DTX Studio Clinic is a computer assisted detection (CADe) device that analyses intraoral radiographs to identify and localize dental findings, which include caries, calculus, periapical radiolucency, root canal filling deficiency, discrepancy at margin of an existing restoration and bone loss.

The DTX Studio Clinic CADe functionality is indicated for the concurrent review of bitewing and periapical radiographs of permanent teeth in patients 15 years of age or older.

Device Description

DTX Studio Clinic features an AI-powered Focus Area Detection algorithm which analyzes intraoral radiographs for potential dental findings or image artifacts. The detected focus areas can be converted afterwards to diagnostic findings after approval by the user. The following dental findings can be detected by the device: Caries, Discrepancy at margin of an existing restoration, Periapical radiolucency, Root canal filling deficiency, Bone loss, Calculus.

AI/ML Overview

The provided text describes the acceptance criteria and the study that proves the device meets those criteria for the DTX Studio Clinic 3.0.

Here's the breakdown:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" as a pass/fail threshold, but rather presents the performance results from the standalone (algorithm only) and clinical (human-in-the-loop) studies. The acceptance is implicitly based on these results demonstrating clinical benefit and safety.

Standalone Performance (Algorithm-Only)

Dental Finding Type	Metric	Reported Performance (95% CI)
Caries	Sensitivity	0.70 [0.65, 0.75]
	Mean IoU	58.6 [56.2, 60.9]%
	Mean Dice	71.9 [69.9, 74.0]%
Periapical Radiolucency	Sensitivity	0.68 [0.59, 0.77]
	Mean IoU	48.9 [44.9, 52.9]%
	Mean Dice	63.7 [59.9, 67.5]%
Root Canal Filling Deficiency	Sensitivity	0.95 [0.91, 0.99]
	Mean IoU	51.9 [49.3, 54.6]%
	Mean Dice	66.9 [64.3, 69.4]%
Discrepancy at Restoration Margin	Sensitivity	0.82 [0.77, 0.87]
	Mean IoU	48.4 [46.0, 50.7]%
	Mean Dice	63.5 [61.3, 65.8]%
Bone Loss	Sensitivity	0.78 [0.75, 0.81]
	Mean IoU	44.8 [43.4, 46.3]%
	Mean Dice	60.1 [58.7, 61.6]%
Calculus	Sensitivity	0.80 [0.76, 0.84]
	Mean IoU	55.5 [53.7, 57.3]%
	Mean Dice	70.1 [68.4, 71.7]%
Overall	Sensitivity	0.79 [0.74, 0.84]
	Precision	0.45 [0.40, 0.50]

Clinical Performance (Human-in-the-Loop)

Metric	Reported Performance (95% CI)
Overall AUC Increase (Aided vs. Unaided)	8.7% [6.5, 10.9]%
Caries AUC Increase	6.1%
Periapical Radiolucency AUC Increase	10.2%
Root Canal Filling Deficiency AUC Increase	13.5%
Discrepancy at Restoration Margin AUC Increase	10.1%
Bone Loss AUC Increase	5.6%
Calculus AUC Increase	7.2%
Overall Instance Sensitivity Increase	22.4% [20.1, 24.7]%
Caries Sensitivity Increase	19.6%
Bone Loss Sensitivity Increase	23.5%
Calculus Sensitivity Increase	18.1%
Discrepancy at Restoration Margin Sensitivity Increase	28.5%
Periapical Radiolucency Sensitivity Increase	20.6%
Root Canal Filling Deficiency Sensitivity Increase	27.4%
Overall Image Level Specificity Decrease	8.7% [6.6, 10.7]%

2. Sample Size and Data Provenance

Test Set (Standalone Performance):
- Sample Size: 452 adult intraoral radiograph (IOR) images (bitewings and periapical radiographs).
- Data Provenance: Not explicitly stated, but implicitly retrospective as they were "assembled" and "ground-truthed" for the study.
Test Set (Clinical Performance Assessment - MRMC Study):
- Sample Size: 216 periapical and bitewing IOR images.
- Data Provenance: Acquired in US-based dental offices by either sensor or photostimulable phosphor plates. This suggests retrospective collection from real-world clinical settings in the US.

3. Number of Experts and Qualifications for Ground Truth

Test Set (Standalone Performance):
- Number of Experts: A group of 10 dental practitioners followed by an additional expert review.
- Qualifications: "Dental practitioners" and "expert review" (no further details on experience or specialized qualifications are provided for this set).
Test Set (Clinical Performance Assessment - MRMC Study):
- Number of Experts: 4 ground truthers.
- Qualifications: All ground truthers have "at least 20 years of experience in reading of dental x-rays."

4. Adjudication Method for the Test Set

Test Set (Standalone Performance): "ground-truthed by a group of 10 dental practitioners followed by an additional expert review." - The specific consensus method (e.g., majority vote) is not explicitly stated.
Test Set (Clinical Performance Assessment - MRMC Study): Ground truth was defined by 4 ground truthers with a 3 out of 4 consensus. This is an explicit 3+1 (or simply 3 out of 4) adjudication method.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

Yes, a MRMC comparative effectiveness study was done.
Effect Size of Human Readers Improvement with AI vs. Without AI Assistance:
- The primary endpoint, overall Area Under the Curve (AUC), showed a statistically significant increase of 8.7% (CI [6.5, 10.9], p<0.001) for all dental finding types combined in the aided reading arm compared to the control (unaided) arm.
- Instance-level sensitivity (reader's ability to detect existing dental findings) improved substantially by 22.4% (CI [20.1, 24.7]) overall.
- Specific AUC increases per finding type ranged from 5.6% (bone loss) to 13.5% (root canal filling deficiency).
- Specific sensitivity increases per finding type ranged from 18.1% (calculus) to 28.5% (discrepancy at restoration margin).
- A mild decrease in image-level specificity of 8.7% (CI [6.6, 10.7]) was observed.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance assessment was done.
This assessment measured the performance of the AI-powered Focus Area Detection algorithm "by itself, in the absence of any interaction with a dentist." The results (Overall sensitivity, precision, and Mean IoU/Dice scores per finding type) are detailed in the table in section 1 above.

7. Type of Ground Truth Used

Expert Consensus:
- For the standalone performance study, ground truth was established by "a group of 10 dental practitioners followed by an additional expert review."
- For the clinical performance (MRMC) study, ground truth was defined by "4 ground truthers with a 3 out of 4 consensus," all having "at least 20 years of experience in reading of dental x-rays."

8. Sample Size for the Training Set

The document does not specify the sample size for the training set. It only describes the test sets.

9. How Ground Truth for the Training Set Was Established

The document does not describe how the ground truth for the training set was established. It only refers to the training process generically as "supervised machine learning" and focuses on the ground truthing of the test sets.

Summary

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

March 28, 2023

Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo features the letters 'FDA' in a blue square, followed by the words 'U.S. FOOD & DRUG' and 'ADMINISTRATION' in blue text.

Nobel Biocare AB % Wim Vrydag QA/RA Manager Nobel Biocare c/o Medicim NV Stationsstraat 102 Mechelen, 2800 BELGIUM

Re: K221921

Trade/Device Name: DTX Studio Clinic 3.0 Regulation Number: 21 CFR 892.2070 Regulation Name: Medical Image Analyzer Regulatory Class: Class II Product Code: MYN Dated: February 24, 2023 Received: February 27, 2023

Dear Wim Vrydag:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's

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

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 (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Lu Jiang

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

Enclosure

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

Indications for Use

510(k) Number (if known) K221921

Device Name DTX Studio Clinic 3.0

Indications for Use (Describe)

The DTX Studio Clinic CADe functionality is indicated for the concurrent review of bitewing and periapical radiographs of permanent teeth in patients 15 years of age or older.

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

Image /page/3/Picture/1 description: The image contains the logo for Nobel Biocare. On the left side of the logo is a red symbol that looks like the letter N. To the right of the symbol is the company name, "Nobel Biocare", in black font. The word "Nobel" is on top of the word "Biocare", and there is a trademark symbol next to the word "Biocare".

510(k) Summary

I. Submitter

Submitted by: Nobel Biocare c/o Medicim NV Stationsstraat 102 Mechelen, 2800, Belgium Establishment Registration No. 3005739655 Telephone: +32 15 44 32 00 Facsimile: +32 15 44 32 09 Email: wim.vrydag@envistaco.com

Submitted for: Nobel Biocare AB Vastra Hamngatan 1 Göteborg, SE-411 17, Sweden Establishment Registration No. 9611992 Date Prepared: March 28, 2023

II. Device

Name of Device: DTX Studio Clinic 3.0 Manufacturer: Nobel Biocare AB Common or Usual Name: Medical Image Analyzer Regulation Number: 21 CFR 892.2070 Classification Name: Medical Image Analyzer Product Code: MYN Device Class: II

III. Predicate Device

Substantial equivalence is claimed to the following devices:

Primary Predicate:

Predicate Device: Videa Caries Assist Predicate 510(k): K213795 Company: Videa Health, Inc Common or Usual Name: Medical Image Analyzer Regulation Number: 21 CFR 892.2070 Classification Name: Medical Image Analyzer

{4}------------------------------------------------

Nobel Biocare AB Traditional 510(k)

Image /page/4/Picture/1 description: The image shows the logo for Nobel Biocare. The logo consists of a red square with a stylized white "N" inside of it. To the right of the square is the text "Nobel Biocare" in black font, with the trademark symbol next to "Biocare".

Product Code: MYN Device Class: II

Secondary Predicate:

Predicate Device: Second Opinion Predicate 510(k): K210365 Company: Pearl Inc. Common or Usual Name: Medical Image Analyzer Regulation Number: 21 CFR 892.2070 Classification Name: Medical Image Analyzer Product Code: MYN Device Class: II

IV. Device Description

Caries: Caries is defined as caries, showing as area with radiographically lower density on a tooth, but does not include occlusal secondary caries under dental fillings.
Discrepancy at margin of an existing restoration: A discrepancy at margin is defined as radiographically visible discontinuities (gaps. overhangs) between outline/margin of dental restoration (e.g, fillings, inlays or crowns/bridges) and remaining tooth substance, also called as misfit', poor fit' or `not-perfectly seated'. Note that non-radiopaque cement/bonding material may radiographically appear as a space.
Periapical radiolucency: A periapical radiolucency is defined as a radiolucent area or radiographic observation of low bone density related to the apical part of the root. A widening of the periodontal ligament is not included.
. Root canal filling deficiency: The root canal filling appears radiographically too short (more than 2mm from the radiographic apex) and/or too small in diameter, or the root filling is not radiographically homogenously dense (e.g., with visible void in root filling or gaps between filling and root dentin), or otherwise show absence of radioopaqueness.
. Bone loss: Bone loss is defined as a radiographically lower density of the marginal bone and/or a lower crest of the alveolar bone compared to what is considered normal for healthy natural dentition. Healthy natural dentition refers to teeth that have not experienced any marginal bone loss and have an alveolar bone that covers the root of the tooth. It is indicated by a focus area annotation, however, the size of the rectangular bounding box is not indicative of the amount of bone loss.

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

Image /page/5/Picture/1 description: The image contains the logo for Nobel Biocare. The logo consists of a red square with a stylized white "N" inside it. To the right of the square is the text "Nobel Biocare" in black font, with the word "Nobel" stacked on top of the word "Biocare". The "TM" symbol is located to the upper right of the word "Biocare".

Calculus: Calculus is a hard, mineralized form of dental plaque that is visible on radiographic images as radiopaque material attached to the tooth surface.

V. Indications for Use

The DTX Studio Clinic CADe functionality is indicated for use by dentists for the concurrent review of bitewing and periapical radiographs of permanent teeth in patients 15 years of age or older.

VI. Substantial Equivalence

Comparing indications:

DTX Studio Clinic 3.0 and the predicate devices (Videa Caries Assist (K213795) and Second Opinion (K210365)) all analyze dental intraoral radiographs and annotate suspected areas of interest for the dentist to review. Both DTX Studio Clinic 3.0 and the primary predicate, Videa Caries Assist perform concurrent detection of dental findings. DTX Studio Clinic identifies four types of dental findings: caries, apical lesions (periapical radiolucency), root canal defect, marginal defect (discrepancy at the margin), bone loss and calculus, while the primary predicate, Videa Caries Assist, only identifies caries. However, the secondary predicate, Second Opinion, also identifies four different types of dental findings: identifies 4 types of dental findings, caries, discrepancy at the margin, calculus, and periapical radiolucency. Although the pathological dental findings differ, they all share the same intended use, as they are all computer-assisted detection devices that accept dental radiographs as inputs and use supervised machine learning to identify and highlight ROIs. The subject device, is intended for a patient population of patients from the age of 15 years where as the primary predicate, Videa Caries Assist is intended only for intraoral radiographs of patients older than 22 years. The secondary predicate, Second Opinion is intended for a patient population of patients from the age of 12 years. Both DTX Studio Clinic and Second Opinion support the dentist on the review of both bitewing and periapical radiographs. The differences in Indications for Use do not constitute a new indented use, as the subject and primary predicate are both intended to assist the dentifying suspected areas of interest in intraoral radiographs

Technical comparisons

The comparison of the technological features of DTX Studio Clinic and the predicate devices can be found in table 1.

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

Image /page/6/Picture/1 description: The image shows the logo for Nobel Biocare. The logo consists of a red square with a stylized white "N" inside it, followed by the words "Nobel Biocare" in black text. The word "Nobel" is on the top line, and "Biocare" is on the bottom line with a trademark symbol.

DTX Studio Clinic 3.0 K221921

Table 1: Comparison of DTX Studio Clinic to Predicate Devices

Criteria	DTX Studio Clinic3.0(Subject Device)(K221921)	Videa Caries AssistPredicate Device(Primary)(K213795)	Pearl - SecondOpinionSecondary PredicateDevice(K210365)	Comments
Regulatory Information
Regulation #	892.2070	892.2070	892.2070	Same
Classification Name	Medical ImageAnalyzer	Medical ImageAnalyzer	Medical ImageAnalyzer	Same
Device Class	II	II	II	Same
Product Code	MYN	MYN	MYN	Same
Indication for Use / Intended Use
Indications for UseStatement	DTX Studio Clinic is acomputer assisteddetection (CADe)device that analysesintraoral radiographsto identify and localizedental findings, whichinclude caries,calculus, periapicalradiolucency, rootcanal fillingdeficiency,discrepancy at the	Videa Caries Assist isa computer-assisteddetection (CADe)device that analyzesintraoral radiographsto identify and localizecarious lesions. VideaCaries Assist isindicated for use byboard licensed dentistsfor the concurrentreview of bitewing(BW) radiographs	Second Opinion® is acomputer aideddetection ("CADe")software to identifyand mark regions inrelation to suspecteddental findings whichinclude Caries,Discrepancy at themargin of an existingrestoration, Calculus,Periapicalradiolucency, Crown	Similar to PrimaryPredicate, except forsome additional dentalfindings and age ofpatient population.Patient population issame as the SecondaryPredicate, but thedifferences do notraise a concern ofsubstantial
margin of an existingrestoration and boneloss. The DTX StudioClinic CADefunctionality isindicated for use bydentists for theconcurrent review ofbitewing andperiapical radiographsof permanent teeth inpatients 15 years ofage or older.		acquired from adultpatients aged 22 yearsor older.	(metal, includingzirconia & non-metal),Filling (metal & non-metal), Root canal,Bridge and Implants. Itis designed to aiddental healthprofessionals to reviewbitewing andperiapical radiographsof permanent teeth inpatients 12 years ofage or older as asecond reader.	equivalence asdemonstrated byperformance testing

Technological Characteristics
Focus Area Detection	Automated DetectionOutputMessage indicating ifand how many dentalfindings are detected	Automated DetectionOutputMessage indicating ifand how many cariouslesions were detected.	Automated DetectionOutputBounding boxes	Same as PrimaryPredicate
	Set of togglablebounding boxesaround suspecteddental findings	Set of togglablebounding boxesaround suspectedlesions
	Dental FindingsCaries, periapicalradiolucency, root	Dental FindingsCaries	Dental FindingsCaries, discrepancy atthe margin, calculus	Similar to PredicateDevices, additionaldental findings are
	canal fillingdeficiency,discrepancy at themargin of an existingrestoration, bone lossand calculus	and periapicalradiolucency	identified but thedifferences do notraise a concern ofsubstantialequivalence asdemonstrated byperformance testing.Same as PrimaryPredicate
Reader workflowConcurrent Reading	Reader workflowConcurrent Reading	Reader workflowSecond reader
Algorithm	Algorithm	Algorithm	Same
Supervised machinelearning	Supervised machinelearning	Supervised machinelearning
Patient populationPermanent teeth inpatients 15 years ofage or older	Patient populationAdults ≥ 22 years	Patient populationPermanent teeth inpatients 12 years ofage or older	Similar to PredicateDevices, thedifferences do notraise a concern ofsubstantialequivalence asdemonstrated byperformance testing.
RadiographsBitewing andPeriapical	RadiographsBitewing	RadiographsBitewing andPeriapical	Same as SecondaryPredicate, thedifferences do notraise a concern ofsubstantialequivalence asdemonstrated byperformance testing.
Intended user	Dentists	US license dentists	Dentists	Same

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

Image /page/7/Picture/1 description: The image contains the logo for Nobel Biocare. The logo consists of a stylized red letter "N" on the left, followed by the words "Nobel Biocare" in black font on the right. The word "Nobel" is above the word "Biocare", and there is a trademark symbol after the word "Biocare".

DTX Studio Clinic 3.0
K221921

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

Image /page/8/Picture/1 description: The image shows the logo for Nobel Biocare. The logo consists of a red square with an "N" shape inside of it on the left. To the right of the square is the text "Nobel Biocare" in black font. The word "Nobel" is on top of the word "Biocare".

DTX Studio Clinic 3.0
K221921

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

Image /page/9/Picture/1 description: The image contains the logo for Nobel Biocare. The logo consists of a red square with a stylized white "N" inside of it. To the right of the square is the text "Nobel Biocare" in black font, with the trademark symbol next to the word Biocare.

VII. Performance Data

DTX Studio Clinic 3.0 is designed and manufactured under the Quality System Regulations as outlined in 21 CFR § 820 and ISO 13485:2016 Standards. This device is in conformance with the applicable parts of IEC 62304:2006+A1:2015 standards. Design Control Activities. including risk management following the ISO 14971:2019, verification/validation testing, were conducted and are included in this submission.

The performance of the subject device was verified and validated following the guidance provided in FDA Guidance General Principles of Software Validation. This documentation includes testing which demonstrates that the requirements for the features have been met. Software documentation for Moderate Level of Concern and description of respective verification and validation activities, per the FDA guidance document, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" issued on May 11, 2005, is also included as part of this submission.

Software Validation

Software verification and validation testing was conducted on the subject device 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".

Standalone Performance

A standalone performance assessment was conducted to measure the performance of the AIpowered Focus Area Detection algorithm by itself, in the absence of any interaction with a dentist. A separate dataset of 452 adult IOR images including both bitewings and periapical radiographs, was assembled. The dataset was ground-truthed by a group of 10 dental practitioners followed by an additional expert review. In total the data set contained 1767 dental findings (365 caries, 110 periapical radiolucencies, 145 root canal filling deficiencies, 216 discrepancies at restoration margins, 588 bone loss instances and 343 calculus instances).

The standalone overall sensitivity was found to be 0.79 (with 95% CI [0.74, 0.84]), standalone sensitivity per dental finding type is listed in Table 2. Overall precision was found to be 0.45 (with 95% CI [0.40, 0.50]). The standalone localization accuracy was studied by measuring the intersection over union (IoU) and the Dice score (see Table 2) of the detected findings. Mean Dice score was found to be in range of 53.5% to 71.9%, indicating a high overlap between the AI detected findings and the ground truth annotations.

DENTAL FINDING TYPE	SENSITIVITY	MEAN IOU (%)	MEAN DICE (%)
CARIES	0.70 [0.65, 0.75]	58.6 [56.2, 60.9]	71.9 [69.9, 74.0]
PERIAPICALRADIOLUCENCY	0.68 [0.59, 0.77]	48.9 [44.9, 52.9]	63.7 [59.9, 67.5]

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

Image /page/10/Picture/1 description: The image shows the logo for Nobel Biocare. On the left is a red square with a stylized "N" inside. To the right of the square is the text "Nobel Biocare" in black font, with a trademark symbol next to the word "Biocare".

ROOT CANAL FILLINGDEFICIENCY	0.95 [0.91, 0.99]	51.9 [49.3, 54.6]	66.9 [64.3, 69.4]
DISCREPANCY ATRESTORATION MARGIN	0.82 [0.77, 0.87]	48.4 [46.0, 50.7]	63.5 [61.3, 65.8]
BONE LOSS	0.78 [0.75, 0.81]	44.8 [43.4, 46.3]	60.1 [58.7, 61.6]
CALCULUS	0.80 [0.76, 0.84]	55.5 [53.7, 57.3]	70.1 [68.4, 71.7]

Table 2: Standalone performance results of the Focus Area Detection algorithm for the 6 dental finding types. For each measure the 95% CI range is listed.

Clinical Performance Assessment

A retrospective fully crossed, multi reader, multi case study was performed to demonstrate that the aid of IOR Focus Area Detection algorithm increases the diagnostic detection and localization performance of dentists for dental findings in IORs. The primary endpoint was a significant Area Under the Curve (AUC) increase in the study arm compared to the control arm. The AUC figure of merit value was obtained based on an AFROC (Alternative Free Response Receiver Operating Characteristic) curve analysis.

The dataset contains 216 periapical and bitewing IOR images that were acquired in US-based dental offices by either sensor or photostimulable phosphor plates. The images were obtained from both male (43%) and female (42%) patients with ages ranging between 15 and 93 years (average age 49.4). The ground truth was defined by 4 ground truthers with a 3 out of 4 consensus. All ground truthers have at least 20 years of experience in reading of dental x-rays.

The IORs were read by 30 readers in a fully crossed design, with half of the readers starting with unaided reading and the other half with aided reading by the support of the AI introduced to DTX Studio Clinic 3.0. After a wash-out period of 4 weeks, the reader groups were swapped, and reading was repeated.

The analysis showed the increase of the AUC from the control arm to the study arm to be highly significant (p<0.001), with an overall increase for all dental finding types together of 8.7% (CI [6.5, 10.9]). The breakdown of the AUC difference per dental finding (secondary endpoints) showed a significant increase for the aided reading for all dental findings compared to the unaided reading. In detail, an increase of 13.5% for root canal filling deficiency, 10.2% for periapical radiolucency, 10.1% for discrepancy at margin of an existing restoration, 7.2% for calculus, 6.1% for caries, and 5.6% for bone loss. The improvement in aided reader performance versus unaided reader performance was moreover seen for each of the 30 readers.

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

Image /page/11/Picture/1 description: The image shows the logo for Nobel Biocare. On the left is a red, stylized letter N. To the right of the N is the company name, "Nobel Biocare", in black text. The TM symbol is in superscript to the right of the word Biocare.

Image /page/11/Figure/3 description: The image is a plot titled "Average AFROC". The plot shows two curves, one in red and one in cyan. The x-axis is labeled "1-Sp" and ranges from 0.00 to 1.00, while the y-axis is labeled "TP/lesions (Se)" and ranges from 0.00 to 1.00. The cyan curve is higher than the red curve.

Figure I : Averaged, interpolated AFROC curve summarizing the overall detection performance. (Control arm in red, Study arm in blue)

Sensitivity on instance level, i.e. the reader's ability to detect existing dental findings, improved substantially for aided reading compared to unaided reading: overall by 22.4% (with CI [20.1, 24.7]), as well as for each dental finding type separately: 19.6% for caries, 23.5% for bone loss, 18.1% for calculus, 28.5% for discrepancy at restoration margin, 20.6% for periapical radiolucency and 27.4% for root canal filling deficiency. A mild decrease in specificity at image level was observed for the aided reading when compared to unaided reading (overall by 8.7 % with CI [6.6, 10.7]).

VIII. Conclusion

The predicate and the subject device have the same intended use as they are both computerassisted detection devices that accept dental radiographs as inputs and use supervised machine learning to identify and highlight dental findings. Although there are technological differences, as discussed above, these differences do not raise different questions of safety and effectiveness, as overall functionality as a reading aid for radiographs and utility within the

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

Image /page/12/Picture/1 description: The image contains the logo for Nobel Biocare. On the left is a red symbol that looks like a stylized letter N. To the right of the symbol is the text "Nobel Biocare" in a sans-serif font. The word "Nobel" is above the word "Biocare", and there is a trademark symbol after the word "Biocare".

associated clinical workflows offered to the dental professional by the subject and predicate are the same.

Software testing verified the device functioned as intended. The results of the Clinical Performance Assessment demonstrate that the performance of DTX Studio Clinic 3.0 is comparable to that of Videa Caries Assist (K213795). Therefore DTX Studio Clinic 3.0 can be found substantially equivalent to Videa Caries Assist (K213795).

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.