Search Results

The GC85A Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GC70 Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GU60A & GU60A-65 Digital X-ray Imaging Systems are intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GF50 Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GF50A Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GR40CW Digital X-ray Imaging System is intended for use in general projection radiographic applications wherever conventional screen-film systems or CR systems may be used. This device is not intended for mammographic applications.

The GM85 Digital Mobile X-ray imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

GC70, GU60&GU60A-65, GF50, GF50A, GR40CW, GM85 and GC85A are used to capture images by transmitting X-ray to a patient's body. The X-ray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process on the S-station, which is the Operation Software (OS) of Samsung Digital Diagnostic X-ray System, and save in DICOM file, a standard for medical imaging. The captured images are tuned up by an Image Post-processing Engine (IPE) which is exclusively installed in S-station, SAMSUNG digital X-ray operation software, and sent to the Picture Archiving & Communication System (PACS) sever for reading images.

The IPE operates, from the input image, the roles of a region-of-interest extraction, tonescale mapping, noise reduction and texture restoration. The IPE employing an advanced noise reduction algorithm (hereinafter "new IPE") is shown that the image quality of PA radiograph for average adult chest, exposed at the condition of 50% lower dose at Entrance Skin Exposure (ESE) in comparison with the condition of the conventional noise reduction algorithm (hereinafter "old IPE"), is substantially equivalent.

The provided text describes the acceptance criteria and a study proving the device meets those criteria, specifically concerning dose reduction capabilities of the Image Post-processing Engine (IPE) with an advanced noise reduction algorithm in Samsung Digital X-ray Systems (GC70, GU60A, GU60A-65, GF50, GF50A, GR40CW, GM85, and GC85A).

Here is the requested information:

Acceptance Criteria and Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

The core acceptance criterion is the ability of the new IPE to reduce X-ray dose while maintaining image quality comparable to the old IPE for diagnostic confidence. The specific dose reduction percentages are the performance metrics.

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

• Adult Abdominal Radiograph Test Set:

  • Anatomical phantom images: Number of images not specified, but taken at "various exposure condition." The study states, "the new IPE with an advanced noise reduction algorithm retained the quality of images captured at 47.5% reduced exposure in comparison with the old IPE."
  • Clinical images: Number of images not specified, but used to "confirm that it was possible to reduce the dose in clinical images as well."
  • Provenance: Not explicitly stated, but the submission is from Samsung Electronics Co., LTD. Republic of Korea. The clinical testing was conducted at "one medical site."
  • Retrospective or Prospective: Not specified.

• Pediatric Population Test Set (Chest, Abdomen, Skull):

  • Number of images: "Series of dose-simulated images" for each body part.
  • Number of patients: Not specified explicitly, but mentioned as "each patient."
  • Provenance: Not explicitly stated, but the submission is from Samsung Electronics Co., LTD. Republic of Korea. The clinical testing was conducted at "one medical site."
  • Retrospective or Prospective: Not specified.

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

• Adult Abdominal Radiograph Test Set:

  • Anatomical phantom images were reviewed by three professional radiologists.
  • Clinical images were reviewed by two professional radiologists.
  • Qualifications: "Professional radiologists" (no further details on experience given).

• Pediatric Population Test Set:

  • Three experienced pediatric radiologists.
  • Qualifications: "Experienced pediatric radiologists" (no further details on experience given).

4. Adjudication Method for the Test Set

The adjudication method is not explicitly detailed. However, for both adult and pediatric studies, images were "scored by the 5-point grading scale" for assessment of image quality. This implies individual scoring, and for the pediatric study, "Three experienced pediatric radiologists assessed the series of dose-simulated images to decide the optimal dose for each patient." The decision for the "optimal dose" for pediatric cases suggests a consensus or agreement among these experts, but the exact method (e.g., majority vote, discussion to reach consensus) is not specified.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

No MRMC comparative effectiveness study was done to evaluate human readers' improvement with AI vs. without AI assistance. The study focused on the device's standalone performance in enabling dose reduction while maintaining image quality as assessed by human readers. The new IPE is a component within the imaging system, not an AI assistance tool for human readers.

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

Yes, the studies evaluated the standalone performance of the new IPE algorithm in terms of enabling dose reduction while maintaining image quality. The performance was assessed by comparing images processed by the new IPE at reduced doses against images from the old IPE or a reference, with human experts providing the assessment of image quality and diagnostic appropriateness.

7. The Type of Ground Truth Used

The ground truth for both adult and pediatric studies was expert consensus/assessment of image quality and diagnostic appropriateness.

• For adult abdominal radiographs: Expert radiologists scored images based on a 5-point grading scale, considering anatomical regions, physical parameters, sharpness, and visualization.
• For pediatric populations: Experienced pediatric radiologists assessed dose-simulated images to determine the "optimal dose" at which image quality remained appropriate for diagnosis.

Additionally, phantom studies (TOR CDR radiography phantom and anthropomorphic phantom) were used to quantitatively assess image quality metrics like Contrast to Noise Ratio (CNR), Detail Compacted Contrast (DCC), and Modulation Transfer Functions (MTF).

8. The Sample Size for the Training Set

The document does not provide information about the training set size for the Image Post-processing Engine (IPE) algorithm. It focuses on the validation of the algorithm's dose reduction capabilities.

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

The document does not provide information on how the ground truth for the training set was established for the IPE algorithm.

Ask a specific question about this device

The GC85A Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GC85A digital X-ray imaging system is a stationary x-ray system designed for general radiography and used to capture images by transmitting X-ray to a patient's body. The Xray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process on the S-station, which is the Operation Software (OS) of Samsung Digital Diagnostic X-ray System, and save in DICOM file, a standard for medical imaging. The captured images are tuned up by an Image Post-processing Engine (IPE) which is exclusively installed in S-station, and sent to the Picture Archiving & Communication System (PACS) sever for reading images.

The GC85A digital X-ray imaging system was previously cleared with K172229, and through this premarket notification, we would like to add more configurations in the previously cleared GC85A as three High Voltage Generators and two detectors are newly added, and three software features are newly added as stated below.

S-Enhance is renamed from Tube & Line Enhancement (TLE), which was cleared before with the predicate device GM85 at K171119, to enhance visibility of tubes and lines and provide enhanced images separately from original images. In this submission, the scope of S-Enhance is expanded from tubes and lines on chest images to foreign body (e.g. tubes, lines and needles) and urinary stones on chest, abdomen, and L-spine. And Pediatric Exposure Management (PEM), which was cleared before with the predicate device GM85 at K171119, is subdivided patient size and exposure conditions especially for pediatric patients based on weight and protocols, and Remote View to enable the images on the device is being displayed on the remote monitor. It was determined that the level of concern for the software contained in the GC85A digital X-ray imaging system was Moderate in accordance with the FDA guidance, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Device".

The provided document, a 510(k) Premarket Notification for the Samsung GC85A digital X-ray imaging system, primarily focuses on demonstrating substantial equivalence to predicate devices rather than establishing novel acceptance criteria or presenting an in-depth study proving a device meets specific performance criteria for new features. The document describes additions and changes to an already cleared device (GC85A, K172229) and incorporates features from another predicate device (GM85, K171119).

However, based on the Clinical data section (page 8), we can infer the following about acceptance criteria and the study conducted for S-Enhance and the new detectors:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria in a table format for new features. Instead, it relies on a qualitative assessment of "equivalence" to predicate devices. For S-Enhance and the new detectors, the acceptance criteria are implicitly based on achieving equivalent image quality to the predicate devices and ensuring S-Enhance provides "clear visibility" for foreign bodies.

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

• Test Set Sample Size: Not explicitly stated. The document mentions "Anthropomorphic phantom images were provided." This indicates that the images used in the evaluation were of phantoms (physical models representing human anatomy), not actual patient data. The exact number of phantom images is not specified.
• Data Provenance: The data is from "Anthropomorphic phantom images." This implies a controlled, laboratory-based study. No information about country of origin is provided, but Samsung Electronics Co., Ltd. is based in the Republic of Korea. It is a prospective study as these images were generated specifically for this evaluation.

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

• Number of Experts: Not explicitly stated. The document mentions "professional radiologists."
• Qualifications of Experts: "professional radiologists." Specific experience (e.g., "10 years of experience") is not provided.

4. Adjudication Method for the Test Set

• Adjudication Method: Not explicitly stated. The phrasing "evaluated by professional radiologists and found to be equivalent" suggests a consensus or majority opinion approach, but the specific method (e.g., 2+1, 3+1) is not detailed. The mention of "average score considering the standard deviation of image quality evaluation" suggests a quantitative assessment that might have been averaged across multiple readers, but the method of handling disagreements is not described.

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

• A formal MRMC comparative effectiveness study to quantify human reader improvement with vs. without AI assistance was not described in the provided text. The study described focuses on whether the device's image quality (including S-Enhance) is equivalent to predicate devices, and whether S-Enhance provides clear visibility. It does not measure the impact of AI assistance on human reader performance.

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

• The document implies that the S-Enhance feature (an algorithm) was evaluated in terms of its ability to "generate a companion image which provide clear visibility for foreign bodies." This is a form of standalone evaluation of the algorithm's output. However, it's not a standalone diagnostic performance study (e.g., sensitivity/specificity of an AI model to detect foreign bodies). The evaluation relies on human radiologists assessing the quality and visibility provided by the algorithm's output.

7. The Type of Ground Truth Used

• For the phantom images, the "ground truth" for the new detectors and S-Enhance would be the inherent properties and known structures within the anthropomorphic phantoms. The "equivalence" assessment by radiologists serves as the validation of how well the device's images represent this known ground truth. It's essentially an expert consensus on image quality and perceptibility of structures in controlled phantom images.

8. The Sample Size for the Training Set

• Details about the training set for S-Enhance (or any other software feature) are not provided in this document. Given that S-Enhance was "renamed from Tube & Line Enhancement (TLE), which was cleared before with the predicate device GM85 at K171119," it's likely that any training for the core functionality occurred prior to this submission and was part of the K171119 clearance. This submission expands the scope of S-Enhance.

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

• As the training set details are not provided, information on how its ground truth was established is also not available in the document.

Ask a specific question about this device

The GC85A Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GC85A digital X-ray imaging system is used to capture images by transmitting X-ray to a patient's body. The X-ray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process device before being sent to the S-Station (Operation Software) and saved in DICOM file, a standard for medical imaging. The captured images are sent to the Picture Archiving & Communication System (PACS) server, and can be used for reading images.

The Image Post-processing Engine is exclusively installed in S-station, which is a Samsung Digital X-ray Operation Software for Samsung Digital X-ray System. It has an image processing algorithm to improve an acquired image and previously cleared with K160997.

The proposed Image Post-processing Engine is upgraded with employing an advanced noise reduction algorithm to improve image quality. The proposed Engine is shown of a post-processed image as substantially equivalent as the image by the predicate Image Post-processing Engine at a certain low dose level.

The acceptance criteria and the study proving the device meets them are detailed below, based on the provided text.

1. Table of Acceptance Criteria and Reported Device Performance

The device is an upgraded Image Post-processing Engine for the GC85A Digital X-ray Imaging System, featuring an advanced noise reduction algorithm. The primary acceptance criterion is achieving substantially equivalent image quality at a 50% reduced radiation dose compared to the predicate device.

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

• Sample Size:
  • Clinical Study: 78 in-vivo data sets of chest PA images.
  • Phantom Study: Not explicitly stated as a number, but "a semi-anatomical chest phantom at a various radiation dose" and "anthropomorphic chest phantom images" were used.
• Data Provenance: The clinical study was conducted at "one facility" and involved "in-vivo data sets." This implies the data is prospective clinical data collected specifically for this study. The country of origin is not explicitly mentioned but the submitter is from the Republic of Korea.

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

• Number of Experts: Three professional radiologists.
• Qualifications: "Three experienced radiologists." Specific years of experience are not provided, but they are described as "professional" and "experienced."

4. Adjudication Method for the Test Set

• The text mentions that "Anthropomorphic chest phantom images were scored by Bureau of Radiological Health (BRH) method and inter-observer agreement was calculated."
• For the clinical images, "Seven anatomical landmarks were evaluated for image quality assessment by three readers."
• While it states that inter-observer agreement was calculated for phantom images and multiple readers evaluated clinical images, it does not explicitly describe a specific adjudication method like 2+1 or 3+1 for resolving discrepancies in reader interpretations for either phantom or clinical studies. It implies a consensus or agreement was sought, but the formal process isn't detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• A MRMC study comparing human readers with AI vs. without AI assistance was not conducted. The study evaluated whether images processed by the new engine at reduced dose were substantially equivalent to those from the predicate engine, evaluating the device's standalone performance in producing equivalent diagnostic images, rather than its assistive role to humans.

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

• Yes, a standalone evaluation of the algorithm's output was critically performed. The primary goal was to demonstrate that the images generated by the new Image Post-processing Engine at 50% dose reduction are diagnostically equivalent to those from the predicate device at full dose. This means the algorithm's ability to process images to an acceptable diagnostic quality was the focus, rather than its interaction with a human reader. SNR and CNR measurements and the radiologists' evaluations of image quality were direct assessments of the algorithm's output.

7. The Type of Ground Truth Used

• The ground truth was established through expert consensus/reader interpretation (three experienced radiologists) during the evaluation of both anthropomorphic phantom images (scored by BRH method) and clinical images (evaluation of seven anatomical landmarks and 18 cases of featured lung lesions). There is no mention of pathology or outcomes data being used as ground truth.

8. The Sample Size for the Training Set

• The document does not explicitly state the sample size for the training set used to develop or train the advanced noise reduction algorithm in the Image Post-processing Engine.

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

• The document does not provide information on how the ground truth for the training set was established. It focuses primarily on the testing and validation of the device's performance.

Ask a specific question about this device

The GC85A Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The SimGrid is a technology that enhances the visibility of major clinical equipment by compensating for the decrease in contrast that is caused by scatter radiation when the portable grid is not used for portable images.

Bone Suppression is a technology that helps to create images with good lung field visibility by removing part of the ribs and clavicle with S/W algorithms. It is used as diagnosis assistance for areas that the image reader is interested in, such as soft tissues and lesions in the lung field.

The GC85A digital X-ray imaging system is used to capture images by transmitting Xray to a patient's body. The X-ray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process device before being sent to the S-Station (Operation Software) and saved in DICOM file, a standard for medical imaging. The captured images are sent to the Picture Archiving & Communication System (PACS) server, and can be used for reading images.

The SimGrid is a post-image processing software option which is able to compensate the contrast loss due to scatter radiations, primarily acquisitions without a physical antiscatter grid.

The Bone Suppression Image (BSI) is a post-image processing software option which provides companion images to assist diagnosis in addition to the images obtained from normal diagnosis protocol. The BSI software option suppresses bone anatomy to enhance visualization of chest pathology in a companion image that is delivered in addition to the original diagnostic image.

The SimGrid and BSI are available as options to be exclusively installed in S-station, which is a Samsung Digital X-ray operation S/W, since this post-image processing software does not depend on how the image is acquired, or with what acquisition device.

The provided text describes the Samsung GC85A Digital X-ray Imaging System, which includes two post-image processing software options: SimGrid and Bone Suppression Image (BSI). However, the document does not contain a detailed study with specific acceptance criteria and reported device performance metrics in tabular form for these software features.

Instead, the document focuses on demonstrating substantial equivalence to predicate devices and generally mentions evaluations without providing quantifiable acceptance criteria or detailed study results.

Here's a breakdown of the information that can be extracted or inferred regarding the evaluation of SimGrid and BSI, along with the information that is not available in the provided text:

SimGrid Evaluation:

• Acceptance Criteria: Not explicitly stated as a quantifiable metric. The stated goal is to "demonstrate that SimGrid processing gives the better local contrast than images acquired without a grid."
• Reported Device Performance: SimGrid processing was found to "give the better local contrast than images acquired without a grid." The "usefulness was validated by a radiographer using clinical images."
• Sample Size (Test Set): "various phantoms at various exposure conditions" and "clinical images." Specific numbers are not provided.
• Data Provenance (Test Set): Not specified (e.g., country of origin, retrospective/prospective).
• Number of Experts & Qualifications (Test Set Ground Truth): "radiographer" validated usefulness. No specific number or detailed qualifications (e.g., years of experience) mentioned.
• Adjudication Method: Not specified.
• MRMC Comparative Effectiveness Study: Not mentioned or implied.
• Standalone Performance: SimGrid software was evaluated with phantoms and clinical images, implying a standalone assessment of its image processing output.
• Type of Ground Truth: For phantoms, it would be based on known phantom properties and quantitative analysis of contrast. For clinical images, it's based on a "radiographer's" qualitative assessment of "usefulness."
• Sample Size (Training Set): Not provided.
• Ground Truth Establishment (Training Set): Not provided.

Bone Suppression Image (BSI) Evaluation:

• Acceptance Criteria: Not explicitly stated as a quantifiable metric. The goal is to provide "good lung field visibility by removing part of the ribs and clavicle" and be "useful as diagnosis assistance."
• Reported Device Performance: "Overall quality of the bone suppressed images was found to be useful as diagnosis assistance for areas that the reader is interested in, such as soft tissues and lesions in the lung field."
• Sample Size (Test Set): "various kinds of clinical images, such as with various sizes of patients at various exposure conditions." Specific numbers are not provided.
• Data Provenance (Test Set): Not specified (e.g., country of origin, retrospective/prospective).
• Number of Experts & Qualifications (Test Set Ground Truth): "a professional radiologist" evaluated the images. No specific number or detailed qualifications (e.g., years of experience) mentioned.
• Adjudication Method: Not specified.
• MRMC Comparative Effectiveness Study: Not mentioned or implied.
• Standalone Performance: BSI software was evaluated with clinical images, implying a standalone assessment of its image processing output.
• Type of Ground Truth: Based on a "professional radiologist's" qualitative assessment of "usefulness as diagnosis assistance."
• Sample Size (Training Set): Not provided.
• Ground Truth Establishment (Training Set): Not provided.

Summary of what's missing for a comprehensive answer to your request:

• Specific, quantifiable acceptance criteria for both SimGrid and BSI.
• Actual quantitative performance metrics for SimGrid (e.g., contrast improvement ratios, SNR, human reader performance).
• Detailed quantitative or qualitative performance metrics for BSI (e.g., lesion conspicuity, false positive/negative rates, agreement with original images).
• Specific sample sizes for both test and training sets.
• Detailed information about the data provenance (retrospective/prospective, specific demographics, geographic origin).
• Precise qualifications and number of experts for establishing ground truth.
• Details on the adjudication method used for the test set.
• Any information regarding MRMC studies and effect sizes.
• Information on the ground truth establishment for training sets, if applicable.

The document primarily focuses on demonstrating substantial equivalence to predicate devices based on technological characteristics and general safety/performance testing, rather than providing detailed clinical study results with specific acceptance criteria for the added software features.

Ask a specific question about this device

The GC85A Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GC85A digital X-ray imaging system consists of High voltage generator (HVG), Ceiling Suspension, X-ray tube, Collimator, Detector, AEC, DAP, CIB(Control Interface Box), Wall Stand, Patient Table, Collimator, Detector, Remote controller, Grid, Foot switch, Barcode scanner and Auto-stitching stand. This system is used to capture images by transmitting X-ray to a patient's body. The X-ray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process device before being sent to the S-Station (Operation Software) and saved in DICOM file, a standard for medical imaging. The captured images are sent to the Picture Archiving & Communication System (PACS) server, and can be used for reading images.

This is a 510(k) premarket notification for the Samsung Electronics Co., Ltd. GC85A Digital X-ray Imaging System. The submission aims to demonstrate substantial equivalence to a predicate device, the XGEO GC80 (K140334).

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a formal "acceptance criteria" table with specific quantitative thresholds. Instead, the approach is to demonstrate substantial equivalence to the predicate device (XGEO GC80) by showing that the proposed device (GC85A) does not significantly differ in technical characteristics or performance in a way that would raise new questions of safety or effectiveness.

The document highlights differences and provides explanations for why these differences do not negatively impact safety or performance, and importantly, states that non-clinical and clinical data show equivalence.

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

• Test Set (Clinical Data): The document states "clinical images were obtained" (Page 9) but does not specify the sample size (number of images or patients) used for the clinical evaluation.
• Data Provenance: The document implies the data is prospective in the sense that the "proposed GC85A" was used to obtain the clinical images. The country of origin for the clinical data is not explicitly stated, but the manufacturer is based in the Republic of Korea.

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

• Number of Experts: One professional radiologist was used.
• Qualifications: "a professional radiologist" and later specified as "a radiologist with equivalent U.S. board certification" (Page 9).

4. Adjudication Method for the Test Set

The document states that "They [clinical images] were evaluated by a professional radiologist" (Page 9). This indicates a single-reader evaluation. Therefore, there was no adjudication method (like 2+1 or 3+1 consensus) used for the clinical image evaluation described.

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

No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not done. The clinical evaluation involved a single radiologist assessing images from the proposed device against the predicate. This is not an MRMC study comparing human readers with and without AI assistance, as the device itself is an X-ray imaging system, not an AI-powered diagnostic tool. The document focuses on demonstrating that the system produces images equivalent to a predicate.

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

This question is not applicable in the context of this device. The GC85A is a digital X-ray imaging system, which means it produces images. Its performance is evaluated on the quality of these images and their equivalence to images from a predicate device, rather than the diagnostic output of an algorithm. Evaluation of "standalone" performance for such a device would pertain to its image acquisition and processing capabilities, which are covered by the MTF and DQE measurements (non-clinical data).

7. The Type of Ground Truth Used

For the clinical evaluation, the "ground truth" was established by expert consensus/opinion (though in this case, a single expert's opinion) comparing the general image quality of the proposed device's images to the predicate device's images. The radiologist "found [the images] to be equivalent to the predicate device."

For the non-clinical data, the ground truth or reference points were standardized measurements (MTF and DQE) as defined by IEC 62220-1.

8. The Sample Size for the Training Set

The document does not mention a training set sample size. This is because the device described is an X-ray imaging system, not an AI/machine learning device that typically requires a large training set for algorithm development. The development process would involve engineering design and physical testing rather than algorithmic training on vast datasets.

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

As no training set is described for this type of device, this question is not applicable.

Ask a specific question about this device