(178 days)
Not Found
Yes
The device description explicitly states that it is based on an "artificial intelligence analysis model, specifically a convolutional network (CNN), which employs deep learning technology to learn features from data."
No
The device is a diagnostic tool designed for triage and prioritization of medical images, not for delivering therapy.
Yes
This device analyzes chest X-ray images for the presence of specific critical findings (pleural effusion and/or pneumothorax) and provides case-level output to assist with worklist prioritization or triage, which are diagnostic support functions. While it states its results are not intended for stand-alone clinical decision-making, its core function is to identify and flag potential medical conditions, which falls under the umbrella of diagnostics.
Yes
The device is described as "software" that analyzes images and provides notifications. There is no mention of accompanying hardware components that are part of the device itself.
Based on the provided information, this device is not an In Vitro Diagnostic (IVD).
Here's why:
- IVDs analyze biological specimens: In Vitro Diagnostics are designed to examine samples taken from the human body, such as blood, urine, tissue, etc., to provide information about a person's health.
- This device analyzes medical images: The VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage analyzes chest X-ray images, which are medical images, not biological specimens.
The device falls under the category of medical image analysis software, specifically a computer-assisted triage and notification tool for radiology.
No
The input document does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device. The section "Control Plan Authorized (PCCP) and relevant text" explicitly states "Not Found".
Intended Use / Indications for Use
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is a radiological computer-assisted triage and notification software that analyzes adult chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax). VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage uses an artificial intelligence algorithm to analyze images for features suggestive of critical findings and provides case-level output available in the PACS/workstation for worklist prioritization or triage. As a passive notification for prioritization-only software tool within standard of care workflow, VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage does not send a proactive alert directly to the appropriately trained medical specialists. VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is not intended to direct attention to specific portions of an image or to anomalies other than pleural effusion and/or pneumothorax. Its results are not intended to be used on a stand-alone basis for clinical decision-making.
Product codes
QFM
Device Description
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is an automated computerassisted triage and notification software that analyzes adult chest X-ray images for the presence of pleural effusion and pneumothorax. It is based on an artificial intelligence analysis model, specifically a convolutional network (CNN), which employs deep learning technology to learn features from data.
The training data is sourced from 4 distinct sites of South Korea and India data provider, including medical imaging centers, data partners, and medical hospitals, and over 13 different modality manufacturers such as GE. Philps, FUJI, Canon, Samsung, SIEMENS, etc.
A "locked" algorithm is used, and the same input gives the same results every time. The software receives an image of a frontal chest radiograph and automatically analyzes it for the presence of pre-specified critical findings. If any findings are suspected, the image is flagged, and a passive notification is provided to the user. Subsequently, trained radiologists or healthcare professionals should make the final decision which is the standard of care at present. A user interface is provided for visualization, displaying the loaded image and any detected findings.
The data can be transmitted from Picture Archive and Communications Systems (PACS) using the DICOM protocol.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
Chest X-ray
Anatomical Site
Chest/Lung
Indicated Patient Age Range
Adult (22 years and older)
Intended User / Care Setting
Trained radiologists and healthcare professionals
Description of the training set, sample size, data source, and annotation protocol
The training data is sourced from 4 distinct sites of South Korea and India data provider, including medical imaging centers, data partners, and medical hospitals, and over 13 different modality manufacturers such as GE. Philps, FUJI, Canon, Samsung, SIEMENS, etc.
Description of the test set, sample size, data source, and annotation protocol
A total dataset of 1,200 scans for pleural effusion and 716 scans for pneumothorax were used in the test dataset to evaluate the standalone performance of VUNO Med-Chest X-ray/VUNO Med-CXR Link Triage for triaging of pleural effusion and pneumothorax, in terms of classification accuracy. The test dataset is independent of the training dataset, with each sourced from a different country.
Each scan sourced from different subjects and was obtained through a general inclusion/exclusion criterion, ensuring comprehensive subgroup representation.
The dataset for pneumothorax included 716 scans with pneumothorax and 474 scans without pneumothorax). It is sourced from various regions of the US: Midwest, West, Northeast, and South. Various demographic and medical characteristics such as gender(males and females), age(22 years and older), race/ethnicity(White. Hispanic and Latino, Black, and Asian), radiographic view position (PA and AP), and vendors(Siemens, Konica Minolta, Samsung Electronics, Canon, GE Medical Systems, Carestream Health, and Fujifilm) are considered to ensure that the device's performance is consistent across the intended population. The dataset consisted of clinical confounders that included opacities, emphysema, scarring, mediastinal widening, pleural thickening, and presence of hardware. The datasets were also obtained from diverse X-ray device vendors, such as GE, Philips, Siemens, Samsung electronics, Konica, Cannon, Fuji film, with an average exposure of 112±13 kVp (range from 49 kVp to 135 kVp) to ensure consistent performance. The ground truth was established by 3 ABR radiologists with a minimum of 5 years of experience.
Test dataset for pleural effusion included 1,200 scans with pleural effusion and 797 scans without pleural effusion) It is sourced from various regions of the US: Midwest, West, Northeast, and South. Various demographic and medical characteristics such as gender(males and females), age(22 years and older), race/ethnicity(White, Hispanic and Latino, Black, and Asian), radiographic view position (PA and AP), and vendors(Siemens, Konica Minolta, Samsung Electronics, Canon, GE Medical Systems, Carestream Health, and Fujifilm) are considered to ensure that the device's performance is consistent across the intended population. The dataset consisted of clinical confounders that included opacities, emphysema, scarring, mediastinal widening, pleural thickening, and presence of hardware. The datasets were also obtained from diverse X-ray device vendors, such as GE, Philips, Siemens, Samsung electronics, Konica, Cannon, Fuji film, with an average exposure of 112±11 kVp (range from 49 kVp to 137 kVp) to ensure consistent performance.
Summary of Performance Studies
Software Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."
Performance Testing - Clinical
The accuracy of classification performance and the timing of notification are validated through clinical tests. These tests are conducted on retrospectively collected chest X-rays to evaluate the performance of the device for triaging pneumothorax and pleural effusion. Both pneumothorax and pleural effusion exceed the acceptance criteria, with ROC AUC values of 0.95.
A total dataset of 1,200 scans for pleural effusion and 716 scans for pneumothorax were used in the test dataset to evaluate the standalone performance of VUNO Med-Chest X-ray/VUNO Med-CXR Link Triage for triaging of pleural effusion and pneumothorax, in terms of classification accuracy.
The AUC of the subject device in triaging scans with findings suspicious of pneumothorax exceeded the acceptance criteria with AUC 98.83 (95%CI, 98.15 - 99.39), Sensitivity 95.45 (92.01 - 97.71), and Specificity 96.41 (94.32 - 97.90).
The AUC of the subject device in triaging scans with findings suspicious of pleural effusion exceeded the acceptance criteria with AUC 99.00 (95%CI, 98.63 - 99.32), Sensitivity 96.53 (94.24 - 98.09), and Specificity 95.11 (93.37 - 96.50).
The subgroup analysis was performed to demonstrate the robustness of the device performance under diverse conditions. Every subgroup, age, gender, view position, dataset, and vendor outperformed the target performance.
The average time for displaying results was 10 seconds for the predicate device, and also below 10 seconds for the subject device.
Key Metrics
Pneumothorax:
AUC: 0.9883 (95% CI: [0.9815, 0.9939])
Sensitivity: 95.45 % (95% CI: [92.01, 97.71])
Specificity: 96.41% (95% CI: [94.32, 97.90])
Pleural Effusion:
AUC: 0.9900 (95% CI: [0.9863, 0.9932])
Sensitivity: 96.53% (95% CI: [94.24, 98.09])
Specificity: 95.11% (95% CI: [93.37, 96.50])
Timing of notification: The average time taken for the notification to travel from VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage to the point at which the result is displayed in the destination Picture Archiving and Communication System(PACS) or workstation/digital radiographic processing system (ex. digital radiography, digital X-ray system etc.) is below 10 seconds.
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.2080 Radiological computer aided triage and notification software.
(a)
Identification. Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
e.g., improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.
0
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA acronym and full name on the right. The Department of Health & Human Services logo features a stylized human figure, while the FDA part includes the acronym in a blue square and the full name "U.S. Food & Drug Administration" in blue text.
VUNO Inc. % Priscilla Chung RA Associate LK Consulting Group USA, Inc. 18881 Von Karman Ave STE 160 Irvine. California 92612
November 15, 2024
Re: K241439
Trade/Device Name: VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QFM Dated: May 21, 2024 Received: October 9, 2024
Dear Priscilla Chung:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
1
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510/k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change reguires premarket review. the OS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
2
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely.
Jessica Lamb
Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
3
Indications for Use
Form Approved: OMB No. 0910-0120 Expiration Date: 07/31/2026 See PRA Statement below.
Submission Number (if known)
Device Name
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage
Indications for Use (Describe)
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is a radiological computer-assisted triage and notification software that analyzes adult chest X-ray images for the presence of prespecified suspected critical findings (pleural effusion and/or pneumothorax). VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage uses an artificial intelligence algorithm to analyze images for features suggestive of critical findings and provides case-level output available in the PACS/ workstation for worklist prioritization or triage.
As a passive notification for prioritization-only software tool within standard of care workflow, VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage does not send a proactive alert directly to the appropriately trained medical specialists. VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is not intended to direct attention to specific portions of an image or to anomalies other than pleural effusion and/or pneumothorax. Its results are not intended to be used on a stand-alone basis for clinical decision-making.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
4
K241439
510(k) Summary
(K241439)
This summary of 510(k) information is being submitted in accordance with requirements of 21 CFR Part 807.92.
1. Date: 10/08/2024
2. Applicant / Submitter
VUNO Inc. 9F, 479, Gangnam-daero, Seocho-gu Seoul, 06541, Republic of Korea Tel : +82-2-515-6646 Fax : +82-2-515-6647
3. U.S. Designated Agent
Priscilla Chung LK Consulting Group USA, Inc. 18881 Von Karman Ave. STE 160 Irvine, CA 92612 Tel: 714.202.5789 Fax: 714.409.3357 Email: juhee.c@LKconsultingGroup.com
4. Trade/Proprietary Name:
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage
5. Common Name:
Radiological Computer Assisted Prioritization Software for Lesions
6. Classification:
21 CFR 892.2080 QFM (Class II) Radiological computer aided triage and notification software
7. Device Description:
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is an automated computerassisted triage and notification software that analyzes adult chest X-ray images for the presence of pleural effusion and pneumothorax. It is based on an artificial intelligence
5
analysis model, specifically a convolutional network (CNN), which employs deep learning technology to learn features from data.
The training data is sourced from 4 distinct sites of South Korea and India data provider, including medical imaging centers, data partners, and medical hospitals, and over 13 different modality manufacturers such as GE. Philps, FUJI, Canon, Samsung, SIEMENS, etc.
A "locked" algorithm is used, and the same input gives the same results every time. The software receives an image of a frontal chest radiograph and automatically analyzes it for the presence of pre-specified critical findings. If any findings are suspected, the image is flagged, and a passive notification is provided to the user. Subsequently, trained radiologists or healthcare professionals should make the final decision which is the standard of care at present. A user interface is provided for visualization, displaying the loaded image and any detected findings.
The data can be transmitted from Picture Archive and Communications Systems (PACS) using the DICOM protocol.
8. Indication for use:
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is a radiological computerassisted triage and notification software that analyzes adult chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax). VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage uses an artificial intelligence algorithm to analyze images for features suggestive of critical findings and provides caselevel output available in the PACS/workstation for worklist prioritization or triage. As a passive notification for prioritization-only software tool within standard of care workflow, VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage does not send a proactive alert directly to the appropriately trained medical specialists. VUNO Med-Chest Xray Triage/VUNO Med-CXR Link Triage is not intended to direct attention to specific portions of an image or to anomalies other than pleural effusion and/or pneumothorax. Its results are not intended to be used on a stand-alone basis for clinical decision-making.
9. Predicate Device:
qXR-PTX-PE (K230899) by Oure.ai Technologies
10. Substantial Equivalence:
Comparison Table
The subject device is substantially equivalent to the following predicate device:
- 510(k) number: K230899
- · Device name: qXR-PTX-PE
6
| Subject Device | Predicate Device | |
|---|---|---|
| Device Name | VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage | qXR-PTX-PE |
| 510(k) Number | K241439 | K230899 |
| Regulation | 21 CFR 892.2080 | 21 CFR 892.2080 |
| Regulation | ||
| Description | Radiological computer aided triage and notification software | Radiological computer aided triage and notification software |
| Product Code | QFM | QFM |
| Device Type | Radiological Computer-Assisted Prioritization Software For Lesions | Radiological Computer-Assisted Prioritization Software For Lesions |
| Manufacturer | VUNO Inc. | Qure.ai Technologies |
| Intended use/ | ||
| Indications for | ||
| Use | VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is a radiological computer-assisted triage and notification software that analyzes adult chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax). VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage uses an artificial intelligence algorithm to analyze images for features suggestive of critical findings and provides case-level output available in the PACS/workstation for worklist prioritization or triage. As a passive notification for prioritization-only software tool within standard of care workflow, VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage does not send a proactive alert directly to the appropriately trained medical specialists. VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is not intended to direct attention to specific portions of an image or to anomalies other than pleural effusion and/or pneumothorax. Its results are not intended to be used on a stand-alone basis for clinical | qXR-PTX-PE is a radiological computer-assisted triage and notification software that analyzes adult chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax). qXR-PTX-PE uses an artificial intelligence algorithm to analyze images for features suggestive of critical findings and provides case-level output available in the PACS/workstation for worklist prioritization or triage. As a passive notification for prioritization-only software tool within standard of care workflow, qXR-PTX-PE does not send a proactive alert directly to the appropriately trained medical specialists. qXR-PTXPE is not intended to direct attention to specific portions of an image or to anomalies other than pleural effusion and/or pneumothorax. Its results are not intended to be used on a standalone basis for clinical decision-making. |
| Subject Device | Predicate Device | |
| decision-making. | ||
| Intended User | Trained radiologists and healthcare | |
| professionals | Radiologists, clinicians, and other | |
| appropriately trained medical | ||
| specialists qualified to read chest | ||
| radiographs | ||
| Modality | Chest X-ray | Chest X-ray |
| Target Clinical | ||
| Conditions | Pneumothorax, Pleural effusion on | |
| Chest/Lung Frontal Chest X-rays | Pneumothorax, Pleural effusion on | |
| Chest/Lung Frontal Chest X-rays | ||
| Algorithm for | ||
| pre-specified | ||
| critical findings | ||
| detection | VUNO Med-Chest X-ray Triage/ | |
| VUNO Med-CXR Link Triage uses | ||
| an AI algorithm to detect | ||
| pneumothorax and pleural effusion | ||
| on chest X-ray images. | ||
| VUNO Med-Chest X-ray Triage/ | ||
| VUNO Med-CXR Link Triage uses | ||
| a vendor agnostic algorithm | ||
| compatible with DICOM chest X- | ||
| ray images. | qXR-PTX-PE uses an AI algorithm | |
| to detect pneumothorax and pleural | ||
| effusion on chest X-ray images. | ||
| qXR-PTX-PE uses a vendor | ||
| agnostic algorithm compatible with | ||
| DICOM | ||
| chest X-ray images. | ||
| Notification | ||
| only/ | ||
| Parallel | ||
| workflow | Yes | Yes |
| Input format | DICOM, JPG, PNG | DICOM |
| Device output in | ||
| case of positive | ||
| detection | When deployed on other | |
| radiological imaging equipment, | ||
| VUNO Med-Chest X-ray | ||
| Triage/VUNO Med-CXR Link | ||
| Triage will automatically run after | ||
| image acquisition to perform triage. | ||
| It displays the analysis result | ||
| through the worklist interface of | ||
| PACS/workstation. | ||
| No markup of the conditions will be | ||
| done on the original image. | ||
| Secondary capture of the device will | ||
| indicate the presence of findings | ||
| suspicious of pneumothorax or | ||
| pleural effusion. | ||
| Upon image acquisition from other | ||
| radiological imaging equipment | ||
| (e.g. X-ray systems) a passive | ||
| notification is generated. | When deployed on other | |
| radiological imaging equipment, | ||
| qXR-PTX-PE will automatically run | ||
| after image acquisition to perform | ||
| triage. It displays the analysis result | ||
| through the worklist interface of | ||
| PACS/workstation. | ||
| No markup of the conditions will be | ||
| done on the original image. | ||
| Secondary capture of the device will | ||
| indicate the presence of findings | ||
| suspicious of pneumothorax or | ||
| pleural effusion. | ||
| Upon image acquisition from other | ||
| radiological imaging equipment | ||
| (e.g. X-ray systems) a passive | ||
| notification is generated. | ||
| Notification | ||
| (i.e., recipient, | Passive notification. Images with | Passive notification. Images with |
| suspicion of pneumothorax and/or | suspicion of pneumothorax and/or | |
| Subject Device | Predicate Device | |
| timing and | ||
| means of | ||
| notification) | pleural effusion are flagged in | |
| PACS/workstation/DICOM viewer. | pleural effusion are flagged in | |
| PACS/workstation/DICOM viewer. | ||
| Where | ||
| generated | ||
| results(i.e., | ||
| DICOM files) | ||
| are stored | PACS/Workstation/DICOM viewer | PACS/Workstation/DICOM viewer |
| Performance | ||
| level |
- Timing of
notification | The average time taken for the
notification to travel from VUNO
Med-Chest X-ray Triage/VUNO
Med-CXR Link Triage to the point
at which the result is displayed in
the destination Picture Archiving
and Communication System(PACS)
or workstation/digital radiographic
processing system (ex. digital
radiography, digital X-ray system
etc.) is below 10 seconds. | The average time taken for the
notification to travel from qXR-
PTX-PE to the point at which the
result is displayed in the destination
Picture Archiving and
Communication System(PACS) or
workstation/digital radiographic
processing system (ex. digital
radiography, digital X-ray system
etc.) is 10 seconds. |
| Performance
level - Accuracy of
classification | Pneumothorax
ROC AUC > 0.95
AUC: 0.9883 (95% CI: [0.9815,
0.9939])
Sensitivity 95.45 % (95% CI:
[92.01, 97.71])
Specificity 96.41% (95% CI: [94.32,
97.90])
Pleural Effusion
ROC AUC > 0.95
AUC: 0.9900 (95% CI: [0.9863,
0.9932])
Sensitivity 96.53% (95% CI: [94.24,
98.09])
Specificity 95.11% (95% CI: [93.37,
96.50]) | Pneumothorax
ROC AUC > 0.95
AUC: 0.9894 (95% CI: [0.9829,
0.9980])
Sensitivity 94.53% (95% CI: [90.42,
97.24])
Specificity 96.36% (95% CI: [94.07,
97.95])
Pleural Effusion
ROC AUC > 0.95
AUC: 0.989 (95% CI: [0.9847,
0.9944])
Sensitivity 96.22% (95% CI: [93.62,
97.97])
Specificity 94.90% (95% CI: [93.04,
96.39]) |
7
8
Substantial Equivalence Discussion
The comparison table shows the description of the subject device and predicate device in each aspect. The comparison rationale and gap between the subject device and the predicate device are provided below.
- Indications for use
9
The indications for use are the same. Both are intended to detect presence of critical findings(pleural effusion and /or pneumothorax).
The intended user, modality, and target clinical condition are the same as the predicate device.
- · Algorithm for pre-specified critical findings detection Both devices use AI algorithm to detect findings. As referred to in the literature, the predicate device uses a series of convolutional neural networks(CNNs) trained to identify different abnormalities on frontal CXRs. The algorithm first resizes and normalizes CXRs to decrease variations in the acquisition process, then applies modifications in either densenet or resnet network architectures to separate CXRs from radiographs of other anatomies. Subsequently, multiple networks, including densenets and resnets, are applied for individual CXR findings.1 Similarly, the subject device uses convolutional networks(CNNs) to analyze prespecified findings. The algorithm firstly resizes and normalizes the image through a preprocessing step, then proceeds through the classification model to detect findings. The algorithm used for both predicate and subject device is equivalent, although there may be minor differences. However, the accuracy of the output is verified through performance test.
- · Notification only/Parallel workflow Both devices are used for notification/triage. The output of device is not directly used to the diagnosis, and the final decision should be performed by user. It is used parallel to the standard workflow.
- Input format
The predicate device generates DICOM format image, while the subject device generates DICOM, JPG, and PNG format.
Both devices utilize the DICOM format. which is the international standard for medical images and related information. It defines the formats for medical images that can be exchanged with the data and quality necessary for clinical use. Additionally, for use convenience, the subject device accepts JPG and PNG format. When user uploads the image, DICOM, JPG or PNG format is acceptable. This functionality is verified and validated through software testing. The input format is considered to be the equivalent.
- Device output in case of positive detection Both devices provide same output in case of positive detection. There is no markup of the conditions, and the secondary capture of result will be sent to the worklist interface of PACS or workstation. Upon image acquisition from other radiological imaging equipment (e.g. X-ray systems) a passive notification is generated.
- · Notification (i.e., recipient, timing and means of notification)
1 Parisa Kaviani, et al., Performance of a Chest Radiography AI Algorithm for Detection of Mislabeled Findings: A Multicenter Study, Diagnostics 2022, 12(9), 2086;
10
Recipient, timing and means of notification is the same between subject and predicate device.
A passive notification is provided in both devices. Images with suspicion of findings(pneumothorax and/or pleural effusion) are flagged in PACS/workstation/DICOM viewer. The performance result of notification timing is described below.
- · Where generated results(i.e., DICOM files) are stored The generated results are stored in the PACS/Workstation/DICOM viewer which is the same between the subject and predicated device.
- · Performance level Timing of notification The timing of notification performance is equivalent. The average time for displaying results was 10 seconds for the predicate device, and 7.86 seconds for the subject device.
- Performance level Accuracy of classification The accuracy of classification performance is equivalent. Both Pneumothorax and Pleural Effusion exceed ROC AUC 0.95.
Clinical studies were conducted on retrospectively collected chest X-rays to evaluate the performance of subject device for triaging of pneumothorax and pleural effusion.
The subgroup analysis was performed to demonstrate the robustness of the device performance under diverse conditions. Every subgroup, age, gender, view position, dataset, and vendor outperformed the target performance.
- · Safety
The risks associated with the use of a medical device should be established, implemented, documented, and maintained to ensure the device's safety. The risk management process complies with ISO 14971:2019. Through risk analysis, the device is determined to be safe and beneficial.
VUNO Med-Chest X-ray Triage/VUNO Med-CXR Link Triage is a radiological computerassisted triage and notification software that analyzes adult chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax). The intended use and other aspects are considered to be the same as the predicate device. However, the algorithm used for data analysis might have difference. Although both use convolutional neural networks(CNNs), which are one of the deep learning models, the detailed mechanisms are different.
Despite the minor differences, the subject device shows reliable output in the performance test. And an analysis results are not intended to be used on a stand-alone basis for clinical decisionmaking.
In conclusion, the subject device is substantially equivalent to the predicate device, and no additional risks are presented in the perspective of safety and effectiveness.
11
11. Performance Data:
Software Validation
Software Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."
Performance Testing - Clinical
The accuracy of classification performance and the timing of notification are validated through clinical tests. These tests are conducted on retrospectively collected chest X-rays to evaluate the performance of the device for triaging pneumothorax and pleural effusion. Both pneumothorax and pleural effusion exceed the acceptance criteria, with ROC AUC values of 0.95.
A total dataset of 1,200 scans for pleural effusion and 716 scans for pneumothorax were used in the test dataset to evaluate the standalone performance of VUNO Med-Chest X-ray/VUNO Med-CXR Link Triage for triaging of pleural effusion and pneumothorax, in terms of classification accuracy. The test dataset is independent of the training dataset, with each sourced from a different country.
Each scan sourced from different subjects and was obtained through a general inclusion/exclusion criterion, ensuring comprehensive subgroup representation.
The dataset for pneumothorax included 716 scans with pneumothorax and 474 scans without pneumothorax). It is sourced from various regions of the US: Midwest, West, Northeast, and South. Various demographic and medical characteristics such as gender(males and females), age(22 years and older), race/ethnicity(White. Hispanic and Latino, Black, and Asian), radiographic view position (PA and AP), and vendors(Siemens, Konica Minolta, Samsung Electronics, Canon, GE Medical Systems, Carestream Health, and Fujifilm) are considered to ensure that the device's performance is consistent across the intended population. The dataset consisted of clinical confounders that included opacities, emphysema, scarring, mediastinal widening, pleural thickening, and presence of hardware. The datasets were also obtained from diverse X-ray device vendors, such as GE, Philips, Siemens, Samsung electronics, Konica, Cannon, Fuji film, with an average exposure of 112±13 kVp (range from 49 kVp to 135 kVp) to ensure consistent performance. The predicate device has used 613 scans (201 scans with pneumothorax and 412 scans without pneumothorax) for performance testing of pneumothorax. The ground truth was established by 3 ABR radiologists with a minimum of 5 years of experience.
The AUC of the subject device in triaging scans with findings suspicious of pneumothorax exceeded the acceptance criteria with AUC 98.83 (95%CI, 98.15 - 99.39), Sensitivity 95.45 (92.01 - 97.71), and Specificity 96.41 (94.32 - 97.90).
The predicated device was reported as (AUC 98.94 (95% CI, 98.28 - 99.82)), Sensitivity 94.53 (90.42-97.24) and Specificity 96.36(94.07-97.95).
12
| AUC (95% CI) | Sensitivity (95% CI) | Specificity (95% CI) |
|---|---|---|
| 98.83 (98.15 - 99.39) | 95.45 (92.01 - 97.71) | 96.41 (94.32 - 97.90) |
The subgroup analysis was performed to demonstrate the robustness of the device performance under diverse conditions. Every subgroup, age, gender, view position, dataset, and vendor outperformed the target performance.
Test dataset for pleural effusion included 1,200 scans with pleural effusion and 797 scans without pleural effusion) It is sourced from various regions of the US: Midwest, West, Northeast, and South. Various demographic and medical characteristics such as gender(males and females), age(22 years and older), race/ethnicity(White, Hispanic and Latino, Black, and Asian), radiographic view position (PA and AP), and vendors(Siemens, Konica Minolta, Samsung Electronics, Canon, GE Medical Systems, Carestream Health, and Fujifilm) are considered to ensure that the device's performance is consistent across the intended population. The dataset consisted of clinical confounders that included opacities, emphysema, scarring, mediastinal widening, pleural thickening, and presence of hardware. The datasets were also obtained from diverse X-ray device vendors, such as GE, Philips, Siemens, Samsung electronics, Konica, Cannon, Fuji film, with an average exposure of 112±11 kVp (range from 49 kVp to 137 kVp) to ensure consistent performance. The predicate device has used 1,070 scans (344 scans with pleural effusion and 726 scans without pleural effusion) for performance testing of pleural effusion.
The AUC of the subject device in triaging scans with findings suspicious of pleural effusion exceeded the acceptance criteria with AUC 99.00 (95%CI, 98.63 - 99.32), Sensitivity 96.53 (94.24 - 98.09), and Specificity 95.11 (93.37 - 96.50).
The predicated device was reported as AUC 98.90 (98.47 -99.44)), sensitivity 96.22 (93.62-97.97) and specificity 94.90 (93.04-96.39).
| AUC (95% CI) | Sensitivity (95% CI) | Specificity (95% CI) |
|---|---|---|
| 99.00 (98.63 - 99.32) | 96.53 (94.24 - 98.09) | 95.11 (93.37 - 96.50) |
[Table 2. Overall results of classification accuracy of Pleural effusion]
The subgroup analysis was performed to demonstrate the robustness of the device performance under diverse conditions. Every subgroup, age, gender, view position, dataset, and vendor outperformed the target performance.
The average time for displaying results was 10 seconds for the predicate device, and also below 10 seconds for the subject device.
13
12. Conclusion:
The subject device is substantially equivalent in the areas of technical characteristics, general function, application, and indications for use. The new device does not introduce a fundamentally new scientific technology, and the device has been validated through performance test. Therefore, we conclude that the subject device described in this submission is substantially equivalent to the predicate device.