Videa Dental Assist is a computer-assisted detection (CADe) device that analyzes intraoral radiographs to identify and localize the following features. Videa Dental Assist is indicated for the review of bitewing, periapical, and panoramic radiographs acquired from patients aged 3 years or older. Suspected Dental Findings: Caries, Attrition, Broken/Chipped Tooth, Restorative Imperfections, Pulp Stones, Dens Invaginatus, Periapical Radiolucency, Widened Periodontal Ligament, Furcation, Calculus. Historical Treatments: Crown, Filling, Bridge, Post and Core, Root Canal, Endosteal Implant, Implant Abutment, Bonded Orthodontic Retainer, Braces. Normal Anatomy: Maxillary Sinus, Maxillary Tuberosity, Mental Foramen, Mandibular Canal, Inferior Border of the Mandible, Mandibular Tori, Mandibular Condyle, Developing Teeth, Erupting Teeth, Non-matured Erupted Teeth, Exfoliating Teeth, Impacted Teeth, Crowding Teeth.

Device Description

Videa Dental Assist (VDA) software is a cloud-based AI-powered medical device for the automatic detection of the features listed in the Indications For Use statement in dental radiographs. The device itself is available as a service via an API (Application Programming Interface) behind a firewalled network. Provided proper authentication and an eligible bitewing, periapical or panoramic image, the device returns a set of bounding boxes representing the suspect dental finding, historical treatment or normal anatomy detected. VDA is accessed by the dental practitioner through their dental image viewer. From within the dental viewer the user can upload a radiograph to VDA and then review the results. The device outputs a binary indication to identify the presence of findings for each indication. If findings are present the device outputs the number of findings by finding type and the coordinates of the bounding boxes for each finding. If no findings are present the device outputs a clear indication that there are no findings identified for each indication. The device output will show all findings from one radiograph regardless of the number of teeth present.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the Videa Dental Assist device, as provided in the document:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that all listed sensitivity, specificity, and AFROC FOM results met their acceptance criteria, but generally does not explicitly list the specific numerical acceptance criteria. For the purpose of this table, "Met Acceptance Criteria" will be used when the text indicates it.

Videa Dental Assist Indication	Performance Metric	Acceptance Criteria	Reported Device Performance (Bench Study)	Reported Device Performance (Clinical Study - Human Aided)
Suspect Dental Findings
Attrition	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.171 (28.5% improvement; p-value 3.3e-16)
Broken/Chipped Tooth	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.105 (15.3% improvement; p-value 1.5e-11)
Calculus	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.163 (23.0% improvement; p-value e-12)
Caries	Sensitivity	Met Acceptance Criteria	Met Acceptance Criteria	0.024 (4.3% improvement; p-value 0.0085)
Caries	Specificity	Not Met, but performed well enough to pass clinical study	Not Met, but performed well enough to pass clinical study	(Implicitly met through AFROC FOM)
Dens Invaginatus	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.236 (36.8% improvement; p-value 1.9e-9)
Furcation	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.199 (29.7% improvement; p-value 0.00057)
Periapical Radiolucency	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.092 (11.5% improvement; p-value 0.0072)
Pulp Stone	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.211 (35.4% improvement; p-value 2.2e-16)
Restorative Imperfection	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.164 (27.9% improvement p-value of <1e-16)
Widened Periodontal Ligament (PDL)	AFROC FOM	Met Acceptance Criteria	Not specified (Sensitivity/Specificity only for standalone)	0.141 (28.4% improvement; p-value of 9.6e-13)
Historical Treatments (All Indications)	Sensitivity/Specificity	Met Acceptance Criteria	Above acceptance criteria	Not applicable (Not a clinical diagnostic aid)
Normal Anatomy (All Indications)	Sensitivity/Specificity	Met Acceptance Criteria	Above acceptance criteria	Not applicable (Not a clinical diagnostic aid)

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

Standalone Performance Assessment (Bench Testing):
- Sample Size: 1,445 radiographs
- Data Provenance: Collected from more than 35 US sites (retrospective).
Clinical Testing (MRMC Study):
- Sample Size: 378 radiographs
- Data Provenance: Collected from over 25 US locations spread across the country (retrospective).

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

Standalone Performance Assessment (Bench Testing):
- Number of Experts: Three
- Qualifications: US board-certified dentists.
Clinical Testing (MRMC Study):
- Number of Experts: Not explicitly stated for the initial labeling, but labels were established by US licensed dentists. One US licensed dentist then adjudicated those labels.
- Qualifications: US licensed dentists.

4. Adjudication Method for the Test Set

Standalone Performance Assessment (Bench Testing): The document states the dataset was "ground-truthed by three US board-certified dentists." It doesn't specify a formal adjudication method (e.g., 2+1, 3+1). It implies a consensus or majority approach by multiple experts.
Clinical Testing (MRMC Study): US licensed dentists labeled the data, and then one US licensed dentist adjudicated those labels to establish a reference standard for the study. This suggests a single adjudicator to resolve discrepancies or confirm final ground truth after initial labeling.

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

Yes, an MRMC comparative effectiveness study was done.
Effect Size (Average Percentage Improvement in AFROC FOM with VDA):
- Attrition: 28.5% improvement (0.171 AFROC FOM increase)
- Broken or Chipped: 15.3% improvement (0.105 AFROC FOM increase)
- Calculus: 23.0% improvement (0.163 AFROC FOM increase)
- Caries: 4.3% improvement (0.024 AFROC FOM increase)
- Dens Invaginatus: 36.8% improvement (0.236 AFROC FOM increase)
- Furcation: 29.7% improvement (0.199 AFROC FOM increase)
- Periapical Radiolucency: 11.5% improvement (0.092 AFROC FOM increase)
- Pulp Stone: 35.4% improvement (0.211 AFROC FOM increase)
- Restorative Imperfection: 27.9% improvement (0.164 AFROC FOM increase)
- Widened Periodontal Ligament: 28.4% improvement (0.141 AFROC FOM increase)

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

Yes, a Standalone Performance Assessment was conducted.

7. The Type of Ground Truth Used

Expert Consensus/Expert Review: For both the standalone performance assessment and the clinical study, the ground truth was established by multiple US board-certified or licensed dentists, either through direct ground-truthing or through labeling followed by adjudication. This falls under expert consensus or expert review.

8. The Sample Size for the Training Set

The document mentions that "Videa Dental Assist artificial intelligence algorithms were trained with bitewing, periapical and panoramic radiographs" and "trained with that patient population" (referring to pediatric). However, the specific sample size of the training set is NOT provided in the document.

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

The document implies that the algorithms were "trained" with data, but does not explicitly describe how the ground truth for the training set was established. It can be inferred that it would also involve expert labeling, similar to the test sets, but no details are given.

Summary

{0}------------------------------------------------

December 15, 2023

Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

VideaHealth, Inc. % Adam Foresman Director of Quality & Regulatory Affairs 179 South Street Floor 5 BOSTON. MA 02111

Re: K232384

Trade/Device Name: Videa Dental Assist Regulation Number: 21 CFR 892.2070 Regulation Name: Medical Image Analyzer Regulatory Class: Class II Product Code: MYN Dated: July 31, 2023 Received: August 8, 2023

Dear Adam Foresman:

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" (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).

{1}------------------------------------------------

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 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.

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.

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,

Lu Jiang

Lu Jiang, Ph.D. Assistant Director Diagnostic X-Ray Systems Team DHT8B: Division of Radiologic Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K232384

Device Name Videa Dental Assist

Indications for Use (Describe)

· Caries

· Attrition
· Broken/Chipped Tooth
· Restorative Imperfections
· Pulp Stones
· Dens Invaginatus
Periapical Radiolucency
· Widened Periodontal Ligament
· Furcation
Calculus

Historical Treatments:

Crown
· Filling
· Bridge
Post and Core
· Root Canal
Endosteal Implant
Implant Abutment
· Bonded Orthodontic Retainer
· Braces

Normal Anatomy:

· Maxillary Sinus
· Maxillary Tuberosity
· Mental Foramen
· Mandibular Canal
· Inferior Border of the Mandible
Mandibular Tori
· Mandibular Condyle
· Developing Teeth
· Erupting Teeth
· Non-matured Erupted Teeth
· Exfoliating Teeth
· Impacted Teeth
· Crowding Teeth

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)

{3}------------------------------------------------

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}------------------------------------------------

510(k) Summary

In accordance with 21 CFR 807.87(h) and 21 CFR 807.92 the 510(k) Summary for the Videa Dental Assist device is provided below.

Applicant:	VideaHealth, Inc.179 South Street, Floor 5Boston, MA, 02111+1 617-340-9940florian@videa.ai
Contact & SubmissionCorrespondent:	Adam ForesmanDirector of Quality & Regulatory AffairsVideaHealth, Inc.+1 617-340-9940adam@videa.ai
Date Prepared:	July 31, 2023

1. SUBMITTER

2. DEVICE

Device Trade Name:	Videa Dental Assist
Device Common Name:	Dental AI System
Classification Name:	Medical Image Analyzer
Classification RegulationNumber:	21 CFR 892.2070
Device Class:	2
Product Code:	MYN

PREDICATE DEVICE

Device Trade Name:	Videa Caries Assist
Device Common Name:	Dental AI System
Classification Name:	Medical Image Analyzer

{5}------------------------------------------------

Classification RegulationNumber:	21 CFR 892.2070
Device Class:	2
Product Code:	MYN

PREDICATE DEVICE 3.

Predicate Device:	K213795 VideaHealth's Videa Caries Assist (VCA)
-------------------	-------------------------------------------------

DEVICE DESCRIPTION 4.

VDA is accessed by the dental practitioner through their dental image viewer. From within the dental viewer the user can upload a radiograph to VDA and then review the results. The device outputs a binary indication to identify the presence of findings for each indication. If findings are present the device outputs the number of findings by finding type and the coordinates of the bounding boxes for each finding. If no findings are present the device outputs a clear indication that there are no findings identified for each indication. The device output will show all findings from one radiograph regardless of the number of teeth present.

The intended users of Videa Dental Assist are trained dental professionals such as dentists and dental hygienists. For the suspect dental findings indications specifically, VDA is intended to be used as an adjunct tool and should not replace a dentist's review of the image. Only dentists that are performing diagnostic activities shall use the suspect dental finding indications.

VDA should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by trained dental professionals including, but not limited to, dentists and dental hygienists.

Depending on the specific VDA indication for use, the intended patients of Videa Dental Assist are patients 3 years of age and older above with primary, mixed and/or permanent dentition undergoing routine dental visits or suspected of one of the suspected dental findings listed in the VDA indications for use statement above. VDA may be used on eligible bitewing, periapical or panoramic radiographs depending on the indication.

See Table 1 below for the specific patient age group and image modality that each VDA indication for use is designed and tested to meet. VDA uses the images metadata to only show

{6}------------------------------------------------

the indications for the patient age and image modalities in scope as shown in Table 1. VDA will not show any findings output for an indication for use that is outside of the patient age and radiographic view scope.

Videa Dental Assist Indication	Patient Age in Scope	Radiographic View inScope
Caries	3 years and older	Bitewing and Periapical
Attrition	3 years and older	Bitewing and Periapical
Broken/Chipped	3 years and older	Bitewing and Periapical
Restorative Imperfection	3 years and older	Bitewing and Periapical
Pulp Stone	12 years of age andolder with permanentdentition	Bitewing and Periapical
Dens Invaginatus	3 years & older	Bitewing and Periapical
Periapical Radiolucency	22 years of age andolder with permanentdentition	Periapical only
Furcation	22 years of age andolder with permanentdentition	Bitewing and Periapical
Calculus	3 years and older	Bitewing and Periapical
Widened Periodontal Ligament	3 years and older	Bitewing and Periapical
Historical Treatments: All Indications	3 years and older	All on Bitewing,Periapical andPanoramic
Normal Anatomy: All Indications	12 years and older	1. Impacted Tooth2. Mental Foramen3. Maxillary TuberosityOn Bitewing, Periapical& Panoramic

	Table 1: VDA Indications Scope by Patient Age and Image Modality Type

{7}------------------------------------------------

Videa Dental Assist Indication	Patient Age in Scope	Radiographic View inScope
	3 years and older	All other indications areon Bitewing, Periapical& Panoramic except:
		1. 'Mandibular Condyle'VDA normal anatomyindication is only onPanoramic images.

INTENDED USE/INDICATIONS FOR USE ર.

Suspected Dental Findings:

Caries ●
Attrition ●
Broken/Chipped Tooth ●
Restorative Imperfections ●
Pulp Stones ●
Dens Invaginatus ●
Periapical Radiolucency ●
Widened Periodontal Ligament
Furcation
Calculus .

Historical Treatments:

Crown .
Filling ●
Bridge ●
Post and Core ●
Root Canal ●
Endosteal Implant ●
Implant Abutment ●
Bonded Orthodontic Retainer ●
Braces ●

{8}------------------------------------------------

Normal Anatomy:

Maxillary Sinus ●
Maxillary Tuberosity ●
Mental Foramen ●
Mandibular Canal ●
Inferior Border of the Mandible ●
Mandibular Tori
Mandibular Condyle ●
Developing Tooth
Erupting Teeth
Non-matured Erupted Teeth
Exfoliating Teeth
Impacted Teeth ●
Crowding Teeth ●

SUBSTANTIAL EQUIVALENCE 6.

Comparison of Indications

Videa Dental Assist is an expansion of the design input scope of Videa Caries Assist. Videa Dental Assist and Videa Caries Assist both analyze dental radiographs and highlight regions of interest in an image viewer. For the VDA suspect dental finding indications, both devices are only intended as an aid to the trained professional and are not intended to replace the diagnosis by the physician. Both devices are intended to assist dental professionals by identifying caries regions of interest. Videa Dental Assist's Indication For Use includes additional description on the output of the device which is not a safety or efficacy concern.

Videa Dental Assist contains historical treatment and normal anatomy indications whereas Videa Caries Assist does not. These indications are not intended to be diagnostic aides. They are used for general understanding of features present in a radiograph and to assist the dental practice in patient operations management. These Videa Dental Assist indications do not assess quality or the need for treatment of these features. Therefore for these Videa Dental Assist indications. dental professionals are included in the intended user scope whereas Videa Caries Assist is limited to dentists as the intended user.

The difference in patient ages does not constitute a safety or efficacy concern. Videa Dental Assist artificial intelligence algorithms were trained with that patient population and VideaHealth followed the pediatric medical device guidance document among other standards and guidance documents listed in Section 7 below in the design process. Videa Dental Assist testing has shown to be safe and effective for patients between 3 and 21 years of age with primary, mixed or permanent dentition in the image.

The difference in radiographic views does not constitute a safety or efficacy concern. Videa Dental Assist artificial intelligence algorithms were trained with bitewing, periapical and panoramic radiographs. Videa Dental Assist testing has shown to be safe and effective for bitewing, periapical and panoramic radiographs. Additionally panoramic radiographs are only

{9}------------------------------------------------

intended to be used on historical treatment and normal anatomy indications which are not diagnostic aides.

Technological Comparisons

Table 2 compares the key technological feature of the subject devices to the predicate device (Videa Caries Assist, K213795).

	Proposed Device	Predicate Device
510(k) Number	TBD	K213795
Applicant	VideaHealth, Inc.	VideaHealth, Inc.
Device Name	Videa Dental Assist	Videa Caries Assist
Classification Regulation	892.2070	892.2070
Product Code	MYN	MYN
Image Modality	X-Ray	X-Ray
Radiograph View Type	Bitewing Images, PeriapicalImages, and PanoramicImages.Radiograph view type scope isVidea Dental Assist indicationspecific.	Bitewing Images
Suspect Dental FindingsIndications	Caries: Active and SecondaryCaries at all penetration depthsAdditional Suspect DentalFindings listed in the VideaDental Assist's Indications ForUse statement.	Caries: Active and SecondaryCaries at all penetrationdepths.
Historical Treatment andNormal AnatomyIndications	Included	Not Included
	Proposed Device	Predicate Device
Tooth Surface	For the caries indication only:Proximal, Buccal/Lingual,Occlusal, Root, Cervical.None of the additional VDA'Suspect Dental Finding'indications are specific to atooth surface.	Caries: Proximal,Buccal/Lingual, Occlusal,Root, Cervical.
Clinical Output	Message indicating if andhow many findings weredetected for each enabledVidea Dental Assist'sindication for use.All Videa Dental Assist'sindications use a set oftogglable bounding boxesaround suspected areas ofinterest.	Message indicating if andhow many carious lesionswere detected.Set of togglable boundingboxes around suspectedlesions.
Patient Population	Patients ≥ 3 years of age.Patient age range is VideaDental Assist indicationspecific.	Adults ≥ 22 years of age
Intended User	Dental professionals	US licensed dentists
Development Technology	Supervised Deep Learning	Supervised Deep Learning
Image Source	X-Ray Sensor	X-Ray Sensor
Image Viewing	Image Viewer	Image Viewer

Table 2: Device Comparison Table

{10}------------------------------------------------

{11}------------------------------------------------

PERFORMANCE DATA 7.

Biocompatibility, Sterilization, and Reprocessing

Not applicable. The subject device is a software-only device. There are no direct or indirect patient-contacting components of the subject device. There are no sterile or reprocessed components.

Electrical Safety and Electromagnetic Compatibility (EMC)

Not applicable. The subject device is a software-only device. It contains no electric components, generates no electrical emissions, and uses no electrical energy of any type.

Software Verification and Validation Testing

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." The software for this device was considered as a moderate level of concern.

Among others, the following standards and guidance documents were used during the Videa Dental Assist design, development, and testing.

ISO 14971:2019 Application of Risk Management to Medical Devices. ●
AAMI CR34971:2022 Guidance on the Application of ISO 14971 to Artificial ● Intelligence and Machine Learning
IEC 62304 Edition 1.1 2015-06 Consolidated Version: Medical Device Software -● Software Life Cycle Processes
Good Machine Learning Practice for Medical Device Development: Guiding Principles . October 2021.
. FDA Premarket Assessment of Pediatric Medical Devices Guidance Document (March 24. 2014)

Bench Testing

A Standalone Performance Assessment was conducted to measure and report the performance of Videa Dental Assist by itself, in the absence of any interaction with a dental professional in identifying the regions of interest for that specific indication. All suspect dental finding, historical treatment and normal anatomy VDA indications were in scope. The dataset was 1.445 radiographs collected from more than 35 US sites that were ground-truthed by three US board-certified dentists. The patients in the dataset were 18% female and 17% male, 16% other and 48% unknown. There were N=17 sensor manufacturers in the study and 8 sensor manufacturers had enough samples to perform generalizability statistical analysis on. Those image sensors were: AirTechniques, Carestream, Dexis, Gendex, Kavo, Schick, PaloDex Group, and Sirona. Tables 3 and 4 describe the distribution of the two significant design input expansions between Videa Dental Assist and the predicate Videa Caries Assist; patient age and radiographic view.

{12}------------------------------------------------

Subject Age(Years)	Percentage
3 - 11	13%
12 - 21	15%
22 - 40	19%
41 - 60	19%
61 and older	16%
Unknown	18%

Table 3: Demographic breakdown by age

All images, regardless of patient age, were classified as being primary dentition only, mixed dentition and permanent dentition only.

Table 4: Image breakdown bv radiographic view

RadiographicView	Percentage
Bitewing	45%
Periapical	43%
Panoramic	12%

Tables 5, 6 and 7 contain the sensitivity and specificity for all Videa Dental Assist indications from the bench study. All of these sensitivity and specificity results met their acceptance criteria.

All of VDA indications' standalone performance was assessed against the following potential patient, device input and image confounders: age, gender, image dentition type, radiograph view type, image quality, imaging sensor manufacturer, bit-depth, image size, and image clinic acquisition location among others.

Additionally VDA indication-specific standalone performance was assessed against the following potential subject and image confounders:

Caries type, severity, location and specific tooth dentition type ●
Periapical radiolucency type
Crown material type ●
Filling material type
Onlay or inlay material type
Bridge material type
Root canal material type ●

{13}------------------------------------------------

The bench study results were:

. All VDA historical treatment and normal anatomy indications that were included in the indications for use statement above met their sensitivity and specificity acceptance criteria. All specificity values for all historical treatment and normal anatomy indications were above their acceptance criteria regardless of their prevalence rates.
All VDA suspect dental findings indications met their sensitivity and specificity acceptance criteria with the exception of caries specificity. Caries specificity was the only to not pass the target however performed well enough to still pass the clinical study

Additional statistical analysis were performed for each VDA indication including the VDA's false positive fraction rate, non-lesion fraction, and positive predictive value.

Generalizability was observed for all confounders and limitations were listed in the Instructions For Use where necessary. The generalizability analysis results and related information including a list of types (such as material types) are in the Videa Dental Assist Instructions For Use for users.

Animal Testing

Not applicable. Animal studies are not necessary to establish the substantial equivalence.

Clinical Testing

A fully crossed, randomized, multiple reader multiple case (MRMC) controlled study was performed to determine whether the diagnostic accuracy of readers aided by VDA is superior to reader accuracy when unaided by VDA, as determined by the AFROC Figure of Merit (AFROC FOM). The hypothesis to be tested is:

Ho: AFROC FOMaided - AFROC FOMumaided ≤ 0

H : AFROC FOMaided - AFROC FOM maided > 0

where AFROC FOMsided is the population-mean AFROC FOM for aided reads, and similarly with AFROC FOMunaided for unaided reads.

All suspect dental finding VDA indications were in scope of the clinical testing was performed on 378 radiographs collected from over 25 US locations spread across the country. US licensed dentists labeled the data and a US licensed dentist adjudicated those labels to establish a reference standard for the study.

There were N=26 readers that participated in the study and reviewed all images with and without VDA AI predictions in a randomized fashion.

The patients in the dataset were 24% female and 21% male, 15% other and 39% unknown. There were N=6 sensor manufacturers that had enough samples to perform generalizability statistical analysis on. Those image sensor manufacturers were: AirTechniques, Carestream, Dexis. Gendex. Kavo. and Schick. Tables 5 and 6 describe the distribution of the study for the

{14}------------------------------------------------

two significant design input expansions between Videa Dental Assist and the predicate Videa Caries Assist; patient age and radiographic view.

Subject Age(Years)	Percentage
3 - 11	28%
12 - 21	20%
22 - 40	14%
41 - 60	14%
61 and older	8%
Unknown	15%

Table 5: Demographic breakdown by age

All images, regardless of patient age, were classified as being primary dentition only, mixed dentition and permanent dentition only.

Table 6: Image breakdown by radiographic view

RadiographicView	Percentage
Bitewing	56%
Periapical	44%
Panoramic	N/A. Not inscope.

Table 7 contains the AFROC FOM results for all Videa Dental Assist indications in the clinical study. All of these results met their acceptance criteria.

Videa Dental AssistIndication	Average Percentage Improvement With VDA(VDA Aided vs. Unaided Mean AFROC FOM)
Attrition	0.171(28.5% improvement; p-value 3.3e-16)
Broken or Chipped	0.105(15.3% improvement; p-value 1.5e-11)

{15}------------------------------------------------

Videa Dental AssistIndication	Average Percentage Improvement With VDA(VDA Aided vs. Unaided Mean AFROC FOM)
Calculus	0.163(23.0% improvement; p-value e-12)
Caries	0.024(4.3% improvement; p-value 0.0085)
Dens Invaginatus	0.236(36.8% improvement; p-value 1.9e-9)
Furcation	0.199(29.7% improvement; p-value 0.00057)
Periapical Radiolucency	0.092(11.5% improvement;p-value 0.0072)
Pulp Stone	0.211(35.4% improvement;p-value 2.2e-16)
Restorative Imperfection	0.164(27.9% improvement p-value of <1e-16)
Widened Periodontal Ligament	0.141(28.4% improvement; p-value of 9.6e-13)
Historical Treatments:All Indications	Not applicable.Not a clinical diagnostic aide.
Normal Anatomy:All Indications	Not applicable.Not a clinical diagnostic aide.

All of VDA indications' clinical performance was assessed against the following potential patient, device input and image confounders among others: age, sex, clinician experience level in years of practice, image dentition type, radiograph view type, image quality, imaging sensor manufacturer, bit-depth, image size, and image clinic acquisition location.

Additionally VDA indication-specific clinical performance was assessed against the following potential lesion and image confounders:

Caries type, severity, location and tooth dentition type ●
'Periapical Radiolucency' type ●

Additional statistical analysis were performed for each VDA indication including the VDA stand-alone Alternative Free-response Receiver Operating Characteristic Figure of Merit (AFROC FOM), false positive fraction rate, non-lesion fraction, and positive predictive value.

{16}------------------------------------------------

Because multiple indications were being tested in parallel, VideaHealth performed a multiple endpoint statistical analysis using the FDA's Multiple Endpoints in Clinical Trials Guidance for Industry (October 2022). Per the guidance, this minimizes the chances of a falsely favorable conclusion for any primary endpoint due to Type 1 error, regardless of which and how many of these endpoints in the study have no effect. VideaHealth performed a Holms analysis according to the FDA guidance document and determined that this Type 1 error risk across all VDA suspect dental finding indications is acceptable. A Type 1 error of 0.05 was used for this analysis (1.E. the probability of falsely finding a favorable effect on at least one primary endpoint (VDA indication) is approximately 0.05). The VDA suspect dental findings indications were verified as being independent for this analysis.

Generalizability was observed for all confounders and limitations were listed in the Instructions For Use where necessary. The clinical testing confirmed that the patient age ranges listed above are appropriate. The generalizability analysis results and related information are in the Videa Dental Assist Instructions For Use for users.

The primary device expansions of VDA over the predicate VCA include adding periapical radiographs and the pediatric patient population. The AFROC analysis for those two device expansions are provided below. These analyses are reference only, therefore no p-values are provided. These tables were a part of the generalizability assessment, but not the primary acceptance criteria, portion of the clinical study.

VDA SuspectDental FindingIndication	Average Percentage Improvement With VDA(VDA Aided vs. Unaided Mean AFROC FOM)
Attrition	0.157(25.9% improvement)
Broken/ChippedTooth	0.075(10.4% improvement)
Calculus	0.207(31.1% improvement)
Caries	0.031(5.0% improvement)
Dens Invaginatus	0.216(34.2% improvement)
Furcation	0.187(29.3% improvement)

AFROC Scores On Periapical Radiographs

{17}------------------------------------------------

Page	14 of 15

VDA SuspectDental FindingIndication	Average Percentage Improvement With VDA(VDA Aided vs. Unaided Mean AFROC FOM)
PeriapicalRadiolucency	N/A. See table above on the overall PRL indication levelresults. PRL is only applicable on periapical radiographs sothere is no subgroup analysis to perform.
Pulp Stones	0.244(39.8% improvement)
RestorativeImperfections	0.167(28.2% improvement)
Widened PDL	0.120(24.4% improvement)

AFROC Scores On Pediatric Patients (Ages 3 to 21 Years of Age Unless Otherwise Noted)

VDA SuspectDental FindingIndication	Average Percentage ImprovementWith VDA(VDA Aided vs. Unaided MeanAFROC FOM)	Notes
Attrition	0.199(35.3% improvement)	None
Broken/ChippedTooth	0.125(18.4% improvement)	None
Calculus	0.230(37.0% improvement)	Calculus is only intended forpatients 12 years of age andolder.
Caries	0.028(5.2% improvement)	None
DensInvaginatus	0.247(39.3% improvement)	None
Furcation	N/A	Furcation is only intended forpatients 22 years of age andolder.
PeriapicalRadiolucency	N/A	Periapical radiolucency is onlyintended for patients 22 yearsof age and older.

{18}------------------------------------------------

VDA SuspectDental FindingIndication	Average Percentage ImprovementWith VDA(VDA Aided vs. Unaided MeanAFROC FOM)	Notes
Pulp Stones	0.196(33.2% improvement)	Pulp Stones indication is onlyintended for patients 12 yearsof age and older.
RestorativeImperfections	0.231(39.4% improvement)	None
Widened PDL	0.131(26.1% improvement)	None

No adverse events were observed during the clinical study.

Clinical testing demonstrated that the Videa Dental Assist meets performance requirements.

Conclusion

There are differences in design input scopes between Videa Dental Assist and Videa Caries Assist namely the indications, patient population, and radiograph view types. As shown in the Videa Dental Assist testing these differences do not raise different questions of safety and efficacy. There are no significant differences between Videa Dental Assist and Videa Caries Assist in the AI model training methodology or other technological differences that raise different questions of safety and efficacy.

Although there are differences in the testing methodology (namely the use of an adjudicator in addition to ground truthers for VDA that was not used for VCA to identify smaller or more subtle findings), they do not raise different questions of safety and efficacy. The calculations methodology for sensitivity, specificity, Alternative Free-response Receiver Operating Characteristic Figure of Merit (AFROC FOM) and other statistical techniques are the same between Videa Dental Assist and Videa Caries Assist. Both Videa Dental Assist and Videa Caries Assist had the same clinical study acceptance criteria. The results of the bench testing and clinical testing demonstrate that the performance of Videa Dental Assist is comparable to that of Videa Caries Assist. Both Videa Dental Assist and Videa Caries Assist met their acceptance criteria. Therefore, Videa Dental Assist can be found substantially equivalent to Videa Caries Assist.

Regulation Number and Section

§ 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.