(196 days)
Not Found
Yes
The device description and mentions of AI, DNN, or ML explicitly state that "Lung AI" is a Computer-Aided Detection (CADe) tool that uses "Artificial intelligence, including non-adaptive machine learning algorithms" and "Supervised Deep Learning including Deep Convolutional Neural Networks".
No
The device is a Computer-Aided Detection (CADe) tool designed to assist in the detection of consolidation/atelectasis and pleural effusion. It is an adjunctive tool for diagnosis and not intended for treatment, therefore it is not a therapeutic device.
No
The document explicitly states multiple times that "Lung AI is not intended for clinical diagnosis and does not replace the healthcare provider's judgment or other diagnostic tests" and "the device does not provide a diagnosis for any disease nor replace any diagnostic testing in the standard of care." It is described as an "adjunctive tool" or "Computer-Aided Detection (CADe) tool" designed to assist in detection, not to diagnose.
Yes
The device explicitly states it is a "software device" and a "module to be integrated by another computer programmer into their legally marketed ultrasound imaging device." It functions as a "post-processing tool" and "does not include a built-in viewer," indicating it relies on existing hardware and software infrastructure rather than providing its own.
No.
This device analyzes ultrasound images, which are medical images obtained from a patient's body, not directly in vitro diagnostic samples. Its function is to assist in the detection of conditions from these images rather than performing a diagnostic test directly on a biological sample.
No
The letter does not mention FDA review, approval, or clearance of a PCCP for this specific device.
Intended Use / Indications for Use
Lung AI software device is a Computer-Aided Detection (CADe) tool designed to assist in the detection of consolidation/atelectasis and pleural effusion during the review of lung ultrasound scans.
The software is an adjunctive tool to alert users to the presence of regions of interest (ROI) with consolidation/atelectasis and pleural effusion within the analyzed lung ultrasound cine clip. Lung AI is intended to be used on images collected from the PLAPS point, in accordance with the BLUE protocol.
The intended users are healthcare professionals who are trained and qualified in performing lung ultrasound and routinely perform lung ultrasounds as part of their current practice in a point-of-care environment - namely Emergency Departments (EDs). The device was not designed and tested with use environments representing EMTs and military medics.
Lung AI is not intended for clinical diagnosis and does not replace the healthcare provider's judgment or other diagnostic tests in the standard care for lung ultrasound findings. All cases where a Chest CT scan and/or Chest X-ray is part of the standard of care should undergo these imaging procedures, irrespective of the device output.
The software is indicated for adults only.
Product codes (comma separated list FDA assigned to the subject device)
MYN
Device Description
Lung AI is a Computer-Aided Detection (CADe) tool designed to assist in the analysis of lung ultrasound images by suggesting the presence of consolidation/atelectasis and pleural effusion in a scan. This adjunctive tool is intended to aid users to detect the presence of regions of interest (ROI) with consolidation/atelectasis and pleural effusion. However, the device does not provide a diagnosis for any disease nor replace any diagnostic testing in the standard of care.
The lung AI module processes Ultrasound cine clips and flags any evidence of pleural effusion and/or consolidation/atelectasis present without aggregating data across regions or making any patient-level decisions. For positive cases, a single ROI per clip from a frame with the largest pleural effusion (or consolidation/atelectasis) is generated as part of the device output. Moreover, the ROI output is for visualization only and should not be relied on for precise anatomical localization. The final decision regarding the overall assessment of the information from all regions/clips remains the responsibility of the user. Lung AI is intended to be used on clips collected only from the PLAPS point, in accordance with the BLUE protocol.
Lung AI is developed as a module to be integrated by another computer programmer into their legally marketed ultrasound imaging device. The software integrates with third-party ultrasound imaging devices and functions as a post-processing tool. The software does not include a built-in viewer; instead, it works within the existing third-party device interface.
Lung AI is validated to meet applicable safety and efficacy requirements and to be generalizable to image data sourced from ultrasound transducers of a specific frequency range.
The device is intended to be used on images of adult patients undergoing point-of-care (POC) lung ultrasound scans in the emergency departments due to suspicion of pleural effusion and/or consolidation/atelectasis. It is important to note that patient management decisions should not be made solely on the results of the Lung AI analysis.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
Ultrasound
Anatomical Site
Lung
Indicated Patient Age Range
Adults only.
Intended User / Care Setting
healthcare professionals who are trained and qualified in performing lung ultrasound and routinely perform lung ultrasounds as part of their current practice in a point-of-care environment - namely Emergency Departments (EDs).
Description of the training set, sample size, data source, and annotation protocol
The underlying deep learning models were trained on a diverse dataset of 3,453 ultrasound cine clips from 1,036 patients across Canada, the U.S., and South America. This dataset includes common pathologies encountered in point-of-care settings, such as emergency departments and ICUs. The clinical confounders in the development set include cases of Pneumonia, Pulmonary Embolism, Congestive Heart Failure (CHF), Tamponade, Covid19, ARDS, and COPD. The ultrasound manufacturers included SonoSite, Philips Lumify, GE, Mindray, Clarius, Exo and Butterfly.
Description of the test set, sample size, data source, and annotation protocol
The standalone performance of the Lung AI device was successfully evaluated on test data encompassing diverse demographic variables, including gender, age (ranging from 21 to 96), and ethnicity from multiple clinical sites in metropolitan cities with diverse racial patient populations. To ensure unbiased data, cases were selected consecutively in the order they were received. The dataset was then enriched with abnormal cases (to have at least 30% abnormal cases per center) to ensure sufficient representation of clinically relevant conditions in line with FDA guidelines.
465 lung scans from 359 unique patients were retrospectively collected from 6 imaging centers in the U.S. and Canada, with more than 50% of the data coming from U.S. centers. There were 239 positive and 226 negative cases for pleural effusion. There were 247 positive and 218 negative cases for consolidation/atelectasis. Adjustments were made to account for intra-subject correlation in calculating confidence intervals.
The presence of consolidation, atelectasis, and pleural effusion was evaluated in subjects with images acquired during routine clinical practice using cart-based and portable ultrasound devices (with frequencies ranging from 1.5 to 7 MHz).
The reference standard was established by two US board-certified experts, experienced in point-of-care ultrasound, reading lung ultrasound scans and diagnostic radiology. The experts indicated their independent assessment of the presence/absence of each indication per cine clip. Adjudication, in case of disagreement, was provided by a third expert.
The experts also provided annotations for the bounding boxes to evaluate localization accuracy.
The test data was entirely separated from the training/validation datasets and was not used for any part of the training.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Bench Testing (Standalone Performance):
- Sample Size: 465 lung scans from 359 unique patients.
- Data Source: Retrospectively collected from 6 imaging centers in the U.S. and Canada.
- Reference Standard: Two US board-certified experts, experienced in point-of-care ultrasound, with a third expert for adjudication.
- Key Results (Detection Performance):
- Pleural Effusion: Se = 0.97 (95% CI 0.94 – 0.99), Sp = 0.91 (95% CI 0.87 – 0.96)
- Consolidation / Atelectasis: Se = 0.97 (95% CI 0.94 – 0.99), Sp = 0.94 (95% CI 0.90 – 0.98)
- Key Results (Localization Performance):
- Pleural Effusion: Se = 0.85 (95% CI 0.80 – 0.89), Sp = 0.91 (95% CI 0.87 – 0.96)
- Consolidation / Atelectasis: Se = 0.86 (95% CI 0.81 – 0.90), Sp = 0.94 (95% CI 0.90 – 0.98)
- Subgroup Analysis: Performance was consistent across a wide range of ultrasound device manufacturers (Sonosite, Exo, Philips) and demographic subgroups (gender, age, sites, confounders: pneumonia, CHF, Covid 19, ARDS, pulmonary edema, pulmonary embolism, tachypnea, COPD), as well as scan laterality and different depths.
Multi-Reader, Multi-Case (MRMC) Study:
- Study Type: MRMC study with 6 readers (emergency physicians).
- Sample Size: 322 unique patients, 748 cases analyzed per reader (total 4488 cases).
- Reading Periods: Two reading periods ("unaided" and "aided") separated by a minimum 4-week washout period.
- Primary Endpoint: Improvement of at least 2% in overall reader performance, as measured by AUC-ROC, when aided by the device.
- Key Results (Pleural Effusion):
- AUC-ROC: AUC_unaided = 0.93 (95% CI .92 - .94) improved to AUC_aided = 0.96 (95% CI .95 - .98). ΔAUC-PLEFF = 0.035 (95% CI .025 – .047).
- Sensitivity (Se): Se_unaided = 0.71 (95% CI .68 – .75) improved to Se_aided = 0.88 (95% CI .86 – .92). ΔSe-PLEFF = 0.18 (95% CI .14 – .20).
- Specificity (Sp): Sp_unaided = 0.96 (95% CI .95 – .97) slightly decreased to Sp_aided = 0.93 (95% CI .88 – .95). ΔSp-CONS = -0.03 (95% CI -.08 to -.02).
- Key Results (Consolidation/Atelectasis):
- AUC-ROC: AUC_unaided = 0.92 (95% CI .91 - .96) improved to AUC_aided = 0.95 (95% CI .94 - .98). ΔAUC-CONS = 0.028 (95% CI .0201 – .0403).
- Sensitivity (Se): Se_unaided = 0.73 (95% CI .72 – .80) improved to Se_aided = 0.89 (95% CI .88 – .93). ΔSp-CONS = 0.16 (95% CI .13 – .19).
- Specificity (Sp): Sp_unaided = 0.92 (95% CI .88 – .93) slightly decreased to Sp_aided = 0.91 (95% CI .87 – .93). ΔSp-CONS = -0.008 (95% CI -.01 to -.005).
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Standalone Performance (Detection Performance Metric):
- Pleural Effusion: Se = 0.97 (95% CI 0.94 – 0.99), Sp = 0.91 (95% CI 0.87 – 0.96)
- Consolidation / Atelectasis: Se = 0.97 (95% CI 0.94 – 0.99), Sp = 0.94 (95% CI 0.90 – 0.98)
Standalone Performance (Localization Performance Metric):
- Pleural Effusion: Se = 0.85 (95% CI 0.80 – 0.89), Sp = 0.91 (95% CI 0.87 – 0.96)
- Consolidation / Atelectasis: Se = 0.86 (95% CI 0.81 – 0.90), Sp = 0.94 (95% CI 0.90 – 0.98)
MRMC Results (Pleural Effusion):
- AUC-ROC: AUC unaided = 0.93 (95% CI .92 - .94), AUC aided = 0.96 (95% CI .95 - .98), ΔAUC-PLEFF = 0.035 (95% CI .025 – .047)
- Sensitivity (Se): Se unaided = 0.71 (95% CI .68 – .75), Se aided = 0.88 (95% CI .86 – .92), ΔSe-PLEFF = 0.18 (95% CI .14 – .20)
- Specificity (Sp): Sp unaided = 0.96 (95% CI .95 – .97), Sp aided = 0.93 (95% CI .88 – .95), ΔSp-CONS = -0.03 (95% CI -.08 to -.02)
MRMC Results (Consolidation/Atelectasis):
- AUC-ROC: AUC unaided = 0.92 (95% CI .91 - .96), AUC aided = 0.95 (95% CI .94 - .98), ΔAUC-CONS = 0.028 (95% CI .0201 – .0403)
- Sensitivity (Se): Se unaided = 0.73 (95% CI .72 – .80), Se aided = 0.89 (95% CI .88 – .93), ΔSp-CONS = 0.16 (95% CI .13 – .19)
- Specificity (Sp): Sp unaided = 0.92 (95% CI .88 – .93), Sp aided = 0.91 (95% CI .87 – .93), ΔSp-CONS = -0.008 (95% CI -.01 to -.005)
Predicate Device(s): If the device was cleared using the 510(k) pathway, identify the Predicate Device(s) K/DEN number used to claim substantial equivalence and list them here in a comma separated list exactly as they appear in the text. List the primary predicate first in the list.
Reference Device(s): Identify the Reference Device(s) K/DEN number and list them here in a comma separated list exactly as they appear in the text.
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information for the subject device only (e.g. presence / absence, what scope was granted / cleared under the PCCP, any restrictions, etc).
Not Found
§ 892.2070 Medical image analyzer.
(a)
Identification. Medical image analyzers, including computer-assisted/aided detection (CADe) devices for mammography breast cancer, ultrasound breast lesions, radiograph lung nodules, and radiograph dental caries detection, is a prescription device that is intended to identify, mark, highlight, or in any other manner direct the clinicians' attention to portions of a radiology image that may reveal abnormalities during interpretation of patient radiology images by the clinicians. This device incorporates pattern recognition and data analysis capabilities and operates on previously acquired medical images. This device is not intended to replace the review by a qualified radiologist, and is not intended to be used for triage, or to recommend diagnosis.(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 image analysis algorithms including a description of the algorithm inputs and outputs, each major component or block, and algorithm limitations.
(ii) A detailed description of pre-specified performance testing methods and dataset(s) used to assess whether the device will improve reader performance as intended and to characterize the standalone device performance. Performance testing includes one or more standalone tests, side-by-side comparisons, or a reader study, as applicable.
(iii) Results from performance testing that demonstrate that the device improves reader performance in the intended use population when used in accordance with the instructions for use. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, predictive value, and diagnostic likelihood ratio). The test dataset must contain a sufficient number of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals of the device for these individual subsets can be characterized for the intended use population and imaging equipment.(iv) 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; and cybersecurity).(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 reading protocol.
(iii) A detailed description of the intended user and user training that addresses appropriate reading protocols for the device.
(iv) A detailed description of the device inputs and outputs.
(v) A detailed description of compatible imaging hardware and imaging protocols.
(vi) 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 or for certain subpopulations), as applicable.(vii) Device operating instructions.
(viii) A detailed summary of the performance testing, including: test methods, dataset characteristics, results, and a summary of sub-analyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.
FDA 510(k) Clearance Letter - Lung AI (LAI001)
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.07.05
April 24, 2025
Exo Inc.
Jacqueline Murray
Senior Regulatory Affairs Specialist
4201 Burton Drive
Santa Clara, California 95054
Re: K243239
Trade/Device Name: Lung AI (LAI001)
Regulation Number: 21 CFR 892.2070
Regulation Name: Medical image analyzer
Regulatory Class: Class II
Product Code: MYN
Dated: October 10, 2024
Received: March 21, 2025
Dear Jacqueline Murray:
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 (the 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.
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"
Page 2
K243239 - Jacqueline Murray Page 2
(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 requires premarket review, the QS 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 (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-reporting-combination-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-devices/device-advice-comprehensive-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-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/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-devices/device-advice-comprehensive-regulatory-
Page 3
K243239 - Jacqueline Murray Page 3
assistance/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, 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
Page 4
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
510(k) Number (if known): K243239
Device Name: Lung AI (LAI001)
Indications for Use (Describe)
Lung AI software device is a Computer-Aided Detection (CADe) tool designed to assist in the detection of consolidation/atelectasis and pleural effusion during the review of lung ultrasound scans.
The software is an adjunctive tool to alert users to the presence of regions of interest (ROI) with consolidation/atelectasis and pleural effusion within the analyzed lung ultrasound cine clip.
Lung AI is intended to be used on images collected from the PLAPS point, in accordance with the BLUE protocol.
The intended users are healthcare professionals who are trained and qualified in performing lung ultrasound and routinely perform lung ultrasounds as part of their current practice in a point-of-care environment—namely Emergency Departments (EDs). The device was not designed and tested with use environments representing EMTs and military medics.
Lung AI is not intended for clinical diagnosis and does not replace the healthcare provider's judgment or other diagnostic tests in the standard care for lung ultrasound findings. All cases where a Chest CT scan and/or Chest X-ray is part of the standard of care should undergo these imaging procedures, irrespective of the device output.
The software is indicated for adults only.
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."
FORM FDA 3881 (8/23) Page 1 of 1 PSC Publishing Services (301) 443-6740 EF
Page 5
510(k) Summary - Lung AI
General Information
| 510(k) Sponsor | Exo Inc. |
|---|---|
| Address | 4201 Burton Drive |
| Santa Clara, CA 95054 | |
| Correspondence Person | Jacqueline Murray |
| Contact Information | jmurray@exo.inc |
| Cell: +1 236-838-5056 | |
| Date Prepared | April 24th 2025 |
Proposed Device
| Proprietary Name | Lung AI (LAI001) |
|---|---|
| Common Name | Lung AI |
| Classification Name | Medical Image Analyzer |
| Regulation Number | 21 CFR 892.2070 |
| Product Code | MYN |
| Regulatory Class | II |
Predicate Device
| Proprietary Name | Lung-CAD |
|---|---|
| Premarket Notification | K230085 |
| Classification Name | Medical Image Analyzer |
| Regulation Number | 21 CFR 892.2070 |
| Product Code | MYN |
| Regulatory Class | II |
Device description
Lung AI is a Computer-Aided Detection (CADe) tool designed to assist in the analysis of lung ultrasound images by suggesting the presence of consolidation/atelectasis and pleural effusion in a scan. This adjunctive tool is intended to aid users to detect the presence of regions of interest (ROI) with consolidation/atelectasis and pleural effusion. However, the device does not provide a diagnosis for any disease nor replace any diagnostic testing in the standard of care.
Page 1 of 7
Page 6
The lung AI module processes Ultrasound cine clips and flags any evidence of pleural effusion and/or consolidation/atelectasis present without aggregating data across regions or making any patient-level decisions. For positive cases, a single ROI per clip from a frame with the largest pleural effusion (or consolidation/atelectasis) is generated as part of the device output. Moreover, the ROI output is for visualization only and should not be relied on for precise anatomical localization. The final decision regarding the overall assessment of the information from all regions/clips remains the responsibility of the user. Lung AI is intended to be used on clips collected only from the PLAPS point, in accordance with the BLUE protocol.
Lung AI is developed as a module to be integrated by another computer programmer into their legally marketed ultrasound imaging device. The software integrates with third-party ultrasound imaging devices and functions as a post-processing tool. The software does not include a built-in viewer; instead, it works within the existing third-party device interface.
Lung AI is validated to meet applicable safety and efficacy requirements and to be generalizable to image data sourced from ultrasound transducers of a specific frequency range.
The device is intended to be used on images of adult patients undergoing point-of-care (POC) lung ultrasound scans in the emergency departments due to suspicion of pleural effusion and/or consolidation/atelectasis. It is important to note that patient management decisions should not be made solely on the results of the Lung AI analysis.
The underlying deep learning models were trained on a diverse dataset of 3,453 ultrasound cine clips from 1,036 patients across Canada, the U.S., and South America. This dataset includes common pathologies encountered in point-of-care settings, such as emergency departments and ICUs. The clinical confounders in the development set include cases of Pneumonia, Pulmonary Embolism, Congestive Heart Failure (CHF), Tamponade, Covid19, ARDS, and COPD. The ultrasound manufacturers included SonoSite, Philips Lumify, GE, Mindray, Clarius, Exo and Butterfly.
Indications for Use
Lung AI software device is a Computer-Aided Detection (CADe) tool designed to assist in the detection of consolidation/atelectasis and pleural effusion during the review of lung ultrasound scans.
The software is an adjunctive tool to alert users to the presence of regions of interest (ROI) with consolidation/atelectasis and pleural effusion within the analyzed lung ultrasound cine clip. Lung AI is intended to be used on images collected from the PLAPS point, in accordance with the BLUE protocol.
The intended users are healthcare professionals who are trained and qualified in performing lung ultrasound and routinely perform lung ultrasounds as part of their current practice in a point-of-care environment - namely Emergency Departments (EDs). The device was not designed and tested with use
Page 2 of 7
Page 7
environments representing EMTs and military medics.
Lung AI is not intended for clinical diagnosis and does not replace the healthcare provider's judgment or other diagnostic tests in the standard care for lung ultrasound findings. All cases where a Chest CT scan and/or Chest X-ray is part of the standard of care should undergo these imaging procedures, irrespective of the device output.
The software is indicated for adults only.
Comparison of Technological Characteristics with the Predicate Device
| Feature/ Function | Subject Device: Lung AI | Predicate Device Lung-CAD by Imagen Technologies (K230085) |
|---|---|---|
| Image Modality | Ultrasound | Digital X-ray |
| Study Type | Chest | Chest |
| Scan type | Multi-frame ultrasound images | Digital X-ray images |
| Clinical Output | Identify and mark regions of interest (ROIs) on lung Ultrasound | Identify and mark regions of interest (ROIs) on chest radiographs and label the box around the ROI as lung hyperinflation |
| Intended User Workflow | Device is intended for use as a concurrent reading aid for trained healthcare professionals qualified in interpreting lung ultrasounds | Device intended for use as a concurrent reading aid for physicians interpreting chest radiographs |
| Patient Population | Adults | Adults |
| Principle of Operation and Technology | Artificial intelligence, including non-adaptive machine learning algorithms trained with clinical data | Artificial intelligence |
Page 3 of 7
Page 8
| AI Algorithm | Supervised Deep Learning including Deep Convolutional Neural Networks for Segmentation, Landmark Detection and Classification | Supervised Deep Learning |
|---|---|---|
| Intended Users | Trained healthcare professionals | Physicians |
Performance Data
The safety and performance of the Lung AI device has been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing. Additionally, the software validation activities were performed in accordance with IEC 62304:2006/AC:2015 - Medical device software – Software life cycle processes, and the following FDA guidences:
- Content of Premarket Submissions for Device Software Functions, Guidance for Industry and Food and Drug Administration Staff
- Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data Premarket Notification [510(k)] Submissions
- Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data in Premarket Notification (510(k)) Submissions.
- Cybersecurity testing was performed in accordance with Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions.
Bench Testing
The standalone performance of the Lung AI device was successfully evaluated on test data encompassing diverse demographic variables, including gender, age (ranging from 21 to 96), and ethnicity from multiple clinical sites in metropolitan cities with diverse racial patient populations. To ensure unbiased data, cases were selected consecutively in the order they were received. The dataset was then enriched with abnormal cases (to have at least 30% abnormal cases per center) to ensure sufficient representation of clinically relevant conditions in line with FDA guidelines.
465 lung scans from 359 unique patients were retrospectively collected from 6 imaging centers in the U.S. and Canada, with more than 50% of the data coming from U.S. centers. There were 239 positive and 226 negative cases for pleural effusion. There were 247 positive and 218 negative cases for consolidation/atelectasis. Adjustments were made to account for intra-subject correlation in calculating confidence intervals.
Page 4 of 7
Page 9
The presence of consolidation, atelectasis, and pleural effusion was evaluated in subjects with images acquired during routine clinical practice using cart-based and portable ultrasound devices (with frequencies ranging from 1.5 to 7 MHz).
The reference standard was established by two US board-certified experts, experienced in point-of-care ultrasound, reading lung ultrasound scans and diagnostic radiology. The experts indicated their independent assessment of the presence/absence of each indication per cine clip. Adjudication, in case of disagreement, was provided by a third expert.
The experts also provided annotations for the bounding boxes to evaluate localization accuracy.
The test data was entirely separated from the training/validation datasets and was not used for any part of the training.
The performance of Lung AI for consolidation/atelectasis and pleural effusion suggestions when compared to reference data is summarized in Table 1 below:
Table 1. Summary of Lung AI performance
| Lung Finding | Detection Performance Metric |
|---|---|
| Pleural Effusion | Se = 0.97 (95% CI 0.94 – 0.99) |
| Sp = 0.91 (95% CI 0.87 – 0.96) | |
| Consolidation / Atelectasis | Se = 0.97 (95% CI 0.94 – 0.99) |
| Sp = 0.94 (95% CI 0.90 – 0.98) |
The localization performance of the Lung AI is assessed using sensitivity and specificity, along with their corresponding confidence intervals, based on the IoU overlap between the device (AI-ROI) and the ground truth (GT-ROI). True positive is when a predicted bounding box (AI-ROI) has an IoU ≥ 0.5 with the GT-ROI. The localization performance of Lung AI is summarized in Table 2 below:
Table 2. Summary of Lung AI localization performance
| Lung Finding | Localization Performance Metric |
|---|---|
| Pleural Effusion | Se = 0.85 (95% CI 0.80 – 0.89) |
| Sp = 0.91 (95% CI 0.87 – 0.96) | |
| Consolidation / Atelectasis | Se = 0.86 (95% CI 0.81 – 0.90) |
| Sp = 0.94 (95% CI 0.90 – 0.98) |
Page 5 of 7
Page 10
The device performance was also assessed across a wide range of ultrasound device manufacturers (including Sonosite, Exo and Philips) and demographic subgroups (gender, age, sites, confounders). The confounders included pneumonia, CHF, Covid 19, ARDS, pulmonary edema, pulmonary embolism, tachypnea, COPD). Additional subgroup analysis included scan laterality (right vs left PLAPs view) and different depths of lung scans. The evaluation concluded that the device's performance was consistent among clinically meaningful subgroups. A detailed subgroup analysis is reported in the labelling.
MULTI-READER, MULTI-CASE (MRMC) STUDY
Lung AI has been validated by a multi-reader, multi-case (MRMC) study. The study consisted of 6 readers with varying levels of training and experience as emergency physicians, who provided analysis on a randomized set of 322 unique patients, presented in two reading periods ("unaided" and "aided") and separated by a minimum 4-week washout period. In total, 748 cases were analyzed per reader for a total of 4488 cases overall.
The primary endpoint was an improvement of at least 2% in overall reader performance, as measured by AUC-ROC, when aided by the device. This study successfully met the acceptance criteria for the detection of consolidation/atelectasis and pleural effusion and fulfilled the design requirements for Lung AI. A summary of the MRMC results is presented below:
Pleural Effusion MRMC results
AUC-ROC: The MRMC analysis for detection of pleural effusion shows AUC_unaided = 0.93 (95% CI .92 - .94) is improved to AUC_aided = 0.96 (95% CI .95 - .98) with a AUC improvement of ΔAUC-PLEFF = AUCaided - AUCunaided = 0.035 (95% CI .025 – .047), which passes the acceptance criteria.
Sensitivity (Se): The MRMC analysis for detection of pleural effusion shows Se_unaided = 0.71 (95% CI .68 – .75) is significantly improved to Se_aided = 0.88 (95% CI .86 – .92) with a Se improvement of ΔSe-PLEFF = Seaided - Seunaided = 0.18 (95% CI .14 – .20)
Specificity (Sp): The MRMC analysis for detection of pleural effusion shows Sp_unaided = 0.96 (95% CI .95 – .97) is slightly decreased to Sp_aided = 0.93 (95% CI .88 – .95) with ΔSp-CONS = Spaided - Spunaided = -0.03 (95% CI -.08 to -.02)
Consolidation/atelectasis MRMC results:
AUC-ROC: The MRMC analysis for detection of consolidation shows AUC_unaided = 0.92 (95% CI .91 - .96) is improved to AUC_aided = 0.95 (95% CI .94 - .98) with a AUC improvement of ΔAUC-CONS = AUCaided - AUCunaided = 0.028 (95% CI .0201 – .0403), which passes the acceptance criteria.
Sensitivity (Se): The MRMC analysis for detection of consolidation shows Se_unaided = 0.73 (95% CI .72 – .80) is improved to Se_aided = 0.89 (95% CI .88 – .93) with a significant Se improvement of ΔSp-CONS = Seaided - Seunaided = 0.16 (95% CI .13 – .19)
Page 6 of 7
Page 11
Specificity (Sp): The MRMC analysis for detection of consolidation shows Sp_unaided = 0.92 (95% CI .88 – .93) is slightly decreased to Sp_aided = 0.91 (95% CI .87 – .93) with ΔSp-CONS = Spaided - Spunaided = -0.008 (95% CI -.01 to -.005)
Conclusions
Exo's Lung AI is substantially equivalent in intended use and technological characteristics to the predicate device as demonstrated by the conclusions drawn from the standalone and clinical studies. There are no different questions of safety and/or effectiveness introduced by Lung AI when used as intended.
Page 7 of 7