Search Results

HESTIA is indicated for generating mammographic images that can be used for screening and diagnosis of breast cancer. HESTIA is intended to be used in the same clinical applications as traditional film/screen systems.

HESTIA is a Full-Field Digital Mammography (FFDM) System for screening, diagnostic on standing or seated patients. The system consists of a control unit with x-ray generator, a compression device(C-arm) with tube housing assembly, and X-ray tube stand, including detector and a console with an operation panel. The HESTIA comes with a variety of compression plates for diagnostic adjunct procedures.

The system is mainly used in internal medicine, examination centers, obstetrics and gynecology, women's medicine, breast surgery, and imaging. Mammography X-rays are used to obtain diagnostic images of the breast's internal structure to diagnose changes more accurately in breast tissue or potential signs of breast cancer, such as micro-calcification or tumors.

HESTIA has three output control mode, Manual mode, Semi-auto mode, and Auto mode.

It is customized and dedicated acquisition workstation and can PACS accessibility with full DICOM capability.

The provided FDA 510(k) clearance letter and summary for the HESTIA Mammography System DOES NOT CONTAIN the detailed information typically found in a study proving a device meets acceptance criteria, particularly for AI/CAD devices. The HESTIA device is a Full-Field Digital Mammography (FFDM) System, a hardware device for generating mammographic images, not an AI/CAD software for interpreting them.

The summary specifically states:

• "A clinical image evaluation... was conducted with the HESTIA and determined that the images, reviewed by MQSA qualified expert radiologists, were of sufficiently acceptable quality for mammographic usage and that the images are substantially equivalent to those from predicate device."

This indicates a human-in-the-loop comparison of image quality (visual assessment by radiologists for diagnostic suitability) rather than an AI/CAD performance study with metrics like sensitivity, specificity, or AUC, which are common for AI algorithms. The "clinical image evaluation" mentioned is likely focused on demonstrating that the images produced by the HESTIA system are diagnostically acceptable and equivalent to those from the predicate device, not on assessing the performance of an AI against a ground truth established by experts.

Therefore, many of the requested items related to AI/CAD study design (e.g., sample size for test set, data provenance, number of experts for ground truth, adjudication method, MRMC studies, standalone performance, training set details) are not applicable or not provided in this document as it describes a hardware imaging system, not an AI interpretation software.

However, based on the information provided, here's what can be extracted and inferred, addressing as many points as possible:

Acceptance Criteria and Study for HESTIA Mammography System

As the HESTIA is a hardware Full-Field Digital Mammography (FFDM) system, not an AI/CAD software, the acceptance criteria and study design are primarily focused on demonstrating the system's ability to produce diagnostically acceptable images and its substantial equivalence to a predicate device in terms of image quality and safety. There is no indication of an AI component or AI performance metrics in this 510(k) summary.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for a FFDM system like HESTIA are typically related to image quality metrics, safety standards, and functional equivalence to predicate devices. The document summarizes compliance with these, rather than providing a quantitative table of specific acceptance thresholds and measured values for image interpretation performance (which would be relevant for AI).

• Electromagnetic Compatibility (EMC): Compliant with IEC 60601-1-2.
• Radiation Protection: Compliant with IEC 60601-1-3.
• Usability: Compliant with IEC 60601-1-6.
• Mammographic X-ray Equipment Specifics: Compliant with IEC 60601-2-45.
• Biocompatibility: Compliant with ISO 10993-1, -5, -10.
• Software Life Cycle: Compliant with IEC 62304.
• Risk Management: Compliant with ISO 14971.
• Physical Laboratory Testing (Image Quality): Met all requirements for: Sensitometric response, Spatial resolution, Noise analysis, Signal-to-Noise Ratio Transfer-DQE, Dynamic range, Repeated exposures Test (Lag Effect), AEC Performance (CNR and SRN), Phantom tests (ACR Map, CDMAM), Patient radiation dose (Mean Glandular Dose). All tests demonstrated substantial equivalence to the predicate device. |
  | Clinical Image Evaluation | - Images reviewed by MQSA qualified expert radiologists were determined to be of "sufficiently acceptable quality for mammographic usage."
• Images were found to be "substantially equivalent to those from predicate device." |
  | Intended Use | - "Generating mammographic images that can be used for screening and diagnosis of breast cancer."
• "Intended to be used in the same clinical applications as traditional film/screen systems." (Met, as indications for use are identical to the predicate device). |

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

The document does not specify a distinct "test set" sample size in terms of patient cases for clinical evaluation, nor does it detail data provenance (country of origin, retrospective/prospective). The "clinical image evaluation" often involves a small number of images for visual quality assessment rather than a large clinical trial with diverse patient populations for diagnostic accuracy.

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

• Number of Experts: Not explicitly stated. The statement refers to "MQSA qualified expert radiologists."
• Qualifications: "MQSA qualified expert radiologists." (MQSA stands for Mammography Quality Standards Act, which sets federal standards for mammography facilities and personnel in the U.S. This implies they are board-certified and meet specific continuing education and interpretation requirements for mammography.)

4. Adjudication Method for the Test Set

Not specified, as this was an image quality assessment by radiologists rather than a diagnostic performance study requiring ground truth establishment through adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size.

No information regarding an MRMC comparative effectiveness study for human readers with vs. without AI assistance. This type of study is relevant for AI/CAD devices, which is not what HESTIA is. The clinical evaluation focuses on the image quality produced by the HESTIA system being comparable to the predicate.

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

Not applicable. HESTIA is a hardware imaging system, not a standalone AI algorithm.

7. The Type of Ground Truth Used

For the clinical image evaluation, the "ground truth" was based on the consensus/judgment of MQSA qualified expert radiologists regarding the diagnostic acceptability and equivalence of the image quality produced by the HESTIA system compared to the predicate device. This is distinct from establishing a clinical ground truth (e.g., biopsy-proven cancer) for an AI's diagnostic performance.

8. The Sample Size for the Training Set

Not applicable. HESTIA is a hardware device; thus, there is no mention of a training set as would be required for an AI algorithm.

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

Not applicable, as there is no training set for a hardware device.

Ask a specific question about this device

The 2430TCA Digital Flat Panel X-Ray Detector is indicated for digital imaging solution designed for a mammographic system. It is intended to replace film or screen based mammographic systems in screening mammography. Xmaru W is an integrated software solution indicated for use with the 2430TCA detector.

2430TCA is a digital mammography X-ray detector that is based on flat-panel technology. This mammographic image detector and processing unit consists of a CsI scintillator coupled to a TFT sensor. This device needs to be integrated with a mammographic imaging system. It can be utilized to capture and digitalize X-ray images for mammographic screening. The RAW files can be further processed as DICOM compatible image files by separate console SW, Xmaru W, for a mammographic screening. 2430TCA detector is connected to the viewing station via a LAN cable.

The provided text is a 510(k) summary for the Rayence 2430TCA with Xmaru W, a digital mammography system. While it discusses the device's characteristics and compares it to a predicate device (2430MCA with Xmaru W), it does NOT contain detailed information about acceptance criteria for an AI/software component, nor a specific study proving it meets such criteria in terms of AI performance.

The document primarily focuses on demonstrating substantial equivalence of the detector (2430TCA) to its predicate (2430MCA) based on physical characteristics, imaging performance (MTF, DQE, NPS), and human expert review of images. It also mentions general software (Xmaru W) but doesn't detail any AI functionality or its validation.

Therefore,Based on the provided FDA 510(k) summary, I cannot provide the requested information about acceptance criteria and a study proving an AI component of the device meets those criteria.

The document discusses the substantial equivalence of a Full-Field Digital Mammography System (including a detector and image processing software). It focuses on the hardware (2430TCA detector) and its image quality parameters (MTF, DQE, NPS) compared to a predicate device. While it mentions "Xmaru W is an integrated software solution," it does not describe any specific AI or machine learning functionality within this software, nor does it discuss validation studies for such a component.

The "Summary of Performance Testing" section describes:

• Human expert review of plain radiographic images from the 2430TCA and 2430MCA, concluding "overall, better image quality of the same anatomical position in the separate patients" for 2430TCA.
• Non-clinical tests (MTF, DQE, NPS) performed on the detector, not an AI algorithm.

Therefore, many of the specific points you've asked for (e.g., sample size for test set, number of experts for ground truth, adjudication method, MRMC study, standalone performance, training set details) are not present in this document because it is focused on the performance of a digital X-ray detector and its fundamental image quality, not an AI algorithm.

If this device were to have an AI component for advanced image analysis (e.g., CADe for lesion detection), that information would typically be in a separate section detailing the AI's performance validation, often with a different set of acceptance criteria and study designs that align with the specific AI function (e.g., sensitivity, specificity, FROC analysis, reader studies). This document does not suggest the presence or validation of such an AI component for diagnostic aid.

Ask a specific question about this device

VIVIX-M detectors are flat panel detectors used in mammographic applications to acquire digital images for screening and diagnosis.

VIVIX-M, a series of flat panel detectors models named; FXMD-2430S, with imaging areas of 24cm x 30cm, 18cm x 24cm, respectively. The device intercepts x-ray photons and the scintillator emits visible spectrum photons that illuminate an array of photo (a-SI)-detectors that create electrical signals. After the electrical signals are generated, it is converted to digital value, and the Software acquires and processes the data values from the detector. The resulting digital images will be displayed on monitors. These devices should be integrated with an operating PC and an X-Ray generator. It can be utilized to digitalize x-ray images and transfer for radiography diagnostic.

VXvue Mammo is a digital X-ray imaging software designed for mammography applications. It acquires, processes, and transmits digital images from VIVIX-M detectors (FXMD-1008S and FXMD-2430S) while ensuring compliance with DICOM standards for seamless integration with PACS and other medical systems.

The provided document is a 510(k) summary for the VIVIX-M Digital X-ray detectors (models FXMD-2430S and FXMD-1008S). It states that the device is substantially equivalent to a predicate device (RSM 2430C, K170930).

However, the document does not contain the detailed acceptance criteria and a comprehensive study that proves the device meets those acceptance criteria in the format requested. Specifically:

• No explicit table of acceptance criteria and reported device performance for clinical endpoints. The document provides a table comparing the subject device to the predicate device for technical parameters (MTF, DQE) and states "Substantially Equivalent" but does not define numerical acceptance thresholds for these or for clinical performance.
• No details on sample size for the test set or data provenance for a clinical study. It mentions a "clinical image evaluation" was conducted but provides no specifics on the number of cases, patient demographics, or whether the data was retrospective or prospective, or its country of origin.
• No information on the number or qualifications of experts used for ground truth.
• No adjudication method specified for the test set.
• No Multi-Reader Multi-Case (MRMC) comparative effectiveness study details. There is no mention of human readers improving with AI assistance because this is a detector, not an AI-enabled device for interpretation.
• No "standalone (i.e. algorithm only without human-in-the-loop performance)" was done for clinical endpoints. This is a hardware device; its performance is assessed through image quality metrics (MTF, DQE, NPS, etc.) and clinical image evaluation for diagnostic capability, not an algorithm's standalone performance.
• The type of ground truth for clinical evaluation is not specified beyond "equivalent diagnostic capability."
• No training set size or ground truth establishment method for a training set. This device is a digital X-ray detector, not an AI/ML algorithm that is trained on a dataset. The performance evaluation is based on non-clinical technical measurements and a clinical image evaluation for diagnostic capability comparison to a predicate, not on a trained AI model.

The document primarily focuses on demonstrating substantial equivalence through:

• Technical performance metrics: MTF, DQE, NPS, Dynamic Range, Image Erasure, AEC Performance, and Phantom Testing. Acceptance for these is generally implied by being "equivalent to the predicate" or exceeding "specified thresholds."
• Clinical image evaluation: A general statement is made that a clinical image evaluation was conducted, confirming "equivalent diagnostic capability to the predicate device."

Therefore, based only on the provided text, I cannot complete the table or provide the requested details about a study proving clinical acceptance criteria. The information is limited to substantiating the device's equivalence to a predicate, not demonstrating it meets specific, predefined clinical acceptance criteria through a detailed study design as might be seen for a novel AI diagnostic device.

If this were an AI device, the "acceptance criteria" would be specific performance metrics (e.g., sensitivity, specificity, AUC) with predefined thresholds derived from clinical needs. For this detector, "acceptance" is framed in terms of substantial equivalence to a legally marketed predicate device.

What is present in the document relevant to performance and equivalence:

The document outlines a non-clinical testing summary and mentions a clinical image evaluation to demonstrate substantial equivalence to a predicate device, rather than meeting specific, numerical acceptance criteria for clinical performance that would typically be associated with an AI diagnostic study.

Here's what can be extracted based on the provided text, and where information is missing:

Non-clinical Performance Comparisons (as presented in the 510(k) summary, specifically for FXMD-2430S model):
| Parameter | Predicate Device (RSM 2430C) | Subject Device (VIVIX-M FXMD-2430S) | Equivalence | Acceptanc

| MTF | 70% at 2lp/mm, 30% at 5lp/mm | 54.9% at 3lp/mm, 33.1% at 5lp/mm | Substantially Equivalent | Implied: Demonstrated spatial resolution equivalent to predicate, exceeding specified thresholds. | DQE | 43% at 2lp/mm, 30% at 5lp/mm | 59.0% at 3lp/mm, 42.5% at 5lp/mm | Substantially Equivalent | Implied: Comparable to predicate, confirming equivalent imaging performance. |
Other Non-Clinical Tests (Results are qualitative in the summary):

• Noise Power Spectrum (NPS): "confirmed consistent noise performance across tested exposure levels."
• Dynamic Range Testing: "exhibited a wide dynamic range suitable for mammographic imaging."
• Image Erasure and Fading Test (Ghosting): "No significant ghosting or residual artifacts were observed."
• Automatic Exposure Control (AEC) Performance: "met manufacturer-defined limits, ensuring consistent image quality."
• Phantom Testing (ACR, TE, CDMAM Phantoms): "All tests demonstrated diagnostic image quality equivalent to or better than the predicate device."

Clinical Performance:

• Overall Diagnostic Capability: "the study confirmed that the new x-ray detectors VIVIX-M provide images of equivalent diagnostic capability to the predicate device." |
  | 2. Sample Size (Test Set) & Data Provenance | Sample Size: Not specified. The document only states "A clinical image evaluation... was conducted."
  Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). |
  | 3. Number of Experts & Qualifications for Ground Truth | Not specified. |
  | 4. Adjudication Method for Test Set | Not specified. |
  | 5. MRMC Comparative Effectiveness Study Effect Size | Not applicable. This is a medical imaging detector, not an AI-assisted diagnostic tool for human readers. There is no AI component that assists human readers. The clinical evaluation verifies equivalent diagnostic capability of the images produced by the detector. |
  | 6. Standalone (Algorithm Only) Performance | Not applicable in the context of an AI algorithm. This is a hardware device (X-ray detector). Its "standalone" performance is measured by its physical and image quality characteristics (MTF, DQE, NPS) and its ability to produce images comparable to a predicate for diagnostic purposes. These non-clinical tests were conducted. |
  | 7. Type of Ground Truth Used (for Clinical Evaluation) | The general statement is "equivalent diagnostic capability" to the predicate. The method for establishing this "diagnostic capability" as ground truth (e.g., expert consensus on clinical cases, pathological confirmation, long-term follow-up) is not explicitly detailed. It's likely based on radiologists' interpretation of the images produced by the device compared to the predicate in clinical scenarios. |
  | 8. Sample Size for Training Set | Not applicable. This device is a digital X-ray detector, not an AI/ML algorithm that requires a training set. |
  | 9. How Ground Truth for Training Set Was Established | Not applicable. (See #8) |

Ask a specific question about this device

The digital mammography system MAMMOMAT B.brilliant is intended to be used for mammography exams, screening, diagnosis, biopsies and dual energy procedures under the supervision of medical professionals. Mammography images can be interpreted by either hard copy film or soft copy workstation.

With Biopsy Option: The InSpect feature for MAMMOMAT B.brilliant with HD Biopsy options is intended to provide digital X-ray images of core biopsy specimens in order to allow rapid verification that the correct tissue has been excised with the biopsy procedure.

MAMMOMAT B.brilliant is a floor-mounted, full field digital mammography system for screening, diagnostic, and biopsy procedures on standing, seated, or recumbent patients.

The system consists of an examination stand with x-ray generator, a gantry with tube housing assembly, and mammography support table, including detector and an acquisition workstation with a radiation shield. The MAMMOMAT B.brilliant comes with a variety of compression plates and a biopsy attachment for diagnostic adjunct procedures.

The MAMMOMAT B.brilliant features an updated detector, a new image acquisition chain (tube, filter, collimator) and improvements to the image acquisition workflow and biopsy workflow. Adaptations have been made to the image processing due to the new image acquisition hardware and the Soft- and hardware feature improvements. Patient positioning features like a head rest have been added.

Here's a breakdown of the acceptance criteria and study information for the MAMMOMAT B.brilliant device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes Used for Test Set and Data Provenance

• Clinical Image Evaluation Test Set: 19 FFDM cases
  • 4 cases with biopsy
  • 2 cases with PRIME
  • 3 cases with contrast-enhanced mammography (TiCEM)
  • 3 of the above cases included magnification views.
• Data Provenance: Not explicitly stated regarding the origin (e.g., country) or whether it was retrospective or prospective. It is implied to be a Siemens-conducted study.

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

• Number of Experts: 3 expert readers.
• Qualifications: "Expert radiologists." No further specific qualifications (e.g., years of experience) are provided in the document.

4. Adjudication Method for the Test Set

• The document implies a consensus-based approach for the clinical image evaluation, stating, "The radiologists found all image sets to be of acceptable overall clinical image quality." However, a specific adjudication method like "2+1" or "3+1" is not detailed. It suggests independent review followed by a collective judgment of acceptability.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study focusing on human readers' improvement with AI vs. without AI assistance was not reported. The clinical image evaluation was to determine if images from the new device (MAMMOMAT B.brilliant) were of acceptable quality and substantially equivalent to the predicate device, not to evaluate AI assistance for human readers.

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

• No, a standalone algorithm performance study was not explicitly reported as a primary clinical test for this submission. The clinical image evaluation focused on the overall image quality generated by the device for interpretation by human radiologists. The device itself (MAMMOMAT B.brilliant) is a mammography system, not primarily an AI-driven image analysis algorithm in the context of this submission.
  • Note: While the device utilizes "Image processing algorithms," the clinical evaluation was on the output images for human interpretation, not on the algorithm's standalone diagnostic performance.

7. The Type of Ground Truth Used

• Clinical Image Evaluation: Expert consensus (judgment of "acceptable overall clinical image quality" by 3 expert radiologists).
• Targeting Accuracy: Physical measurement against a phantom and calibration needle.

8. The Sample Size for the Training Set

• The document does not specify a training set size or provide details about a training set for any AI/software components within the device. The clinical evaluation focuses on comparing the new device's images to the predicate and determining acceptability, not on performance of a trained AI diagnostic algorithm.

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

• As no training set is described for an AI diagnostic algorithm, this information is not applicable and is not provided in the document. The document primarily concerns the hardware and basic image processing of a mammography system.

Ask a specific question about this device

The RMF-2000 generates 2D digital mammography images. The RMF-2000 is intended to be used for screening and diagnosis of breast cancer. This unit is intended for use in the same clinical applications as traditional screen film mammography systems.

The system consists of a gantry with integrated high-voltage generator as well as an optional radiation shield with a height-adjustable control desk with an integrated Acquisition Workstation (AWS). The moveable swivel C-arm on the gantry contains the X-ray tube on the top end and the breast support with the X-ray detector on the bottom end. The detector is a full field digital mammography detector. RMF-2000 acquires digital mammographic images for diagnosis of the breast cancer. RMF-2000 is designed to be used in the same clinical application for 2D screening mammographic systems. The screening examination exposes X-rays to the left and the right breasts of the patient to acquire images. Also, the RMF-2000 can be used to additional precision diagnosis for breasts. The device's software provides an integrated solution for X-ray projection. It integrates with the X-ray generator and the digital detector and acquires and processes images. In addition, it complies with DICOM standards and is able to transmit and receive data with the PACS system, and print images through the DICOM printer.

The provided document is a 510(k) summary for the DRTECH Corporation's RMF-2000 Full-Field Digital Mammography system. The document focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study proving the device meets specific performance acceptance criteria for an AI/software as a medical device (SaMD).

However, I can extract information related to the device's performance evaluation as presented in the document, framed within the context of substantial equivalence. The document describes a clinical image evaluation to demonstrate that the images produced by the RMF-2000 are of sufficient quality for mammographic use and substantially equivalent to those from the predicate device.

Here's an attempt to answer your questions based on the provided text, acknowledging that the depth of information about "acceptance criteria" and the "study" is limited to what's required for a 510(k) submission showing substantial equivalence of an imaging device, not necessarily an AI/SaMD.

Acceptance Criteria and Device Performance

The document doesn't explicitly list "acceptance criteria" in a quantitative table for device performance in the way one might expect for a robust AI/SaMD study (e.g., specific sensitivity, specificity, or AUC thresholds). Instead, the acceptance criterion for the clinical evaluation was implicitly the "sufficiently acceptable quality for mammographic usage" and "substantial equivalence to those from predicate device" concerning image quality, as determined by qualified physicians.

Table of Acceptance Criteria and Reported Device Performance (as inferred from the document):

Study Details:

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

   • The document states "A clinical image evaluation... was conducted," but it does not specify the sample size (number of images or patients) used for this evaluation.
   • Data Provenance: Not explicitly stated (e.g., country of origin). The study is described as a "clinical image evaluation." It's retrospective as it involves evaluation of images.

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

   • The document states "images, reviewed by MQSA qualified interpreting physicians."
   • Number of experts: Not specified (e.g., it doesn't say how many physicians reviewed the images).
   • Qualifications: "MQSA qualified interpreting physicians." MQSA (Mammography Quality Standards Act) qualification implies specific training and experience requirements for reading mammograms in the U.S.

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

   • The document does not specify an adjudication method for the clinical image evaluation. It simply states "reviewed by MQSA qualified interpreting physicians."

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, an MRMC study comparing human readers with AI assistance versus without AI assistance was not done. The RMF-2000 is described as a digital mammography system (hardware + associated software for image acquisition and processing), not an AI algorithm for interpretation. The "clinical image evaluation" was to assess the image quality produced by the device, not to evaluate an AI's impact on human readers.

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

   • Not applicable in the context of this document. This document describes a full-field digital mammography system, a medical device that produces images, not a standalone AI algorithm for image analysis. The evaluation was of the images produced by the device.

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

   • The "ground truth" here is the expert assessment of image quality by MQSA qualified interpreting physicians and their determination of equivalence to images from a predicate device. There's no mention of pathology or outcomes data being used to establish a ground truth for disease presence, as the study's purpose was to evaluate device-produced image quality, not disease detection performance of an AI.

7. The sample size for the training set:

   • This question is not applicable to the information provided. The document describes a full-field digital mammography system, not an AI model that requires a training set. The "clinical image evaluation" is a validation of the device's image output, not a dataset for training.

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

   • This question is not applicable as there is no mention of a training set or AI model in the context of this 510(k) submission for the RMF-2000.

Ask a specific question about this device

The Planmed Clarity 2D and S mammography units acquire digital 2D mammographic images. The Planmed Clarity 2D and S systems are intended to be used for screening and diagnosis of breast cancer. The Planmed Clarity 2D and S systems may also be used for additional diagnostic workup of the breast. Additionally, the Planmed Clarity 2D and S systems can be used to provide digital x-ray images of breast biopsy specimens.

The Planmed Clarity 2D and Clarity S are Full Field Digital Mammography (FFDM) systems for generating mammographic x-ray images that can be used for screening and diagnosis of breast cancer. Planmed Clarity 2D and Clarity S utilize an amorphous silicon based digital image receptor to capture images. The receptor directly converts the incoming X-ray photons to digital image data.

The workflow with Clarity 2D is controlled by the side displays/touch panels and the workflow of Clarity S is controlled from the acquisition workstation and Clarity Manager acquisition and communications software. The patient information is entered manually or received from the hospital, radiology, or mammography information systems (HIS, RIS, or MIS, respectively), as a format of modality worklist. Subsequently, the images are acquired, processed, and displayed for preview. After initial evaluation by the user, the images are either printed or transferred for soft-copy review.

Acceptance Criteria and Study for Planmed Clarity 2D and S

This response synthesizes the information provided about the Planmed Clarity 2D and S mammography systems, focusing on the acceptance criteria and the studies conducted to demonstrate compliance.

1. Table of Acceptance Criteria and Reported Device Performance

The provided document primarily details performance testing rather than explicitly stated acceptance criteria with numerical targets. However, based on the descriptions, we can infer the acceptance criteria. The device's performance is deemed acceptable if it meets these inferred criteria and demonstrates clinical image quality comparable to the predicate device.

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

• Test Set Sample Size: 6 patients particpated in routine breast cancer screening. The clinical evaluation used images from these 6 patients, with some cases also including diagnostic mammograms (spot and/or magnification images).
• Data Provenance: The data was obtained from two sites: one in Belgium and one in Bulgaria. The study appears to be prospective in nature, as images were "taken at one site in Belgium and one site in Bulgaria where altogether 6 patients participated to routine breast cancer screening."

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

• Number of Experts: Three
• Qualifications: "MQSA qualified experienced US interpreting physicians independently."

4. Adjudication Method for the Test Set

The document states, "The images were then reviewed by three MQSA qualified experienced US interpreting physicians independently." This indicates that there was no formal adjudication method (e.g., 2+1 or 3+1 consensus) described. Each expert provided an independent assessment, and the aggregate finding (all images rated good or excellent) was reported.

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

No, a formal MRMC comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not described in the provided text. The study primarily focused on the standalone performance of the image processing algorithm and its impact on image quality for human interpretation. The clinical image evaluation assessed if the image quality produced by the new software was acceptable for human readers, not whether AI assistance improved human performance.

6. Standalone Performance Study

Yes, a standalone performance evaluation of the new image processing algorithm (CORE) was implicitly performed. While not in the context of a "standalone algorithm" in isolation from the hardware, the "Clinical image evaluation" aimed to determine if the images processed with the new Planmed CORE software algorithm were of "sufficiently acceptable quality for mammographic usage when reviewed by MQSA qualified experienced interpreting physicians." This assesses the algorithm's output quality as a standalone component contributing to the overall system's diagnostic utility. The physical laboratory testing also evaluates the image chain, including the processing, in a standalone manner from actual diagnostic human interpretation.

7. Type of Ground Truth Used

For the clinical image evaluation, the "ground truth" used for assessing image quality was expert consensus on image quality acceptability. The experts rated images as "good" or "excellent," and the overall judgment ("acceptable for all cases and image types") served as the ground truth criterion. The selection of cases with BI-RADS score 1 or 2 suggests that the intent was to evaluate images from non-cancerous breasts (or breasts with benign findings) to assess general image clarity, rather than a diagnostic accuracy study where pathology or outcomes data would be directly compared.

8. Sample Size for the Training Set

The document does not provide information regarding the sample size for a training set for the CORE image processing algorithm. The algorithm is described as "developed by Planmed in-house," but details on its development data (training, validation, testing) are not included in this summary.

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

As no information is provided about a training set, the method for establishing its ground truth is not described in the document.

Ask a specific question about this device

The Fujifilm Digital Mammography System, ASPIRE Cristalle (FDR MS-3500) generates full-field digital mammography images that can, as other full-field digital mammography systems, be used for screening and diagnosis of breast cancer and is intended for use in the same clinical applications as traditional screen-film mammography systems.

Dual energy procedures is an optional feature of the ASPIRE Cristalle that can capture images consecutively under two different tube voltage conditions during one compression, and then create and display a subtraction image of the two acquired images. This optional feature shall enable contrast enhanced breast imaging and is used as an adjunct following mammography. Dual energy procedures is not intended for primary screening or diagnosis.

The ASPIRE Cristalle (K173132) (FDR MS-3500) is an integrated FFDM system combining an X-ray system made by Fuiifilm's a-Se detector and Acquisition Workstation (AWS). The ASPIRE Cristalle creates digital mammography images by direct capture of x-ray energy using the a-Se detector. The detector is a Fujifilm design utilizing an a-Se photoconversion layer with TFT Readout circuitry to acquire image data and transfer images to the A WS for automated post processing, technologist preview and QC, and subsequent transmission to hard copy printers, diagnostic workstations and archiving systems. The ASPIRE Cristalle provides powered compression and three AEC modes.

The ASPIRE Cristalle Acquisition Workstation (FDR 3000AWS) includes an off the shelf personal computer, the application software, Windows Operating System, a 5megapixel portrait type monitor, and a hub. The hub transmits signals between the personal computer and control cabinet, and between the personal computer and exposure stand.

The AWS display primarily consists of three windows:

• . Patient Information Input window
• Exposure Menu Selection window ●
• . Study window.

The user may switch between these windows depending on the operation being performed. The X-ray control panel, which controls and observes the exposure stand, is always displayed in the lower part of each window. This allows setting the exposure conditions and confirming the radiation conditions on a single view.

This 510(k) submission introduces the optional feature of Dual energy procedures for the ASPIRE Cristalle. Dual energy procedures can capture images consecutively under two different tube voltage conditions during one compression, and then create and display a subtraction image of the two acquired images. This optional feature shall enable contrast enhanced breast imaging and is used as an adjunct following mammography. It should only be used with FDA approved contrast agents according to the manufacturer's instructions. The X-ray exposures must be performed after the contrast agent has diffused into the breast and before its washout, which is typically between 2 to 7 minutes after beginning of injection according to Clinical publications and/or the manufacturer's instructions. For the image acquisition in one direction, it takes about 25 seconds from the first X-ray exposure to the display of energy subtraction images.

The provided text describes the Fujifilm ASPIRE Cristalle (FDR MS-3500) device and its optional Dual Energy Procedures feature. The 510(k) summary explains that the device is substantially equivalent to a predicate device for standard mammography, and that the dual-energy feature was evaluated through non-clinical and limited clinical testing.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria for the dual-energy feature in terms of diagnostic performance metrics (e.g., sensitivity, specificity, AUC). Instead, it relies on demonstrating acceptable image quality and substantial equivalence.

2. Sample Size for Test Set and Data Provenance

• Sample Size for Test Set: 10 patient CEDM images were used for the clinical evaluation of the Dual Energy Procedures feature.
• Data Provenance: Not explicitly stated (e.g., country of origin). The text refers to "10 patient CEDM images," implying prospective or retrospective acquisition for the purpose of the study, but no details are given.

3. Number of Experts and Their Qualifications

• Number of Experts: Three (3)
• Qualifications: "MOSA qualified expert mammographic radiologists."

4. Adjudication Method

The text states that the clinical evaluation was "performed on 10 patient CEDM images by three (3) MOSA qualified expert mammographic radiologists." It does not specify an adjudication method like 2+1 or 3+1 for establishing ground truth or determining a consensus on image quality. It's implied the experts individually or collectively assessed acceptability, but the process is not detailed.

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

No MRMC comparative effectiveness study was performed comparing human readers with AI vs. without AI assistance. The study described is a clinical evaluation of image quality performed by human readers on the new dual-energy images, not an AI-assisted interpretation study.

6. Standalone (Algorithm Only) Performance

The document does not describe a standalone performance study of an algorithm independent of human-in-the-loop performance. The dual-energy feature is described as enabling contrast-enhanced breast imaging and producing subtraction images for human interpretation, not for automated standalone diagnosis.

7. Type of Ground Truth Used

For the clinical evaluation of the dual-energy images, the ground truth was expert consensus (or individual expert assessment) on "acceptable quality for mammographic usage." There is no mention of pathology, long-term outcomes data, or other objective diagnostic ground truth being used to validate the accuracy of findings from these dual-energy images. The evaluation primarily focused on image quality for human interpretation.

8. Sample Size for Training Set

The document does not mention a training set or any machine learning algorithm for diagnostic interpretation in the context of the dual-energy feature. The Dual Energy Procedures feature is described as a method to capture and display subtraction images based on X-ray physics, not an AI-based diagnostic tool requiring a training set.

9. How Ground Truth for Training Set Was Established

Not applicable, as no training set for an AI/ML algorithm is described in the provided text for the Dual Energy Procedures feature.

Ask a specific question about this device

The Digimamo D ® Full-Field Digital Mammography System is a device intended to produce planar digital x-ay images of the entire breast. The Digimamo D is indicated for generating mammographic images that can be used for screening and diagnosis of breast cancer. The Digimamo D is intended to be used in the same clinical applications as traditional film/screen systems.

This is a mammography system available in only a digital version. The main characteristics are: Operation Panel/Console, X-ray tube information, Filter Selection, Window Material and thickness, Focal Spot Sizes, Operating principle, Radiological Characteristics, Column and Gantry, Flat Panel Detector, Workstation.

The provided text describes the Digimamo D Full-Field Digital Mammography System and its comparison to a predicate device (Adani MammoScan K172027) and a reference device (DRTECH RSM2430C K170930). The information primarily focuses on the device's technical specifications and a summary of non-clinical and clinical testing performed to establish substantial equivalence.

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

Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly listed in a table format with specific quantitative thresholds. Instead, the document states that the device was tested to establish "substantial equivalence" to a predicate device, meaning it is "as safe and effective." The performance is deemed acceptable if the images are of "sufficiently acceptable quality for mammographic usage."

However, we can infer some "acceptance" from the successful outcome of the comparison and the conclusion of substantial equivalence. The key is that the new device's performance aligns with the predicate device and that the images were found to be diagnostic quality by experts.

Study Details:

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

   • Test Set Sample Size: "Sixty images" were evaluated. The document further clarifies "Totally, there are 12 sets of images presented in this review." Each set consists of four standard views (right CC, right MLO, left CC, left MLO), so 12 sets * 4 views/set = 48 images initially. However, it also states "If requested by the radiologist, additional image with magnification was taken." This suggests more than 48 images could have been evaluated, up to 60 total. It's not explicitly clear if all "sixty images" were unique patient cases or if "12 sets of images" corresponds to 12 patient cases, each with multiple views. The phrasing "Sixty images were evaluated" followed by "Totally, there are 12 sets of images" could be interpreted as 60 individual images selected from these 12 sets, or 60 total images including any additional magnification views for the 12 cases.
   • Data Provenance: Images were taken during the "standard screening procedure in Fundação Municipal de Saúde de Macaé, Rio de Janeiro, Brazil." This indicates the data is retrospective as it was already acquired.

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

   • Number of Experts: "Three Board Certified US based radiologists."
   • Qualifications of Experts: "US-based MQSA qualified radiologists." MQSA (Mammography Quality Standards Act) qualification ensures competence in mammography interpretation.

3. Adjudication method for the test set:

   • The document states, "Images were reviewed by US-based MQSA qualified radiologists. The results of clinical image evaluation determined that the clinical images reviewed by the expert radiologists were of sufficiently acceptable quality for mammographic usage."
   • There is no explicit description of an adjudication method (e.g., 2+1, 3+1 consensus). It sounds like a qualitative assessment by individual radiologists, and the collective outcome was that the images were acceptable. It doesn't describe a process for resolving disagreements or reaching a formal consensus for a specific ground truth label.

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, an MRMC comparative effectiveness study was not done. The study described is a clinical image evaluation by human readers of images produced by the device to confirm diagnostic quality, not a study comparing human performance with vs. without AI assistance. The device itself is a full-field digital mammography system, not an AI-based reading aid.

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

   • Not explicitly described as a standalone algorithm study. The device is an imaging system (hardware + software for image acquisition and display). The "clinical testing" refers to human readers evaluating the image output of the system, not an algorithm's classification performance. The "digital panel software employed was already reviewed by FDA in the reference submission list," which implies its performance characteristics (e.g., image quality metrics) would have been assessed as part of its original clearance. This is an assessment of the entire system's output through human review.

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

   • The "ground truth" for the clinical image evaluation was the qualitative assessment by the three Board Certified US-based MQSA qualified radiologists that the images were of "sufficiently acceptable quality for mammographic usage." This is a form of expert opinion/consensus on image quality for diagnostic purposes. It is not described as being based on pathology or clinical outcomes.

7. The sample size for the training set:

   • The document does not mention a training set sample size as this device is a mammography imaging system (hardware and associated acquisition/processing software), not an AI algorithm requiring a training set in the conventional sense (e.g., for classification or detection). The software involved (digital panel software) was from a previously cleared device (DRTECH RSM2430C K170930), implying its development and validation were part of that prior submission.

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

   • As no "training set" for an AI algorithm is described for this device's new performance evaluation, the method for establishing ground truth for a training set is not applicable/not provided in this document.

Ask a specific question about this device

Helianthus is intended to produce two dimensional digital mammographic images of the breast cancer. Its intended use is for diagnosis, screening, or for needle localization in case of stereotactic biopsy.

Helianthus is a mammography solution composed of equipment and software for different examination types and optimized for digital imaging.

Helianthus is a digital mammography system also called full-field digital mammography (FFDM) system. It is an integrated system that includes both the X-ray delivery system and integrated detector. It consists of an x-ray generator, x-ray control, x-ray tube, collimator, beam filter, breast compression system, grid, image receptor system, and accessories. The image receptor system consists of a built-in full-filed solid state detector, acquisition software, acquisition work station (AWS), and accessories. It includes an optional stereotactic biopsy device (BYM 3D DMD) with its respective Operator's Manual.

Helianthus is intended to produce two-dimensional digital mammographic images of the breast for diagnosis of breast cancer. Its intended use is for diagnosis, screening, or for needle localization in case of stereotactic biopsy

Based on the provided text, the document describes the substantial equivalence determination for the Helianthus full-field digital mammography system, comparing it to the predicate device, Planmed Clarity. However, the text does not contain detailed information about acceptance criteria or a specific study proving the device meets these criteria in the format requested.

The document states that:

• Non-Clinical Performance Data (Section 9) demonstrates that "Results confirm that the design inputs and performance specifications for the device are met." This section lists various tests (e.g., electrical safety, software verification, imaging characteristics through physical laboratory testing).
• Clinical Performance Data (Section 10) states: "A clinical image evaluation as required by the Guidance for Industry and FDA Staff: Class II Special Controls Guidance Document: Full-Field Digital Mammography System issued on April 4, 2012 (Section 9 Clinical Image Evaluation) was conducted with the Helianthus and determined that the images, reviewed by expert radiologists, were of sufficiently acceptable quality for mammographic usage and that the images are substantially equivalent to those from a predicate device."

Therefore, the full details required to populate all fields of your request (e.g., specific acceptance criteria values, sample sizes for test/training sets, exact number and qualifications of experts, adjudication methods, MRMC study details, types of ground truth) are NOT present in the provided text.

Below, I will fill in what can be inferred or explicitly stated from the provided text, and clearly mark where information is not provided.

Acceptance Criteria and Device Performance (Inferred/Stated from Text)

Study Details:

1. A table of acceptance criteria and the reported device performance: Included above. (Note: Specific quantitative values for imaging acceptance criteria are not provided, only that they were assessed per FDA guidance and found equivalent.)

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

   • Sample Size (Test Set): Not provided. The text only states "A clinical image evaluation... was conducted."
   • Data Provenance: Not provided (e.g., country of origin, retrospective/prospective).

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

   • Number of Experts: Not provided. The text states "images, reviewed by expert radiologists."
   • Qualifications: "expert radiologists" - Further specific qualifications (e.g., years of experience, subspecialty) are not provided.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not provided. The text only states images were "reviewed 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: Not applicable / Not provided. The document describes a traditional 510(k) for a Full-Field Digital Mammography System (the imaging device itself), not an AI-assisted interpretation or CAD device. The clinical study was to demonstrate image quality equivalence rather than reader performance with/without AI.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The device is an FFDM system, meaning it produces images for human interpretation, not an algorithm that performs diagnosis standalone. The physical laboratory tests (Section 9) could be considered "standalone" evaluation of the system's technical image quality parameters.

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

   • For clinical image evaluation, the ground truth for acceptability and equivalence was based on the review by expert radiologists. The text implies a subjective assessment of image quality for mammographic usage and comparison to the predicate. It does not mention pathology or outcomes data as "ground truth" for the image evaluation itself, though such data would underpin the overall purpose of mammography.
   • For non-clinical performance tests, the ground truth was based on compliance with established international standards (e.g., ISO, IEC) and internal requirements.

8. The sample size for the training set: Not applicable/Not provided. This device is a traditional imaging system, not an AI model requiring a "training set" in the machine learning sense. The testing (non-clinical and clinical) is for verification and validation.

9. How the ground truth for the training set was established: Not applicable. As above, there's no mention of a "training set" for an AI model.

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.

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