Search Results

INNOVISION-EXII is a stationery X-ray system intended for obtaining radiographic images of various anatomical parts of the human body, both pediatrics and adults, in a clinical environment. INNOVISION-EXII is not intended for mammography, angiography, interventional, or fluoroscopy use.

INNOVISION-EXII can receive X-ray signals from X-ray irradiation and digitize them into X-ray images by converting digital images to DICOM image format using Elui imaging software. INNOVISION-EXII is a general radiography X-ray system and not for mammography nor fluoroscopy. In addition, the system must be operated by a user who is trained and licensed to handle a general radiography X-ray system to meet the regulatory requirements of a Radiologic Technologist. Target areas for examinations include the head, spine, chest, and abdomen for diagnostic screening of orthopedic, respiratory, or vertebral discs. The system can capture a patient's postures, such as sitting, standing, or lying. This system can be used for patients of all ages, but it should be used with care for pregnant women and infants. The INNOVISION-EXII system has no part directly touching the patient's body.

The provided text describes a 510(k) summary for the INNOVISION-EXII stationary X-ray system, asserting its substantial equivalence to a predicate device (GXR-Series Diagnostic X-Ray System). However, the document does not contain information about acceptance criteria or a detailed study proving the device meets specific acceptance criteria related to its performance metrics for diagnostic imaging or AI assistance.

The "Clinical testing" section on page 9 merely states: "Clinical image evaluation of INNOVISION-EXII has been performed. The evaluation results demonstrated that INNOVISION-EXII generated images are adequate and suitable for expressing contour and outlines. The image quality including contrast and density are appropriate and acceptable for diagnostic exams." This is a very general statement and does not provide specific acceptance criteria or detailed study results.

Similarly, there are no details regarding AI performance (standalone or human-in-the-loop), sample sizes, ground truth establishment, or expert qualifications for such studies. The document focuses on establishing substantial equivalence based on intended use, technological characteristics, and compliance with various safety and performance standards (electrical safety, EMC, software validation, risk analysis).

Therefore, based solely on the provided text, the requested information about acceptance criteria and a study proving the device meets these criteria cannot be extracted or inferred. The document is a 510(k) summary focused on demonstrating substantial equivalence, not a detailed clinical performance study report.

Here is a breakdown of why each requested point cannot be addressed from the given text:

1. A table of acceptance criteria and the reported device performance: Not present. The "clinical testing" section is too vague.
2. Sample sized used for the test set and the data provenance: Not present. No specific test set for clinical performance is detailed.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not present. No ground truth establishment process is described beyond a general "clinical image evaluation."
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not present.
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 present. The document does not mention any AI component or MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not present. No mention of an algorithm or standalone performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not detailed. Only a general "clinical image evaluation" is mentioned.
8. The sample size for the training set: Not present. The document describes a medical imaging device, not a machine learning model requiring a training set.
9. How the ground truth for the training set was established: Not applicable, as there's no mention of a training set or machine learning components.

In summary, the provided FDA 510(k) summary largely focuses on engineering and regulatory compliance (electrical safety, EMC, software validation, comparison of technical specifications to a predicate device) to establish substantial equivalence, rather than detailed clinical performance metrics derived from a study with specific acceptance criteria and ground truth for diagnostic accuracy.

Ask a specific question about this device

The Jumong General is intended for use by a qualified/trained doctor or technician on both adult and pediatric subjects for taking diagnostic radiographic exposures of the skull, spinal column, extremities, and other body parts. Applications can be performed with the patient sitting, standing, or lying in the prone or supine position. Not for mammography.

This device represents a combination of an already cleared solid state digital x-ray acquisition panel with software and diagnostic x-ray components required to make a complete system. Film cassettes may be employed in place of the x-ray generator has been changed to a Delta Electronics Delta DMP 100R The collimator has been changed to a Fairy Medical Electronics model CRUX FR04. The tubehead has been changed to a Hangzhou Kailong Medical Instruments Co., Ltd H1074X. The system complies with the CDRH Radiological Health performance standard in the Code of Federal Regulations, as well as the voluntary IEC standards IEC 60601-1 and IEC 60601-1-2.

The provided text is a 510(k) Pre-market Notification document for the "Jumong General" stationary x-ray system. This document is a submission to the FDA demonstrating that a new device is substantially equivalent to a legally marketed predicate device.

It's important to understand that in this context, "acceptance criteria" and "study that proves the device meets the acceptance criteria" refer to the demonstration of substantial equivalence, primarily through non-clinical performance testing and comparison to an established predicate device, rather than a clinical study with human-in-the-loop performance measurement of an AI algorithm.

The document states:

• "5. Safety and Effectiveness, comparison to predicate device. This combination device has the same indications for use and very similar technological characteristics as the predicate device, and employs already 510(k) cleared digital panels and software."
• "No software modifications were made to the imaging chain."
• "8. Summary of clinical testing: Not applicable."

This clearly indicates that this submission does not involve an AI algorithm that requires a separate performance study with human readers or standalone algorithm performance assessment. The device is a conventional x-ray imaging system, albeit with some updated components compared to its predicate.

Therefore, many of the requested points related to AI performance, such as MRMC studies, standalone AI performance, ground truth establishment for AI training/testing, and expert adjudication, are not applicable to this specific submission.

However, I can still interpret how the concept of "acceptance criteria" and "proof" apply to this device based on the provided text, focusing on its non-clinical performance and substantial equivalence demonstration.

Acceptance Criteria and Study for Jumong General X-Ray System

Given that the Jumong General is a stationary x-ray system (Product Code: KPR, MQB) and not an AI-powered diagnostic device, the "acceptance criteria" and "proof" focus on demonstrating substantial equivalence to a previously cleared predicate device (K150816, Jumong Series Stationary Radiographic System). This is achieved primarily through non-clinical performance testing, safety standards compliance, and direct comparison of functional characteristics. The document explicitly states "No software modifications were made to the imaging chain," and "Clinical testing: Not applicable."

The "acceptance criteria" for demonstrating substantial equivalence primarily revolve around meeting recognized performance standards, electrical safety, EMC compliance, and demonstrating comparable image quality and intended use to the predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

The new components are:

• Generator: Delta Electronics DMP 100R (same kVp range as CPI CMP 200 DR predicate)
• Collimator: Fairy Medical Electronics CRUX FR04 (changed from Ralco Model R225)
• Tubehead: Hangzhou Kailong Medical Instruments Co., Ltd H1074X (changed from Varian RAD14)

Digital Panel Models, Image acquisition panel specifications, DICOM, Image acquisition software, and Power Source are all SAME as predicate. (page 5, comparison chart).

Conclusion: "This combination device has the same indications for use and very similar technological characteristics as the predicate device, and employs already 510(k) cleared digital panels and software." (page 4, section 5) |
| Safety & Performance Standards | Compliance with relevant US Radiation Safety Performance Standards and IEC standards for medical electrical equipment. | - Conforms to the US Performance Standard. (page 6, section 7)

• New generator complies with: IEC 60601-2-54:2009+A1+A2, IEC 60601-1:2005+Corrigendum 1+Corrigendum 2+A1, IEC 60601-1-3:2008+A1, and IEC 60601-1-6:2010+A1. (page 6, section 7)
• EMC testing complies with IEC 60601-1-2:2014. (page 6, section 7)
• New collimator tested for compliance with EN/IEC 60601-2-54 for radiation leakage. (page 6, section 7)
• New tubehead tested to IEC 60613:2010 and IEC 60336:2005. (page 6, section 7)
• "Every unit is tested for electrical safety, input power, display of operation and exposure factors, collimator operation, reproducibility, and accuracy." (page 6, section 7) |
  | Image Quality | Image quality should be diagnostically acceptable and comparable to the predicate device. | "Test images were acquired which showed excellent diagnostic quality." (page 6, section 7) |
  | Risk Analysis | Assessment of risks associated with modifications and demonstration of acceptable risk profile. | "A risk analysis was performed with regard to the modifications. No software modifications were made to the imaging chain." (page 6-7, section 7) The conclusion states the device is "as safe and effective as the predicate device." (page 7, section 9) |

As this is a conventional X-ray system submission and not an AI/CADe device, the following points are largely "Not Applicable."

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

• Not Applicable in the traditional sense of a clinical test set for an AI algorithm. The "test set" here refers to the physical system undergoing non-clinical verification and validation tests. The document references "test images" acquired for image quality assessment, but the sample size or specific provenance of these images is not detailed as it would be for a clinical AI study. The testing is described as non-clinical ("integration and image quality testing").

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

• Not Applicable. Ground truth, in the context of diagnostic accuracy for AI, is not relevant here. The "diagnostic quality" of images was assessed, presumably by qualified personnel, but this is a standard engineering and quality assurance assessment for image generators, not an AI ground truth establishment process.

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

• Not Applicable. This pertains to clinical AI studies for diagnostic accuracy.

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 is specific to AI-assisted diagnostic devices. The document explicitly states "Summary of clinical testing: Not applicable."

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

• Not Applicable. This is specific to the performance of an AI algorithm. The device is a hardware x-ray system, and no AI algorithm's standalone performance is being evaluated.

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

• Not Applicable. Ground truth for diagnostic accuracy is not relevant here as it's a hardware device demonstrating fundamental imaging capability and safety, not a diagnostic interpretation tool.

8. The sample size for the training set

• Not Applicable. There is no AI algorithm being trained for this device as per the submission details ("No software modifications were made to the imaging chain").

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

• Not Applicable. As there is no AI algorithm being trained by the applicant, this point is not relevant.

Ask a specific question about this device

The Jumong Series Stationary Radiographic System is intended for use by a qualified/trained doctor or technician on both adult and pediatric subjects for taking diagnostic radiographic exposures of the skull, spinal column, chest. abdomen, extremities, and other body parts. Applications can be performed with the patient sitting, standing, or lying in the prone or supine position. Not for mammography.

This device represents a new combination of an already cleared solid state digital x-ray acquisition panel with software and diagnostic x-ray compnents required to make a complete system. Film cassettes may be employed in place of the digital panel. The purchaser can select from one of four configurations. The x-ray generator is a CPI CMP 200DR. The x-ray tubes are supplied by Varian (RAD-14), and the collimator is the Ralco R225 ACS DHHS. The system complies with the CDRH Radiological Health performance standard in the Code of Federal Regulations, as well as the voluntary IEC standards IEC 60601-1 and IEC 60601-1-2. All major components are either UL or CSA listed.

The provided text is a 510(k) summary for the "Jumong Series Stationary Radiographic System." It primarily focuses on demonstrating substantial equivalence to a predicate device rather than providing specific acceptance criteria and performance data from a standalone study. Therefore, much of the requested information cannot be extracted directly from this document.

Here's what can be gathered:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly state quantitative acceptance criteria for image quality or clinical performance that the device was tested against. Instead, it relies on demonstrating that the device meets general safety and performance standards, and that its components (like digital panels) are previously cleared. The "performance" assessment is framed as "bench, safety test, and software validation documentation indicates that the new device is as safe and effective as the predicate device" and that the device "conforms to US Performance Standards" and various IEC/NEMA voluntary standards.

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

The document mentions that "Clinical images were provided," but does not specify the sample size, data provenance (e.g., country of origin), or whether they were retrospective or prospective. It explicitly states these images "were not necessary to establish substantial equivalence."

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

This information is not provided in the document. The phrase "clinical images were provided" suggests some form of evaluation but no details on expert involvement or ground truth establishment for a test set.

4. Adjudication Method:

This information is not provided in the document.

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

No MRMC comparative effectiveness study is mentioned in the document. The submission focuses on substantial equivalence based on technical characteristics and safety/performance standards, rather than a clinical trial comparing human reader performance.

6. Standalone Performance Study:

The document implies that images were used to show the "complete system works as intended," suggesting some form of standalone evaluation. However, it does not describe a formal standalone performance study with specific metrics, acceptance criteria, or a detailed methodology. The "non-clinical testing" section primarily covers integration, bench, safety, and software validation.

7. Type of Ground Truth Used:

The document does not explicitly state the type of ground truth used for any clinical image evaluation, given that the clinical images were "not necessary to establish substantial equivalence."

8. Sample Size for the Training Set:

This information is not applicable as the document describes a device (X-ray system), not an AI algorithm that would typically require a training set.

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

This information is not applicable as the document describes a device (X-ray system), not an AI algorithm.

Ask a specific question about this device

Intended for use by a qualified/trained doctor or technologist. As part of a radiographic system, the KrystalRad "New Series" is intended to acquire digital radiographic images. It is suitable for all routine radiography exams, including specialist areas like intensive care or trauma work, excluding fluoroscopy, angiography and mammography.

This device represents the combination of already cleared software and already cleared digital receptor panels. This device is a functional replacement for radiographic film. It serves as an upgrade to film based or older digital panel diagnostic x-ray systems. Digital radiography uses digital X-ray sensors instead of traditional photographic film. Advantages include time efficiency through bypassing chemical processing and the ability to digitally transfer and enhance images. Also less radiation can be used to produce an image of similar contrast to conventional radiography. This gives advantages of immediate image preview and availability; elimination of costly film processing steps; a wider dynamic range, which makes it more forgiving for over- and under-exposure; as well as the ability to apply special image processing techniques that enhance overall display of the image.

This document describes the premarket notification (510(k)) for the KrystalRad "New Series" Digital Radiographic Portable Retrofit System. The device is intended as an upgrade for radiographic film-based or older digital panel diagnostic x-ray systems.

1. Table of Acceptance Criteria and Reported Device Performance:

The provided document does not explicitly define "acceptance criteria" in a quantitative manner for performance metrics like sensitivity, specificity, or image quality scores. Instead, the demonstration of safety and effectiveness relies on establishing substantial equivalence to a predicate device (KrystalRad 660, K112132). The "acceptance criteria" in this context are primarily the absence of significant differences in technical characteristics and diagnostic quality, and compliance with relevant safety and performance standards.

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

• Sample Size for Test Set: The document states that "Clinical images were acquired and compared to our predicate images by a board certified radiologist." However, it does not specify the number of clinical images or cases used in this comparison.
• Data Provenance: The document does not explicitly state the country of origin of the data or whether it was retrospective or prospective. Given the context of a 510(k) submission to the FDA, it is highly likely that the images would have been collected in a manner compliant with US regulations, potentially from a US healthcare setting. The term "acquired" suggests prospective collection for the purpose of the comparison, but this is not definitively stated.

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

• Number of Experts: One (1) board certified radiologist.
• Qualifications of Experts: Board certified radiologist. No further details on years of experience or specific sub-specialty are provided.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable. Only one radiologist was used for comparison, so there was no need for an adjudication method. The radiologist directly compared the images from the new device to those from the predicate device.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of Human Readers Improvement with AI vs Without AI Assistance:

• MRMC Comparative Effectiveness Study: No, an MRMC comparative effectiveness study was not performed, nor was it applicable. This device is a digital X-ray panel and software system, not an AI-assisted diagnostic tool. Its purpose is to acquire and display images, not to interpret them or provide AI assistance to readers. Therefore, there is no AI component for human readers to improve with, and no effect size on human reader performance is reported.

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

• Standalone Performance Study: No, a standalone performance study in the context of an "algorithm only" or AI performance was not done, nor was it applicable. The device is a hardware and software system for image acquisition and display, not an AI algorithm. Its performance is assessed through its ability to produce diagnostically acceptable images, not through an independent algorithm's diagnostic accuracy.

7. The Type of Ground Truth Used:

• Type of Ground Truth: The "ground truth" for the clinical image comparison was established by the expert opinion (board certified radiologist), who assessed the "diagnostic quality" and "significant differences" of the images from the new device compared to the predicate device. This is a form of expert consensus, although with only one expert, it's essentially a single expert's opinion. There is no mention of pathology, outcomes data, or other objective measures for ground truth.

8. The Sample Size for the Training Set:

• Sample Size for Training Set: The document does not mention a training set in the context of machine learning or AI development. This device is a digital X-ray system, and its development process, as described, involves engineering and integration of already cleared components. No AI model training is indicated.

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 or AI model development.

Ask a specific question about this device