(133 days)
Denti. Al Auto-Chart is a Medical Image Management and Processing System (MIMPS) device aimed to assist dental professionals (Users), comprising general dental specialists, and dental hygienists, in detecting dental structures and producing dental charting data based on the interpretation of intraoral and extraoral 2D X-Ray images.
Denti.AI Auto-Chart is intended to assist in:
· Detecting natural dental structures: teeth and missing teeth
· Detecting dental structures added through past restment: implants, crowns, pontics, endodonic treatment, fillings
· Choosing treatment options
• Producing dental charts based on image analysis results as well as conditions added manually or produced by integrated CAD devices
The device is aimed to be used with images from the adult population only (≥22 years old and do not have remaining primary teeth). The device is not intended as a replacement for a complete clinical judgment that considers other relevant information from the image or patient history.
Denti.AI Auto-Chart is a Medical Image Management and Processing System (MIMPS) device aimed to assist dental professionals in detecting dental structures and producing dental charting data based on the interpretation of 2D X-Ray images. The device is intended to assist dental professionals in detecting teeth and missing teeth, numbering teeth, and detecting dental structures added through past restorative treatment, including implants, crowns, pontics, endodontic treatment, and fillings.
The Denti.AI Auto-Chart device's performance was evaluated through a standalone study to demonstrate its safety and effectiveness.
1. Acceptance Criteria and Device Performance:
The document explicitly states that "All conducted tests produced results that exceeded predefined acceptance criteria." However, the specific numerical acceptance criteria are not provided in the provided text. Only the "Value" and "95% Confidence Interval" of the device's reported performance are listed.
| Test ID | Test Name | Metric | Value | 95% Confidence Interval |
|---|---|---|---|---|
| 1 | Teeth Detection | Sensitivity (teeth in the field of view) | 97.4% | (96.6%, 98.2%) |
| PPV (Positive Predictive Value) | 99.6% | (99.3%, 99.9%) | ||
| 2 | Teeth Numbering | Overall classification accuracy | 85.9% | (82.6%, 88.9%) |
| 3 | Restorative Findings Identification | Sensitivity averaged across all restoration types | 88.5% | (86.1%, 90.6%) |
| Specificity averaged across all restoration types | 98.3% | (97.8%, 98.7%) | ||
| 4 | Binding Dental Findings to Teeth | Classification accuracy averaged across all findings | 98.3% | (97.5%, 99.0%) |
| 5 | Classifying Filling By Type | Classification accuracy averaged across all types | 98.0% | (96.9%, 98.9%) |
| 6 | Classifying Filling By Surface | Classification accuracy averaged across all surfaces | 88.9% | (87.0%, 90.7%) |
| 7 | Classifying Crowns by Type | Classification accuracy | 94.8% | (92.2%, 97.1%) |
| 8 | Summary Performance | Manual charting reduction rate | 71.2% | (68.2%, 74.1%) |
2. Sample Size for Test Set and Data Provenance:
- Sample Size: The test dataset consisted of 336 images (1 image per patient).
- Data Provenance: The images were "taken from the multiple dental clinics across the US." The patient population was "roughly uniformly distributed by age and gender." The study utilized a retrospective dataset, as the images were "taken from" existing clinics for testing.
3. Number of Experts for Ground Truth and Qualifications:
- Number of Experts: Two (2) experienced dental hygienists and one (1) experienced dentist.
- Qualifications of Experts: The document states "two experienced dental hygienists" and "an experienced dentist." Specific years of experience or board certifications are not specified beyond "experienced."
4. Adjudication Method for the Test Set:
The ground truth was established with the "help of two experienced dental hygienists with an experienced dentist reviewing cases of disagreement." This indicates an adjudication method where an expert (dentist) resolves discrepancies between the initial reviewers (dental hygienists). This can be described as a 2+1 model, where two initial reviewers establish the ground truth, and a third, more senior expert, resolves disagreements.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
No information is provided about a multi-reader multi-case (MRMC) comparative effectiveness study being performed. The study described is a standalone performance evaluation of the device.
6. Standalone (Algorithm Only) Performance:
Yes, a standalone study was conducted. The document states: "Denti.AI completed the standalone study according to the protocol to demonstrate the safety and effectiveness of the Denti.AI Auto-Chart device for its indications for use." The performance metrics listed in the table (Sensitivity, PPV, Accuracy) are characteristic of standalone algorithm performance.
7. Type of Ground Truth Used:
The ground truth used was expert consensus. It was established by "two experienced dental hygienists with an experienced dentist reviewing cases of disagreement."
8. Sample Size for the Training Set:
The sample size for the training set is not mentioned in the provided text. The document only describes the "testing dataset" of 336 images.
9. How Ground Truth for Training Set was Established:
The method for establishing ground truth for the training set is not mentioned in the provided text. Only the method for the testing set's ground truth is detailed.
{0}------------------------------------------------
November 22, 2022
Image /page/0/Picture/1 description: The image shows the logos of the Department of Health and Human Services and the Food and Drug Administration (FDA). The Department of Health and Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.
Denti.AI Technology Inc. % Donna-Bea Tillman Senior Consultant Biologics Consulting 1555 King Street ALEXANDRIA, VA 22314
Re: K222054
Trade/Device Name: Denti.AI Auto-Chart Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: LLZ Dated: October 25, 2022 Received: October 25, 2022
Dear Donna-Bea Tillman:
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
{1}------------------------------------------------
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 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 medical devices and radiation-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 2022.11.22
18:06:58 -05'00'
Lu Jiang, Ph.D. Assistant Director Diagnostic X-Ray Systems Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
{2}------------------------------------------------
Indications for Use
510(k) Number (if known) K222054
Device Name Denti.AI Auto-Chart
Indications for Use (Describe)
Denti. Al Auto-Chart is a Medical Image Management and Processing System (MIMPS) device aimed to assist dental professionals (Users), comprising general dental specialists, and dental hygienists, in detecting dental structures and producing dental charting data based on the interpretation of intraoral and extraoral 2D X-Ray images.
Denti.AI Auto-Chart is intended to assist in:
· Detecting natural dental structures: teeth and missing teeth
· Detecting dental structures added through past restment: implants, crowns, pontics, endodonic treatment, fillings
· Choosing treatment options
• Producing dental charts based on image analysis results as well as conditions added manually or produced by integrated CAD devices
The device is aimed to be used with images from the adult population only (≥22 years old and do not have remaining primary teeth). The device is not intended as a replacement for a complete clinical judgment that considers other relevant information from the image or patient history.
Type of Use (Select one or both, as applicable)
| Prescription Use (Part 21 CFR 801 Subpart D) | ✖ |
|---|---|
| Over-The-Counter Use (21 CFR 801 Subpart C) | ☐ |
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
In accordance with 21 CFR 807.87(h) and 21 CFR 807.92 the 510(k) Summary for the Denti.AI Auto-Chart is provided below.
1. SUBMITTER
| Applicant: | Denti.AI Technology Inc.99 Yorkville Ave, Suite 214Toronto, Ontario, Canada M5R3K5 |
|---|---|
| Contact/SubmissionCorrespondent: | Donna-Bea Tillman, Ph.D.Biologics Consulting Group1555 King Street, Suite 300Alexandria, VA 22314(410) 531-6542dtillman@biologicsconsulting.com |
| Date Prepared: | October 24, 2022 |
2. DEVICE
| Device Trade Name: | Dent.AI Auto-Chart |
|---|---|
| Device Common Name: | Image Processing System |
| Classification Name | 21 CFR 892.2050 Medical Image Management andProcessing System |
| Regulatory Class: | II |
| Product Code: | LLZ |
3. PREDICATE DEVICE
Predicate Device: Ewoosoft EzOrtho V1.3 (K220003)
DEVICE DESCRIPTION 4.
Denti.AI Auto-Chart is a Medical Image Management and Processing System (MIMPS) device aimed to assist dental professionals in detecting dental structures and producing dental charting data based on the interpretation of 2D X-Ray images. The device is intended to assist dental professionals in detecting teeth and missing teeth, numbering teeth, and detecting dental structures added through past restorative treatment, including implants, crowns, pontics, endodontic treatment, and fillings.
{4}------------------------------------------------
INTENDED USE/INDICATIONS FOR USE 5.
Denti.AI Auto-Chart is a Medical Image Management and Processing System (MIMPS) device aimed to assist dental professionals (Users), comprising general dentists, dental specialists, and dental hygienists, in detecting dental structures and producing dental charting data based on the interpretation of intraoral and extraoral 2D X-Ray images.
Denti.AI Auto-Chart is intended to assist in:
- Detecting natural dental structures: teeth and missing teeth .
- . Detecting dental structures added through past restorative treatment: implants, crowns, pontics, endodontic treatment, fillings
- . Choosing treatment options
- . Producing dental charts based on image analysis results as well as conditions added manually or produced by integrated CAD devices
The device is aimed to be used with images from the adult population only (≥22 years old and do not have remaining primary teeth). The device is not intended as a replacement for a complete clinician's review or clinical judgment that considers other relevant information from the image or patient history.
SUBSTANTIAL EQUIVALENCE 6.
Comparison of Indications
Both the subject Denti.AI Auto-Chart and the predicate Ewoosoft EzOrtho are intended for use to create dental charts to track patient information and treatments. Both devices are intended for use by trained dental practitioners who are responsible for making the final clinical decisions. The devices differ in the type of dental treatment (general dentistry for Auto-Chart and orthodontics for EzOrtho), but this does not change the fundamental purpose of the devices which is to create patient records.
Technological Comparisons
Table 1 compares the key technological feature of the subject devices to the predicate device Ewoosoft EzOrtho V1.3 (K220003).
| Denti-AI Auto-Chart(Proposed Device) | Ewoosoft EzOrtho V1.3 (K220003)(Predicate Device) | |
|---|---|---|
| 510(k) Number | TBD | K220003 |
| Applicant | Denti.AI Technology Inc. | Ewoosoft Co., Ltd. |
| ClassificationRegulation | CFR 892.2050 Medical ImageManagement and ProcessingSystem | CFR 892.2050 Medical ImageManagement and Processing System |
Technological Comparison Table 1:
{5}------------------------------------------------
| Denti-AI Auto-Chart(Proposed Device) | Ewoosoft EzOrtho V1.3 (K220003)(Predicate Device) | |
|---|---|---|
| Product Code | LLZ | LLZ |
| Prescription Use | Yes | Yes |
| Intended Users | Dental professionals | Licensed practitioners or dentists |
| Patient Population | Adult patients receiving generaldental care | Patients receiving orthodontic care |
| Platform | Cloud-based | IBM-compatible PC or PC network |
| Imaging Modality | 2-D intraoral or extraoral X-rays | Digital camera or radiologicalimaging device |
| Supported Fileformats | jpeg, jpg, tiff, tif, png, bmp,DICOM | bmp, jpg, png, tif, DICOM |
| Detection Features | Detecting and numbering teethDetecting and identifying pastrestorative treatments | Detecting anatomical landmarks |
| Imagemanipulationfeatures | Invert, brightness, contrast,sharpen, rotate, flip, annotations,zoom in/out, magnifier | Grayscale, invert, emboss, brightness,contrast, gamma, sharpen, median,despeckle, hue, saturation, equalizeflip, mirror, masking, rotate,annotation, cephalometric tracing,implant simulations |
| Technology | AI-based algorithms for thedetection of natural dentalstructures and structures addedthrough past restorative treatment | AI-based algorithms for detection ofvarious anatomical landmarks |
7. PERFORMANCE DATA
Biocompatibility Testing
There are no direct or indirect patient-contacting components of the subject device. Therefore, patient contact information is not needed for this device.
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
{6}------------------------------------------------
Premarket Submissions for Software Contained in Medical Devices." The software for this device was considered as a Moderate Level of Concern a malfunction of, or a latent design flaw in, the Software Device lead to an erroneous diagnosis or a delay in delivery of appropriate medical care that would likely lead to Minor Injury. Verification of the software was conducted to ensure that the product works as designed. Validation was conducted to check the design and performance of the product.
Bench Testing
Denti. AI completed the standalone study according to the protocol to demonstrate the safety and effectiveness of the Denti.AI Auto-Chart device for its indications for use.
Dataset
The testing dataset used in the study consisted of the 336 images (1 image per patient) taken from the multiple dental clinics across the US. The patient population was roughly uniformly distributed by age and gender. The following distribution of imaging modalities and sensor manufacturers were present in the testing dataset:
Image distribution by Modality
Image /page/6/Figure/7 description: The image is a pie chart that shows the image distribution by modality. The three modalities are periapical, bitewing, and pan. Periapical is 35.4%, bitewing is 45.5%, and pan is 19.0%.
{7}------------------------------------------------
Image /page/7/Figure/2 description: This image is a pie chart showing the market share of different dental imaging companies. Dexis has the largest market share at 31.3%, followed by Gendex at 19.0% and Kavo at 12.2%. Air Techniques has 9.5%, Carestream has 8.0%, and Duerr has 7.7%. Vatech has 4.5%, while Acteon and Sirona each have 2.1%. Soredex and Palodex each have 1.8%.
Image distribution by Sensor Manufacturer
Reference Standard
The ground truth annotations (GT) were used as the reference standard when measuring the device performance. The GT was established with the help of two experienced dental hygienists with an experienced dentist reviewing cases of disagreement.
Study Results
The primary tests and the metrics are listed in the table below:
- "Sensitivity (teeth in the field of view)" of Teeth Detection shows the percentage of ● actual positive teeth (teeth annotated in the GT) in the image field of view that are successfully found by the device
- "PPV" of Teeth Detection shows the percentage of teeth found by the device that are actual positive teeth
- "Overall classification accuracy" of Teeth Numbering shows the percentage of detected teeth that are correctly numbered by the device according to the standard dental notation
- "Sensitivity averaged across all restoration types" of Restorative Findings Identification shows the percentage of actual positive teeth (teeth showing the restorative finding in the GT with the matching restoration type) that are successfully classified by the device as positive
- . "Specificity averaged across all restoration types" of Restorative Findings Identification shows the percentage of actual negative teeth (teeth that do NOT show the restorative finding in the GT with the matching restoration type) that are successfully classified by the device as negative
- "Classification accuracy averaged across all findings" of Binding Dental Findings to ● Teeth shows the percentage of findings that are associated with the correct tooth
{8}------------------------------------------------
- . "Classification accuracy averaged across all types" of Classifying Filling By Type shows the percentage of teeth with detected fillings that are correctly classified by the filling type
- . " Classification accuracy averaged across all surfaces" of Classifying Filling By Surface shows the percentage of teeth with detected fillings that are correctly classified by affected surfaces
- . "Classification accuracy" of Classifying Crowns by Type shows the percentage of teeth with detected crowns that are correctly classified by the crown type
- . "Manual charting reduction rate" of the Summary Performance shows the percentage of reduction in the number of manual operations when pre-filling the charting data with Denti.AI Auto-Chart compared to entering all the charting records manually
| Test ID | Test Name | Metric | Value | 95% Confidence Interval |
|---|---|---|---|---|
| 1 | Teeth Detection | Sensitivity (teeth in the field ofview) | 97.4% | (96.6%, 98.2%) |
| PPV | 99.6% | (99.3%, 99.9%) | ||
| 2 | Teeth Numbering | Overall classification accuracy | 85.9% | (82.6%, 88.9%) |
| 3 | Restorative FindingsIdentification | Sensitivity averaged across allrestoration types | 88.5% | (86.1%, 90.6%) |
| Specificity averaged across allrestoration types | 98.3% | (97.8%, 98.7%) | ||
| 4 | Binding Dental Findings toTeeth | Classification accuracy averagedacross all findings | 98.3% | (97.5%, 99.0%) |
| 5 | Classifying Filling ByType | Classification accuracy averagedacross all types | 98.0% | (96.9%, 98.9%) |
| 6 | Classifying Filling BySurface | Classification accuracy averagedacross all surfaces | 88.9% | (87.0%, 90.7%) |
| 7 | Classifying Crowns byType | Classification accuracy | 94.8% | (92.2%, 97.1%) |
| 8 | Summary Performance | Manual charting reduction rate | 71.2% | (68.2%, 74.1%) |
Conclusions
All conducted tests produced results that exceeded predefined acceptance criteria. The Summary Performance "Manual charting reduction rate" metric shows that the number of manual operations is reduced by over 70% when using Denti.AI Auto-Chart for initial dental chart pre-filling compared to the fully manual entry of the same dental charting information.
Stratified analysis by patient gender and age demonstrated that there is no significant difference in any of the reported endpoints. Stratified analysis by sensors demonstrated the overall high level of generalizability: no sensor is a clear outlier. Stratified analysis by modality demonstrated differences in two main endpoints:
- Classification accuracy of teeth numbering is higher on extraoral images. This difference can be explained by the fact that extraoral images show a full mouth picture, whereas intraoral images show only a segment of the jaw, sometimes as few as 3-4 teeth. Numbering teeth on intraoral images is naturally more challenging than on panoramic images
{9}------------------------------------------------
- . Restorative Findings Identification sensitivity metric is higher on intraoral images. The main difference is in detecting crowns and fillings, whereas the performance in detecting implants and endodontic treatments is close for each modality. The difference can be explained by the fact that intraoral images have a much higher spatial resolution compared to panoramic images While having some natural tradeoffs in terms of producing charting data, both modalities demonstrated close estimates of Summary Performance metrics ("Manual charting reduction rate")
Animal Testing
Not applicable. Animal studies are not necessary to establish the substantial equivalence of this device.
Clinical Data
Not applicable. Clinical studies are not necessary to establish the substantial equivalence of this device.
CONCLUSION 8.
The predicate device and subject device have the same intended use, as they are both intended for use to create dental charts to track patient information and treatments. Both devices are intended for use by trained dental practitioners who are responsible for making the final clinical decisions. Although there are technical differences, as discussed above, these differences in technological characteristics do not raise different questions of safety and effectiveness. The predefined Acceptance Criteria established for the stand-alone study are based on the current state of dental practice and are appropriate to demonstrate that Auto-Chart performs in accordance with specifications and will meet user needs and intended uses.
Based on the detailed comparison between the predicate devices and the subject devices, the software verification testing and performance testing, the Denti.AI Auto-Chart can be found substantially equivalent to the predicate device.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).