus on hardware performance and image quality validation against established medical standards and comparison to a predicate device.

Ask a specific question about this device