Search Results

The RADspeed PRO is intended to generate digital or conventional radiographic images of the skull, spinal column, chest, abdomen, extremities, and other body parts of human anatomies in all routine radiography examinations. The RADspeed Pro enables radiographic or tomographic exposures of the whole body of all ages including pediatric patients. Exposures may be taken with the patient sitting, standing, or lying in the prone or supine position. The RADspeed PRO uses portable or integrated flat panel detectors to generate diagnostic images by converting x-rays into electronic signals. The device is also designed to be used with conventional film/screen or computed radiography (CR) cassettes. The Tomosynthesis option is intended to generate tomographic images of human anatomies. Tomosynthesis technique is used to produce a specific cross-sectional plane of the body by reconstruction. The device is intended to be used in hospitals, clinics, imaging centers, and/or other healthcare facilities by qualified/trained professionals. The device is not intended for mammographic applications.

The RADspeed PRO is an X-ray radiography system that is mainly used for the radiography of various regions of the patient's body in a standing or recumbent position. The RADspeed PRO can be used in a wide range of applications from general radiography using X-ray film or Computed Radiography (CR) cassettes, to digital radiography. The RADspeed PRO consists of an X-ray high voltage generator, X-ray tube unit, X-ray tube support and collimator. The system can be configured with radiographic table, radiographic stand and digital radiography system as well. Optionally, the device is also used to perform tomosynthesis radiography by three different reconstruction modes. Filtered Back-Projection (FBP) mode is used to obtain a tomosynthesis image by performing back-projection after correcting the projection data. Shift Addition (SA) mode is used to obtain a tomosynthesis image at an arbitrary slice plane height by shifting each image according to projection angle of the tube based on the reconstruction height, and by applying image addition processing to them. Iteration (IR) mode is used to reduce metal artifact in tomosynthesis image. FBP mode is generally recommended for all body parts. In case an artifact is observed at joints and other similar places, SA mode may remedy this artifact. In case metal artifact is obviously displayed, IR mode is recommended to reduce metal artifact.

The provided document is a 510(k) premarket notification for the Shimadzu Corporation's RADspeed PRO, referencing K233722. It primarily focuses on demonstrating substantial equivalence to a predicate device (K152244) rather than presenting a performance study against specific acceptance criteria for a new clinical indication or AI algorithm.

The modifications to the RADspeed PRO are described as mainly cosmetic and updates to hardware components (larger displays, updated imaging panels that are themselves cleared 510k devices) and software infrastructure (programming language, operating system) without changes to the underlying software functionality or core technological features. The device does not appear to incorporate a new AI algorithm for diagnostic purposes that would require a study with clinical performance metrics like sensitivity, specificity, or reader improvement.

Therefore, the requested information regarding acceptance criteria and performance study results for an AI algorithm (including sample sizes, ground truth establishment, expert adjudication, MRMC studies, or standalone performance) is not present in the provided text.

The document states:

• "The fundamental technological features are the same for the subject and the predicate systems. The modifications are mainly cosmetic in nature." (Page 4)
• "The software functionality remains unchanged." (Page 5, Page 6)
• "The imaging components were replaced by more recently cleared digital x-ray receptor panels made by FUJIFILM. ... All the imaging panels have 510(k) clearance... The integration software, although updated, has the identical functionality to the predicate." (Page 5)
• "The radiation safety aspects of the device have not changed. The device remains compliant with the FDA Radiation Safety Standards." (Page 9)
• "The non-clinical data supports the safety of the device and the hardware and software verification and validation demonstrate that new device should performs as intended in the specified use. Based on our risk analysis and bench testing, the differences do not affect its clinical safety or effectiveness." (Page 9)

The performance testing mentioned (Software Validation, EMC and Electrical Safety Testing) is related to regulatory compliance and safety for the modified device, not to the clinical performance of a new diagnostic algorithm.

Ask a specific question about this device

The device is designed to perform radiographic x-ray examinations on pediatric and adult patient treatment areas.

The Rover product concept was developed under a contract from the Australian Department of Defense to fulfil a need for a full performance digital medical x-ray imager, light enough to be used in deployed medical facilities. Key Design Features: Full trauma imaging capability 40-110kV, 0.2-20mAs; Ultra-light weight at 105 kg; Ground Clearance allows for 75mm step up; Operation on uneven ground; Spare battery tray swap out in under a minute; The unit uses FDA cleared digital image capture panels and software made by FujiFilm OR Varex.

The provided document is a 510(k) summary for a mobile x-ray system (ROVER) and does not describe acceptance criteria for an AI/ML device or detailed studies proving such a device meets those criteria. The document focuses on establishing substantial equivalence for a hardware medical device to previously cleared devices.

Therefore, many of the requested items (e.g., sample size for test set, data provenance, number of experts, adjudication method, MRMC comparative effectiveness, ground truth type, training set size and ground truth establishment methods) are not applicable or cannot be extracted from this document as it pertains to an X-ray system, not an AI/ML diagnostic aid.

Here's the information that can be extracted or inferred:

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

The document does not specify quantitative acceptance criteria in terms of diagnostic performance metrics for an AI/ML device. Instead, it relies on regulatory standards and the equivalence to predicate devices. The "reported device performance" is essentially that it operates properly and produces diagnostic quality images.

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

Not applicable. The document states "Clinical testing was not required to establish substantial equivalence because all digital x-ray receptor panels have had previous FDA clearance." The testing described is bench testing and verification of system operation, not a clinical study with a test set of patient data.

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, as no clinical test set requiring expert ground truth was used.

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

Not applicable.

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 X-ray system, not an AI diagnostic aid requiring MRMC studies to assess reader improvement.

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

Not applicable. This is an X-ray system, not an AI algorithm.

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

Not applicable, as no clinical test set requiring ground truth was used. The focus was on engineering verification and compliance with standards.

8. The sample size for the training set

Not applicable. This is not an AI/ML device, so there is no training set mentioned.

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

Not applicable.

Ask a specific question about this device

DIAMOND-5A/6A/8A, is a stationary digital diagnostic x-ray system that is indicated for use in generating radiographic images of human anatomy. This device is not intended for mammography, bone density, fluoroscopy and angiography applications.

DIAMOND-5A/6A/8A, system is a digital radiographic system. There are 3 power output configurations which are reflected in the model designation "5A/6A/8A". The models have 3 different output power ratings: 52kW, 68kW, 82kW. DIAMOND 5A/6A/8A, incorporates digital flat panel detector technology, along with an automatic motorized U-arm radiographic stand and mobile patient table that can fit into smaller rooms without the need of ceiling support structures for X-Ray tube suspensions. The subject device comes in 2 hardware configurations; a Radiographic Stand configuration for a wired detector and a Radiographic Stand for removable detectors. The main components of the subject device are the same as the predicate. Components of the x-ray source are the tube assembly, motorized x-ray collimator, HV cable assembly and high frequency x-ray generator. A touch screen LCD based x-ray control console provides a user interface and technique selection. The automatic collimator supports high accuracy for selected x-ray field size over SID. Selection of an anatomical study on the imaging software automatically sets up the x-ray generator's pre-programmed exposure technique setting, motorized radiographic stand positioning, x-ray collimation and post image processing for selected study. Also, removable high-resolution grids which have 100 and 180cm (40 and 72 inch) focal distance. The integrated touch screen console located on the tube side, operator can easily control the radiographic techniques and stand positioning. Furthermore, the operator can verify the digital x-ray image on this screen. The GUI, automatically rotates corresponds to rotation angle of U-arm.

The provided text is a 510(k) summary for the DRGEM Corporation's DIAMOND-5A/6A/8A stationary digital diagnostic x-ray system. This summary focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study of the device's diagnostic performance for measuring accuracy against a ground truth.

Therefore, much of the requested information (e.g., acceptance criteria for diagnostic capability, sample sizes for test/training sets, expert qualifications, MRMC studies, standalone performance, and ground truth types for diagnostic accuracy) is not available in this document. The document primarily addresses the safety and performance of the hardware components and software in comparison to a previously cleared device.

Here's the information that can be extracted from the provided text:

Acceptance Criteria and Reported Device Performance (as pertains to safety and technical function):

Detailed Study Information (as requested, with notes on unavailability):

1. Sample size used for the test set and the data provenance: Not applicable/available. The document describes non-clinical testing for safety and functionality, not a clinical study on diagnostic accuracy.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable/available. No clinical test set requiring expert ground truth for diagnostic accuracy is described.

3. Adjudication method for the test set: Not applicable/available.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not applicable/available. This device is a digital X-ray system, not an AI-powered diagnostic aide for human readers.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable/available. This refers to the performance of the X-ray system itself. The document states "The complete system has been assessed and tested at the factory and by Standards testing facilities. DIAMOND-5A/6A/8A, has passed all predetermined testing criteria." This indicates standalone testing for the system's technical function and safety.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable/available for diagnostic accuracy. For safety and performance testing, the "ground truth" would be adherence to the cited international standards and predetermined testing criteria.

7. The sample size for the training set: Not applicable/available. The device is not an AI algorithm that requires a training set in the conventional sense for diagnostic tasks. Its software (RADMAX) is for image management and system control.

8. How the ground truth for the training set was established: Not applicable/available.

Summary of the Study (as described in the document):

The "study" described in the 510(k) summary is a non-clinical performance and safety assessment comparing the DIAMOND-5A/6A/8A system to its predicate device (also DIAMOND-5A/6A/8A, K192453). The primary purpose was to demonstrate that adding new digital flat panel detectors (Fujifilm, Varex, i-Ray models) and an updated version of the RADMAX image management software (version 1.01) did not negatively impact safety or efficacy and did not raise new safety risks.

The testing involved assessing the complete system's adherence to various international standards for medical electrical equipment, radiation protection, usability, software lifecycle processes, and risk management. The conclusion was that the device met all predetermined testing criteria and demonstrated a safe and effective profile similar to the predicate device. No clinical (diagnostic accuracy) studies are reported in this summary.

Ask a specific question about this device

The device is designed to perform radiographic x-ray examinations on pediatric and adult patients treatment areas.

The Rover product concept was developed under a contract from the Australian Department of Defense to fulfil a need for a full performance digital medical x-ray imager, light enough to be used in deployed medical facilities. Key Design Features:

• Full trauma imaging capability 40-110kV, 0.2-20mAs;
• Ultra-light weight at 105 kg;
• Ground Clearance allows for 75mm step up;
• Operation on uneven ground;
• Spare battery tray swap out in under a minute;
  The unit uses FDA cleared digital image capture panels and software made by FujiFilm.

The provided document is a 510(k) Premarket Notification for the "Rover" mobile x-ray system. It details the device's technical specifications and compares it to a legally marketed predicate device (DRX-Revolution Nano Mobile X-ray System). The acceptance criteria and testing described are focused on demonstrating substantial equivalence to an existing device, rather than proving performance against specific acceptance criteria for an AI/ML-based device.

Therefore, the document does not contain the information requested regarding acceptance criteria related to AI/ML device performance, ground truth establishment, expert adjudication, MRMC studies, or standalone algorithm performance.

Here's why the document doesn't provide the requested information and what it does provide:

• Device Type: The Rover is a mobile x-ray system, a physical medical device for capturing x-ray images. It uses FDA-cleared digital image capture panels and software (specifically, Fujifilm and Fuji FDX Console Advance DR-ID 300CL Software) which are themselves "previously cleared." This submission is about the system integrating these components, not about a novel AI/ML algorithm for image analysis or diagnosis.
• Basis for Clearance: The basis for clearance is "substantial equivalence" to a predicate device, focusing on functional, technical, and safety equivalence of the hardware and integrated pre-cleared software.
• Testing: The testing detailed is primarily non-clinical bench testing to confirm proper system operation and safety standards compliance (e.g., IEC standards, radiation performance, cybersecurity, wireless technology).
• Clinical Testing: The document explicitly states: "Clinical testing was not required to establish substantial equivalence because all digital x-ray receptor panels have had previous FDA clearance." This means no new clinical data (and thus no associated ground truth, expert reads, or AI performance metrics) was generated for this specific 510(k) submission.

Summary of what is present in the document that somewhat relates to the request, but not in the context of AI/ML acceptance criteria:

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

   • Acceptance Criteria (Implicit): Substantial equivalence to the predicate device in terms of indications for use, configuration, generator specifications, panel interfaces, and meeting US performance standards (21 CFR 1020.30 and 21 CFR 1020.31). Also, compliance with various IEC standards (60601-1, 60601-1-2, 60601-1-3, 60601-1-6, 60601-2-28, 60601-2-54).
   • Reported Device Performance: The "Substantial Equivalence Chart" (page 5) compares the Rover to the predicate, showing "SAME" or "Equivalent" for most characteristics. "Bench testing indicate that the new devices are as safe and effective as the predicate devices. Proper system operation is fully verified upon installation. We verified that the modified combination of components worked properly and produced diagnostic quality images as good as our predicate generator/panel combination." (page 6)

2. Sample sized used for the test set and the data provenance: Not applicable in the context of AI/ML performance testing. Testing was system-level functional and safety verification.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for image interpretation was not established as part of this submission. The software components were previously cleared.

4. Adjudication method for the test set: Not applicable.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done: No, an MRMC study was not done.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: No, as this is a mobile x-ray system, not a standalone AI algorithm. The imaging software used is a pre-cleared component.

7. The type of ground truth used: Not applicable for AI/ML performance. The "ground truth" for the device's acceptable performance was its compliance with safety standards and its ability to produce diagnostic quality images comparable to the predicate, as verified through bench testing.

8. The sample size for the training set: Not applicable. This device is not an AI/ML algorithm that requires a training set.

9. How the ground truth for the training set was established: Not applicable.

In conclusion, the document describes the clearance of a medical device (a mobile X-ray system) based on substantial equivalence to a predicate, not the performance claims of a novel AI/ML-based diagnostic or analytical tool. Therefore, it does not provide the specific information requested about acceptance criteria and studies for AI/ML device performance.

Ask a specific question about this device

The Wireless/Wired FDR D-EVO III flat panel detector system is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications including pediatric and neonatal exams wherever conventional film/screen or CR systems may be used. The FDR D-EVO III is not intended for mammography, fluoroscopy, tomography, and angiography applications.

The subject device FDR D-EVO III Flat Panel Detector System (DR-ID1800) is a portable digital detector system that interfaces with, and acquires and digitizes x-ray exposures from, standard radiographic systems. DR-ID1800 is designed to be used in any environment that would typically use a radiographic cassette for examinations of adults, pediatrics and neonates. The detector models support both wireless and wired/tethered data communication between the detector and the system. Detectors can be placed in a wall bucky for upright exams, a table bucky for recumbent exams, or removed from the bucky for non-grid or free cassette exams. The software that supports the functions of the FDR D-EVO III Flat Panel Detector System is unchanged from the predicate device, cleared under K142003.

This document describes the FDR D-EVO III Flat Panel Detector System (DR-ID1800) and its substantial equivalence to the predicate device, FDR D-EVO II Flat Panel Detector System (DR-ID1200). The information provided heavily relies on a comparison between the two devices and non-clinical testing.

Here's a breakdown of the requested information based on the provided text:

1. Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" in a quantitative, pass/fail manner for each performance metric. Instead, it relies on demonstrating that the subject device's performance is substantially equivalent to or slightly improved over the predicate device, particularly in areas like DQE. The primary "acceptance criterion" appears to be equivalence through non-clinical testing.

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

• Sample Size for Test Set: The document explicitly states "No clinical study has been performed." Therefore, there is no clinical test set for performance evaluation. Non-clinical studies were performed, but details about sample sizes for those specific tests (e.g., number of detectors tested for DQE) are not provided.
• Data Provenance: The studies are described as "Non-clinical Performance Data." There is no mention of country of origin for any data or whether it was retrospective or prospective, as no human subject data was involved in the substantial equivalence claim.

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

As "No clinical study has been performed" and no human-reviewed test set is mentioned, this information is not applicable (N/A).

4. Adjudication Method for the Test Set

As "No clinical study has been performed" and no human-reviewed test set is mentioned, this information is not applicable (N/A).

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done

No. The document explicitly states: "No clinical study has been performed."

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

Yes, in essence. The evaluation focused on the device's technical specifications and imaging capabilities (e.g., DQE, MTF) without human interpretation as the primary endpoint for regulatory submission. The comparison is between the subject device and the predicate device's measured physical characteristics and image quality (as defined by objective metrics). The statement "the image quality evaluation confirmed that the image quality of the FDR D-EVO III Flat Panel Detector System (DR-ID1800) is substantially equivalent to that of the predicate device" refers to objective measurements, not human reader performance.

7. The Type of Ground Truth Used

The "ground truth" for the non-clinical studies was established by objective technical measurements and conformity to voluntary standards. This includes:

• Physical measurements of detector characteristics (dimensions, pixel size, weight).
• Quantifiable image quality metrics (DQE, MTF) measured using standardized phantom/test conditions (e.g., RQA5).
• Compliance with various international standards (AAMI/ANSI ES60601-1, IEC 60601-1-2, IEC 62304, IEC 62366-1, IEC 62494-1, DICOM).
• Following FDA guidance documents for solid-state X-ray imaging devices and wireless technology.

8. The Sample Size for the Training Set

Not applicable. This device is a hardware component (flat panel detector system), not an AI algorithm. Therefore, there is no training set in the context of machine learning. The "training" for such a device would refer to its design and engineering iterations, not a data-driven training process.

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

Not applicable. As explained above, this is a hardware device, not an AI algorithm requiring a training set.

Ask a specific question about this device

The FDR AQRO (DR-XD 1000) is a digital mobile X-ray system intended for use in general purpose radiography for generating radiographic images of human anatomy, including adult, pediatric, and neonatal exams. The FDR AORO is not intended for mammography.

FUJIFILM's FDR AQRO (DR-XD1000) is a compact, economical, lightweight, nonmotorized, low power (2.5 kW), mobile X-ray system designed to work with FUJIFILM's GOS and Csl scintillator FDR D-EVO2 (DR-ID 12XXSE) family of digital X-ray detectors coupled. The D-EVO2 detectors received clearance on 7/23/2014 via 510(k) K142003. The FDR AQRO includes a built-in operation console. The AQRO's console uses Version 10.0 of Fujifilm's FDX Console Software. This software received 510(k) clearance via K170451 on 3/16/2017. The console software includes Virtual Grid 2 (VG2) Image Processing functionality. The VG2 function allows using the mobile X-ray system without a physical grid, resulting in a dose reduction of up to 50% (when compared to using a physical grid). The Virtual Grid 2 Image Processing software received clearance on 4/8/2016 via K153464. The reduction in the external dimensions of FDR AQRO enables smooth movement in the hospital and at the bedside because of an integrated X-ray tube and high-voltage generator (mono-block) that eliminates the need for High Voltage cables and utilizes less space. A high performance Li-ion battery provides up to twelve (12) hours of continuous use (at ~20 exposures/hour) with a quick full charge in four hours. A quick charge of 15 minutes provides one hour of usage. Exposure may also be made when the AC power cord is plugged in.

This document describes the 510(k) premarket notification for the Fujifilm FDR AQRO (DR-XD1000) Mobile X-ray System. As such, it primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed clinical study with specific acceptance criteria, comprehensive performance metrics, and a full statistical plan often found in PMA applications or de novo submissions for novel AI/ML devices.

Therefore, many of the typical elements requested in your prompt regarding acceptance criteria and performance studies (e.g., number of experts for ground truth, adjudication methods, MRMC studies, effect sizes, training set details) are not explicitly provided or applicable in this 510(k) summary for a mobile X-ray system. The performance is assessed primarily through non-clinical (phantom images, compliance with standards) and limited clinical data (sample clinical images) to demonstrate that the device is as safe and effective as the predicate.

However, I can extract the information that is present and explain why certain details are missing based on the nature of this submission.

Here's the breakdown based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document does not present "acceptance criteria" in the sense of specific quantitative thresholds for clinical performance (e.g., sensitivity, specificity, AUC) that a novel diagnostic AI algorithm would typically undergo. Instead, the "performance" is demonstrated through:

• Compliance with recognized standards: This serves as a primary form of "acceptance criteria" for safety and basic performance of X-ray systems.
• Comparison to a predicate device: The core argument is substantial equivalence, meaning the new device performs "as safe and effective as" the legally marketed predicate.
• Image Quality: Assessed via sample phantom and clinical images, which are qualitatively evaluated rather than against quantitative metrics in this summary.
• Technical Specifications: Comparison of technical specs to the predicate.

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

• Test Set Sample Size: The document does not specify a quantitative "test set" sample size in terms of number of cases for a clinical performance study. The evaluation appears to involve "sample phantom images" and "sample clinical images" for qualitative assessment. This is typical for a 510(k) for an X-ray system, which focuses on device safety and basic image generation capabilities, rather than a diagnostic algorithm that analyzes images for specific findings.
• Data Provenance: Not specified within this summary. It's likely general radiography data, but no country of origin or whether it's retrospective/prospective is mentioned.

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

• Not Applicable/Not Specified: For a 510(k) submission of an X-ray system, the "ground truth" is typically the physical output and image quality of the device (compared to a predicate and standards), not a diagnostic finding that requires expert interpretation to establish a gold standard. Without a diagnostic study quantifying performance against a true disease state, there's no mention of experts establishing ground truth for a test set.

4. Adjudication Method for the Test Set

• Not Applicable/Not Specified: As there isn't a stated clinical study with a test set requiring interpretation for specific findings, there is no adjudication method described.

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

• No: The document does not mention an MRMC study comparing human readers with and without AI assistance. This device is an X-ray system, not an AI software for diagnosis. While it includes "Virtual Grid 2" software, its clearance (K153464) and functionality relate to image processing affecting dose and image appearance, not to diagnostic AI assistance for readers that would warrant an MRMC study.

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

• No: This is a physical X-ray system. While it contains software components (FDX Console Software and Virtual Grid 2), the "standalone performance" refers to the system as a whole in generating images, not an AI algorithm analyzing images independently. The performance data is primarily demonstrated through technical specifications, compliance with standards, and visual assessment of sample images.

7. The Type of Ground Truth Used

• Technical Specifications & Compliance Standards/Predicate Comparison: The "ground truth" used for this device is effectively its ability to generate radiographic images safely and effectively, achieving comparable technical performance metrics (e.g., DQE, MTF, tube characteristics, radiation control) to a legally marketed predicate device, and compliance with relevant industry and medical device standards. Qualitative visual assessment of sample phantom and clinical images also contributes.

8. The Sample Size for the Training Set

• Not Applicable/Not Specified: This is not an AI/ML device that learns from a "training set" of images in the conventional sense. It's an X-ray system. The software components like FDX Console and Virtual Grid 2 would have been developed and tested through software validation processes (IEC 62304 compliance is noted), but this does not involve a "training set" of patient images in the way an AI diagnostic algorithm would.

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

• Not Applicable/Not Specified: Since there is no "training set" for an AI/ML model described, there is no ground truth established in this context. Device performance is evaluated against engineering specifications, safety standards, and equivalence to a predicate.

Ask a specific question about this device