Velmeni for Dentists (V4D) Endo-Perio
Device Facts
| Record ID | K252953 |
|---|---|
| Device Name | Velmeni for Dentists (V4D) Endo-Perio |
| Applicant | Velmeni, Inc. |
| Product Code | MYN · Radiology |
| Decision Date | May 11, 2026 |
| Decision | SESE |
| Submission Type | Traditional |
| Regulation | 21 CFR 892.2070 |
| Device Class | Class 2 |
| Attributes | AI/ML, Software as a Medical Device |
AI Performance
| Output | Algorithm | Acceptance | Observed | Dev DS | Dev Readers | Test DS | Test Readers |
|---|---|---|---|---|---|---|---|
| Tooth anatomy detection | — | Sensitivity >= 85% and FPR per image <= 0.50 | Sensitivity >= 85% and FPR per image <= 0.50 (p < 0.001) | — | — | Standalone performance study: 128 patients/272 images (bitewing) and 137 patients/271 images (periapical) | 3 (US-licensed dentists) + 1 (US-licensed dental radiologist) |
| Root canal treated tooth detection | — | Sensitivity >= 80% and specificity >= 85% | Sensitivity >= 80% and specificity >= 85% (p < 0.001) | — | — | Standalone performance study: 137 root canal images from 89 bitewing, 110 periapical, and 134 panoramic patients | 3 (US-licensed dentists) + 1 (US-licensed dental radiologist) |
| Bone level landmark detection | — | Mean absolute error < 0.5 mm | Mean absolute error < 0.5 mm (p < 0.001) | — | — | Standalone performance study: 193 patients/images (bitewing) and 186 patients/images (periapical) | 3 (US-licensed dentists) + 1 (US-licensed dental radiologist) |
| Jaw anatomy detection | — | — | Mandibular Canal: 99.8% sensitivity, 0.00 FPR; Maxillary Sinus: 99.8% sensitivity, 0.00 FPR; Mental Foramen: 81.5% sensitivity, 0.18 FPR | — | — | Standalone performance study: 245 patients/248 images | 3 (US-licensed dentists) + 1 (US-licensed dental radiologist) |
Indications for Use
VELMENI for DENTISTS (V4D) Endo-Perio is a concurrent-read, computer-assisted detection software intended to assist dentist in the clinical detection of tooth anatomy (enamel, dentine in crown, pulp, and root), jaw anatomy (mental foramen, inferior alveolar canal, and maxillary sinus), bone level (cementoenamel junction and crestal bone) and root canal treated tooth (RCT) in digital bitewing, periapical and panoramic radiographs of permanent teeth in patients 15 years of age or older. This device provides additional information for dentists in examining radiographs of patients' teeth. This device is not intended as a replacement for a complete examination by the dentist or their clinical judgment that considers other relevant information from the image, patient history, or actual in vivo clinical assessment. Final diagnoses and patient treatment plans are the responsibility of the dentist.
Device Story
Software-based medical image analyzer; assists dentists in detecting tooth/jaw anatomy, bone levels, and root canal treated teeth. Inputs: digital bitewing, periapical, panoramic radiographs (JPEG/PNG). Processing: ML engine performs classification (radiograph type, rotation) and segmentation (anatomy, RCT, bone landmarks). Output: visual overlays on radiographs via web interface; editable by clinicians. Used in dental clinics; operated by dentists. Facilitates clinical decision-making by providing supplemental anatomical information; does not replace clinical judgment or complete examination. Benefits: improved efficiency and accuracy in radiographic assessment.
Clinical Evidence
Bench testing only. Evaluated on dataset of 128-245 patients per modality. Ground truth established by three dentists and one radiologist (majority rule/adjudication). Primary endpoints: sensitivity, FPR per image, mean absolute error. Tooth anatomy sensitivity ≥85% (p<0.001); RCT sensitivity ≥80%, specificity ≥85% (p<0.001); bone level mean absolute error <0.5mm (p<0.001). Subgroup analyses (sex, age, sensor) showed no significant performance differences.
Technological Characteristics
Web-based software application; ML-driven image analysis. Components: Web UI, Backend API, Queue, AI-Worker, Database/File Storage. Connectivity: VELMENI BRIDGE for third-party software integration. Outputs: segmentation and landmark detection. Software verification/validation performed per FDA guidance. Cybersecurity controls implemented.
Indications for Use
Indicated for patients 15 years of age or older requiring clinical detection of tooth anatomy, jaw anatomy, bone levels, and root canal treated teeth in digital bitewing, periapical, and panoramic radiographs.
Regulatory Classification
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.
Special Controls
*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.
Predicate Devices
- Velmeni for Dentists (K240003)
Reference Devices
Submission Summary (Full Text)
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
May 11, 2026
Velmeni, Inc.
% Mini Suri
Chief Executive Officer
333 W. Maude Ave, STE 207
SUNNYVALE, CA 94085
Re: K252953
Trade/Device Name: Velmeni for Dentists (V4D) Endo-Perio
Regulation Number: 21 CFR 892.2070
Regulation Name: Medical Image Analyzer
Regulatory Class: Class II
Product Code: MYN
Dated: April 9, 2026
Received: April 10, 2026
Dear Mini Suri:
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.
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
{1}
K252953 - Mini Suri
Page 2
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (Preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-
{2}
K252953 - Mini Suri
Page 3
assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
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
Enclosure
{3}
| Indications for Use | | |
| --- | --- | --- |
| Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. | K252953 | ? |
| Please provide the device trade name(s). | | ? |
| Velmeni for Dentists (V4D) Endo-Perio | | |
| Please provide your Indications for Use below. | | ? |
| VELMENI for DENTISTS (V4D) Endo-Perio is a concurrent-read, computer-assisted detection software intended to assist dentist in the clinical detection of tooth anatomy (enamel, dentine in crown, pulp, and root), jaw anatomy (mental foramen, inferior alveolar canal, and maxillary sinus), bone level(cementoenamel junction and crestal bone) and root canal treated tooth(RCT) in digital bitewing, periapical and panoramic radiographs of permanent teeth in patients 15 years of age or older. This device provides additional information for dentists in examining radiographs of patients' teeth. This device is not intended as a replacement for a complete examination by the dentist or their clinical judgment that considers other relevant information from the image, patient history, or actual in vivo clinical assessment. Final diagnoses and patient treatment plans are the responsibility of the dentist. | | |
| Please select the types of uses (select one or both, as applicable). | ☑ Prescription Use (Part 21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C) | ? |
{4}
VELMENI for DENTISTS (V4D) Endo-Perio
K252953
510(k) Summary
In accordance with 21 CFR 807.87(h) and 21 CFR 807.92, the following 510(k) Summary for VELMENI for DENTISTS (V4D) is provided:
Submitter Information
Submitter:
Velmeni Inc.
333 West Maude Avenue, STE 207
Sunnyvale, CA 94085
Phone: 201-289-3500
Date Prepared: May 11, 2026
Contact Person: Mini Suri, CEO
Velmeni Inc.
Phone: 201-289-3500
Email: mini@velmeni.com
Identification of the Device
Trade Name: VELMENI for DENTISTS (V4D) Endo-Perio
Common Name: Medical image analyzer
Classification Name: Medical image analyzer
21CFR892.2070
Product Code: MYN
Device Class: Class II
Predicate Device(s)
Predicate Device: Velmeni for Dentists (K240003)
Reference Device: Overjet Charting Assist(K233590)
Reference Device: Denti.AI Detect (K230144)
Device Description
VELMENI for DENTISTS (V4D) Endo-Perio software medical device comprises of the following key components:
- Web Application Interface delivers front-end capabilities and is the point of interaction between the device and the user. Users may edit the outputs of the model.
- Machine Learning (ML) Engine delivers V4D Endo-Perio's core ML capabilities through the radiograph type classifier, rotation classifier, tooth numbering module, root canal treated tooth (RCT) module, tooth anatomy module, jaw anatomy module, and merging module. These functionalities are added to the previously cleared CADe device, Velmeni for Dentists (K240003)
- Backend API allows interaction between all the components, as defined in this section, in order to fulfill the user's requests on the web application interface.
{5}
- Queue receives and stores messages from Backend API to send to AI-Worker.
- AI-Worker accepts radiograph analysis requests from Backend API via the Queue, passes gray scale radiographs to the ML Engine in the supported extensions (jpeg and png), and returns the ML analysis results to the Backend API.
- Database and File Storage store critical information related to the application, including user data, patient profiles, analysis results, radiographs, and associated data.
The following non-medical interfaces are also available with VELMENI for DENTISTS (V4D) Endo-Perio:
- VELMENI BRIDGE (VB) acts as a conduit enabling data and information exchange between Backend API and third-party software like Patient Management or Imaging Software
- Rejection Review (RR) module captures the ML-detected conditions rejected by dental professionals to aid in future product development and to be evaluated in accordance with VELMENIs post-market surveillance procedure.
## Intended Use/ Indications for Use
VELMENI for DENTISTS (V4D) Endo-Perio is a concurrent-read, computer-assisted detection software intended to assist dentist in the clinical detection of tooth anatomy (enamel, dentine in crown, pulp, and root), jaw anatomy (mental foramen, inferior alveolar canal, and maxillary sinus), bone level (cementoenamel junction and crestal bone) and root canal treated tooth (RCT) in digital bitewing, periapical and panoramic radiographs of permanent teeth in patients 15 years of age or older. This device provides additional information for dentists in examining radiographs of patients' teeth.
This device is not intended as a replacement for a complete examination by the dentist or their clinical judgment that considers other relevant information from the image, patient history, or actual in vivo clinical assessment. Final diagnoses and patient treatment plans are the responsibility of the dentist.
## Substantial Equivalence and Technological Comparison
The proposed VELMENI for DENTISTS (V4D) Endo-Perio device is substantially equivalent to the primary predicate device; VELMENI for DENTISTS(K240003). Two reference devices were identified, Overjet Charting Assist (K233590) and Overjet Dental Assist (K210187).
The proposed VELMENI for DENTISTS (V4D) Endo-Perio is a concurrent-read, computer-assisted detection software intended to assist dentist in the clinical detection of tooth anatomy (enamel, dentine in crown, pulp, and root), bone level (cementoenamel junction and crestal bone), jaw anatomy (mental foramen, inferior alveolar canal, and maxillary sinus), and root canal treated tooth (RCT) in digital bitewing, periapical and panoramic radiographs of permanent teeth in patients 15 years of age or older. Users may edit the output segmentations and bone level landmarks of the model. 2D Non-Pathologies introduced in the proposed device will be accessible as a functionality from the existing V4D Analyze Page. The underlying architecture of device components between predicate and proposed device is the same.
The major difference between the proposed device and the predicate devices is that the proposed
{6}
device's output adds detection and segmentation capabilities for tooth anatomy, jaw anatomy, bone level and root canal treated tooth in the ML engine component versus the predicate device's output has detection of dental caries, restorations, fixed prostheses, and implants. Reference devices, K233590 Overjet Charting Assist, and K230144 Denti.AI Detect were identified because they demonstrate the Agency's familiarity with computer-assisted technology's ability to identify and detect anatomical regions introduced in the proposed device. The test methods used by V4D Endo-Perio to evaluate safety and effectiveness of the proposed device are acceptable. The differences in the software were evaluated against predetermined acceptance criteria and demonstrated acceptable results. The proposed device's output was evaluated in standalone performance testing to demonstrate the safety and effectiveness of the device.
## Performance Data
### Software Verification and Validation Tests:
Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submission for Device Software Functions." Verification of the software was conducted to ensure that the product works as designed. Validation was conducted to validate the design and the performance of the device to meet user needs and intended uses. VELMENI FOR DENTISTS (V4D) Endo-Perio passed all verification and validation software tests. Overall, the VELMENI for DENTISTS (V4D) Endo-Perio was found to be safe and effective for all intended users, uses, and use environments.
### Cybersecurity:
Software verification and validation testing, and cybersecurity testing per FDA guidance, "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions", were conducted to ensure that the software meets its specifications and performs as intended.
### Bench Testing:
The standalone analyses confirmed that the device exceeded the performance goals of tooth anatomy detection for the tooth and root canal treated tooth primary analyses and for the bone level analyses.
The software was tested on a dataset of the following composition: Bitewing tooth anatomy analyses were performed on a set of 128 patients, 272 images, and 1791 teeth. Periapical tooth anatomy analyses were performed on a set of 137 patients, 271 images, and 1213 teeth. Panoramic jaw anatomy analyses were performed on a set of 245 patients, 248 images, and 496 sides. A total of 137 root canal images were used for all root canal analyses which were provided by 89 bitewing patients, 110 periapical patients, and 134 panoramic patients. Bitewing bone level analyses were performed on a set of 193 patients and images and 1067 teeth. Periapical bone level analyses were performed on a set of 186 patients and images and 492 teeth.
The ground truth was assessed by three US-licensed dentists with more than 5 years of experience and a US licensed dental radiologist with advanced training in Oral and Maxillofacial Radiology. The three ground-truthers provided their segmentations and labels for each instance of interest, without consulting one another. The final ground truth was derived through the majority rule, and, for any radiograph in which such a consensus could not be derived, a dental radiologist (adjudicator)
{7}
considered all annotations by the 3 ground truthers and made the final independent ground-truthing decision. A consensus is defined when the intersection over union (IOU) of ground truthers' localizations is at least $70\%$ , and the labels of these overlapping localizations are the same.
The primary tooth endpoints of sensitivity and mean FPR per image produced p-values less than $< 0.001$ across dentine crown, enamel, pulp, and root for both bitewing and periapical images; indicating that tooth analysis had a sensitivity $\geq 85\%$ and a FPR per image $\leq 0.50$ . The primary root canal endpoints of sensitivity and specificity produced p-values less than $< 0.001$ across the bitewing, periapical, and panoramic image types, indicating that the performance goals were surpassed and that sensitivity $\geq 80\%$ and specificity $\geq 85\%$ . The primary bone level endpoint of mean absolute error produced p-values of $< 0.001$ when compared to the performance goal of 0.5 mm error tolerance for all comparisons. All segmentation outputs and bone level landmarks may be edited by the end user, as needed.
Table 1, Tooth Anatomy Primary Endpoint Sensitivity Analysis, Bitewing Images
| | Sensitivity | | |
| --- | --- | --- | --- |
| | % (n/N) | 95% CI1 | P-value2 |
| Dentine Crown | 100.0% (1743/1743) | NA, NA | NA |
| Enamel | 94.4% (1673/1773) | 92.6%, 96.0% | <0.001 |
| Pulp | 99.5% (1652/1661) | 98.8%, 99.9% | <0.001 |
| Root | 98.4% (1748/1777) | 97.6%, 99.0% | <0.001 |
Table 2, Tooth Anatomy Primary Endpoint Sensitivity Analysis, Periapical Images
| | Sensitivity | | |
| --- | --- | --- | --- |
| | % (n/N) | 95% CI1 | P-value2 |
| Dentine Crown | 97.9% (1139/1164) | 96.8%, 98.7% | <0.001 |
| Enamel | 96.2% (1126/1170) | 94.8%, 97.5% | <0.001 |
| Pulp | 99.6% (1121/1126) | 99.1%, 99.9% | <0.001 |
| Root | 99.8% (1208/1210) | 99.6%, 100.0% | <0.001 |
Table 3, Tooth Anatomy Primary Endpoint FPR Per Image, Bitewing Images
| | False Positive Rate | |
| --- | --- | --- |
| | % (n/N) | P-value2 |
| FP Counts per Dentine Crown Image, n (%) None | 100.0% (272/272) | |
| FP Counts per Dentine Crown Image Mean (SD) 95% CI† | 0 (NA) NA, NA | NA |
| FP Counts per Enamel Image, n (%) None 1 2 3 | 73.5% (200/272) 18.8% (51/272) 5.1% (14/272) 2.6% (7/272) | |
| FP Counts per Enamel Image Mean (SD) 95% CI† | 0.26 (0.442) 0.20, 0.34 | <0.001 |
{8}
| | False Positive Rate | |
| --- | --- | --- |
| | % (n/N) | P-value2 |
| FP Counts per Pulp Image, n (%) | | |
| None | 97.1% (264/272) | |
| 1 | 2.6% (7/272) | |
| 2 | 0.4% (1/272) | |
| FP Counts per Pulp Image | | |
| Mean (SD) | 0.03 (0.169) | <0.001 |
| 95% CI1 | 0.01, 0.06 | |
| FP Counts per Root Image, n (%) | | |
| None | 90.8% (247/272) | |
| 1 | 8.1% (22/272) | |
| 2 | 0.7% (2/272) | |
| 3 | 0.4% (1/272) | |
| FP Counts per Root Image | | |
| Mean (SD) | 0.09 (0.289) | <0.001 |
| 95% CI1 | 0.06, 0.13 | |
Table 4, Tooth Anatomy Primary Endpoint FPR Per Image, Periapical Images
| | False Positive Rate | |
| --- | --- | --- |
| | % (n/N) | P-value2 |
| FP Counts per Dentine Crown Image, n (%) | | |
| None | 91.8% (247/269) | |
| 1 | 7.4% (20/269) | |
| 2 | 0.4% (1/269) | |
| 3 | 0.4% (1/269) | |
| FP Counts per Dentine Crown Image | | |
| Mean (SD) | 0.08 (0.275) | <0.001 |
| 95% CI1 | 0.05, 0.12 | |
| FP Counts per Enamel Image, n (%) | | |
| None | 86.5% (230/266) | |
| 1 | 10.9% (29/266) | |
| 2 | 2.3% (6/266) | |
| 3 | 0.4% (1/266) | |
| FP Counts per Enamel Image | | |
| Mean (SD) | 0.14 (0.343) | <0.001 |
| 95% CI1 | 0.09, 0.18 | |
| FP Counts per Pulp Image, n (%) | | |
| None | 98.9% (268/271) | |
| 1 | 1.1% (3/271) | |
| FP Counts per Pulp Image | | |
| Mean (SD) | 0.01 (0.105) | <0.001 |
| 95% CI1 | 0.00, 0.03 | |
| FP Counts per Root Image, n (%) | | |
| None | 99.3% (269/271) | |
| 1 | 0.7% (2/271) | |
| FP Counts per Root Image | | |
| Mean (SD) | 0.01 (0.086) | <0.001 |
| 95% CI1 | 0.00, 0.02 | |
Table 5, Bone Level Mean Absolute Error Analysis, Bitewing and Periapical Images
{9}
| | Bitewing Images | | Periapical Images | |
| --- | --- | --- | --- | --- |
| | Mean (95% CI)1 | P-value1 | Mean (95% CI)1 | P-value1 |
| Distal Error | 0.15 (0.13, 0.17) | NA | -0.04 (-0.11, 0.03) | NA |
| Distal Absolute Error | 0.25 (0.23, 0.26) | <0.001 | 0.44 (0.39, 0.49) | <0.001 |
| Mesial Error | 0.17 (0.14, 0.19) | NA | -0.05 (-0.13, 0.03) | NA |
| Mesial Absolute Error | 0.27 (0.25, 0.29) | <0.001 | 0.47 (0.42, 0.52) | <0.001 |
The standalone primary analysis for jaw anatomy indicates the Mandibular Canal and Maxillary Sinus anatomical features reached the sensitivity and FPR per image estimates, with Mandibular Canal estimates of $99.8\%$ and 0.00 (p-values $< 0.001$ ), and Maxillary Sinus estimates of $99.8\%$ and 0.00 (p-values of $< 0.001$ generated for both). For the Mental Foramen tooth anatomy, a sensitivity estimate of $81.5\%$ was produced with a $95\%$ CI of $77.7\%$ , $85.3\%$ and a p-value of 0.220. For the FPR co-primary endpoint, an estimate of 0.18 with a $95\%$ CI of 0.13, 0.23 and a p-value of $< 0.001$ was produced. All segmentation outputs may be edited by the end user, if needed. Panoramic images are used for general examination and prescreening of the mandible due to low cost, ease of use and ability to cover an area. For procedures involving higher accuracy, advanced imaging would be followed up by dentists in practice and is indicated in the instructions for use to notify device users.
Table 6, Panoramic View Features Primary Endpoint Sensitivity Analysis, Panoramic Images
| | Sensitivity | | |
| --- | --- | --- | --- |
| | % (n/N) | 95% CI1 | P-value2 |
| Mandibular Canal | 99.8% (495/496) | 99.4%, 100.0% | <0.001 |
| Mental Foramen | 81.5% (393/482) | 77.7%, 85.3% | 0.220 |
| Maxillary Sinus | 99.8% (495/496) | 99.4%, 100.0% | <0.001 |
Subgroup analyses were conducted across subject sex, age, and sensor type. In the subgroup analyses, across all three analyses there was never a case of one subgroup factor performing significantly better or worse than any other subgroup levels within the same subgroup, as each $95\%$ CI always overlapped with at least one of the other subgroup level $95\%$ CI's when it was available. There was no consistent trend of subgroup performance that affected multiple different endpoints.
Generalizability was ensured through independence of the test set and representation across the subgroups within the data. The patient and teeth demographics for the study are well-represented. There was sufficient tooth anatomy, sensor, study site representation.
# Conclusion
Both the predicate device and the proposed VELMENI for DENTISTS (V4D) Endo-Perio device share the same intended purpose. Despite minor technological differences, these differences in technological features do not raise concerns regarding safety or effectiveness. Following the information reviewed as part of this 510k, it can be concluded that the VELMENI for DENTISTS (V4D) Endo-Perio is substantially equivalent to the predicate device.
