Search Results

The DIGITAL RADIOGRAPHY CXDI-Pro / D1 provides digital image capture for conventional film/screen radiographic examinations. This device is intended to capture, for display, radiographic images of human anatomy, and to replace radiographic film/screen systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.

The DIGITAL RADIOGRAPHY CXDI-Pro, also called the DIGITAL RADIOGRAPHY D1, (hereinafter referred to as CXDI-Pro) is a solid-state x-ray imager. The CXDI-Pro is a series of detectors, and in the predicate submission (K221876) consists of the CXDI-703C Wireless and CXDI-403C Wireless detectors, also called the AR-D3543W and AR-D4343W detectors respectively. The detectors intercept x-ray photons, and the scintillator emits visible spectrum photons that illuminate an array of photodetectors that create electrical signals. After the electrical signals are generated, the signals are converted to digital values. The digital values are sent to the PC via a wired or wireless connection, converted to images with the CXDI Control Software, and then displayed on the PC/monitors. The PC/monitors used with the CXDI-Pro are not a part of this submission. The proposed changes to the predicate device, CXDI-Pro, includes the addition of the new detector, CXDI-803C Wireless (also called the AR-D2735W) to the CXDI-Pro series; a firmware update from 01.01.03.00 to 01.02.00.01; and a CXDI Control Software version update from 3.10.2.2 to 3.10.2.6. The new detector, CXDI-803C Wireless, which differs in pixel count, imaging area, external dimensions, and weight, has the same image performance as the predicate detectors. None of the CXDI-Pro detectors have any dynamic functions (such as fluoroscopy).

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical "acceptance criteria" in the format of a table with thresholds and corresponding performance values. Instead, it focuses on demonstrating substantial equivalence to a predicate device by comparing technological characteristics and ensuring continued conformance with safety and performance standards.

The closest to "reported device performance" are the shared technical specifications and the statement that the new detector has the "same image performance as the predicate detectors."

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

The document states: "Adequate detector bench testing should be sufficient to demonstrate that the subject detector. CXDI-Pro, works as intended."
It also mentions "verification/validation activities" which included "detector bench testing."

• Sample Size for Test Set: Not explicitly stated in terms of number of images or cases. The testing appears to be primarily at the component level (detector, firmware, software) through bench testing and conformance to standards, rather than a clinical study with a specific number of patient cases.
• Data Provenance: Not specified, but given the nature of "bench testing" and "conformance with U.S. Performance Standard," it would likely involve laboratory test data and manufactured test images, rather than patient data from specific countries. This is a "Special 510(k) Submission" for modifications, so extensive new clinical data is often not required if substantial equivalence can be demonstrated through non-clinical means.

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

Not applicable. This was a non-clinical submission focused on technical equivalency, safety, and performance standards. There was no clinical ground truth established by experts.

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

Not applicable. This was a non-clinical submission; no adjudication method for a clinical test set was required or mentioned.

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. The device described is a digital radiography detector system, not an AI-powered diagnostic tool. Therefore, an MRMC comparative effectiveness study regarding human reader improvement with AI assistance is not relevant or reported.

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

Not applicable. The device is a hardware component (detector) and associated software/firmware for image acquisition and display, not an algorithm providing a standalone diagnostic output.

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

Not applicable. For this specific submission, the "ground truth" was established against technical specifications, engineering performance metrics (e.g., MTF, DQE), and conformance to internationally recognized safety and performance standards (e.g., IEC 60601 series). There was no clinical ground truth (expert consensus, pathology, outcomes data) as this was a non-clinical submission for device modifications.

8. The sample size for the training set

Not applicable. This device is a diagnostic imaging system component, not a machine learning algorithm that requires a "training set."

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

Not applicable. There was no training set for a machine learning algorithm.

Ask a specific question about this device

The AS-10 is indicated for use in generating fluoroscopic and radiographic images of human anatomy for angiography, diagnostic, and interventional procedures. The device is intended to replace spot-film devices. The device is also intended to replace fluoroscopic images obtained through image intensifier technology. Not intended for mammography applications.

The AS-10 is a solid state x-ray imager. It intercepts x-ray photons and the scintillator of the AS-10 emits visible spectrum photons that illuminate an array of photo-detectors that create electrical signals. After the electrical signals are generated, it is converted to digital value.

The subject of this Special 510(k) submission is a change to the AS-10 to make the PowerBox (PB-09), Power Supply Cable, and Optical Cable optional components. This change will allow for the use of any power source and non-Canon cables, given they meet the provided specifications. In addition, changes have been made to the firmware in the AS-10 detector unit and PowerBox to implement bug fixes and functional improvements. Together, these changes make up the AS-10.

The provided document describes a Special 510(k) submission for the Canon AS-10 device, detailing changes made to its optional components and firmware. The focus of this submission is to demonstrate substantial equivalence to its predicate device (Canon AS-10 / CXDI-401RF, K171194), rather than a de novo performance study. Therefore, the document does not contain specific acceptance criteria, reported device performance metrics against those criteria, or a study design involving expert readers, ground truth establishment, or multi-reader multi-case (MRMC) comparative effectiveness.

Instead, the submission focuses on affirming that the modifications did not negatively impact the device's conformance with existing performance and safety standards.

Here's a breakdown of the information that is and is not available based on your request:

1. Table of acceptance criteria and the reported device performance

The document does not provide a table of acceptance criteria for diagnostic performance (e.g., sensitivity, specificity, accuracy) or reported performance metrics against such criteria. The "Performance" section focuses on demonstrating continued conformance with regulatory standards after modifications.

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

Not applicable. This is a Special 510(k) submission for modifications, not a new device requiring a clinical performance study with a test set. The changes involved making PowerBox, Power Supply Cable, and Optical Cable optional components, and updating firmware for bug fixes and functional improvements.

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

Not applicable, as no clinical test set requiring ground truth establishment is described.

4. Adjudication method for the test set

Not applicable, as no clinical test set requiring adjudication is 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 study is mentioned. The AS-10 is an imaging device (Solid State X-Ray Imager), not an AI-driven interpretive tool for physicians.

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

Not applicable. The AS-10 is the imaging hardware itself, not an algorithm.

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

Not applicable, as no clinical performance study requiring ground truth is described.

8. The sample size for the training set

Not applicable. This document describes a hardware and firmware modification, not a machine learning model that would require a training set.

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

Not applicable, as no training set for a machine learning model is described.

Summary of Device Modifications and Performance Activities (as per document):

The submission for the Canon AS-10 is a Special 510(k), indicating minor modifications to an already cleared device (predicate K171194).

The modifications are:

• Making the PowerBox (PB-09), Power Supply Cable, and Optical Cable optional components. This allows for the use of any power source and non-Canon cables that meet provided specifications.
• Updating firmware in the AS-10 detector unit and PowerBox to implement bug fixes and functional improvements.

How Performance was Addressed in this Submission:

The document states:

• "The fundamental scientific technology of the AS-10 has not been modified."
• "The detector unit of the AS-10 has not been modified..."
• "Evaluation of the changes to the AS-10 confirmed that the changes did not impact AS-10 conformance with the U.S. Performance Standard for radiographic equipment and with relevant voluntary safety standards for Electrical safety and Electromagnetic Compatibility testing, specifically IEC standards 60601-1, 60601-1-2, 60601-1-3, 60601-1-6, 62366, 60601-2-54, 60825-1, and 62304." (Note: IEC 62220-1 is also listed elsewhere but not explicitly linked to the conformance statement here).
• "These verification/validation activities successfully demonstrated that the device continues to meet the standards for the areas impacted by the device modifications to the predicate device and raises no new questions regarding either safety or effectiveness when compared to the predicate device."

Therefore, the "acceptance criteria" in this context are adherence to established international and U.S. performance/safety standards for medical electrical equipment and X-ray systems, and the "study" involves verification and validation (V&V) activities to confirm that the modifications did not degrade this conformance. This is a common approach for Special 510(k) submissions where the changes are limited and do not introduce new risks or alter the fundamental operating principles of the device.

Ask a specific question about this device

The DIGITAL RADIOGRAPHY CXDI-702C Wireless and CXDI-402C Wireless provides digital image capture for conventional film/screen radiographic examinations. This device is intended to capture, for display, radiographic images of human anatomy, and to replace radiographic film/screen systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.

The CXDI-702C Wireless and CXDI-402C Wireless are solid-state x-ray imagers with approximate imaging areas of 350 x 426 mm and 415 x 426 mm, respectively. The detector intercepts x-ray photons, and the scintillator emits visible spectrum photons that illuminate an array of photodetectors that create electrical signals. After the electrical signals are generated, the signals are converted to digital values and the images will be displayed on monitors. The digital value can be communicated to the operator console via wired or wireless connection.
The subject of this Special 510(k) submission is a change to the Digital Radiography CXDI-710C Wireless and CXDI-410C Wireless to add the X-ray I/F unit option, update to the CXDI control software, change the IP Level, make changes to the case, and remove Standalone mode. The X-Ray I/F unit synchronizes the timing of the X-ray irradiation with the detector's capture and has been included in other Canon devices (CXDI-701C Wireless (K131106)). The X-Ray I/F Unit is an optional unit that allows the proposed device work together with several older units that use the X-ray I/F Unit instead of the multibox. The IP Level was changed from IPX7 to IP54. The Standalone mode was removed from the proposed devices. The imaging process to sharpen images, Edge Enhancement, was included in the Digital Radiography CXDI-710C Wireless and CXDI-410C Wireless, but adjustments of multiple imaging parameters were required to enhance structured edges. The optional feature, Advanced Edge Enhancement, for CXDI-702C Wireless and CXDI-402C Wireless automatically adjusts the six image processing parameters (Enhancement - Edge Enhancement, Enhancement - Edge Frequency, Enhancement - Contrast Boost, Dynamic Range Adjustment - Dark Region, Dynamic Range Enhancement - Bright Region, and Noise Reduction - Effect) by one button to enhance structures. The CXDI control software has been updated to a new version for functional improvements. The material of the casing of the detector has changed from fiberglass to magnesium alloy. Together, these changes to the Digital Radiography CXDI-710C Wireless and CXDI 410C Wireless make up the Digital Radiography CXDI-702C Wireless and CXDI-402C Wireless.

The provided text describes a 510(k) premarket notification for two digital radiography devices, the CXDI-702C Wireless and CXDI-402C Wireless. This submission is a "Special 510(k)," indicating that the changes made to the devices are minor and fall within established performance specifications, meaning a direct comparative effectiveness study with human readers (MRMC) might not have been the primary focus of the submission for overall device clearance, but rather a demonstration of continued equivalence through specific performance tests and comparative data with predicate devices.

The acceptance criteria and study proving the device meets these criteria can be inferred from the "Summary of Non-Clinical / Test Data" section and the "Comparisons with the predicate devices" table.

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

1. Table of Acceptance Criteria and Reported Device Performance

The submission focuses on demonstrating substantial equivalence to predicate devices (CXDI-710C Wireless and CXDI-410C Wireless) after specific modifications. Therefore, the "acceptance criteria" are primarily that the modified devices maintain performance comparable to the predicate devices and meet relevant safety and performance standards. The "reported device performance" is largely framed as successful verification and validation tests and comparability data.

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

• Sample Size: The document does not explicitly state a numerical sample size for the "non-clinical image comparisons" or "interviews with experienced clinicians." It refers to "tests performed on the models" and "non-clinical image comparisons." For a 510(k) Special submission, the focus is often on demonstrating that the modifications do not adversely affect performance, rather than a large-scale clinical trial.
• Data Provenance: Not explicitly stated. Given that it's a submission for products by Canon, Inc. (Japan), the non-clinical tests would typically be performed internally or by contracted labs. The "interviews with experienced clinicians" likely involved healthcare professionals in a relevant market, but the specific country is not detailed. The data is retrospective in the sense that it evaluates the modified device against known performance of the predicate device.

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

• Number of Experts: Not explicitly stated for image evaluation.
• Qualifications of Experts: The document mentions "experienced clinicians" for interviews regarding the usability of the Advanced Edge Enhancement feature. Their specific qualifications (e.g., "radiologist with 10 years of experience") are not detailed. For the image comparisons, it implies internal testing and comparison to established predicate performance rather than requiring independent expert reads to establish ground truth in the same way a diagnostic AI would.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified. For non-clinical image comparisons demonstrating comparability, a formal adjudication process like 2+1 or 3+1 by multiple readers is not typically detailed in this type of 510(k) submission. It's more about objective image quality metrics and visual comparison against predicate performance.

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

• MRMC Study: No, the document does not indicate that a formal MRMC comparative effectiveness study was conducted. This type of study is more common for novel diagnostic AI devices where the primary claim is an improvement in human reader performance with AI assistance. For a Special 510(k) of a digital X-ray detector with minor modifications, the focus is on maintaining equivalence rather than demonstrating improvement over human readers.
• Effect Size: Not applicable, as an MRMC study was not described.

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

• Standalone Performance: Not applicable in the context of a digital X-ray detector. The device itself (the detector) processes images and provides them for display, but it doesn't have a diagnostic "algorithm" that operates independently to provide outputs like disease detection that would require a standalone performance evaluation in the same way a diagnostic AI software would. The "Advanced Edge Enhancement" is an image processing feature, not a diagnostic algorithm. The document explicitly states the "Standalone mode was removed from the proposed devices" for how the detector operates, meaning it always communicates with an operator console (human-in-the-loop for image review).

7. The Type of Ground Truth Used

• Ground Truth: For the non-clinical image comparisons, the "ground truth" would be established by comparing the images from the modified device against the known and accepted image quality and characteristics of the legally marketed predicate devices. This isn't "expert consensus" or "pathology" in the diagnostic sense, but rather a technical comparison of image properties (e.g., resolution, contrast, noise, and the visual appearance of anatomical structures) to ensure the modifications did not degrade quality. The "usability" of the Advanced Edge Enhancement was evaluated through clinician interviews, where their feedback implicitly serves as a form of ground truth for user experience.

8. The Sample Size for the Training Set

• Training Set Sample Size: The document does not describe a "training set" because the device is a digital X-ray detector, not an AI algorithm that learns from data. The "Advanced Edge Enhancement" is likely a rule-based or engineered image processing algorithm, not a machine learning model that requires a training set.

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

• Ground Truth for Training Set: Not applicable, as there is no mention of a training set for an AI algorithm.

Ask a specific question about this device

As a part of the CXDI series radiography system, the CXDI Control Software when used with a compatible CXDI detector is intended to provide digital image capture, and display for conventional film/screen radiographic examinations. This device is intended to replace radiographic film/screen systems in all general purpose diagnostic procedures including specialist areas like intensive care, trauma, and pediatric work. This device is not intended for fluoroscopic, angiographic, or mammography applications.

The subject of this Special 510(k) submission is a change to the CXDI Control Software to incorporate the ability to capture an automatically stitched long length image in a single exposure. The addition of the One Shot Long Length to the cleared Scatter Correction of CXDI Series is the subject of this Special 510(k) Submission. The One Shot Long Length stitches long length images into a single image which is accomplished by using multiple detectors, a single exposure, and the automatic stitching software. The One Shot Long Length software feature along with the Scatter Correction cleared under K153312 make up the Enhanced Feature Software Pack for CXDI Series. The Scatter Correction clearance and compatible detectors are not impacted by this submission. This submission adds the One Shot Long Length feature to limited compatible FPDs. The One Shot Long Length feature included in the Enhanced Feature Software Pack for CXDI Series also includes features for manual stitching to allow for users to manually adjust and fine-tune the stitch positions after the automatic stitch operation. By incorporating the One Shot Long Length imaging into the CXDI Control Software, images up to 120cm in length can be acquired in one exposure. The firmware within the flat panel detectors did not require updating. The flat panel detectors that have been previously cleared by FDA and are compatible with the Enhanced Feature Software Pack for CXDI Series have not been physically modified and performance have not changed.

Here's a summary of the acceptance criteria and study information for the Enhanced Feature Software Pack for CXDI Series, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text focuses on demonstrating substantial equivalence to a predicate device, rather than explicit acceptance criteria and device performance metrics. However, the core change in the proposed device is the "One Shot Long Length Imaging" feature, which involves automatic stitching of images from multiple detectors with manual adjustment capabilities. The performance is largely implied by the claim of substantial equivalence and successful mitigation of risks.

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

The provided document does not specify the sample size used for any test set or the data provenance (e.g., country of origin, retrospective/prospective). The submission refers to a "Special 510(k) Submission" for a software change, and typically such submissions might rely on internal validation and verification testing demonstrating that the new feature does not adversely affect the already cleared device's performance.

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

This information is not provided in the document. The submission focuses on the technical aspects of the software modification and its substantial equivalence. Clinical studies with expert-adjudicated ground truth are not explicitly mentioned in this summary.

4. Adjudication Method for the Test Set

This information is not provided in the document.

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

There is no mention of an MRMC comparative effectiveness study or any assessment of human reader improvement with or without AI assistance. The "Enhanced Feature Software Pack" introduces an "One Shot Long Length Imaging" feature that automatically stitches images, but it's not described as an AI-driven diagnostic aid that would typically involve an MRMC study for assessing reader performance. It's more of an image acquisition and processing enhancement.

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

The document does not explicitly state that a standalone performance study was done for the "One Shot Long Length Imaging" algorithm. However, given that it's an automated stitching process, internal verification and validation testing would have been conducted to ensure the accuracy and quality of the stitched images generated by the algorithm. This would be a form of standalone testing, but specific metrics and methodology are not detailed here.

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

The document does not specify the type of ground truth used for any testing. For an image stitching feature, ground truth would likely involve measurements of anatomical alignment and continuity as determined by expert review or comparison to reference images, but this is not explicitly stated.

8. The Sample Size for the Training Set

This information is not provided in the document. The device primarily involves an automated image stitching algorithm, rather than a machine learning model that typically requires a large training set in the conventional sense.

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

This information is not provided in the document. As mentioned above, it's unclear if a traditional "training set" with ground truth, as used for machine learning, was employed in the development of this image stitching feature.

Ask a specific question about this device

The AS-10 / CXDI-401RF is indicated for use in generating fluoroscopic and radiographic images of human anatomy for angiography, diagnostic, and interventional procedures. The device is intended to replace spot-film devices is also intended to replace fluoroscopic images obtained through image intensifier technology. Not intended for mammography applications.

The AS-10 / CXDI-401RF is a solid state x-ray imager. It intercepts x-ray photons and the scintillator of the AS-10 / CXDI-401RF emits visible spectrum photons that illuminate an array of photo-detectors that create electrical signals. After the electrical signals are generated, it is converted to digital value.

The provided text describes a 510(k) premarket notification for a medical device, the AS-10 / CXDI-401RF, an x-ray imager. The submission focuses on demonstrating substantial equivalence to predicate devices rather than proving specific performance criteria through a detailed clinical study with acceptance metrics for a diagnostic device.

Therefore, the requested information cannot be fully extracted as it pertains to a diagnostic AI/CADe device, which this submission does not explicitly detail. This submission focuses on the safety and effectiveness of new imaging hardware (a flat panel detector) and its comparability to existing technology.

However, I can extract information related to the device's technical specifications and the non-clinical tests performed to demonstrate its equivalence.

Here's an attempt to answer based on the provided text, recognizing the limitations of the document's content for your specific questions:

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

The document does not explicitly state "acceptance criteria" in the context of a diagnostic performance study with specific metrics (like sensitivity, specificity, or AUC) as one might find for an AI/CADe device. Instead, it compares the technical specifications and non-clinical performance of the AS-10 / CXDI-401RF to its predicate devices. The "performance" is implicitly demonstrated by showing that the new device's technical parameters are comparable to or improved upon the predicates and that it is safe and effective.

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

The document mentions "non-clinical image comparisons involving flat panel display static and dynamic images taken with the new device and the predicate device CXDI-50RF." However, it does not specify a "sample size" in terms of number of patients or specific images, nor does it provide details on data provenance (country, retrospective/prospective). The testing focused on technical performance rather than clinical data sets.

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)

This information is not provided. The non-clinical tests described focus on technical image quality and system performance rather than a diagnostic evaluation requiring expert readers to establish ground truth.

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

Not applicable, as no expert human readers or adjudication process for diagnostic interpretations are 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

Not applicable. This submission is for new imaging hardware, not an AI/CADe device designed to assist human readers.

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

Not applicable. This is not an algorithm.

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

For the "non-clinical image comparisons," the "ground truth" would likely be objective measurements of image quality (e.g., DQE, MTF, noise characteristics) comparing the new device's output to the predicate device's output, rather than a clinical ground truth established by medical experts or pathology.

8. The sample size for the training set

Not applicable. This is not a machine learning or AI device that requires a training set.

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

Not applicable.

Ask a specific question about this device

The DIGITAL RADIOGRAPHY CXDI-710C Wireless and CXDI-810C Wireless provides digital image capture for conventional film/screen radiographic examinations. This device is intended to capture, for display, radiographic images of human anatomy, and to replace radiographic film/screen systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.

The two models of detectors included in this submission are solid state x-ray imagers. Model CXDI-710C Wireless has an approximate imaging area of 35.0 x 42.6 cm, while model CXDI-810C Wireless has an approximate imaging area of 35.0 x 27.4 cm. For both models, the detector intercepts x-ray photons and the scintillator emits visible spectrum photons that illuminate an array of photo-detectors that create electrical signals. After the electrical signals are generated, the signals are converted to digital values and the images will be displayed on monitors. The digital value can be communicated to the operator console via wiring connection or wireless. For the proposed models, temporary image storage is now possible and the detector weight has been reduced from that of the predicates. The proposed models have increased protection against ingress, continue to include the Non-Generator Connection Mode (detection of x-ray irradiation without direct electrical connection to the x-ray generator) and are compatible with the Scatter Correction feature.

This document is a 510(k) summary for the Canon Digital Radiography CXDI-710C Wireless and CXDI-810C Wireless devices. It describes their equivalence to predicate devices rather than proving a new or unique performance based on specific clinical acceptance criteria in the way a novel AI algorithm might. Therefore, the information typically found for AI/ML device approval concerning acceptance criteria, ground truth establishment, and clinical study details (like MRMC studies) is not present.

However, based on the provided text, we can infer some aspects and extract relevant information about the non-clinical testing performed to demonstrate substantial equivalence.

Here's an analysis based on the provided document:

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

Since this is a 510(k) for a digital radiography detector aiming for substantial equivalence to a predicate device, the "acceptance criteria" are primarily related to meeting performance specifications comparable to the predicate and complying with relevant standards, rather than clinical efficacy metrics for a new diagnostic claim.

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

• Sample Size for Test Set: The document does not specify a "test set" in terms of patient images for clinical evaluation in the way an AI algorithm study would. The testing appears to be primarily non-clinical, involving functional specifications, image comparisons (presumably phantom or test patterns given the context of a DR detector), and compliance testing. No specific number of images or cases for clinical validation is mentioned.
• Data Provenance: Not applicable as no specific clinical patient data set or clinical study is described. The tests are non-clinical (e.g., "non-clinical image comparisons," "verification/validation testing to internal functional specifications").

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

• Not applicable. As this is a 510(k) for a digital radiography panel showing substantial equivalence to a predicate, and not a novel diagnostic AI algorithm, there is no mention of human expert readers establishing ground truth on a clinical test set.

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

• Not applicable. No clinical test set with human readers requiring adjudication is 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 study was done. This 510(k) is for a digital X-ray detector, not an AI-assisted diagnostic software.

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

• The device itself is a standalone imaging device (digital radiography detector). Its performance is evaluated intrinsically through physical and image quality metrics and comparison to a predicate, not as an algorithm performing a diagnostic task. The "Standalone function" mentioned under "Control SW" and "Device FW" (Page 4) refers to the detector's ability to save captured images internally without immediate connection to an external device, which is a technical feature, not a diagnostic performance claim.

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

• Not applicable in the context of diagnostic ground truth from patient data. The "ground truth" for this device's evaluation is primarily its adherence to engineering specifications, image quality standards (e.g., MTF), and compliance with regulatory standards, as demonstrated through non-clinical testing. Comparison is made against a predicate device.

8. The sample size for the training set:

• Not applicable. This is not an AI/ML algorithm that requires a training set.

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

• Not applicable. This is not an AI/ML algorithm that requires a training set or ground truth establishment for training.

Ask a specific question about this device

The flat panel detector CSX-30 is designed to provide fluoroscopic and spot radiographic images of human anatomy during diagnostic, surgical and interventional procedures. Examples of clinical application may include angiography, endoscopy, urologic, orthopedic, neurologic, vascular, critical-care and emergency room procedures or other imaging applications at the physician's discretion. The device is intended to replace spot-film device is also intended to replace fluoroscopic images obtained through image intensifier technology. Not intended for mammography applications.

The CSX-30 is a digital radiography flat panel detector that can take fluoroscopic and spot radiographic images of any part of the body. It directly converts the X-ray images captured by the sensor into high-resolution digital images. The instrument is a component of an x-ray system and as such cannot be used outside of such a system. This unit converts the X-rays into digital signals. Not intended for mammography applications.

The provided text describes a 510(k) summary for a flat panel detector (CSX-30), which is a component of an X-ray system. The study described focuses on demonstrating substantial equivalence to a predicate device (CSX-10) rather than proving "device meets acceptance criteria" in the context of clinical performance or diagnostic accuracy of an AI algorithm.

Therefore, many of the requested criteria for AI/diagnostic studies, such as sample size for test sets, number of experts, adjudication methods, MRMC studies, or specific ground truth methodologies for clinical conditions, are not applicable or detailed in this document because the device is a hardware component (a flat panel detector), not an AI-driven diagnostic system.

The "acceptance criteria" here relate to engineering specifications, safety standards, and performance characteristics compared to a predicate device.

However, I can extract the information that is present and note what is not applicable.

Here's the summary based on the provided document:

Acceptance Criteria and Device Performance Study for CSX-30 Flat Panel Detector

The study aimed to demonstrate substantial equivalence of the new device (CSX-30 Flat Panel Detector) to a legally marketed predicate device (CSX-10 Flat Panel Detector). The "acceptance criteria" are implied by the comparison to the predicate device and compliance with relevant standards.

1. Table of Acceptance Criteria (Implied by Comparison) and Reported Device Performance

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

• Sample Size: The document does not specify a distinct "test set" sample size in terms of number of patients or images for clinical performance evaluation, as this is a hardware device submission focusing on engineering and safety. It mentions "non-clinical image comparisons involving flat panel display images." The exact number of images or test runs for these comparisons is not specified.
• Data Provenance: Not explicitly stated regarding country of origin. The study appears to be "non-clinical," focusing on device performance and safety characteristics rather than clinical trial data on specific patient populations. It is retrospective in the sense that a comparison is made to an existing predicate device's characteristics.

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

• Not Applicable/Not Specified: As this is a hardware device submission focused on technical specifications and safety standards, the concept of "ground truth" derived from expert consensus on clinical diagnoses (e.g., by radiologists) is not relevant in the way it would be for an AI diagnostic device. The "truth" is established by direct measurement of device parameters and compliance with engineering standards.

4. Adjudication Method for the Test Set

• Not Applicable: No clinical adjudication process is described as this is not a clinical diagnostic performance study requiring expert consensus on findings.

5. MRMC Comparative Effectiveness Study

• Not Performed/Applicable: An MRMC study is typically for evaluating the impact of an AI system on human reader performance. This study is for a flat panel detector (hardware component), not an AI algorithm.

6. Standalone Performance Study (Algorithm Only)

• Not Applicable: This is not an AI algorithm. The performance of the flat panel detector is assessed through its technical specifications (e.g., pixel count, frame rate, A/D conversion), compliance with safety standards, and non-clinical image quality comparisons with the predicate.

7. Type of Ground Truth Used

• Engineering Specifications and Standard Compliance: The "ground truth" for this device's performance is based on its measured physical and electrical characteristics (e.g., pixel count, dimensions, weight, frame rate, A/D conversion), its ability to meet specified performance parameters (e.g., DOE, dynamic range), and its adherence to established national and international safety and performance standards (e.g., IEC 60601 series, FDA Guidance documents). Comparison of "flat panel display images" implies direct image quality assessment, often against a reference or the predicate.

8. Sample Size for the Training Set

• Not Applicable: This is a hardware device, not an AI model that requires a training set.

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

• Not Applicable: As there is no training set for an AI model, this question is not relevant.

In conclusion, the provided document details a 510(k) submission for a non-AI medical imaging hardware component, focusing on demonstrating substantial equivalence to a predicate device through technical specification comparisons and compliance with relevant safety and performance standards. Many of the questions posed are specifically for AI/software as a medical device (SaMD) clinical performance studies and therefore do not apply to this submission type.

Ask a specific question about this device

The DIGITAL RADIOGRAPHY CXDI-401C Wireless provides digital image capture for conventional film/screen radiographic examinations. This device is intended to replace radiographic film/screen systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.

The model of detector included in this submission is a solid state x-ray imager. Model CXDI-401C Wireless has an approximate imaging area of 41.5 x 42.6 cm. For this model, the detector intercepts x-ray photons and the scintillator emits visible spectrum photons that illuminate an array of photo-detectors that create electrical signals. After the electrical signals are generated, the signals are converted to digital values and the images will be displayed on monitors. The digital value can be communicated to the operator console via wiring connection or wireless. The proposed model includes the Non-Generator Connection Mode, allowing this model to detect x-ray irradiation without direct electrical connection to the x-ray generator.

The Canon DIGITAL RADIOGRAPHY CXDI-401C Wireless device is a flat panel digital imager intended to replace conventional film/screen radiographic systems for general diagnostic procedures, excluding mammography. The provided document details its substantial equivalence to predicate devices, but it does not contain information about acceptance criteria or specific studies proving device performance against such criteria in the way a clinical performance study would.

Instead, the document focuses on demonstrating substantial equivalence to existing FDA-cleared predicate devices (K131106 MQB DIGITAL RADIOGRAPHY CXDI-701C Wireless and K103591 MQB DIGITAL RADIOGRAPHY CXDI-401C COMPACT). The performance claim is that the device is "safe and effective, performs comparably to the predicate device(s), and is substantially equivalent."

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

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly present a table of quantitative acceptance criteria for clinical performance (e.g., sensitivity, specificity, accuracy, or image quality metrics for specific disease detection) or compare the device's performance against such criteria. The "performance" described is largely comparative to predicate devices for technological characteristics and compliance with safety and established standards.

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

The document mentions "non-clinical image comparisons involving flat panel display images taken with the new device and the predicate devices" and "image quality evaluation." However, it does not specify the sample size for any test set (number of images, patients, or types of cases) nor the data provenance (e.g., country of origin, retrospective/prospective). These appear to be internal verification and validation tests rather than a formal clinical trial with a defined test set.

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

The document does not provide information on the number or qualifications of experts used to establish ground truth for any image comparisons or evaluations.

4. Adjudication method for the test set:

The document does not specify any adjudication method for a test set.

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. The device described is a digital radiography system, not an AI-assisted diagnostic tool.

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

The device is a hardware component (flat panel detector) for digital radiography. It is not an algorithm that performs image analysis in a "standalone" fashion as would be discussed for AI. The performance is related to its image capture capabilities, implying a human-in-the-loop for interpretation.

7. The type of ground truth used:

The document implies "image quality evaluation" and "non-clinical image comparisons." The nature of the "ground truth" for these evaluations is not explicitly stated. For "image quality," it could refer to objective metrics, visual assessment against a reference, or comparison to known image characteristics. For "non-clinical image comparisons," it likely refers to direct comparison of images from the new device versus predicate devices. This is not a clinical ground truth derived from pathology or patient outcomes.

8. The sample size for the training set:

The document describes a hardware device. There is no mention of a training set in the context of an algorithm or AI model.

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

As there is no training set mentioned for an algorithm, this information is not applicable.

Ask a specific question about this device

The Digital Retinal Camera CR-2 Plus AF is intended to be used for taking digital images of the retina of the human eye without a mydriatic. The CR-2 Plus AF has the following photography modes: color, red free, cobalt digital and fundus autofluorescence (FAF).

The Digital Retinal Camera CR-2 Plus AF is used for taking digital images of a human retina without a mydriatic. Canon EOS Digital Camera is mounted to the CR-2 Plus AF. Images can be viewed immediately, and procedures of imaging are more efficient with many different applications such as telemedicine and electronic filing. The CR-2 Plus AF is equipped with autofocus/automatic shooting/automatic switching function from anterior segment image to fundus image.

The provided text describes a 510(k) summary for the "Digital Retinal Camera CR-2 Plus AF." This document outlines the device's technical characteristics, its intended use, and a comparison to a predicate device (K111612 Canon Digital Retinal Camera CR-2 Plus). However, it focuses on the device's safety and effectiveness being substantially equivalent to a predicate device rather than presenting a detailed study with specific acceptance criteria and performance metrics for an AI-powered diagnostic device.

The essential information requested in the prompt, such as detailed acceptance criteria, specific performance metrics, sample sizes for test and training sets, expert qualifications, and ground truth establishment, is largely absent from this type of regulatory submission for a non-AI medical imaging device.

Here's an analysis based on the provided text, highlighting what is (and isn't) present:

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

This information is not provided in the document. The document states that "The unit complies with the US Performance Standard for ophthalmic equipment" and "The CR-2 Plus AF met all requirements of the standards," but it does not specify what those standards are or what the acceptance criteria within them entailed. No specific device performance metrics (e.g., sensitivity, specificity, accuracy) are reported for the AF function.

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

This information is not provided. The document mentions "non-clinical tests were performed" to evaluate safety and effectiveness, but it does not specify a test set size or data provenance.

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):

This information is not provided. Since this is an imaging device rather than a diagnostic AI, there is no mention of establishing ground truth by experts in the context of diagnostic performance.

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

This information is not provided.

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 and not mentioned. The device is a digital retinal camera, and the modifications are related to autofocus, automatic shooting, and automatic switching, not AI assistance for human readers in diagnostic interpretation.

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

This is not applicable and not mentioned. The device is an imaging camera, not an AI algorithm. Its automated features (autofocus, auto-shooting) are inherent to its operation, not a separate standalone algorithm performance.

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

This is not applicable and not mentioned in the context of diagnostic interpretation. For the device itself, the "ground truth" for its performance would be its ability to capture clear images according to technical specifications and safety standards, but these details are not elaborated upon.

8. The sample size for the training set:

This information is not provided. As this is not an AI/machine learning device, there wouldn't typically be a "training set" in the common sense.

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

This information is not provided. (Not applicable for this type of device.)

Summary of Device and Performance Information from the Text:

The document describes the Canon Digital Retinal Camera CR-2 Plus AF, an ophthalmic camera used for taking digital images of the human retina without mydriatic.

Acceptance Criteria and Device Performance (as inferred):

Key Takeaways from the document:

• This is a 510(k) premarket notification for a medical imaging device (digital retinal camera), not an AI diagnostic tool.
• The focus of the submission is to demonstrate substantial equivalence to an existing predicate device (K111612 Canon Digital Retinal Camera CR-2 Plus).
• The "study" referenced involves non-clinical tests (performance, software validation, electrical safety, electromagnetic compatibility) to ensure the modified device (CR-2 Plus AF) remains safe and effective despite added features like autofocus and automatic shooting.
• The document states the device "met all requirements of the standards" and "does not raise any new safety and effectiveness concerns." However, it does not detail specific quantitative performance metrics beyond this general statement of compliance.

Ask a specific question about this device

The XEPHILIO MC-1100 mobile fluoroscopy system is designed to provide fluoroscopic and spot-film radiographic images of the patient during diagnostic, surgical and interventional procedures. Examples of clinical application may include cholangiography, endoscopy, urologic, orthopedic, neurologic, vascular, cardiac, critical care and emergency room procedures. The system may be used for other imaging applications at the physician's discretion.

The XEPHILIO MC-1100 mobile fluoroscopy system consists of two mobile units: a Mainframe (C-Arm) and a Workstation. The Mainframe (C-Arm) is comprised of a high voltage generator, x-ray control, and a "C" shaped apparatus, which supports an X-ray tube and a flat panel detector [Canon CSX-10]. The Mainframe is designed to perform linear and rotational motions that allow the user to position the x-ray imaging components at various angles and distances with respect to the patient. The Mainframe can be used to acquire both still and moving images. The Workstation is a mobile platform that supports image display monitors and image processing. Interfaces are provided for optional peripherals such as recording and printing devices.

The provided document, K121303, a 510(k) summary for the XEPHILIO MC-1100 mobile fluoroscopy system, primarily focuses on demonstrating substantial equivalence to predicate devices through comparisons of technological characteristics, non-clinical test data, and compliance with safety standards. It does not contain detailed information about specific acceptance criteria, a study proving those criteria, or the specific performance metrics typically associated with AI/algorithm-based medical devices.

Therefore, many of the requested sections about acceptance criteria, detailed study design, ground truth establishment, expert involvement, and AI performance metrics cannot be directly extracted from this document.

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

1. Table of Acceptance Criteria and Reported Device Performance:

Based on the provided text, specific quantitative acceptance criteria and their corresponding reported device performance values in a comparative study are not detailed. The document generally states that "Tests were performed on the XEPHILIO MC-1100 which demonstrated that the device is safe and effective, performs comparably to the predicate device(s), and is substantially equivalent to the predicate device(s)." This indicates qualitative acceptance of comparable performance rather than specific numerical thresholds.

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

The document mentions "non-clinical image comparisons involving flat panel display images taken with the new device and the predicate device(s)." However, it does not specify the sample size (number of images or cases) used in these comparisons for the test set, nor does it provide any information on the data provenance (e.g., country of origin, retrospective or prospective).

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

The document does not mention using experts to establish ground truth for image comparisons. The "non-clinical image comparisons" likely refer to technical image quality assessments rather than clinical interpretation.

4. Adjudication Method for the Test Set:

No information about an adjudication method is provided, as no expert review process is described for the test set.

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

The document does not indicate that an MRMC comparative effectiveness study was conducted to evaluate human reader improvement with or without AI assistance. The device is a mobile C-Arm system, and the evaluation focuses on its performance against predicate hardware, not on AI-assisted diagnostic effectiveness.

6. Standalone (Algorithm Only) Performance Study:

The document does not describe a standalone (algorithm only) performance study. The device is a hardware system, and the evaluations are about its overall safety and effectiveness as a medical imaging system.

7. Type of Ground Truth Used:

For the "non-clinical image comparisons," the "ground truth" would likely be based on technical image quality metrics and specifications, compared against the predicate devices. It is not based on expert consensus, pathology, or outcomes data in a clinical diagnostic sense, as this is a hardware device submission.

8. Sample Size for the Training Set:

The document does not mention or imply the existence of a "training set" in the context of an AI/algorithm. The device is a hardware imaging system, and its development and testing are described in terms of engineering validation and verification, not machine learning model training.

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

As there is no mention of a "training set" or an AI/algorithm being developed, there is no information on how ground truth for a training set would have been established.

Ask a specific question about this device