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 K222353, and through this premarket notification, we would like to add more configurations in the previously cleared GM85 as a detector, accessories are newly added and software is updated for user convenience.

The new detector added in the proposed device is designed to achieve a higher IP rating of Dust and Water and reduce weight while maintaining durability, functionality and operation like the detector of the predicate device. The new detector and predicate device's detector are both an x-ray conversion device using an amorphous silicon flat panel and absorb incident x-rays, converts it to a digital signal, and then transmits it to the Samsung Digital X-ray System like that of the predicate device.

The provided text is a 510(k) Premarket Notification for the GM85 Digital Mobile X-ray Imaging System. It describes changes made to a previously cleared device (K222353) and argues for substantial equivalence.

Based on the provided text, the device is the GM85 Digital Mobile X-ray Imaging System. It is an X-ray imaging system, and the study focuses on the performance of a new detector (F4343-AW) and other accessories and software updates compared to the predicate device, also named GM85.

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

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly state "acceptance criteria" in a quantitative format for specific imaging metrics. Instead, it focuses on demonstrating that the proposed device, with its new detector, accessories, and software, is substantially equivalent to the predicate device (GM85, K222353). The performance is assessed by comparing technical specifications and qualitative evaluation by experts.

The key performance characteristics and comparisons are as follows:

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

• Test Set Sample Size: The document refers to "Anthropomorphic phantom images" but does not specify the number of phantom images used for evaluation. It also notes that clinical data was not required.
• Data Provenance: The study is non-clinical. The "Anthropomorphic phantom images" would have been generated in a controlled testing environment, likely at the manufacturer's facility. The country of origin of the data is implicitly South Korea, where SAMSUNG ELECTRONICS Co., Ltd. is located. The study is a prospective evaluation of the new detector and modified system against the predicate.

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

• Number of Experts: The document states that phantom images "were evaluated by professional radiologists." It does not specify the number of radiologists who participated in this evaluation.
• Qualifications of Experts: The experts are described as "professional radiologists." No further details on their experience level (e.g., years of experience, subspecialty) are provided.

4. Adjudication Method for the Test Set

The document states that phantom images "were evaluated by professional radiologists and found to be equivalent to the predicate devices" and that there was "no significant difference in the average score of image quality evaluation." This suggests a comparative scoring or assessment. However, the specific adjudication method (e.g., consensus, majority vote, independent reads with statistical comparison) is not described.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly done, nor was there a "human readers improve with AI vs without AI assistance" component. The study for substantial equivalence focused on comparing the image quality of the proposed device (with new detector) against the predicate device using phantom images, evaluated by radiologists. The purpose was to show equivalence of the device's output, not the improvement of human readers with AI assistance.

6. Standalone Performance Study (Algorithm Only)

The provided text describes the device as a "Digital Mobile X-ray Imaging System," which includes hardware (X-ray generator, detector) and software for image processing (IPE, S-Station). The evaluation primarily focuses on the entire system's ability to generate radiographic images with equivalent quality to the predicate, particularly with the new detector.

While software features are mentioned (S-Share, S-Enhance, SimGrid, PEM, QAP, Bone Suppression, Remote View, Mirror View, RFID, Value-up Package), and software was updated for user convenience, the study does not report a standalone algorithm-only performance (without human-in-the-loop performance) in terms of diagnostic accuracy or reader improvement for specific diagnostic tasks. The "phantom image evaluation" evaluates the quality of the images produced by the overall system, not an AI algorithm's diagnostic output.

7. Type of Ground Truth Used

The ground truth for the phantom image evaluation was established based on expert consensus/evaluation of image quality metrics. The "professional radiologists" evaluated the anthropomorphic phantom images. This is not pathology, nor outcomes data.

8. Sample Size for the Training Set

The document does not provide information on the sample size for the training set. Training data would typically be applicable if this were an AI/CADe device with a specific machine learning model for diagnostic tasks, which is not the primary focus of this 510(k) for a basic X-ray imaging system with incremental changes. The "Image Post-processing Engine (IPE)" and features like "Bone Suppression" would have been developed using some form of training data previously, but details are absent here for this particular submission.

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

As no training set sample size is provided, the method for establishing ground truth for a training set is not mentioned in this document.

Ask a specific question about this device

The GF85 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 GF85 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 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 GF85 Digital X-ray Imaging System includes two models, namely the GF85-3P and GF85-SP. These two models differ primarily in terms of their respective configurations of High Voltage Generators (HVGs). Specifically, the GF85-3P features capacities of 80 kW, 65 kW and 50 kW with 3 phases, whereas the GF85-SP provides a capacity of 40 kW with a single phase. However, all other specifications remain consistent across both models.

The provided text describes the GF85 Digital X-ray Imaging System and its substantial equivalence to predicate devices (GC85A and GM85). The key study mentioned for demonstrating equivalence is a non-clinical phantom image evaluation.

Here's a breakdown of the requested information based on the provided text, with "N/A" for information not present:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in a table format. Instead, it relies on a comparison with predicate devices and a general statement that "All test results were satisfying the standards" and that the phantom image evaluations "found to be equivalent to the predicate device."

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

The document states "The phantom image evaluations were performed...".

• Sample size for test set: The document does not specify the number of phantom images used in the evaluation.
• Data provenance: Phantom images are synthetic data, not from human subjects. The country of origin for the data is not specified, but the submission is from Samsung Electronics Co., Ltd. in South Korea.

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

The document states, "...and were evaluated by three different professional radiologists..."

• Number of experts: Three.
• Qualifications of experts: "professional radiologists." Specific experience levels (e.g., "10 years of experience") are not provided.

4. Adjudication method for the test set

The document states the images "were evaluated by three different professional radiologists and found to be equivalent to the predicate device." It does not specify a formal adjudication method (e.g., 2+1, 3+1 consensus). It implies a collective agreement on equivalence.

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

• MRMC study: No. The study conducted was a non-clinical phantom image evaluation to compare the device's image quality to a predicate device, as evaluated by radiologists. It was not a comparative effectiveness study involving human readers' performance with and without AI assistance.
• Effect size of human reader improvement with AI: N/A, as no such study was conducted or reported.

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

• The primary evaluation described (phantom image reviews) involved human radiologists assessing images generated by the device. The device itself is an X-ray imaging system, not an AI algorithm performing diagnostic interpretation. While the software features list "Lunit INSIGHT CXR Triage" as a new feature for the GF85, the provided text does not detail any standalone performance study specifically for this AI component or any other algorithmic component of the GF85. The "phantom image evaluations" are about the device's image quality, not an algorithm's diagnostic performance.

7. The type of ground truth used

For the phantom image evaluation, the ground truth is implicitly defined by the known characteristics and standards of the phantom images themselves, as well as the comparison against the predicate device. It is not expert consensus on pathology, or outcomes data.

8. The sample size for the training set

• Training set sample size: N/A. The document describes a traditional X-ray imaging system and its non-clinical evaluation for substantial equivalence. It does not refer to a machine learning model's training set. While there are "Software Features" like "Lunit INSIGHT CXR Triage" which would involve AI, the document does not discuss their training data.

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

• Ground truth for training set: N/A, as no training set for a machine learning model is directly discussed for the GF85 system itself in the context of its substantial equivalence.

Ask a specific question about this device

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 provided text describes a 510(k) premarket notification for the GM85 Digital Mobile X-ray Imaging System. The primary purpose of this notification is to add a new detector configuration to an already cleared device (K220175). As such, the study described focuses on demonstrating the substantial equivalence of the new detector and its integration, rather than establishing primary performance metrics from scratch for a completely new device.

Here's a breakdown of the acceptance criteria and the study conducted based on the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly tied to demonstrating equivalence to the predicate device's existing performance, particularly for the new detector. The non-clinical and clinical (phantom image evaluation) data serve to show that the new detector maintains similar performance characteristics.

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

• Sample Size for Test Set: The document mentions "Anthropomorphic phantom images were provided." It does not specify the exact number of phantom images or the number of distinct phantom cases used in the evaluation.
• Data Provenance: The nature of phantom images means the data is synthetic/simulated clinical data (using phantoms to mimic human anatomy) rather than human patient data. The country of origin for the data is not explicitly stated, but it would have been generated as part of the manufacturer's internal testing as advised by FDA guidance. The study is prospective in the sense that the evaluations were specifically conducted for this submission.

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

• Number of Experts: The document states that phantom images "were evaluated by professional radiologists." It does not specify the exact number of radiologists involved.
• Qualifications of Experts: They are described as "professional radiologists." Specific lengths of experience or subspecialties are not provided.

4. Adjudication Method for the Test Set

• The document implies a consensus or comparison approach: "They were evaluated by professional radiologists and found to be equivalent to the predicate devices. There is no significant difference in the average score of image quality evaluation between the proposed device and the predicate device." However, a specific adjudication method (e.g., 2+1, 3+1 decision rule) is not explicitly stated. It seems to be a comparative evaluation aiming for no significant performance degradation.

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

• No MRMC comparative effectiveness study was done. This submission focuses on hardware modification (new detector) to an existing device, not an AI-assisted diagnostic tool. Therefore, the concept of improving human readers with AI assistance is not applicable here.

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

• This is not an AI/algorithm-only device. The GM85 is an X-ray imaging system. The "standalone" performance here refers to the device's ability to produce images with acceptable quality on its own. Non-clinical data (MTF, DQE measurements) and phantom images contribute to demonstrating this standalone image performance. The evaluation by radiologists of the phantom images is more about confirming the quality of the "output" of the device in a clinical context, rather than evaluating an algorithm's diagnostic capability.

7. The Type of Ground Truth Used

• For the phantom image evaluation, the "ground truth" is established by the known characteristics of the anthropomorphic phantoms. The purpose of the radiologists' evaluation is to determine if the images produced by the new detector (compared to the predicate's detector) adequately represent these known phantom structures and maintain diagnostic quality. In essence, the ground truth is the known physical properties of the phantom, and the evaluation confirms the device's ability to render these properties accurately in images.

8. The Sample Size for the Training Set

• This submission describes a modification to an existing medical device's hardware (a detector), not an AI or machine learning algorithm. Therefore, there is no "training set" in the context of AI model development that would typically be described here. The device itself is "trained" or designed through engineering and validated through performance testing.

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

• As there is no AI training set as commonly understood in this context, the concept of establishing ground truth for a training set does not apply. The device's design and engineering would be based on established physics principles of X-ray imaging and medical imaging standards.

Ask a specific question about this device

The GEMS-H is a robotic exoskeleton that fits orthotically on the wearer's waist and thighs, outside of clothing. The device is intended to help assist ambulatory function in rehabilitations under the supervision of a trained healthcare professional for the following population:

· Individuals with stroke who have gait deficits and exhibit gait speeds of at least 0.4 m/s and are able to walk at least 10 meters with assistance from a maximum of one person.

The trained healthcare professional must successfully complete a training program prior to use of the device. The device is not intended for sports.

The GEMS-H is a lightweight, robotic exoskeleton designed to help assist ambulatory function of stroke patients who meet the assessment criteria, in rehabilitations under the supervision of a trained healthcare professional. The GEMS-H device provides assistance to the patient during hip flexion and extension.

The device is worn over clothing around the wearer's waist and fastened with Velcro straps to assists hip flexion and extension. The device weighs 4.7 lbs (2.1 kg) and has two motors that run on a single rechargeable battery. The device is equipped with joint angle and electrical current sensors to monitor hip joint angle and torque output, respectively.

The assist torque is transmitted to the wearer's thighs via thigh support frames. A trained healthcare professional, who operates the device, can change assist settings through software that runs on the tablet PC.

This document describes the premarket notification (510(k)) for the Samsung GEMS-H, a powered lower extremity exoskeleton. The information provided primarily focuses on establishing substantial equivalence to a predicate device, rather than proving the device meets specific acceptance criteria related to an AI's performance.

Based on the provided text, the device itself (GEMS-H exoskeleton) is the subject of the regulatory review, and the "study" described is a clinical trial to assess its safety and effectiveness in assisting ambulatory function in stroke patients. There is no mention of an AI component requiring specific performance acceptance criteria for an algorithm or model.

Therefore, many of the requested points regarding AI acceptance criteria, ground truth establishment, expert adjudication, and MRMC studies are not applicable directly to this document's content, as it's not about an AI-powered diagnostic or predictive device.

However, I can extract information related to the device's clinical performance and the study design:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the device are defined in terms of safety and effectiveness, based on a clinical trial.

Note: The primary effectiveness endpoint reported (+0.12 m/s) did not explicitly meet the stated objective of "≥0.14 m/s". However, the FDA's clearance indicates that the overall evidence was sufficient for substantial equivalence. The document highlights that the exploratory endpoints showed larger improvements with the device, and that the "study subjects achieved a mean clinically significant improvement (MCID) in gait speed as measured by the 10MWT, and in walking endurance as measured by the 6MWT."

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

• Test Set Sample Size: The clinical study enrolled 53 subjects, of whom 41 completed the entire protocol. This effectively serves as the "test set" for the device's performance.
• Data Provenance: The study was conducted in the United States (Shirley Ryan AbilityLab, Northwestern University, Chicago, IL). It was a prospective, single arm, interventional, open-label, single center study.

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

This question is not applicable in the context of this device. The "ground truth" for the device's performance is objective physiological measurements (gait speed, walking endurance) and adverse event reporting, observed by medical professionals (licensed physical therapists and physicians) during rehabilitation sessions. It's not a diagnostic AI where experts label images or data for truth.

4. Adjudication Method for the Test Set

Not applicable. This is not an imaging or diagnostic study requiring adjudication of expert interpretations.

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. This device is an exoskeleton for physical assistance, not an AI for human reader enhancement.

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

This question is not directly applicable. The device itself performs its function (providing mechanical assistance), and its performance is evaluated with human-in-the-loop (the patient wearing it and being supervised by a healthcare professional). The document states the device is intended to assist ambulatory function "under the supervision of a trained healthcare professional." There is no "standalone algorithm" performance to report in this context.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance was based on:

• Objective functional mobility measures: 10-Meter Walk Test (10MWT) for gait speed and 6-Minute Walk Test (6MWT) for walking endurance. These are standardized, objective measures of physical performance.
• Adverse Event reporting: Clinical observation and documentation of any adverse events during the study.

8. The Sample Size for the Training Set

Not applicable, as this is not an AI model requiring a training set in the typical sense. The clinical study of 41 subjects who completed the protocol served as the primary evidence.

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

Not applicable for the same reason as #8. The data collected from the 41 patients in the clinical study are the direct evidence of the device's performance in a real-world (rehabilitation) setting.

Ask a specific question about this device

The CUBE Air Purifier is a device intended for medical purposes that is used to destroy bacteria and viruses in the air by exposure to ultraviolet radiation.

The CUBE Air Purifier has been demonstrated to destroy the following MS2 bacteriophage, Staphylococus epidermidis, Escherichia coli entrained on the filter of the under the following exposure conditions:

The CUBE Air Purifier employs a photocatalytic oxidation (PCO) ultraviolet air purification technology that destroys bacteria and viruses in air in medical facilities. The CUBE Air Purifier includes a pre-filter, a dust collecting filter, UV-A LED lights (320-400 nm), and a catalytic filter.

The device is intended to be placed in medical and healthcare facilities.

The provided text describes the acceptance criteria and the study that proves the CUBE Air Purifier meets those criteria. Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document describes non-clinical performance testing conducted in a controlled laboratory environment. The "sample size" here refers to the number of tests performed on the device itself, rather than human subjects or a dataset of medical images.

• Sample Size for performance testing: The document does not explicitly state the number of repetitions for each performance test (e.g., how many times the aerosolized bacteria/virus reduction was measured). It typically presents average results with standard deviations, implying multiple runs were conducted.
• Data Provenance: The studies were conducted as part of the device's premarket notification (510(k)) submission to the FDA. This indicates that the data was generated specifically for regulatory purposes in a controlled laboratory setting (e.g., environmental bioaerosol chamber). The country of origin for the studies is not explicitly stated, but the submitter (Samsung Electronics Co., Ltd.) is based in South Korea. The studies are prospective in nature, as they involve actively testing the device's performance under specified conditions.

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

This information is not applicable (N/A) to this type of device (air purifier). The "ground truth" for air purifiers is established through direct laboratory measurements of microbial reduction and filter efficiency, not through human expert interpretation of data like in medical imaging.

4. Adjudication Method for the Test Set

This is not applicable (N/A). Adjudication methods (e.g., 2+1, 3+1 consensus) are typically used in studies involving human interpretation (like in diagnostic imaging studies) to resolve disagreements among readers. For an air purifier, the "ground truth" is determined by objective scientific measurements in a lab.

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

This is not applicable (N/A). MRMC studies are relevant for diagnostic devices where human readers (e.g., radiologists) interpret cases (e.g., medical images), often with or without AI assistance. This document describes the performance of an air purifier in reducing airborne pathogens, not a diagnostic tool requiring human interpretation.

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

This concept is not directly applicable in the context of an air purifier. The "device performance" is the standalone performance. The machine itself is performing the intended function (destroying bacteria and viruses). There isn't an "algorithm only" that then needs to be compared to a human-in-the-loop performance, as the device's function is purely mechanical and chemical (UV-A and photocatalytic oxidation). The tests performed (e.g., log reduction of microbes in a chamber) are measures of its standalone efficacy.

7. The Type of Ground Truth Used

The ground truth used in these studies is based on direct laboratory measurements of microbial viability and particle count reduction.

• For microbial reduction: The ground truth is the measured decrease in the concentration of specific bacteria and viruses (MS2 bacteriophage, Phi-X174 bacteriophage, Staphylococcus epidermidis, Escherichia coli) in a sealed chamber after exposure to the CUBE Air Purifier. This is a quantitative outcome data obtained through standard microbiological assay techniques.
• For filter efficiency: The ground truth is the measured percentage of particles (0.3 to 1.0 micron size) removed by the filter, according to ASHRAE 52.2 standards, which is a performance standard/outcome data.

8. The Sample Size for the Training Set

This is not applicable (N/A). The CUBE Air Purifier is a physical device employing UV and photocatalytic oxidation for air purification. It is not an AI/ML-based device that requires a "training set" of data to learn or develop an algorithm. Its performance is based on established physical and chemical principles.

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

This is not applicable (N/A), as there is no "training set" described for this device.

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 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 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 GC70 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 GC70 digital X-ray imaging system consists of HVG (High Voltage Generator), ceiling suspension, X-ray tube, collimator, detector, wall stand, patient table, ACE (Auto Exposure Control), DAP (Dose Area Product), CIB (Control Interface Box), remote controller, grid, foot switch, barcode scanner, auto-stitching stand, weight distribution cap and workstation for S-station including Image Post-processing Engine (IPE).

The GC70 digital X-ray imaging system was previously cleared under K180543, and some hardware options and three software features are added to the predicate device GC70. The changes are as follows:

• Two High Voltage Generators
• . Two detectors
• . Slim wall stand
• . Software features called as S-Enhance, PEM (Pediatric Exposure Management) and Remote View
  • The S-Enhance is optional software to improve clarity of a foreign body (e.g. tube, line) and stone in chest, abdomen and L-spine images. With a single onscreen click, the companion image is created without additional settings or xray exposure, streamlining the process.
  • Pediatric Exposure Management is subdivided patient size and exposure conditions especially for pediatric patients based on weight and protocols. It follows same methodologies to define preset of patient size compare to preset of standard patient size from predicate device but specially optimized for pediatric patients.
  • The Remote view function provided images on another PC, not just on the device.

The Samsung GC70 Digital X-ray Imaging System, under K182647, is intended for generating radiographic images of human anatomy. This submission is a special 510(k) for changes to a previously cleared GC70 device (K180543), adding hardware options and three software features (S-Enhance, PEM, and Remote View) identical or similar to those cleared in predicate device GC85A (K181629).

1. Table of Acceptance Criteria and Reported Device Performance

No specific acceptance criteria or quantitative device performance metrics (e.g., sensitivity, specificity, accuracy) are provided in the document for the new features. The submission relies on the assertion that the new hardware and software features are identical or similar to previously cleared predicates and have undergone verification and validation testing to meet requirement specifications, functioning as safely and effectively.

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

The document does not specify a separate "test set" in the context of image data for evaluating the clinical performance of the software features. The verification and validation of the software features were conducted "in accordance with internal design change procedure." The non-clinical testing data, including MTF and DQE measurements, were provided in conformance to FDA guidance for solid-state X-ray imaging devices. However, no specific sample size of images or patients is reported, and there is no information on the country of origin or whether data was retrospective or prospective.

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

This information is not provided. The submission focuses on technical equivalence and verification/validation against internal specifications, rather than clinical performance studies requiring expert-adjudicated ground truth.

4. Adjudication method for the test set

This information is not provided. Given the nature of the submission (special 510(k) for hardware/software additions to an already cleared device, asserting equivalence), a formal adjudication process for a clinical test set is not described.

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

No MRMC comparative effectiveness study is mentioned or provided. The document explicitly states: "The application of these hardware options and software features, cleared with K181629, to the proposed device GC70 do not require clinical data." This indicates that no studies involving human readers or AI assistance were deemed necessary for this submission.

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

No standalone algorithm performance study is described in the provided text. The software features (S-Enhance, PEM, Remote View) are described as tools or enhancements to the imaging system, rather than standalone diagnostic algorithms requiring independent performance metrics like sensitivity or specificity. Their verification and validation were conducted against "internal design change procedure" and "requirement specifications."

7. The type of ground truth used

The document does not detail the type of ground truth used as it does not report clinical efficacy studies. The "ground truth" for the non-clinical tests (MTF, DQE) would be based on physical measurements and established phantom standards (e.g., IEC 62220-1). For the software features, the "ground truth" was likely defined by internal "requirement specifications" within Samsung's design change procedures, focusing on functional correctness and qualitative improvements as described (e.g., "improve clarity," "subdivided patient size").

8. The sample size for the training set

This information is not provided. Since the software features are described as "optional software to improve clarity" or "subdivided patient size and exposure conditions" and are stated to be "identical or similar" to features in a predicate device, it's possible they involve image processing or rule-based systems rather than deep learning models that require large training sets. Even if machine learning was used, the training data details are not disclosed.

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

This information is not provided. Similar to the training set sample size, the methodology for establishing ground truth for any potential training data is not detailed.

Ask a specific question about this device

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 GU60A, GU60A-65 digital X-ray imaging systems are a stationary x-ray system designed for general radiography and 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 Postprocessing Engine (IPE) which is exclusively installed in S-station, and sent to the Picture Archiving, Communication System (PACS) sever for reading images.

The GU60A, GU60A-65 digital X-ray imaging systems consist of HVG (High Voltage Generator), U-arm positioner, X-ray tube, collimator, detector, ACE (Auto Exposure Control), DAP (Dose Area Product), CIB (Control Interface Box), remote controller, grid, barcode scanner, auto-stitching stand, weight distribution cap and workstation for Sstation including Image Post-processing Engine (IPE).

The difference between GU60A and GU60A-65 is that the option of their HVG is different. In detail, 50 kW and 68 kW are for GU60A and 65 KW is for GU60A-65.

The GU60A, GU60A-65 digital X-ray imaging systems were previously cleared under K180543, and some hardware options and three software features are added to the predicate device GU60A, GU60A-65. The changes are as follows:

• Two detectors
• Software features called as S-Enhance, PEM (Pediatric Exposure Management) and Remote View
  • The S-Enhance is optional software to improve clarity of a foreign body (e.g. tube, line) and stone in chest, abdomen and L-spine images. With a single onscreen click, the companion image is created without additional settings or xray exposure, streamlining the process.
  • Pediatric Exposure Management is subdivided patient size and exposure conditions especially for pediatric patients based on weight and protocols. It follows same methodologies to define preset of patient size compare to preset of standard patient size from predicate device but specially optimized for pediatric patients.
  • The Remote view function provided images on another PC, not just on the device.

The provided text describes a 510(k) premarket notification for the GU60A and GU60A-65 Digital X-ray Imaging Systems. It details the device, its intended use, and comparisons to predicate devices. However, the document does not contain any information about acceptance criteria or a study proving the device meets specific acceptance criteria based on performance metrics like accuracy, sensitivity, or specificity for a particular clinical task.

The document states:

• "Non-clinical data demonstrates that the proposed devices are as safe, as effective, and perform as well as the legally marketed predicate devices."
• "The application of detectors and software features, cleared with K181629, to the proposed device GU60A, GU60A-65 does not require clinical data."
• "The verification and validation for the software features added to the proposed device were also conducted and reviewed in accordance with internal design change procedure. As a result, requirement specifications were met and the proposed device shows no difference in non-clinical testing data such as MTF and DQE measurements from the predicate device."

This implies that the acceptance was primarily based on:

1. Substantial equivalence to predicate devices: The new features (S-Enhance, PEM, Remote View, and new detectors) were already cleared with previous predicate devices (K180543 and K181629).
2. Compliance with non-clinical performance and safety standards: Electrical, mechanical, environmental safety, EMC, and X-ray specific performance (MTF, DQE measurements) were conducted according to relevant IEC and FDA standards (e.g., ES 60601-1, IEC 60601-1-2, IEC 60601-1-3, IEC 60601-2-28, IEC 60601-2-54, ISO14971, 21CFR1020.30, 21CFR1020.31).
3. Software verification and validation: Conducted according to internal design change procedures.

Therefore, I cannot provide the requested information regarding acceptance criteria and a study proving the device meets clinical performance acceptance criteria because the provided text explicitly states that clinical data was not required for this 510(k) submission.

The document focuses on demonstrating substantial equivalence to pre-existing, cleared devices and adherence to engineering and non-clinical performance standards for X-ray imaging systems. It does not describe a study involving an AI component with specific performance metrics (like accuracy for a diagnostic task) and associated acceptance criteria that would typically involve human-in-the-loop studies, multi-reader multi-case studies, or expert ground truth adjudication.

If the question is implicitly asking about the "acceptance criteria" and "study" in the context of the entire X-ray system meeting regulatory clearance, then the answer is based on "substantial equivalence" and compliance with non-clinical performance and safety standards, as detailed in the document, rather than a clinical performance study for a specific diagnostic AI feature.

Based solely on the provided text, and understanding that it does not describe a clinical performance study for an AI component's diagnostic accuracy:

I cannot populate the requested table and answer many of the specific questions because the document does not contain the necessary information about a clinical performance study or diagnostic AI acceptance criteria. The submission is for a general radiographic imaging system and an enhancement software (S-Enhance) for clarity of foreign bodies/stones, but without specifying diagnostic performance metrics or a study to prove them.

Here's what can be inferred or stated based on the text's lack of this information:

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

The document's acceptance criteria related to safety and general performance are:

• Compliance with electrical, mechanical, environmental safety standards (ES 60601-1, IEC 60601-1-2, IEC 60601-1-3, IEC 60601-2-28, IEC 60601-2-54, ISO14971, 21CFR1020.30 and 21CFR1020.31).
• Compliance with EMC testing (IEC 60601-1-2).
• Compliance with wireless function guidance.
• Conformity to FDA "Guidance for the Submission of 510(k)'s for Solid-State X-ray Imaging Devices" for non-clinical data (MTF and DQE measurements).
• Software verification and validation meeting "requirement specifications" in accordance with internal design change procedure.

The reported device performance in these areas is that "All test results were satisfying the standards" and "requirement specifications were met and the proposed device shows no difference in non-clinical testing data such as MTF and DQE measurements from the predicate device."

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

• Sample Size: Not applicable/Not specified, as no clinical test set for diagnostic performance was described. The non-clinical performance data (MTF, DQE) would use physical phantoms or test objects, not patient data in the typical sense of a test set for AI.
• Data Provenance: Not applicable/Not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable/Not specified, as no clinical test set or ground truth establishment process for diagnostic performance was described.

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

• Not applicable/Not specified, as no clinical test set or adjudication process was described.

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

• Was an MRMC study done? No. The document states "The application of detectors and software features... does not require clinical data."
• Effect size: Not applicable.

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

• Not applicable/Not specified, as no standalone diagnostic performance study for an AI algorithm was described. The S-Enhance is described as "optional software to improve clarity," which suggests image processing, not a standalone diagnostic AI.

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

• Not applicable/Not specified, as no clinical ground truth for diagnostic performance was described. For non-clinical validation (MTF, DQE), the "ground truth" would be the known physical properties of the test phantoms.

8. The sample size for the training set

• Not applicable/Not specified, as no information about an AI training set is provided.

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

• Not applicable/Not specified, as no information about an AI training set or its ground truth establishment is provided.

Ask a specific question about this device

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 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