Search Results

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.

The GM85 Digital Mobile 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 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 send to the Picture Archiving & Communication System (PACS) sever for reading images.

The GM85 Digital Mobile X-ray imaging System was previously cleared with K180543, and through this premarket notification, we would like to add more configurations in the previously cleared GM85 as a fixed column type 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 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 Manual Stitching to capture a body part that is larger than the detector's by capturing multiple images and Remote View function to remote access to view the current image on the workstation through a web browser. It was determined that the level of concern for the software contained in the GM85 Digital Mobile 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 text does not contain detailed acceptance criteria or a comprehensive study report specifically outlining acceptance criteria with reported device performance metrics in a tabular format. However, it does discuss performance characteristics, non-clinical data, and clinical data used to establish substantial equivalence.

Here's an attempt to extract and infer the information based on the provided document.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria. Instead, it focuses on demonstrating substantial equivalence to a predicate device. The performance is generally reported as "equivalent to the predicate devices" or "satisfying the standards."

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

• Test Set Sample Size: The document does not specify a numerical sample size for the clinical image evaluation. It only mentions "Anthropomorphic phantom images were provided."
• Data Provenance: The document does not specify the country of origin of the data. The study involved "Anthropomorphic phantom images." It is a prospective evaluation using phantoms, rather than retrospective patient data.

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

• Number of Experts: "a professional radiologist" (singular)
• Qualifications of Experts: The document specifies "a professional radiologist." It does not provide additional details such as years of experience.

4. Adjudication Method for the Test Set

The document states that the phantom images "were evaluated by a professional radiologist." It does not mention any adjudication method (e.g., 2+1, 3+1) involving multiple readers or a consensus process.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No, a multi-reader multi-case (MRMC) comparative effectiveness study focusing on human readers improving with AI vs. without AI assistance was not explicitly described or reported. The study focused on demonstrating the equivalenc of the device's image quality and the S-Enhance feature's ability to provide clear visibility.

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

The S-Enhance feature and new detectors were evaluated, suggesting an assessment of the algorithm's output (the enhanced image) and the detector's image characteristics. While not a purely "standalone algorithm" in the sense of a diagnostic AI making decisions, the evaluation of the S-Enhance feature generating "companion images which provide clear visibility" effectively assesses the algorithm's performance without direct human interaction during the image generation process. The radiologist then evaluates these generated images.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

For the clinical data, the ground truth was based on the inherent properties of the anthropomorphic phantom images, which simulate human anatomy and disease conditions. The radiologist's evaluation of the clarity and visibility in these phantom images served as the assessment against this simulated ground truth.

8. The Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set for features like S-Enhance.

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

The document does not provide details on how the ground truth for training data was established for the S-Enhance feature or any other software components. It mentions that S-Enhance is the same image processing technology as a previously cleared feature (TLE) and extends its scope. This implies that previous development and potentially associated training (if applicable to the algorithm) would have been used.

Ask a specific question about this device

The GM85 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 of all kinds of anatomical regions.

The Tube & Line Enhancement enhances the visibility of tube and line to support radiologists or ICU clinicians who may need to find tubes and line on chest radiographs by trained professionals, such as physician, radiologists, and technicians.

The Pediatric Exposure Management support radiologists to select suitable patient's size or take steps to serve an optimal exposure conditions to the lowest possible levels especially for the pediatric patients.

The GM85 Digital Mobile X-ray imaging System is the equipment that captures 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 SimGrid is an additional image processing software option which is able to compensate the contrast loss due to scatter radiations, primarily acquisitions without a physical anti-scatter grid of all kinds of anatomical regions.

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

The Tube & Line Enhancement (TLE) is that after generating a normal post processing image, pressing the TLE button will create a companion view. For making a better tube & line look in chest radiography, input raw image is processed by using stronger contrast and detail enhancement algorithm. This supports clearer visibility of tube & lines than normal post processing image.

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

The Pediatric Exposure Management provides subdivided patient size and exposure conditions of chest and abdomen radiographs specially optimized for pediatric patients. It helps an optimal dose for radiographic procedures of pediatric patients by providing guidance of optimized exposure conditions according to patient's weight and procedures.

The provided text describes the safety and effectiveness information for the Samsung GM85 Digital X-ray imaging System, including its optional features SimGrid and Tube & Line Enhancement (TLE).

1. Table of acceptance criteria and the reported device performance:

The document does not explicitly state pre-defined acceptance criteria with numerical thresholds. Instead, the "acceptance" is implicitly based on demonstrating substantial equivalence to predicate devices through a combination of non-clinical and clinical data, as required by FDA 510(k) submission guidelines. The performance is reported in terms of comparative benefits over baseline or predicate devices.

• Gantry (Newly designed for enhanced coverage and usability) has same structures (battery powered, wheel-based, built-in console, rotational collapsible column, extractable arm, rotational tube head) as predicate GM60A, thus no significant changes in acquiring radiographic images.
• Extended coverage of GM85's moving range is more helpful for positioning than GM60A.
• Tube target angle of 14° does not have significant changes in image characteristics compared to GM60A's 12°-16°.
• Collimator has same design as predicate GC85A but with mechanical changes to mount sub-display unit, no significant changes in performance.
• S-Align has same design but operates only manually (compared to GC85A), with no adverse impacts on safety/performance.
• Conclusion: "The non-clinical and clinical data demonstrate that the proposed device is as safe, as effective, and performs as well as the legally marketed predicate devices #1, #2 and #3." |
  | SimGrid Software| Demonstrates better local contrast than images acquired without a physical anti-scatter grid, extending to additional anatomical regions as compared to the predicate device's description. | - Evaluated with various phantoms at various exposure conditions.
• Demonstrates that SimGrid processing gives better local contrast than images acquired without a grid at expanded anatomical regions. (Previously 510(k) cleared with predicate device #2). |
  | Tube & Line Enhancement (TLE) Software| Enhances the visibility of tubes and lines on chest radiographs to support radiologists or ICU clinicians, functioning as an assistant tool without being a substitute for the original image. Performance should be comparable or superior to the predicate device ClearRead +Confirm (K123526) in enhancing tube and line visibility. It should also be applicable to all patients, including pediatric patients, without compromise. | - "After generating a normal post processing image, pressing the TLE button will create a companion view."
• Uses stronger contrast and detail enhancement algorithm for clearer visibility of tubes & lines than normal post processing image.
• Evaluated with a chest phantom (with an inserted tube line). Comparison between normal post image and TLE image proved TLE processing gives better tube and line visibility than original post processing.
• The intended use specifies it "generates a companion image which can provide clear visibility of tubes and lines in addition to the original chest radiograph."
• "TLE software amplify specific frequencies suitable for tubes and lines partially, it does not depend on the size of patients. Therefore TLE software can be used for all patients including the pediatric patient."
• No significant changes in performance compared to predicate device #3. |

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

• Sample Size for Test Set: "Evaluated 30 case of phantom image includes eight parts of the body."
• Data Provenance: Not explicitly stated, but given it's a 510(k) submission from SAMSUNG ELECTRONICS Co., Ltd. (Republic of Korea), it's highly likely the testing was conducted in Korea, or by a contract research organization. The study used non-clinical phantom images, not human patient data.

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

• Number of Experts: "Evaluated by a professional radiologist." (Implies one professional radiologist was used).
• Qualifications: "professional radiologist." No further details on years of experience or sub-specialty are provided.

4. Adjudication method for the test set:

• The document states the phantom images were "evaluated by a professional radiologist." There is no mention of an adjudication method (like 2+1 or 3+1) or multiple readers.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No MRMC study mentioned. The clinical data section only refers to phantom image evaluations reviewed by one radiologist for equivalence. The TLE and SimGrid features are described as enhancing images or providing better contrast/visibility, but without a formal MRMC study to quantify human reader improvement.

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

• Yes, in essence. The evaluations for SimGrid and TLE were primarily focused on the algorithm's output performance (e.g., "better local contrast," "better tube and line visibility") when applied to phantom images. While a radiologist reviewed the outputs, the assessment was about the visual quality of the processed image rather than a diagnostic performance study of the radiologist using the device. The GM85 system itself, including its basic image acquisition and processing, also undergoes standalone performance testing (e.g., MTF, DQE).

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

• For the phantom images, the "ground truth" is based on the known physical properties of the phantom and the expert assessment of image quality (e.g., contrast, visibility of structures) by a professional radiologist. This is a form of expert assessment of image features rather than a clinical ground truth like pathology or patient outcomes.

8. The sample size for the training set:

• The document does not specify the sample size for the training set for any of the software features (SimGrid, TLE, PEM). It implies that SimGrid was cleared previously, and TLE/PEM are new additions with their own evaluations.

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

• The document does not provide details on how ground truth was established for the training sets of SimGrid, TLE, or PEM. It generally states that SimGrid was previously cleared and TLE/PEM are based on algorithms designed for specific enhancements. For TLE, it mentions "input raw image is processed by using stronger contrast and detail enhancement algorithm," suggesting expert knowledge of what constitutes "better contrast" for tubes and lines likely informed the algorithm's development.

Ask a specific question about this device