Search Results

The Wireless and Wired Yushan X-Ray Flat Panel Detector is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications wherever conventional film/screen or CR systems may be used. The Yushan X-Ray Flat Panel Detector is not intended for mammography, fluoroscopy, tomography, and angiography applications. The use of this product is not recommended for pregnant women and the risk of radioactivity must be evaluated by a physician.

The Subject Device Yushan X-Ray Flat Panel Detector is static digital x-ray detector, model V14C PLUS, F14C PLUS, V17C PLUS are portable (wireless/ wired) detectors, while V17Ce PLUS is a non-portable (wired) detector. The Subject Device is equivalent to it's predicate device K243171, K201528, K210988, and K220510.

The Subject Device is designed to be used in any environment that would typically use a radiographic cassette for examinations. 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 Subject Device has memory exposure mode, and extended image readout feature. Additionally, rounded-edge design for easy handling, image compression algorithm for faster image transfer, LED design for easy detector identification, extra protection against ingress of water.The Detector is currently indicated for general projection radiographic applications and the scintillator material is cesium iodide (CsI).

The Subject Device can automatically collect x-ray images from an x-ray source. It collects x-rays and digitizes the images for their transfer and display to a computer. The x-ray generator (an integral part of a fully-functional diagnostic system) is not part of the device. The sensor includes a flat panel for x-ray acquisition and digitization and a computer (including proprietary processing software) for processing, annotating and storing x-ray images.

The Subject Device is working by using DROC (Digital Radiography Operating Console), Xresta or DR console, which are unchanged from the predicate device, cleared under K201528 for DROC and K243171 for Xresta and DR console. The DROC or Xresta is a software running on a Windows PC/Laptop as a user interface for radiologist to perform a general radiography exam. The function includes:

1. Detector status update
2. Xray exposure workflow
3. Image viewer and measurement
4. Post image process and DICOM file I/O
5. Image database: DROC or Xresta supports the necessary DICOM Services to allow a smooth integration into the clinical network

The DR Console is a software/app-based device, which is a software itself. When this app is operating the OTS can be considered as the iOS system (iOS 16 or above), the safety and effectiveness of this OTS has been assessed and evaluated through the software testing (compatibility) action and also the usability test (summative evaluation). All the functions operate normally and successfully under this OTS framework. The function includes:

1. Imaging procedure review
2. Worklist settings
3. Detector connection settings
4. Calibration
5. Image processing

The software level of concern for the Yushan X-Ray Flat Panel Detector with DROC, Xresta, or DR Console has been determined to be basic based on the "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices"; and the cybersecurity risks of the Yushan X-Ray Flat Panel Detector with DROC, Xresta, or DR Console have also been addressed to assure that no new or increased cybersecurity risks were introduced as a part of device risk analysis. These risks are defined as sequence of events leading to a hazardous situation, and the controls for these risks were treated and implemented as proposed in the risk analysis (e.g., requirements, verification).

Acceptance Criteria and Study for Yushan X-Ray Flat Panel Detector (K250211)

This documentation describes the acceptance criteria and the study conducted for the Yushan X-Ray Flat Panel Detector (models V14C PLUS, F14C PLUS, V17C PLUS, V17Ce PLUS). The device has received 510(k) clearance (K250211) based on substantial equivalence to predicate devices (K243171, K201528, K210988, K220510).

The primary change in the subject device compared to its predicates is an increase in the CsI scintillator thickness from 400µm (in some predicate CsI models) to 600µm. This change impacts image quality metrics but, according to the manufacturer, does not introduce new safety or effectiveness concerns.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for this device are implicitly tied to demonstrating that the changes in scintillator thickness do not negatively impact safety or effectiveness, and ideally, improve image quality. The primary performance metrics affected by the scintillator change are DQE, MTF, and Sensitivity.

Summary of Device Performance vs. Acceptance:
The subject device demonstrates improved DQE, superior noise performance, and smoother images compared to the predicate device (specifically, CsI models), while maintaining comparable MTF and meeting all other safety and performance standards. The slight reduction in MTF compared to the highest performing predicate CsI model (0.69 vs 0.64 at 1 lp/mm) is likely considered an acceptable trade-off given the improvements in DQE and noise, and it is still significantly higher than GOS models.

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

The document does not explicitly state the numerical sample size for the test set used for the performance evaluation of the image quality metrics (DQE, MTF, Sensitivity, noise, smoothness). These metrics are typically derived from physical measurements on a controlled test setup rather than a clinical image dataset.

Data Provenance: Not explicitly stated regarding country of origin or retrospective/prospective nature. However, the evaluation results for image quality metrics, noise, and smoothness are generated internally by the manufacturer during design verification and validation activities.

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

Not applicable. The ground truth for DQE, MTF, and Sensitivity measurements is established through standardized physical phantom measurements (e.g., using RQA5 beam quality) rather than expert consensus on clinical images. These are quantifiable engineering parameters.

4. Adjudication Method for the Test Set

Not applicable. The evaluation of DQE, MTF, and Sensitivity is based on objective instrumental measurements, not on reader interpretations or consensus methods.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or performed as part of this 510(k) submission. The submission focuses on demonstrating substantial equivalence based on technical specifications and physical performance measurements rather than a clinical trial assessing reader performance.

6. Standalone Performance Study

Yes, a standalone performance evaluation was conducted for the device. The reported DQE, MTF, and Sensitivity values, as well as the assessments of noise performance and image smoothness, are measures of the algorithm's (and the underlying detector hardware's) intrinsic performance without human-in-the-loop assistance. The comparison of these metrics between the subject device and the predicate device forms the basis of the standalone performance study.

7. Type of Ground Truth Used

The ground truth used for the performance evaluations (DQE, MTF, Sensitivity, noise, smoothness) is based on objective physical measurements and standardized phantom evaluations. These are quantitative technical specifications derived under controlled laboratory conditions, not expert consensus on pathology, clinical outcomes, or interpretations of patient images.

8. Sample Size for the Training Set

Not applicable. This device is an X-ray flat panel detector, a hardware component that captures images. While it includes embedded software (firmware, image processing algorithms), the document does not indicate that these algorithms rely on a "training set" in the context of machine learning. The image processing algorithms are likely deterministic or parameter-tuned, not learned from a large dataset like an AI model for diagnosis.

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

Not applicable, as there is no indication of a machine learning "training set" as described in the context of AI models. The ground truth for the development and validation of the detector's physical performance characteristics is established through established metrology and engineering testing protocols.

Ask a specific question about this device

The Wireless (V14C, V14G, F14C, F14G, V17C, V17G)/Wired (V14C, V14G, F14C, F14G, V17C, V17G, V17Ge, V17Ce) Yushan X-Ray Flat Panel Detector is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications wherever conventional film/screen or CR systems may be used. The Yushan X-Ray Flat Panel Detector is not intended for mammography, fluoroscopy, tomography, and angiography applications. The use of this product is not recommended for pregnant women and the risk of radioactivity must be evaluated by a physician.

The subject device Yushan X-Ray Flat Panel Detector, model V14C, V14G, V17C, V17G, F14C, F14G are portable(wireless/wired) detectors, while V17Ce, V17Ge are a non-portable(wired) detector. The Yushan X-Ray Flat Panel Detector is designed to be used in any environment that would typically use a radiographic cassette for examinations. 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. Additionally, rounded-edge design for easy handling, image compression algorithm for faster image transfer, LED design for easy detector identification, extra protection against ingress of water.

Yushan series is working by using Xresta and DR console.

The Xresta is a software running on a Windows PC as an user interface for radiologist to perform a general radiography exam. The function includes:

• 1. Detector status update
• 2. Xray exposure workflow
• 3. Image viewer and measurement.
• 4. Post image process and DICOM file I/O
• 5. Image database: DROC support the necessary DICOM Services to allow a smooth integration into the clinical network

The DR Console is a software/app-based device, which is a software itself. When this app is operating the OTS can be considered as the iOS system (iOS 16 or above), the safety and effectiveness of this OTS has been assessed and evaluated through the software testing (compatibility) action and also the usability test (summative evaluation). All the functions operate normally and successfully under this OTS framework.

The function includes:

• 1. Imaging procedure review
• 2. Worklist settings
• 3. Detector connection settings
• 4. Calibration
• 5. Image processing

The provided document is a 510(k) summary for the Yushan X-Ray Flat Panel Detector. It outlines the device's technical characteristics and compares it to predicate devices to establish substantial equivalence. However, it does not describe a clinical study that proves the device meets specific acceptance criteria in terms of diagnostic performance (e.g., sensitivity, specificity for a particular condition).

Instead, the document focuses on non-clinical performance data to demonstrate substantial equivalence, primarily by showing that the device adheres to recognized voluntary standards and exhibits comparable physical and image quality characteristics to previously cleared devices.

Here's an analysis based on the provided text, addressing your points where possible:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria for diagnostic performance (e.g., a specific sensitivity or specificity target for a clinical task) and the device's performance against those criteria. It focuses on technical specifications and compliance with standards.

The closest to "acceptance criteria" are the technical specifications listed for the subject device and the predicate devices, implying that meeting or being comparable to these specifications is considered acceptable for substantial equivalence.

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

• Test Set Sample Size: Not applicable in the context of a clinical performance study. The document states: "No clinical study has been performed."
• Data Provenance: Not applicable. The evaluation relies on non-clinical (laboratory/technical) testing.

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 study with expert ground truth was performed.

4. Adjudication method for the test set

Not applicable, as no clinical study with a test set requiring adjudication was performed.

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 device is an X-ray flat panel detector, not an AI software intended to assist human readers.

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

Not applicable. This is a hardware device (X-ray detector) with associated software for image processing and display, not an AI algorithm. Its performance is inherent in its image acquisition capabilities. The "standalone" performance here refers to the detector's physical performance metrics (DQE, MTF, resolution).

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

For the image quality evaluation mentioned: The ground truth implicitly refers to the ideal image quality parameters as defined by industry standards (e.g., IEC standards for DQE, MTF) and the performance of the legally marketed predicate devices. It is not a clinical ground truth for diagnostic accuracy.

8. The sample size for the training set

Not applicable. This device is not an AI/machine learning model that requires a distinct training set in the typical sense. Its "training" would be the engineering and manufacturing processes to ensure it meets its design specifications.

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

Not applicable, as there is no training set in the context of an AI model for this device. The "ground truth" for the device's development would be its design requirements and engineering specifications validated through non-clinical testing.

Summary of the Study that Proves the Device Meets Acceptance Criteria:

The "study" referenced in the document is a compilation of non-clinical performance tests and adherence to voluntary standards.

• Non-clinical Performance Data: The device conforms to voluntary standards such as AAMI/ANSI ES60601-1, IEC 60601-1, IEC 60601-1-2, IEC 62304, IEC 60601-1-6, ANSI AAMI IEC 62366-1, and ANSI/AAMI HE75.
• FDA Guidance adherence: The "FDA's Guidance for the Submission of 510(k)s for Solid State X-ray Imaging Devices" (September 1, 2016) was followed to describe detector characteristics. Guidance documents for software (June 14, 2023) and cybersecurity (September 27, 2023) were also followed.
• Specific Tests Conducted:
  • Risk analysis, verification, and validation activities.
  • Load-bearing characteristics and protection against ingress of water (passed).
  • EMC emission testing (IEC60601-1-2) – results satisfactory.
  • Biocompatibility testing (ISO 10993 series) for materials in contact with patients.
  • Image Quality Evaluation: Confirmed that the image quality of the Yushan X-Ray Flat Panel Detector is substantially equivalent to that of the predicate device. This is the key "performance" study, demonstrating that the new device's images are comparable to those produced by already-cleared devices, implying acceptable clinical usability for its stated indications.

Conclusion stated in the document: Based on these non-clinical studies and comparisons, the manufacturer concluded that the device is "as safe and effective" as the legally marketed predicate devices and does not raise "different questions of safety and effectiveness."

Ask a specific question about this device

The Wired Yushan X-Ray Flat Panel Detector is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications wherever conventional film/screen or CR systems may be used. The Yushan X-Ray Flat Panel Detector is not intended for mammography, fluoroscopy, tomography, and angiography applications. The use of this product is not recommended for pregnant women and the risk of radioactivity must be evaluated by a physician.

InnoCare's Yushan X-Ray Flat Panel Detector with DROC, model V17Ce is a nonprotable(wired) digital detector. The Yushan X-Ray Flat Panel Detector with DROC is designed to be used in any environment that would typically use a radiographic cassette for examinations. 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. V17Ce have memory exposure mode, and extended image readout feature. Additionally, rounded-edge design for easy handling, image compression algorithm for faster image transfer, LED design for easy detector identification, extra protection against ingress of water. The Yushan X-Ray Flat Panel Detector with DROC is currently indicated for general projection radiographic applications and the scintillator material is cesium iodide (Csl). The Yushan X-Ray Flat Panel Detector with DROC sensor can automatically collects x-ray images from an x-ray source. It collects x-rays and digitizes the images for their transfer and display to a computer. The x-ray generator (an integral part of a complete x-ray system), is not part of the submission. The sensor includes a flat panel for x-ray acquisition and digitization and a computer (including proprietary processing software) for processing, annotating and storing x-ray images, The personal computer is not part of this submission. Yushan series is working by using DROC(Digital Radiography Operating Console). The DROC is a software running on a Windows PC as an user interface for radiologist to perform a general radiography exam. The function include: 1. Detector status update 2. Xray exposure workflow 3. Image viewer and measurement. 4. Post image process and DICOM file I/O 5. Image database: DROC support the necessary DICOM Services to allow a smooth integration into the clinical network.

This document is a 510(k) summary for the InnoCare Optoelectronics Corp.'s Yushan X-Ray Flat Panel Detector with DROC (model V17Ce). It seeks to demonstrate substantial equivalence to a predicate device (Yushan X-Ray Flat Panel Detector with DROC, model V17Ge, K201528).

Based on the provided text, the device in question is an X-ray flat panel detector, not an AI/ML medical device. Therefore, the questions related to AI/ML acceptance criteria, ground truth, expert adjudication, MRMC studies, and training/test sets are not applicable to this submission.

The document primarily focuses on demonstrating substantial equivalence through non-clinical performance data and technical comparisons to a predicate device.

Here's how the provided information relates to acceptance criteria and performance, as much as can be extracted for a non-AI/ML device:

1. Table of Acceptance Criteria and Reported Device Performance

For an X-ray flat panel detector, acceptance criteria are typically related to technical specifications and compliance with standards. The document presents a comparison table between the new device (V17Ce) and the predicate device (V17Ge).

• European Medical Devices Directive (93/42/EEC)
• EN ISO 13485
• ISO 14971
• ANSI/AAMI ES60601-1
• CAN/CSA C22.2 No. 60601-1:14
• IEC 60601-1-2
• IEC 62304
• IEC 60601-1-6
• IEC 62366-1
• ISO 10993-1
• ISO 10993-5
• ISO 10993-10
• ISO 15223-1 | - FDA Standards 21 CFR 892.1680 for stationary x-ray system
• European Medical Devices Directive (93/42/EEC)
• EN ISO 13485
• ISO 14971
• ANSI/AAMI ES60601-1
• CAN/CSA C22.2 No. 60601-1:14
• IEC 60601-1-2
• IEC 62304
• IEC 60601-1-6
• IEC 62366-1
• ISO 10993-1
• ISO 10993-5
• ISO 10993-10
• ISO 15223-1 | The V17Ce confirms to the same comprehensive set of voluntary standards as the V17Ge. This indicates the V17Ce meets the acceptance criterion of regulatory and safety compliance. |
  | Dimensions (mm) | V17Ge: 460(W)×460(L)×15(H) | V17Ce: 460(W)×460(L)×15(H) | Identical dimensions. Meets acceptance criterion of physical compatibility. |
  | Weight (Kg) | V17Ge: 3.5 | V17Ce: 3.6 | Slightly heavier, but this minor difference (0.1kg) is likely considered acceptable in the context of substantial equivalence for this device type. |
  | Scintillator | V17Ge: GOS (Gadolinium Oxysulfide) | V17Ce: CsI (Cesium Iodide) | This is the primary difference highlighted in the document. The shift from GOS to CsI is significant for image quality. The document states that the "image quality evaluation confirmed that the image quality of the Yushan X-Ray Flat Panel Detector with DROC is substantially equivalent to that of the predicate device," implying that despite the different scintillator, the resulting image quality performance is acceptable. Specific acceptance criteria for image quality would be implied by this statement. The DQE and MTF values (below) support the performance of the CsI scintillator. |
  | Pixel Pitch | 140 μm | 140 μm | Identical. Meets acceptance criterion. |
  | DQE (at 1 lp/mm, RQA5) | GOS: 0.27 | CsI: 0.48 | The CsI scintillator (V17Ce) shows a significantly higher DQE (Detective Quantum Efficiency) than the GOS scintillator (V17Ge). A higher DQE indicates better X-ray signal utilization and potentially lower dose requirements for the same image quality, or better image quality at the same dose. This is an improvement that generally supports effectiveness. The acceptance criterion would be that image quality is at least equivalent or better, which this meets. |
  | MTF (at 1 lp/mm, RQA5) | GOS: 0.52 | CsI: 0.69 | The CsI scintillator (V17Ce) shows a higher MTF (Modulation Transfer Function) than the GOS scintillator (V17Ge). A higher MTF indicates better spatial resolution and image sharpness. This is an improvement that generally supports effectiveness. The acceptance criterion would be that image quality is at least equivalent or better, which this meets. |
  | Max. Resolution | GOS: 3.57 lp/mm | CsI: 3.57 lp/mm | Identical. Meets acceptance criterion. |
  | A/D Conversion | 16 bit | 16 bit | Identical. Meets acceptance criterion. |
  | Pixels | V17Ge: 3072 x 3072 | V17Ce: 3072 x 3072 | Identical. Meets acceptance criterion. |
  | Interface | Wired: Gigabit Ethernet (100BASE-TX or 10BASE-T) | Wired: Gigabit Ethernet (100BASE-TX or 10BASE-T) | Identical. Meets acceptance criterion. |
  | Power Source | Rechargeable Lithium Battery (Not applicable on V17Ge) | Not applicable | The V17Ce is described as a "nonportable (wired) digital detector," indicating it does not use a battery for operation. This is a distinction from the predicate (V17Ge), which could be wireless/wired and had an optional battery. For the wired V17Ce, "Not applicable" for power source aligns with its wired nature, differentiating it from the predicate's wireless capability (which leveraged a battery). This is not an acceptance criterion but a design difference explained by the "wired" nature. |
  | Biological Safety | All material contact with patients are in accordance with ISO 10993. | All material contact with patients are in accordance with ISO 10993. | Identical. Meets acceptance criterion related to biocompatibility. |
  | Image Quality Evaluation| Implied to be acceptable (as predicate is cleared) | Confirmed to be "substantially equivalent" to predicate device. | This is a high-level statement confirming that the overall image quality meets the necessary standard for substantial equivalence, overcoming the difference in scintillator material. Specific quantitative criteria for this "evaluation" are not detailed in this summary. |
  | Mechanical Integrity | Implied to be acceptable | Load-bearing characteristics and protection against ingress of water were tested and passed. | Demonstrates robustness. Meets implied acceptance criteria for physical durability. |
  | EMC Emission | Implied to be acceptable | IEC60601-1-2 testing resulted in "satisfactory" results. | Confirms electromagnetic compatibility. Meets acceptance criterion. |
  | Cybersecurity Risks | Implied to be addressed | Addressed to assure no new or increased risks. Device software used unchanged from predicate. | Meets acceptance criteria for cybersecurity risk management for medical devices. |
  | Software Level of Concern | Implied to be acceptable | Determined to be "moderate" based on FDA guidance; verification and validation activities performed. | Meets acceptance criterion for software safety and documentation. |

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 (N/A) for AI/ML device.
• For this traditional X-ray detector, the performance evaluation is based on non-clinical bench testing:
  • Compliance with various international standards (e.g., IEC 60601-1-2 for EMC, ISO 10993 series for biocompatibility).
  • Specific technical measurements (DQE, MTF, resolution).
  • Mechanical tests (load-bearing, water ingress).
• The document implies that these tests were conducted on the V17Ce device. There is no mention of "data provenance" in the sense of clinical image datasets or patient data, as no clinical study was performed.

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)

• N/A for AI/ML device.
• For this detector, "ground truth" is established through physical measurements and adherence to engineering standards and specifications. There are no human experts "reading" images for ground truth in the context of device performance in this type of submission.

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

• N/A for AI/ML device. Adjudication relates to resolving disagreements among human readers or experts, which is not relevant here as there are no human readers or clinical image interpretations involved in establishing device performance.

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

• N/A. This is not an AI-enabled device. No MRMC study was conducted. The evaluation is solely based on the physical and image quality characteristics of the detector itself.

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

• N/A. This is not an AI algorithm. Its performance is inherent to its hardware and associated processing software, which is evaluated against engineering benchmarks and standards.

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

• Not "ground truth" in the AI/ML sense. For this device, performance is evaluated against:
  • Engineering specifications and measurements: DQE, MTF, resolution, pixel pitch, dimensions, etc.
  • Compliance with international safety and performance standards: e.g., IEC 60601 series, ISO 10993 series, FDA regulations.
  • Comparative technical characteristics to a legally marketed predicate device.

8. The sample size for the training set

• N/A. There is no "training set" as this is not an AI/ML device subject to machine learning model training.

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

• N/A. As there is no training set, there is no ground truth for it.

In summary: The substantial equivalence determination for the Yushan X-Ray Flat Panel Detector with DROC (V17Ce) is based on thorough non-clinical bench testing and comparison of technical specifications to a predicate device, focusing on compliance with established safety and performance standards. The primary difference (scintillator material) and its impact on image quality (improved DQE and MTF) were evaluated and deemed to result in performance that is substantially equivalent to the predicate, not raising new questions of safety or effectiveness. No clinical studies or AI/ML-specific evaluations were performed or required for this 510(k) submission.

Ask a specific question about this device

The Wireless/Wired Yushan X-Ray Flat Panel Detector with DROC is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications wherever conventional film/screen or CR systems may be used. The Yushan X-Ray Flat Panel Detector with DROC is not intended for mammography, fluoroscopy, tomography, and angiography applications.

InnoCare's Yushan X-Ray Flat Panel Detector with DROC, model F14C, F14G are portable digital detector system. The Yushan X-Ray Flat Panel Detector with DROC is designed to be used in any environment that would typically use a radiographic cassette for examinations. Model F14C, F14G 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. Every model have memory exposure mode, and extended image readout feature. Additionally, roundededge design for easy handling, image compression algorithm for faster image transfer, LED design for easy detector identification, extra protection against ingress of water.

The Yushan X-Ray Flat Panel Detector with DROC is currently indicated for general projection radiographic applications and offers two different detector types in terms of scintillator materials (gadolinium oxysulfide (GOS) and cesium iodide (CsI)).

The Yushan X-Ray Flat Panel Detector with DROC sensor can automatically collects x-ray images from an x-ray source. It collects x-rays and digitizes the images for their transfer and display to a computer. The sensor does not have an x-ray source, which is provided and controlled by independent system manufacturers. The sensor includes a flat panel for x-ray acquisition and digitization and a computer (including proprietary processing software) for processing, annotating and storing x-ray images.

Yushan series is working by using DROC(Digital Radiography Operating Console). The DROC is a software running on a Windows PC as an user interface for radiologist to perform a general radiography exam. The function include:

• 1. Detector status update
• 2. Xray exposure workflow
• 3. Image viewer and measurement.
• 4. Post image process and DICOM file I/O
• 5. Image database: DROC support the necessary DICOM Services to allow a smooth integration into the clinical network

This document describes the premarket notification for the "Yushan X-Ray Flat Panel Detector with DROC," models F14C and F14G. The submission aims to demonstrate substantial equivalence to a previously cleared predicate device (K201528).

Acceptance Criteria and Device Performance:

The document focuses on non-clinical performance data to demonstrate substantial equivalence. It does not provide a table of acceptance criteria with specific numerical targets for particular metrics (e.g., sensitivity, specificity, or specific image quality metrics like DQE or MTF at certain conditions) and corresponding reported performance values for a clinical study with a human-in-the-loop component or standalone AI performance.

Instead, the performance data presented primarily confirms adherence to voluntary standards and established guidance documents for X-ray imaging devices. The comparison table (pages 6-7) outlines technical specifications of the new device and the predicate.

Here's a breakdown of the relevant information provided:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly present a "table of acceptance criteria" with numerical performance targets for an AI algorithm's diagnostic performance. The context is a 510(k) submission for an X-ray flat panel detector, not an AI diagnostic software. Therefore, the "acceptance criteria" discussed are related to the hardware's technical specifications and compliance with established standards, and the "reported device performance" are measurements of these technical specifications and confirmations of compliance.

Key finding for substantial equivalence: "Furthermore, the image quality evaluation confirmed that the image quality of the Yushan X-Ray Flat Panel Detector with DROC is substantially equivalent to that of the predicate device." (Page 10)

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

The document states: "Clinical Performance Data: No clinical study has been performed. The substantial equivalence has been demonstrated by non-clinical studies." (Page 10)

Therefore, there is no "test set" in the context of clinical image data for evaluating AI or human reader performance. The "testing" referred to is for the physical and electrical characteristics of the device. The data provenance is non-clinical, likely laboratory measurements conducted by the manufacturer, InnoCare Optoelectronics Corp. in Tainan City, Taiwan (R.O.C.).

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

Not applicable, as no clinical study or test set for diagnostic performance (such as for an AI algorithm) was used.

4. Adjudication Method for the Test Set:

Not applicable, as no clinical study or test set for diagnostic performance was used.

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

No, an MRMC study was not done. The device is an X-ray detector, not an AI-powered diagnostic tool requiring this type of clinical evaluation. The submission relies on non-clinical data to demonstrate substantial equivalence to the predicate device.

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

Not applicable. This device is an X-ray detector, a hardware component for acquiring images, not an AI algorithm.

7. The Type of Ground Truth Used:

The "ground truth" for this submission is established through objective measurements of technical specifications (e.g., DQE, MTF, pixel pitch), and compliance with recognized industry standards (IEC, ISO, FCC, etc.) and FDA guidance documents for medical devices. There is no biological or diagnostic ground truth (e.g., pathology, outcomes data, or expert consensus on disease presence) associated with this submission, as it relates to the performance of the image acquisition hardware.

8. The Sample Size for the Training Set:

Not applicable. The device is hardware, an X-ray detector, not an AI algorithm that requires a training set of images.

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

Not applicable, as there is no training set for an AI algorithm.

Ask a specific question about this device

The Wireless(V14C, V14G, V17C, V17G)/Wired(V14C, V14G, V17C, V17G, V17Ge) Yushan X-Ray Flat Panel Detector with DROC is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications wherever conventional film/screen or CR systems may be used. The Yushan X-Ray Flat Panel Detector with DROC is not intended for mammography, tomography, and angiography applications.

InnoCare's Yushan X-Ray Flat Panel Detector with DROC, model V14C, V14G, V17C, V17G are portable digital detector system, while V17Ge is a non-protable digital detector. The Yushan X-Ray Flat Panel Detector with DROC is designed to be used in any environment that would typically use a radiographic cassette for examinations. Model V14C, V14G, V17C, V17G support both wireless and wired/tethered data communication between the detector and the system, while model V17Ge is only applicable for wired use. 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. Every model have memory exposure mode, and extended image readout feature. Additionally, rounded-edge design for easy handling, image compression algorithm for faster image transfer, LED design for easy detector identification, extra protection against ingress of water.

The Yushan X-Ray Flat Panel Detector with DROC is currently indicated for general projection radiographic applications and offers two different detector types in terms of scintillator materials (gadolinium oxysulfide (GOS) and cesium iodide (CsI)).

The Yushan X-Ray Flat Panel Detector with DROC sensor can automatically collects x-ray images from an x-ray source. It collects x-rays and digitizes the images for their transfer and display to a computer. The sensor does not have an x-ray source, which is provided and controlled by independent system manufacturers. The sensor includes a flat panel for x-ray acquisition and digitization and a computer (including proprietary processing software) for processing, annotating and storing x-ray images.

Yushan series is working due to the combination of SDK(software development kit) and DROC(Digital Radiography Operating Console).

The SDK provides the interface for DROC to control the Yushan X-Ray Flat Panel Detector. SDK initiates the taking of X-ray images from the Yushan X-Ray Flat Panel Detector, through the Sensor Driver application. Once an X-ray is taken, Sensor Driver reads it from the flat panel and transfers it to SDK. Then the DROC will take the image data from SDK for further image process and display.

The DROC is a software running on a Windows PC as an user interface for radiologist to perform a general radiography exam. The function include:

• 1. Detector status update
• 2. Xray exposure workflow
• 3. Image viewer and measurement.
• 4. Post image process and DICOM file I/O
• 5. Image database: DROC support the necessary DICOM Services to allow a smooth integration into the clinical network

The provided text describes the Yushan X-Ray Flat Panel Detector with DROC, a device for capturing radiographic images. However, it does not include detailed acceptance criteria or a study proving its performance against such criteria in the way typically expected for an AI/CADe device.

The document is a 510(k) summary for a medical device that integrates software (DROC) for processing, annotating, and storing x-ray images, but the primary device is still a flat panel detector. The regulatory submission primarily focuses on demonstrating substantial equivalence to a predicate device, not on specific AI performance metrics or clinical studies comparing AI-assisted vs. non-AI-assisted reads.

Here's a breakdown of the requested information based on the provided text, and where information is not available:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size (Test Set): Not mentioned for any AI/software performance evaluation. The document states "No clinical study has been performed." The "image quality evaluation" mentioned is a non-clinical study, but details about the number of images/phantoms used are not provided.
• Data Provenance: Not mentioned.

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

• Not mentioned. The document focuses on demonstrating substantial equivalence through non-clinical performance and engineering tests, rather than a clinical study requiring expert ground truth for diagnostic accuracy.

4. Adjudication method for the test set

• Not applicable as there is no described clinical test set with ground truth established by experts.

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. The document explicitly states: "No clinical study has been performed." and "The substantial equivalence has been demonstrated by non-clinical studies."

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

• The document implies that an "image quality evaluation" was performed for the device's output. While the DROC includes processing software, the submission appears to treat it as an integral part of the flat panel detector system rather than a separate AI algorithm with standalone performance metrics. No specific standalone algorithm performance (e.g., sensitivity, specificity for a specific condition) is provided or discussed, as the device's primary function is to capture and display radiographic images, not to automatically interpret them or provide diagnoses.

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

• For the non-clinical image quality evaluation, the ground truth would likely be based on established physical phantoms and objective measurements (e.g., DQE, MTF under controlled conditions) rather than expert consensus on clinical findings, pathology, or outcomes data, as no clinical study was performed.

8. The sample size for the training set

• Not applicable / Not mentioned. The device is a flat panel detector system. While it has software (DROC) for image processing and display, the document does not describe it as an AI/CADe device that performs automated diagnostic interpretations requiring a training set in the conventional sense. The "processing software" mentioned is for general image display and manipulation, not for machine learning-based diagnostic assistance.

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

• Not applicable / Not mentioned. (See point 8).

Ask a specific question about this device

The Wireless/Wired Yushan X-Ray Flat Panel Detector is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications wherever conventional film/screen or CR systems may be used. The Yushan X-Ray Flat Panel Detector is not intended for mammography, fluoroscopy, tomography, and angiography applications.

InnoCare's Yushan X-Ray Flat Panel Detector (Yushan V14C, Yushan V14G) is a portable digital detector system. The Yushan X-Ray Flat Panel Detector is designed to be used in any environment that would typically use a radiographic cassette for examinations of adults. 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 Yushan X-Ray Flat Panel Detector is currently indicated for general projection radiographic applications and offers two different detector types in terms of scintillator materials (gadolinium oxysulfide (GOS) and cesium iodide (Csl)). The Yushan X-Ray Flat Panel Detector sensor can automatically collects x-ray images from an x-ray source. The Yushan X-Ray Flat Panel Detector sensor collects xrays and digitizes the images for their transfer and display to a computer. The sensor does not have an x-ray source, which is provided and controlled by independent system manufacturers. The sensor includes a flat panel for x-ray acquisition and digitization and a computer (including proprietary processing software) for processing, annotating and storing x-ray images. The SDK(software development kit) software library runs on a PC workstation and provides the interface for system manufacturer to control the Yushan X-Ray Flat Panel Detector. SDK initiates the taking of X-ray images from the Yushan X-Ray Flat Panel Detector, through the Sensor Driver application. Once an X-ray is taken, Sensor Driver reads it from the flat panel and transfers it to SDK. Then the user interface which designed by the system manufacture will take the image data from SDK for further image process and display.

The provided text is a 510(k) summary for the InnoCare Optoelectronics Corp.'s Yushan X-Ray Flat Panel Detector. It primarily focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance data and technical comparisons.

There is no information regarding the acceptance criteria for an AI/ML powered device, nor a study proving an AI/ML device meets such criteria. The device described is a digital X-ray detector, not an AI/ML algorithm.

Therefore, I cannot provide the requested information from the provided text. The document clearly states:

• Clinical Performance Data: No clinical study has been performed.
• The software level of concern for the Yushan X-Ray Flat Panel Detector has been determined to be moderate... Please be noted that the software is not based on the predicate device. (This refers to the SDK, not an AI/ML algorithm)

The request asks about an "AI vs without AI assistance" study, "standalone algorithm only" performance, and ground truth establishment for a training set, all of which are pertinent to AI/ML devices. This document does not describe such a device or studies related to it.

Ask a specific question about this device