(214 days)
Not Found
Yes
The document explicitly states that the device "analyze radiographs using machine learning techniques" and that the radiographs are "automatically processed by the AI algorithm".
No
The device is intended to analyze radiographs and highlight fractures as a reading aid, which is a diagnostic function, not a therapeutic one.
Yes
BoneView is intended to "identify and highlight fractures," and its purpose is to "aid during the interpretations of radiographs" that allows users to "provide their diagnosis." Identifying and highlighting fractures and aiding in interpretations for diagnosis directly relates to making a medical diagnosis.
Yes
The device description explicitly states that BoneView is intended to analyze radiographs using machine learning techniques and can be deployed on-premises or on cloud, connecting to existing computing and imaging platforms (PACS, X-ray systems). It processes DICOM images and generates DICOM result files. There is no mention of any proprietary hardware component being part of the device itself; it functions as software interacting with existing medical imaging infrastructure.
Based on the provided information, BoneView is not an In Vitro Diagnostic (IVD).
Here's why:
- IVDs analyze specimens from the human body. The core function of an IVD is to examine biological samples like blood, urine, tissue, etc., to provide information about a person's health.
- BoneView analyzes medical images. BoneView's intended use is to analyze radiographs (X-ray images), which are not biological specimens. It processes visual data, not biological samples.
- The intended use is image analysis for fracture identification. The description clearly states that BoneView analyzes radiographs to identify and highlight fractures. This is a function related to medical imaging interpretation, not in vitro testing.
Therefore, BoneView falls under the category of a medical device that processes and analyzes medical images, rather than an In Vitro Diagnostic device.
No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
BoneView is intended to analyze radiographs using machine learning techniques to identify and highlight fractures during the review of radiographs of:
| Study Type (Anatomical Area of Interest) | Compatible Radiographic View(s) |
|---|---|
| Ankle | Frontal, Lateral, Oblique |
| Foot | Frontal, Lateral, Oblique |
| Knee | Frontal, Lateral |
| Tibia/Fibula | Frontal, Lateral |
| Femur | Frontal, Lateral |
| Wrist | Frontal, Lateral, Oblique |
| Hand | Frontal, Oblique |
| Elbow | Frontal, Lateral |
| Forearm | Frontal, Lateral |
| Humerus | Frontal, Lateral |
| Shoulder | Frontal, Lateral, Axillary |
| Clavicle | Frontal |
| Pelvis | Frontal |
| Hip | Frontal, Frog Leg Lateral |
| Ribs | Frontal Chest, Rib series |
| Thoracic Spine | Frontal, Lateral |
| Lumbosacral Spine | Frontal, Lateral |
BoneView is intended for use as a concurrent reading aid during the interpretations of radiographs. BoneView is for prescription use only and is indicated for adults only.
Product codes (comma separated list FDA assigned to the subject device)
QBS
Device Description
BoneView is intended to analyze radiographs using machine learning techniques to identify and highlight fractures during the review of radiographs.
BoneView can be deployed on-premises or on cloud and be connected to several computing platforms and X-ray imaging platforms such as X-ray radiographic systems, or PACS. More precisely, BoneView can be deployed:
- In the cloud with a PACS as the DICOM Source
- On-premises with a PACS as the DICOM Source
- On-premises with an X-ray system as the DICOM Source
It is important to note that no matter the deployment mode that is chosen for BoneView, the overall principle of use of BoneView and its user interface remain the same; only the place where BoneView is housed, and the DICOM Source/DICOM Destination with which BoneView communicates, may vary. Below is a description of the data flow.
After the acquisition of the radiographs on the patient and their storage in the DICOM Source, the radiographs are automatically received by BoneView from the user's DICOM Source through an intermediate DICOM node (for example, a specific Gateway, or a dedicated API). The DICOM Source can be the user's image storage system (for example, the Picture Archiving and Communication System, or PACS), or other radiological equipment (for example X-ray systems).
Once received by BoneView, the radiographs are automatically processed by the AI algorithm to identify regions of interest. Based on the processing result, BoneView generates result files in DICOM format. These result files consist of a summary table and result images (annotations on a copy of the original images or annotations to be toggled on/off). BoneView does not alter the original images, nor does it change the order of original images or delete any image from the DICOM Source.
Once available, the result files are sent by BoneView to the DICOM Destination through the same intermediate DICOM node. Similar to the DICOM Source, the DICOM Destination can be the user's image storage system (for example, the Picture Archiving and Communication System, or PACS), or other radiological equipment (for example X-ray systems). The DICOM Source and the DICOM Destination are not necessarily identical.
The DICOM Destination can be used to visualize the result files provided by BoneView or to transfer the results to another DICOM host for visualization. The users are then able to use them as a concurrent reading aid to provide their diagnosis.
The general layout of images processed by BoneView is comprising:
(1) The "summary table" – it is a first image that is derived from the detected regions of interest in the following result images and that displays the results of the overall study along with the Gleamer – BoneView logo. This summary can be configured to be present or not.
(2) The result images – they are provided for all the images that were processed by BoneView and contain:
- Around the Regions of Interest (if any), a rectangle with a solid or dotted line depending on the confidence of the algorithm (see below)
- Around the entire image, a white frame showing that the images were processed by BoneView
- Below the image:
- The Gleamer BoneView logo
- The number of Regions of interest that are displayed in the result image
- (if any) The caution message if it was identified that the image was not part of the indication for use of BoneView
The training of BoneView was performed on a training dataset of 44,649 radiographs, representing 151,096 images (52.4% of males, with age: range [0 – 109]; mean 42.4 +/- 24.6) for all anatomical areas of interest in the Indications for Use and from various manufacturers. BoneView has been designed to solve the problem of missed fractures including subtle fractures, and thus detects fractures with a high sensitivity. In this regard, the display of findings is triggered by a "high-sensitivity operating point" (DOUBT FRACT) that will enable the display of a dotted-line bounding box around the region of interest. Additionally, the users need to be confident that when BoneView identifies a fracture, it is actually a fracture. In this regard, an additional information is introduced to the user with a "high-specificity operating point" (FRACT).
These two operating points are implemented in the User Interface as follow:
- Dotted-line Bounding Box: suspicious area / subtle fracture (when the level of confidence of the Al algorithm associated with the finding is above "high-sensitivity operating point" and below "high-specificity operating point") displayed as a dotted bounding box around the area of interest
- Solid-line Bounding Box: definite or unequivocal fractures (when the level of confidence of the AI algorithm associated with the finding is above "high-specificity operating point") displayed as a solid bounding box around the area of interest
BoneView can provide 4 levels of results: - FRACT: BoneView identified at least one solid-line bounding box on the result images,
- DOUBT FRACT: BoneView did not identify any solid-line bounding box on the result images but it identified at least one dotted-line bounding box in the result images,
- NO FRACT: BoneView did not identify any bounding box at all in the result images,
- NOT AVAILABLE: BoneView identified that the original images are out of its Indications for Use
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
2D X-ray Images
Anatomical Site
Ankle, Foot, Knee, Tibia/Fibula, Femur, Wrist, Hand, Elbow, Forearm, Humerus, Shoulder, Clavicle, Pelvis, Hip, Ribs, Thoracic Spine, Lumbosacral Spine
Indicated Patient Age Range
adults only (greater than 21 years of age)
Intended User / Care Setting
The intended users of BoneView are clinicians with the authority to diagnose fractures in various settings including primary care (e. g., family practice, internal medicine), emergency medicine, urgent care, and specialty care (e. g. orthopedics), as well as radiologists who review radiographs across settings.
Description of the training set, sample size, data source, and annotation protocol
The training of BoneView was performed on a training dataset of 44,649 radiographs, representing 151,096 images (52.4% of males, with age: range [0 – 109]; mean 42.4 +/- 24.6) for all anatomical areas of interest in the Indications for Use and from various manufacturers.
Description of the test set, sample size, data source, and annotation protocol
Standalone performance testing on a dataset of 8,918 radiographs (47.2% of males, with age: range [21 – 113]; mean 52.5 +/- 19.8) for all anatomical areas of interest in the Indications for Use and from various manufacturers (Agfa, Fujifilm, GE Healthcare, Kodak, Konica Minolta, Philips, Primax, Samsung, Siemens). This dataset was independent of the data used for model training, and establishment of device operating points.
Clinical validation study: 24 clinical readers each evaluated a dataset of 480 cases (31.9% of males, with age: range [21 – 93]: mean 59.2 +/- 16.4) in BoneView's Indications for Use and from various manufacturers (GE Healthcare, Kodak, Konica Minolta, Philips, Samsung). This dataset was independent of the data used for model training, and establishment of device operating points. Each case had been previously evaluated by a panel of three U.S. board-certified radiologists who assigned a ground truth label indicating the presence or absence of a fracture and its location.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Bench Testing (Standalone Performance Testing):
- Sample Size: 8,918 radiographs (47.2% of males, with age: range [21 – 113]; mean 52.5 +/- 19.8)
- Key Results:
- Global (n(positive)= 3,886, n(negative)= 5,032):
- High-sensitivity operating point: Specificity = 0.811 [0.8 - 0.821], Sensitivity = 0.928 [0.919 - 0.936]
- High-specificity operating point: Specificity = 0.932 [0.925 - 0.939], Sensitivity = 0.841 [0.829 - 0.853]
- Subgroup analysis by anatomical areas of interest also showed varying specificity and sensitivity values for both operating points.
- Global (n(positive)= 3,886, n(negative)= 5,032):
Clinical Studies (MRMC Retrospective Reader Study):
- Sample Size: 24 clinical readers, 480 cases (31.9% of males, with age: range [21 – 93]: mean 59.2 +/- 16.4)
- Study Type: Fully-crossed multiple reader, multiple case (MRMC) retrospective reader study.
- Key Results: The diagnostic accuracy of readers aided by BoneView is superior to the diagnostic accuracy of readers unaided by BoneView, as measured at the task of fracture detection using the Specificity/Sensitivity pair.
- Reader specificity improved significantly from 0.906 (95% bootstrap CI: 0.898-0.913) to 0.956 (95% bootstrap CI: 0.951-0.960): +5% increase of the Specificity.
- Reader sensitivity improved significantly from 0.648 (95% bootstrap CI: 0.640-0.656) to 0.752 (95% bootstrap CI: 0.745-0.759): +10.4% increase of the Sensitivity.
- Subgroup analysis found that Sensitivity and Specificity were higher for Aided reads versus Unaided reads for all anatomical areas of interest.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
- Standalone Performance:
- High-sensitivity operating point:
- Specificity: 0.811 [0.8 - 0.821]
- Sensitivity: 0.928 [0.919 - 0.936]
- High-specificity operating point:
- Specificity: 0.932 [0.925 - 0.939]
- Sensitivity: 0.841 [0.829 - 0.853]
- High-sensitivity operating point:
- Clinical Study (MRMC study on reader performance):
- Unaided:
- Specificity: 0.906 (95% bootstrap CI: 0.898-0.913)
- Sensitivity: 0.648 (95% bootstrap CI: 0.640-0.656)
- Aided:
- Specificity: 0.956 (95% bootstrap CI: 0.951-0.960)
- Sensitivity: 0.752 (95% bootstrap CI: 0.745-0.759)
- Unaided:
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
§ 892.2090 Radiological computer-assisted detection and diagnosis software.
(a)
Identification. A radiological computer-assisted detection and diagnostic software is an image processing device intended to aid in the detection, localization, and characterization of fracture, lesions, or other disease-specific findings on acquired medical images (e.g., radiography, magnetic resonance, computed tomography). The device detects, identifies, and characterizes findings based on features or information extracted from images, and provides information about the presence, location, and characteristics of the findings to the user. The analysis is intended to inform the primary diagnostic and patient management decisions that are made by the clinical user. The device is not intended as a replacement for a complete clinician's review or their clinical judgment that takes into account other relevant information from the image or patient history.(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 algorithm, including a description of the algorithm inputs and outputs, each major component or block, how the algorithm and output 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 improved assisted-read detection and diagnostic performance as intended in the indicated user population(s), and to characterize the standalone device performance for labeling. Performance testing includes standalone test(s), side-by-side comparison(s), and/or a reader study, as applicable.
(iii) Results from standalone performance testing used to characterize the independent performance of the device separate from aided user performance. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Devices with localization output must include localization accuracy testing as a component of standalone testing. The test dataset must be representative of the typical patient population with enrichment made only to ensure that the test dataset contains a sufficient number of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant disease, 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) Results from performance testing that demonstrate that the device provides improved assisted-read detection and/or diagnostic performance as intended in the indicated user population(s) when used in accordance with the instructions for use. The reader population must be comprised of the intended user population in terms of clinical training, certification, and years of experience. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Test datasets must meet the requirements described in paragraph (b)(1)(iii) of this section.(v) Appropriate software documentation, including device hazard analysis, software requirements specification document, software design specification document, traceability analysis, system level test protocol, pass/fail criteria, testing results, and cybersecurity measures.
(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 device instructions for use, including the intended reading protocol and how the user should interpret the device output.
(iii) A detailed description of the intended user, and any user training materials or programs that address appropriate reading protocols for the device, to ensure that the end user is fully aware of how to interpret and apply the device output.
(iv) A detailed description of the device inputs and outputs.
(v) A detailed description of compatible imaging hardware and imaging protocols.
(vi) 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) 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 anatomical characteristics, patient demographics and medical history, user experience, and imaging equipment.
0
Image /page/0/Picture/0 description: The image shows the logo for the U.S. Food & Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services seal on the left and the FDA acronym followed by the full name of the agency on the right. The FDA part of the logo is in blue, with the acronym in a solid blue square and the agency name in a lighter blue. The text reads "FDA U.S. FOOD & DRUG ADMINISTRATION".
Gleamer % Antoine Tournier Head of Quality & Regulatory 5 avenue du Général de Gaulle Saint Mandé, 94160 FRANCE
March 1, 2022
Re: K212365
Trade/Device Name: BoneView Regulation Number: 21 CFR 892.2090 Regulation Name: Radiological computer assisted detection and diagnosis software Regulatory Class: Class II Product Code: QBS Dated: January 28, 2022 Received: January 31, 2022
Dear Antoine Tournier:
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 (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 located 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.
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 803) for
1
devices or postmarketing safety reporting (21 CFR 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 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 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.
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, Ph.D. Assistant Director Mammography Ultrasound and Imaging Software Branch Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
2
DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration
Indications for Use
510(k) Number (if known)
Device Name
BoneView
Indications for Use (Describe)
BoneView is intended to analyze radiographs using machine learning techniques to identify and highlight fractures during the review of radiographs of:
| Study Type (Anatomical Area of Interest) | Compatible Radiographic View(s) |
|---|---|
| Ankle | Frontal, Lateral, Oblique |
| Foot | Frontal, Lateral, Oblique |
| Knee | Frontal, Lateral |
| Tibia/Fibula | Frontal, Lateral |
| Femur | Frontal, Lateral |
| Wrist | Frontal, Lateral, Oblique |
| Hand | Frontal, Oblique |
| Elbow | Frontal, Lateral |
| Forearm | Frontal, Lateral |
| Humerus | Frontal, Lateral |
| Shoulder | Frontal, Lateral, Axillary |
| Clavicle | Frontal |
| Pelvis | Frontal |
| Hip | Frontal, Frog Leg Lateral |
| Ribs | Frontal Chest, Rib series |
| Thoracic Spine | Frontal, Lateral |
| Lumbosacral Spine | Frontal, Lateral |
BoneView is intended for use as a concurrent reading aid during the interpretations of radiographs. BoneView is for prescription use only and is indicated for adults only.
| Type of Use (Select one or both, as applicable) | |
|---|---|
| ------------------------------------------------- | -- |
X 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."
3
Image /page/3/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon to the left of the word "GLEAMER" in a sans-serif font. The icon appears to be a stylized letter "G" or a circular shape with a gap in the upper right quadrant.
Date prepared: 01*, March 2022
K212365
In accordance with 21 CFR 807.87(h) and (21 CFR 807.92) the 510(k) Summary for BoneView is provided below.
1. Submitter
| Submitter | GLEAMER SAS
5, avenue du Général de Gaulle
94160 Saint-Mandé - FRANCE |
|-----------------------------|---------------------------------------------------------------------------------------------------------------------------|
| Primary Contact
Person | Antoine Tournier
Head of Quality & Regulatory Affairs
Tel: 0033 6 15 81 23 45
Email: antoine.tournier@gleamer.ai |
| Secondary Contact
Person | Christian Allouche
CEO
Tel: 0033 6 58 53 70 46
Email: christian@gleamer.ai |
2. Device
| Trade Name | BoneView |
|---|---|
| 510(k) reference | K212365 |
| Common Name | Radiological computer assisted detection/diagnosis software for |
| fracture | |
| Regulation | 21 CFR 892.2090 |
| Product Code | QBS |
| Classification | Class II |
3. Predicate Device
| Predicate Device | Imagen Technologies, Inc - FractureDetect |
|---|---|
| 510(k) reference | K193417 |
4
4. Device Description
BoneView is intended to analyze radiographs using machine learning techniques to identify and highlight fractures during the review of radiographs.
BoneView can be deployed on-premises or on cloud and be connected to several computing platforms and X-ray imaging platforms such as X-ray radiographic systems, or PACS. More precisely, BoneView can be deployed:
- In the cloud with a PACS as the DICOM Source
- . On-premises with a PACS as the DICOM Source
- On-premises with an X-ray system as the DICOM Source
It is important to note that no matter the deployment mode that is chosen for BoneView, the overall principle of use of BoneView and its user interface remain the same; only the place where BoneView is housed, and the DICOM Source/DICOM Destination with which BoneView communicates, may vary. Below is a description of the data flow.
After the acquisition of the radiographs on the patient and their storage in the DICOM Source, the radiographs are automatically received by BoneView from the user's DICOM Source through an intermediate DICOM node (for example, a specific Gateway, or a dedicated API). The DICOM Source can be the user's image storage system (for example, the Picture Archiving and Communication System, or PACS), or other radiological equipment (for example X-ray systems).
Once received by BoneView, the radiographs are automatically processed by the AI algorithm to identify regions of interest. Based on the processing result, BoneView generates result files in DICOM format. These result files consist of a summary table and result images (annotations on a copy of the original images or annotations to be toggled on/off). BoneView does not alter the original images, nor does it change the order of original images or delete any image from the DICOM Source.
Once available, the result files are sent by BoneView to the DICOM Destination through the same intermediate DICOM node. Similar to the DICOM Source, the DICOM Destination can be the user's image storage system (for example, the Picture Archiving and Communication System, or PACS), or other radiological equipment (for example X-ray systems). The DICOM Source and the DICOM Destination are not necessarily identical.
5
Image /page/5/Picture/0 description: The image shows the word "GLEAMER" in a sans-serif font. To the left of the word is a red circular logo. The logo appears to be a stylized letter "G" or a symbol representing connectivity or data flow.
The DICOM Destination can be used to visualize the result files provided by BoneView or to transfer the results to another DICOM host for visualization. The users are then able to use them as a concurrent reading aid to provide their diagnosis.
The general layout of images processed by BoneView is comprising:
(1) The "summary table" – it is a first image that is derived from the detected regions of interest in the following result images and that displays the results of the overall study along with the Gleamer – BoneView logo. This summary can be configured to be present or not.
(2) The result images – they are provided for all the images that were processed by BoneView and contain:
- . Around the Regions of Interest (if any), a rectangle with a solid or dotted line depending on the confidence of the algorithm (see below)
- . Around the entire image, a white frame showing that the images were processed by BoneView
- . Below the image:
- o The Gleamer BoneView logo
- o The number of Regions of interest that are displayed in the result image
- (if any) The caution message if it was identified that the image was not part of o the indication for use of BoneView
The training of BoneView was performed on a training dataset of 44,649 radiographs, representing 151,096 images (52.4% of males, with age: range [0 – 109]; mean 42.4 +/- 24.6) for all anatomical areas of interest in the Indications for Use and from various manufacturers. BoneView has been designed to solve the problem of missed fractures including subtle fractures, and thus detects fractures with a high sensitivity. In this regard, the display of findings is triggered by a "high-sensitivity operating point" (DOUBT FRACT) that will enable the display of a dotted-line bounding box around the region of interest. Additionally, the users need to be confident that when BoneView identifies a fracture, it is actually a fracture. In this regard, an additional information is introduced to the user with a "high-specificity operating point" (FRACT).
These two operating points are implemented in the User Interface as follow:
- Dotted-line Bounding Box: suspicious area / subtle fracture (when the level of . confidence of the Al algorithm associated with the finding is above "high-sensitivity
6
Image /page/6/Picture/0 description: The image shows the word "GLEAMER" in a sans-serif font. The letters are a dark blue color. To the left of the word is a red circular logo with a white circle inside.
operating point" and below "high-specificity operating point") displayed as a dotted bounding box around the area of interest
-
. Solid-line Bounding Box: definite or unequivocal fractures (when the level of confidence of the AI algorithm associated with the finding is above "high-specificity operating point") displayed as a solid bounding box around the area of interest
BoneView can provide 4 levels of results: -
. FRACT: BoneView identified at least one solid-line bounding box on the result images,
-
. DOUBT FRACT: BoneView did not identify any solid-line bounding box on the result images but it identified at least one dotted-line bounding box in the result images,
-
. NO FRACT: BoneView did not identify any bounding box at all in the result images,
-
NOT AVAILABLE: BoneView identified that the original images are out of its Indications for Use
5. Intended use/Indications for use
BoneView is intended to analyze radiographs using machine learning techniques to identify and highlight fractures during the review of radiographs of:
| Study Type (Anatomical Area of Interest) | Compatible Radiographic View(s) |
|---|---|
| Ankle | Frontal, Lateral, Oblique |
| Foot | Frontal, Lateral, Oblique |
| Knee | Frontal, Lateral |
| Tibia/Fibula | Frontal, Lateral |
| Femur | Frontal, Lateral |
| Wrist | Frontal, Lateral, Oblique |
| Hand | Frontal, Oblique |
| Elbow | Frontal, Lateral |
| Forearm | Frontal, Lateral |
| Humerus | Frontal, Lateral |
| Shoulder | Frontal, Lateral, Axillary |
| Clavicle | Frontal |
| Pelvis | Frontal |
| Hip | Frontal, Frog Leg Lateral |
| Ribs | Frontal Chest, Rib series |
| Thoracic Spine | Frontal, Lateral |
| Lumbosacral Spine | Frontal, Lateral |
GLEAMER 5 avenue du Général de Gaulle, 94160 Saint-Mandé - FRANCE SAS au capital de 115 372 euros – RCS Créteil 834 105 470 SIRET : 834 105 470 00027 – admin@gleamer.ai
7
Image /page/7/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon to the left of the word "GLEAMER" in a dark blue sans-serif font. The icon appears to be a stylized letter "G" or a circular shape with a break in the upper right quadrant.
BoneView is intended for use as a concurrent reading aid during the interpretations of radiographs. BoneView is for prescription use only and is indicated for adults only.
| Features and
Characteristics | Subject Device
Gleamer
BoneView | Predicate Device
Imagen Technologies
Inc.
FractureDetect |
|---------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Regulation Information | | |
| Regulation
Number/Name | 21 CFR 892.2090 / Radiological Computer
Assisted Detection and Diagnosis Software for
Fracture | Same |
| Regulation Description | A radiological computer assisted detection
and diagnostic software for suspected
fracture is an image processing device
intended to aid in the detection, localization,
and/or characterization of fracture on
acquired medical images (e.g. radiography,
MR, CT). The device detects, identifies, and/or
characterizes fracture based on features or
information extracted from images, and may
provide information about the presence,
location, and/or characteristics of the fracture
to the user. Primary diagnostic and patient
management decisions are made by the
clinical user. | Same |
| Intended Use | The device is intended to aid in the detection,
localization, and characterization of fractures
on acquired medical images (per 21 CFR
892.2090 Radiological Computer Assisted
Detection and Diagnosis Software For
Fracture). | Same |
| Indications for Use | | |
| Image Modality | 2D X-ray Images | Same |
| Features and
Characteristics | Subject Device
Gleamer
BoneView | Predicate Device
Imagen Technologies
Inc.
FractureDetect |
| Clinical Finding and
Clinical Output | Fracture
To inform the primary diagnostic and patient
management decisions that are made by the
clinical user. | Same |
| Mode of action | Image processing software using machine
learning to aid in identifying and highlighting
fractures during the review of radiographs. | Same |
| Anatomic Areas of
Interest and Patient
Population | For adults (greater than 21 years of age):
• Ankle
• Foot
• Knee
• Tibia/Fibula
• Femur
• Wrist
• Hand
• Elbow
• Forearm
• Humerus
• Shoulder
• Clavicle
• Pelvis
• Hip
• Ribs
• Thoracic Spine
• Lumbosacral Spine | For adults (greater than
21 years of age):
• Ankle
• Clavicle
• Elbow
• Femur
• Forearm
• Hip
• Humerus
• Knee
• Pelvis
• Shoulder
• Tibia / Fibula
• Wrist |
| Intended Users | The intended users of BoneView are clinicians
with the authority to diagnose fractures in
various settings including primary care (e. g.,
family practice, internal medicine), emergency
medicine, urgent care, and specialty care (e. g.
orthopedics), as well as radiologists who
review radiographs across settings. | Same |
| Software and Technical Information | | |
| Machine Learning
Methodology | Supervised Deep Learning | Same |
| Features and
Characteristics | Subject Device
Gleamer
BoneView | Predicate Device
Imagen Technologies
Inc.
FractureDetect |
| Image Source | DICOM Source (e.g., imaging device,
intermediate DICOM node, PACS system, etc.) | Same |
| Image Viewing | PACS system
Image annotations made on copy of original
image or image annotations toggled on/off | PACS system
Image annotations
toggled on/off |
| Deployment Platform | Deployment on-premises or on cloud and
connection to several computing platforms
and X-ray imaging platforms such as X-ray
radiographic systems, or PACS | Secure local processing
and delivery of DICOM
images |
| Privacy | HIPAA Compliant | Same |
| Software Level of
Concern | Moderate | Same |
6. Substantial equivalence
8
Image /page/8/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon to the left of the word "GLEAMER" in a sans-serif font. The icon appears to be a stylized letter "G" within a circle.
5 avenue du Général de Gaulle, 94160 Saint-Mandé - FRANCE SAS au capital de 115 372 euros – RCS Créteil 834 105 470 SIRET : 834 105 470 00027 – admin@gleamer.ai
9
Image /page/9/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon to the left of the word "GLEAMER" in a dark blue sans-serif font. The icon appears to be a stylized letter "G" or a circular target symbol.
7. Performance data
7.1. Biocompatibility Testing
As a standalone software, BoneView has no direct patient or user contacting components. Therefore, biocompatibility information is not required for this device.
7.2. Software Verification and Validation Testing
BoneView is a standalone software that is considered a moderate level of concern as per the guidance document from the FDA: "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices". Indeed, a failure or latent design flaw of BoneView could directly result in minor injury to the patient or operator.
Consequently, software verification and validation testing were conducted and documented as per the requirements of the abovementioned FDA guidance document for a moderate level of concern device.
7.3. Electrical safety and Electromagnetic compatibility Testing
10
Image /page/10/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon to the left of the word "GLEAMER" in a simple, sans-serif font. The icon appears to be a stylized letter "G" or a circular shape with a gap in it. The overall design is clean and modern.
As a standalone software, BoneView is not subject to electromagnetic compatibility or electrical safety testing activities. Therefore, Electrical safety and Electromagnetic compatibility information is not required for this device.
7.4. Bench Testing
Gleamer performed a standalone performance testing on a dataset of 8,918 radiographs (47.2% of males, with age: range [21 – 113]; mean 52.5 +/- 19.8) for all anatomical areas of interest in the Indications for Use and from various manufacturers (Agfa, Fujifilm, GE Healthcare, Kodak, Konica Minolta, Philips, Primax, Samsung, Siemens). This dataset was independent of the data used for model training, and establishment of device operating points.
The results of the standalone testing demonstrated that BoneView detects fractures in radiographs with high sensitivity and high specificity:
Specificity (with 95% Clopper-Pearson CI) and Sensitivity (with 95% Clopper-Pearson CI) of BoneView at the examination-level at the high-sensitivity operating point and high-specificity operating point on the merged datasets
| High-sensitivity operating point | High-specificity operating point | |||
|---|---|---|---|---|
| Standalone | ||||
| Performance | Specificity – 95% | |||
| Clopper-Pearson CI | Sensitivity – 95% | |||
| Clopper-Pearson CI | Specificity – 95% | |||
| Clopper-Pearson CI | Sensitivity – 95% | |||
| Clopper-Pearson CI | ||||
| Global | ||||
| n(positive)= 3,886 | ||||
| n(negative)= 5,032 | 0.811 [0.8 - 0.821] | 0.928 [0.919 - 0.936] | 0.932 [0.925 - 0.939] | 0.841 [0.829 - 0.853] |
Specificity (with 95% Clopper-Pearson Cl) and Sensitivity (with 95% Clopper-Pearson Cl) of BoneView at the examination-level for the subgroup analysis of anatomical areas of interest at the high-sensitivity operating point and high-specificity operating point on the merged datasets
| | High-sensitivity operating point
DOUBT FRACT | | High-specificity operating point
FRACT | |
|--------------------------------------------------------------|-------------------------------------------------|---------------------------------------------|--------------------------------------------|---------------------------------------------|
| Anatomical
Areas of
Interest | Specificity – 95%
Clopper-Pearson CI | Sensitivity –
95% Clopper-Pearson CI | Specificity – 95%
Clopper-Pearson CI | Sensitivity –
95% Clopper-Pearson CI |
| Ankle
n(positive)= 378
n(negative)= 805 | 0.784 [0.754 -
0.812] | 0.95 [0.923 - 0.969] | 0.897 [0.874 -
0.917] | 0.899 [0.865 -
0.928] |
| Clavicle
n(positive)= 147
n(negative)= 255 | 0.757 [0.699 -
0.808] | 0.905 [0.845 -
0.947] | 0.929 [0.891 -
0.958] | 0.83 [0.759 - 0.887] |
| | High-sensitivity operating point
DOUBT FRACT | | High-specificity operating point
FRACT | |
| Anatomical
Areas of
Interest | Specificity - 95%
Clopper-Pearson
Cl | Sensitivity -
95% Clopper-
Pearson Cl | Specificity - 95%
Clopper-Pearson
Cl | Sensitivity -
95% Clopper-
Pearson Cl |
| Elbow
n(positive)= 145
n(negative)= 227 | 0.718 [0.655 -
0.776] | 0.924 [0.868 -
0.962] | 0.899 [0.852 -
0.935] | 0.531 [0.446 -
0.614] |
| Femur
n(positive)= 63
n(negative)= 161 | 0.733 [0.658 -
0.799] | 0.937 [0.845 -
0.982] | 0.944 [0.897 -
0.974] | 0.825 [0.709 -
0.909] |
| Foot
n(positive)= 985
n(negative)= 1,097 | 0.793 [0.768 -
0.817] | 0.934 [0.917 -
0.949] | 0.924 [0.907 -
0.939] | 0.874 [0.852 -
0.894] |
| Forearm
n(positive)= 94
n(negative)= 102 | 0.676 [0.577 -
0.766] | 0.989 [0.942 - 1.0] | 0.912 [0.839 -
0.959] | 0.851 [0.763 -
0.916] |
| Hand
n(positive)= 1,168
n(negative)= 1,003 | 0.809 [0.783 -
0.832] | 0.966 [0.954 -
0.975] | 0.917 [0.898 -
0.934] | 0.915 [0.898 -
0.931] |
| Hip
n(positive)= 145
n(negative)= 235 | 0.77 [0.711 - 0.822] | 0.938 [0.885 -
0.971] | 0.953 [0.918 -
0.976] | 0.793 [0.718 -
0.856] |
| Humerus
n(positive)= 114
n(negative)= 175 | 0.731 [0.659 -
0.796] | 0.904 [0.834 -
0.951] | 0.92 [0.869 - 0.956] | 0.833 [0.752 -
0.897] |
| Knee
n(positive)= 128
n(negative)= 1,045 | 0.889 [0.868 -
0.907] | 0.891 [0.823 -
0.939] | 0.975 [0.964 -
0.984] | 0.797 [0.717 -
0.863] |
| Lumbosacral
Spine
n(positive)= 125
n(negative)= 209 | 0.737 [0.672 -
0.795] | 0.776 [0.693 -
0.846] | 0.947 [0.908 -
0.973] | 0.6 [0.509 - 0.687] |
| Pelvis
n(positive)= 230
n(negative)= 479 | 0.745 [0.704 -
0.784] | 0.887 [0.839 -
0.925] | 0.939 [0.914 -
0.959] | 0.743 [0.682 -
0.799] |
| Ribs
n(positive)= 252
n(negative)= 95 | 0.684 [0.581 -
0.776] | 0.753 [0.7 - 0.802] | 0.926 [0.854 - 0.97] | 0.488 [0.425 -
0.552] |
| Shoulder
n(positive)= 255
n(negative)= 586 | 0.782 [0.746 -
0.814] | 0.929 [0.891 -
0.958] | 0.947 [0.926 -
0.964] | 0.851 [0.801 -
0.892] |
| | High-sensitivity operating point
DOUBT FRACT | | High-specificity operating point
FRACT | |
| Anatomical | Specificity - 95% | Sensitivity - | Specificity - 95% | Sensitivity - |
| Areas of | Clopper-Pearson | 95% Clopper- | Clopper-Pearson | 95% Clopper- |
| Interest | Cl | Pearson Cl | Cl | Pearson Cl |
| Thoracic Spine
n(positive)= 74
n(negative)= 105 | 0.676 [0.578 -
0.764] | 0.878 [0.782 -
0.943] | 0.905 [0.832 -
0.953] | 0.689 [0.571 -
0.792] |
| Tibia/Fibula
n(positive)= 72
n(negative)= 184 | 0.712 [0.641 -
0.776] | 0.972 [0.903 -
0.997] | 0.815 [0.751 -
0.869] | 0.931 [0.845 -
0.977] |
| Wrist
n(positive)= 573
n(negative)= 502 | 0.771 [0.732 -
0.807] | 0.97 [0.953 - 0.983] | 0.892 [0.862 -
0.918] | 0.934 [0.91 - 0.953] |
11
Image /page/11/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon with a white design inside, followed by the word "GLEAMER" in a simple, sans-serif font. The text is a dark blue color and is spaced evenly.
12
Image /page/12/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon to the left of the word "GLEAMER" in a dark blue sans-serif font. The icon appears to be a stylized letter "G" formed by concentric circles with a gap in the outer circle.
Additionally, the performance of BoneView was validated for potential confounders including weight-bearing and non-weight bearing bone fractures and different X-ray system manufacturers.
7.5. Animal Studies
No animal studies were conducted in support of the 510(k) submission of BoneView.
7.6. Clinical studies
Gleamer conducted a fully-crossed multiple reader, multiple case (MRMC) retrospective reader study to determine the impact of BoneView on reader performance in diagnosing fractures. The primary objective of the study was to determine whether the diagnostic accuracy of readers aided by BoneView is superior to the diagnostic accuracy of readers unaided by BoneView as determined by the Specificity/Sensitivity pair (primary endpoint).
The clinical validation study design was the following:
- . 24 clinical readers each evaluated a dataset of 480 cases (31.9% of males, with age: range [21 – 93]: mean 59.2 +/- 16.4) in BoneView's Indications for Use and from various manufacturers (GE Healthcare, Kodak, Konica Minolta, Philips, Samsung) under both Aided and Unaided conditions.
- . This dataset was independent of the data used for model training, and establishment of device operating points.
- . Each case had been previously evaluated by a panel of three U.S. board-certified radiologists who assigned a ground truth label indicating the presence or absence of a fracture and its location.
13
Image /page/13/Picture/0 description: The image shows the logo for Gleamer. The logo consists of a red circular icon with a white shape inside, followed by the word "GLEAMER" in a dark blue sans-serif font. The logo is simple and modern, and the colors are eye-catching.
- . Cases are from all the anatomical areas of interest included in BoneView's Indications for Use.
- . The MRMC study consisted of two independent reading sessions separated by a washout period of at least one month in order to avoid memory bias.
- . For each case, each reader was required to provide a determination of the presence or absence of a fracture and provide its location.
The results of the study found that the diagnostic accuracy of readers in the intended use population is superior when aided by BoneView than when unaided by BoneView, as measured at the task of fracture detection using the Specificity/Sensitivity pair.
In particular, the study results demonstrated:
- . Reader specificity improved significantly from 0.906 (95% bootstrap CI: 0.898-0.913) to 0.956 (95% bootstrap CI: 0.951-0.960): +5% increase of the Specificity
- Reader sensitivity improved significantly from 0.648 (95% bootstrap CI: 0.640-0.656) to . 0.752 (95% bootstrap CI: 0.745-0.759): +10.4% increase of the Sensitivity
Additionally, subgroup analysis was carried out by anatomical areas of interest, listed in the Indications for Use. The subgroup analysis found that the Sensitivity and Specificity were higher for Aided reads versus Unaided reads for all of the anatomical areas of interest.
8. Conclusion
BoneView is as safe and effective as the predicate device.
BoneView and the predicate device are both computer-assisted detection and diagnostic devices that take radiographs in DICOM format and use machine learning techniques to identify and highlight fractures.
The overall design of the software and the basic functionality that it provides to the end user are the same. The minor differences between subject and predicate device in indications do not alter the intended use of the device and do not raise new or different questions regarding its safety and effectiveness when used as labeled.
The results of performance and clinical studies demonstrate that the subject device performs in accordance with specifications and meets user needs and intended use and that BoneView can be found to be substantially equivalent to the predicate device.