(224 days)
Yes
The device description explicitly mentions "Machine Learning Modules ("ML Modules")" and states, "Second Opinion PC uses machine learning to detect periapical radiolucencies."
No.
The device is a diagnostic aid, providing detection of periapical radiolucencies. It does not actively treat or deliver therapy.
Yes
The device, Second Opinion PC, is explicitly described as "computer aided detection ("CADe") software to aid dentists in the detection of periapical radiolucencies," and it "produce[s] detection output" and displays "polygonal overlays atop the original radiograph which indicate to the practitioner which teeth contain which detected periapical radiolucencies that may require clinical review." This functionality directly supports the identification and interpretation of medical conditions, which falls under the definition of a diagnostic device.
Yes
The device is described purely as software components (API, ML Modules, Client UI) and its functionality is entirely based on processing images and providing visual overlays. There is no mention of hardware components provided or required by the device itself beyond the input images.
No.
The device analyzes medical images (radiographs) to aid in the detection of periapical radiolucencies, which are internal to the body, and does not involve the in vitro examination of specimens derived from the human body.
No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
Second Opinion PC is a computer aided detection ("CADe") software to aid dentists in the detection of periapical radiolucencies by drawing bounding polygons to highlight the suspected region of interest.
It is designed to aid dental health professionals to review periapical radiographs of permanent teeth in patients 12 years of age or older as a second reader.
Product codes
MYN
Device Description
Second Opinion PC (Periapical Radiolucency Contouring) is a radiological, automated, computer-assisted detection (CADe) software intended to aid in the detection of periapical radiolucencies on periapical radiographs using polygonal contours. The device is not intended as a replacement for a complete dentist's review or their clinical judgment which considers other relevant information from the image, patient history, or actual in vivo clinical assessment.
Second Opinion PC consists of three parts:
- Application Programing Interface ("API")
- Machine Learning Modules ("ML Modules")
- Client User Interface ("Client")
The processing sequence for an image is as follows:
- Images are sent for processing via the API
- The API routes images to the ML modules
- The ML modules produce detection output
- The UI renders the detection output
The API serves as a conduit for passing imagery and metadata between the user interface and the machine learning modules. The API sends imagery to the machine learning modules for processing and subsequently receives metadata generated by the machine learning modules which is passed to the interface for rendering.
Second Opinion PC uses machine learning to detect periapical radiolucencies. Images received by the ML modules are processed yielding detections which are represented as metadata. The final output is made accessible to the API for the purpose of sending to the UI for visualization. Detected periapical radiolucencies are displayed as polygonal overlays atop the original radiograph which indicate to the practitioner which teeth contain which detected periapical radiolucencies that may require clinical review. The clinician can toggle over the image to highlight a potential condition for viewing.
Mentions image processing
The processing sequence for an image is as follows:
- Images are sent for processing via the API
- The API routes images to the ML modules
- The ML modules produce detection output
- The UI renders the detection output
The API serves as a conduit for passing imagery and metadata between the user interface and the machine learning modules. The API sends imagery to the machine learning modules for processing and subsequently receives metadata generated by the machine learning modules which is passed to the interface for rendering.
Mentions AI, DNN, or ML
- Second Opinion PC uses machine learning to detect periapical radiolucencies.
- The proposed secondary predicate device is Overjet Periapical Radiolucency Assist by Overjet Inc., cleared on September 21, 2023 (K231678) under product code MYN. The Overjet Periapical Radiolucency Assist has the same technology (AI software) and intended use as CADe to aid in dental review of radiographs and detection of periapical radiolucencies using polygonal contours.
- Both devices employ computer vision and machine learning to output detections, use cloud-based environments to conduct processing, and demarcate detected periapical radiolucencies within a user interface with a graphical overlay over radiographs.
- Utilizes computer vision neural network algorithms, developed from open-source models using supervised machine learning techniques
- Automated, concurrent-read, CADe software that utilizes machine learning
- The fundamental technological principle for both the candidate and predicate devices is the automatic detection of periapical radiolucencies using machine learning
- All devices use neural network-based computer vision algorithms for periapical radiolucencies detection.
Input Imaging Modality
periapical radiographs
Radiograph
digital intraoral radiographs
Anatomical Site
permanent teeth
Dental
Indicated Patient Age Range
12 years of age or older
Intended User / Care Setting
dentists
dental health professionals
professionally trained and licensed dentists
Description of the training set, sample size, data source, and annotation protocol
Not Found
Description of the test set, sample size, data source, and annotation protocol
The ground truth (GT) was established using the consensus approach based on agreement among at least three out of four expert readers. Each GT expert independently marked areas on any radiograph wherein they marked using the smallest possible polygonal contour to encompass the entire region identified. 500 images were reviewed by all four GT readers and used for the standalone comparison study.
The GT dataset for the clinical evaluation of the Second Opinion PC system is characterized by a representative distribution of radiographs across important cohorts (various geographical regions, patient cohorts, imaging devices, and image types). Geographically, with respect to the United States, the dataset includes 116 radiographs from the Northwest (23.2%), 46 from the Southwest (9.2%), 141 from the South (28.2%), 84 from the East (16.8%), 113 from the Midwest (22.6%).
In terms of age distribution, 4 radiographs are from individuals aged 12-18 (0.8%), 209 from those aged 18-75 (41.8%), 8 from those aged 75+ (1.6%), and 279 with unknown age (55.8%).
The imaging devices used include 70 radiographs from Carestream-Trophy KodakRVG6100 (14.0%), 7 from Carestream-Trophy RVG5200 (1.4%), 95 from Carestream-Trophy RVG6200 (19.0%), 2 from DEXIS (0.4%), 27 from DEXIS Platinum (5.4%), 6 from KaVo Dental Technologies DEXIS Titanium (1.2%), 130 from Kodak-Trophy KodakRVG6100 (26.0%), 103 from XDR EV71JU213 (20.6%), and 60 from unknown devices (12.0%).
Table 2 - Summary of image characteristics.
| | Total
N=500 |
|---|---|
| Overall status, n (%) | |
| Normal | 380 (76.0) |
| Abnormal | 120 (24.0) |
| Number of lesions on abnormal images | |
| Total, n | 151 |
| Mean (SD) | 1.3 (0.46) |
| Median (range) | 1.0 (1, 3) |
| Lesion size on abnormal images (percent of image pixels) | |
| Mean (SD) | 2.8 (3.02) |
| Median (range) | 1.7 (0, 17) |
Source table: S_IMG_ALL.rtf
The Jaccard Index used for the study was 0.4.
Summary of Performance Studies
Study Type: Clinical evaluation, non-inferiority trial, standalone testing.
Sample Size: 500 unique unannotated images.
Metrics: The Weighted Alternative Free-Response Receiver Operating Characteristic (wAFROC) paradigm was used as the metric of efficacy. A secondary analysis was carried out using HR-ROC-AUC.
Key Results:
- The Obuchowski-Rockette analysis of jackknife and ANOVA estimate of the FOM difference between Second Opinion devices showed the estimated difference (95% CI) was 0.15 (0.10, 0.21).
- The lower bound of the 95% CI exceeded -0.05 showing Second Opinion PC was non-inferior to Second Opinion at the 5% level of significance.
- The wAFROC-FOM, 95% CI for Second Opinion PC was 0.85 (0.81, 0.89) and HR-ROC-AUC, 95% CI was 0.93 (0.90, 0.96). The null hypothesis was rejected.
- Second Opinion PC demonstrated a lesion level sensitivity (95% CI) of 77% (69%, 84%) and average false positives per image (95% CI) of 0.28 (0.23, 0.33).
Key Metrics
- Estimated difference (95% CI) based on Obuchowski-Rockette analysis: 0.15 (0.10, 0.21)
- wAFROC-FOM (95% CI) for Second Opinion PC: 0.85 (0.81, 0.89)
- HR-ROC-AUC (95% CI) for Second Opinion PC: 0.93 (0.90, 0.96)
- Lesion level sensitivity (95% CI): 77% (69%, 84%)
- Average false positives per image (95% CI): 0.28 (0.23, 0.33)
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 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.
FDA 510(k) Clearance Letter - Second Opinion Periapical Radiolucency Contours
Page 1
April 11, 2025
Pearl Inc.
℅ Ashley Brown
Director of Regulatory Affairs
2515 Benedict Canyon Dr.
BEVERLY HILLS, CA 90210
Re: K242600
Trade/Device Name: Second Opinion Periapical Radiolucency Contours
Regulation Number: 21 CFR 892.2070
Regulation Name: Medical Image Analyzer
Regulatory Class: Class II
Product Code: MYN
Dated: August 20, 2024
Received: March 14, 2025
Dear Ashley Brown:
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.
Page 2
K242600 - Ashley Brown 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 System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (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 systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
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-
Page 3
K242600 - Ashley Brown 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
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
Page 4
FORM FDA 3881 (8/23) Page 1 of 1 PSC Publishing Services (301) 443-6740 EF
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
510(k) Number (if known)
K242600
Device Name
Second Opinion Periapical Radiolucency Contours
Indications for Use (Describe)
Second Opinion PC is a computer aided detection ("CADe") software to aid dentists in the detection of periapical radiolucencies by drawing bounding polygons to highlight the suspected region of interest.
It is designed to aid dental health professionals to review periapical radiographs of permanent teeth in patients 12 years of age or older as a second reader.
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."
Page 5
K242600 510(K) SUMMARY
1. Submitter's Identification
Pearl Inc.
2515 Benedict Canyon Dr.
Beverly Hills, CA, 90210
USA
(239) 450-8829
Contact Person: William Birdsall Position: Chief Compliance Officer Date Summary Prepared: August 16, 2024
2. Trade Name of the Device
Second Opinion Periapical Radiolucency Contours
3. Common or Usual Name
Analyzer, Medical Image
4. Classification Name, Regulatory Classification & Product Code
Classification Name: Medical Image Analyzer
Regulatory Classification: 21CFR 892.2070, Class II
Product Code: MYN
5. Predicate Information
Predicate device: The proposed primary predicate device is the first clearance of the Second Opinion device, by Pearl Inc., cleared on March 04, 2022 (K210365) classified as a Class II Medical Image Analyzer pursuant to 21 CFR §892.2070, under product code MYN (Analyzer, Medical Image).
The cleared device is a computer aided detection (CADe) software device, indicated for use by dental health professionals as an aid in their assessment of bitewing and periapical radiographs of permanent teeth in patients 12 years of age or older, as second reader. The device utilizes computer vision technology, developed using machine learning techniques, to identify and mark potential periapical radiolucencies with bounding boxes.
The subject device is substantially equivalent to the first clearance as the overall intended use and nature of the software remains the same. Periapical radiolucency detection was originally cleared (K210365) based on standalone and MRMC studies. Second Opinion PC (Periapical Radiolucency Contouring) has the same intended use for detection of periapical radiolucencies in periapical radiographs. The only difference is that Second Opinion PC uses polygons instead of boxes to mark the detection.
Page 6
The proposed secondary predicate device is Overjet Periapical Radiolucency Assist by Overjet Inc., cleared on September 21, 2023 (K231678) under product code MYN. The Overjet Periapical Radiolucency Assist has the same technology (AI software) and intended use as CADe to aid in dental review of radiographs and detection of periapical radiolucencies using polygonal contours.
6. Device Description
Second Opinion PC (Periapical Radiolucency Contouring) is a radiological, automated, computer-assisted detection (CADe) software intended to aid in the detection of periapical radiolucencies on periapical radiographs using polygonal contours. The device is not intended as a replacement for a complete dentist's review or their clinical judgment which considers other relevant information from the image, patient history, or actual in vivo clinical assessment.
Second Opinion PC consists of three parts:
- Application Programing Interface ("API")
- Machine Learning Modules ("ML Modules")
- Client User Interface ("Client")
The processing sequence for an image is as follows:
- Images are sent for processing via the API
- The API routes images to the ML modules
- The ML modules produce detection output
- The UI renders the detection output
The API serves as a conduit for passing imagery and metadata between the user interface and the machine learning modules. The API sends imagery to the machine learning modules for processing and subsequently receives metadata generated by the machine learning modules which is passed to the interface for rendering.
Second Opinion PC uses machine learning to detect periapical radiolucencies. Images received by the ML modules are processed yielding detections which are represented as metadata. The final output is made accessible to the API for the purpose of sending to the UI for visualization. Detected periapical radiolucencies are displayed as polygonal overlays atop the original radiograph which indicate to the practitioner which teeth contain which detected periapical radiolucencies that may require clinical review. The clinician can toggle over the image to highlight a potential condition for viewing.
7. Indications for Use
Second Opinion PC is a computer aided detection ("CADe") software to aid dentists in the detection of periapical radiolucencies by drawing bounding polygons to highlight the suspected region of interest.
It is designed to aid dental health professionals to review periapical radiographs of
Page 7
permanent teeth in patients 12 years of age or older as a second reader.
8. Summary of Substantial Equivalence:
The primary and secondary predicate devices and subject device are similar CADe devices in the following ways:
-
Intended use: All three devices are intended to be used to aid dental clinicians in their detection of periapical radiolucencies in radiographs of permanent teeth.
-
Technology characteristics: Both devices employ computer vision and machine learning to output detections, use cloud-based environments to conduct processing, and demarcate detected periapical radiolucencies within a user interface with a graphical overlay over radiographs.
-
Safety: As both the candidate and predicate device are CADe systems, neither pose a direct safety hazard to the patient. The primary hazards for all devices, subject and predicates, are potential false positives and false negatives. In the case of each device, users are not meant to rely solely on detection output for clinical decision-making.
-
Clinical Performance: Both predicate devices have undergone clinical studies which demonstrate statistically significant improvement in aided reader performance. Head-to-head standalone performance comparison was used to demonstrate consistency in performance suggesting comparable reader aid/effect when using the subject device.
Table 1: Comparison of Second Opinion PC with the predicate devices.
| | Subject Device
Second Opinion PC | Primary Predicate
Second Opinion
K210365 | Secondary Predicate
Overjet
K231678 |
|---|---|---|---|
| Manufacturer | Pearl Inc. | Pearl Inc. | Overjet, Inc. |
| Classification | 892.2070 | 892.2070 | 892.2070 |
| Product Code | MYN | MYN | MYN |
| Image Modality | Radiograph | Radiograph | Radiograph |
| Intended Use | Dental CADe to aid in dental radiograph review by HCP | Dental CADe to aid in dental radiograph review by HCP | Dental CADe to aid in dental radiograph review by HCP |
Page 8
| Full IFU | Second Opinion PC is a computer aided detection ("CADe") software to aid dentists in the detection of periapical radiolucencies by drawing bounding polygons to highlight the suspected region of interest.
It is designed to aid dental health professionals to review periapical radiographs of permanent teeth in patients 12 years of age or older as a second reader. | Second Opinion is a computer aided detection ("CADe") software to identify and mark regions in relation to suspected dental findings which include Caries, Discrepancy at the margin of an existing restoration, Calculus, Periapical radiolucency, Crown (metal, including zirconia & non-metal), Filling (metal & non-metal), Root canal, Bridge and Implants.
It is designed to aid dental health professionals to review bitewing and periapical radiographs of permanent teeth in patients 12 years of age or older as a second reader. | Overjet Periapical Radiolucency (PARL) Assist is a radiological, automated, concurrent read computer-assisted detection software intended to aid in the detection of periapical radiolucencies on permanent teeth captured on periapical radiographs. The device provides additional aid for the dentist to use in their identification of periapical radiolucency. The device is not intended as a replacement for a complete dentist's review or their clinical judgment that considers other relevant information from the image or patient history. The system is to be used by professionally trained and licensed dentists.
The Overjet Periapical Radiolucency Assist software is indicated for use on patients 12 years of age or older. |
| Intended body part | Dental | Dental | Dental |
| Technology | Utilizes computer vision neural network algorithms, developed from open-source models using supervised machine learning techniques | Utilizes computer vision neural network algorithms, developed from open-source models using supervised machine learning techniques | Automated, concurrent-read, CADe software that utilizes machine learning |
| Device Description | Detection of periapical radiolucencies using polygons. | Detection of radiological dental findings: 5 restorations (crowns, bridges, implants, root canals, fillings), 4 pathologies (caries, margin discrepancy, calculus, periapical radiolucency) using bounding boxes. | Detection and segmentation of periapical radiolucencies using polygons. |
9. Technological Comparison to Predicate Devices
The fundamental technological principle for both the candidate and predicate devices is the automatic detection of periapical radiolucencies using machine learning
The candidate and predicate devices are technologically equivalent as follows:
- All are software devices designed to run on Windows operating systems.
- All devices are designed to process digital intraoral radiographs.
- All devices use neural network-based computer vision algorithms for periapical radiolucencies detection.
Page 9
- All devices demarcate detections within the user interface with a graphical overlay on the radiograph.
- All devices produce near-instantaneous detection results.
- All devices are considered to be Basic Documentation.
- All devices passed all verification and validation testing requirements.
The candidate and predicate devices are technologically different as follows:
- Second Opinion localizes periapical radiolucencies detections as bounding boxes whereas Overjet Periapical Radiolucency Assist and Second Opinion PC localize periapical radiolucency detections with polygons.
10. Assessment of Benefit-Risk, Safety and Effectiveness, and Substantial Equivalence to Predicate Device
Pearl demonstrated the benefits of the device through a non-inferiority standalone clinical study. The results of the study showed statistically significant non-inferiority in periapical radiolucency detection accuracy in the subject device using polygon contouring to delineate potential periapical radiolucencies when compared to the bounding boxes of Second Opinion. This study was conducted using ground truth periapical radiolucencies represented as polygons. When the probable benefits and probable risks of Second Opinion PC are weighed against one another, the weight of benefits significantly exceeds that of risks. This judgement can be made based on review of the submitted materials showing that Second Opinion PC meets the design verification and validation and labeling Special Controls required for clearance of Class II medical image analyzers. It is thus concluded that Second Opinion PC can be considered safe and effective such that the device will aid users in the indicated user population in their radiographic detection of periapical radiolucencies.
11. Discussion of Non-Clinical Tests Performed
The device is a software-only device, so most testable characteristics common to other device types, including Biocompatibility/Materials, Shelf Life/Sterility, Electromagnetic Compatibility and Electrical Safety, Magnetic Resonance (MR) Compatibility, are not applicable to this device.
12. Discussion of Clinical Tests Performed
Clinical evaluation of Second Opinion PC was performed to validate the efficacy of the system in detecting potential periapical radiolucencies using polygons instead of bounding boxes on intraoral radiographs. Second Opinion PC was clinically tested as a standalone device in comparison to the predicate device, Second Opinion, using a non-inferiority study.
The Weighted Alternative Free-Response Receiver Operating Characteristic (wAFROC)
Page 10
paradigm was used as the metric of efficacy for the study. The ground truth (GT) was established using the consensus approach based on agreement among at least three out of four expert readers. Each GT expert independently marked areas on any radiograph wherein they marked using the smallest possible polygonal contour to encompass the entire region identified. 500 images were reviewed by all four GT readers and used for the standalone comparison study.
The GT dataset for the clinical evaluation of the Second Opinion PC system is characterized by a representative distribution of radiographs across important cohorts (various geographical regions, patient cohorts, imaging devices, and image types). Geographically, with respect to the United States, the dataset includes 116 radiographs from the Northwest (23.2%), 46 from the Southwest (9.2%), 141 from the South (28.2%), 84 from the East (16.8%), 113 from the Midwest (22.6%).
In terms of age distribution, 4 radiographs are from individuals aged 12-18 (0.8%), 209 from those aged 18-75 (41.8%), 8 from those aged 75+ (1.6%), and 279 with unknown age (55.8%).
The imaging devices used include 70 radiographs from Carestream-Trophy KodakRVG6100 (14.0%), 7 from Carestream-Trophy RVG5200 (1.4%), 95 from Carestream-Trophy RVG6200 (19.0%), 2 from DEXIS (0.4%), 27 from DEXIS Platinum (5.4%), 6 from KaVo Dental Technologies DEXIS Titanium (1.2%), 130 from Kodak-Trophy KodakRVG6100 (26.0%), 103 from XDR EV71JU213 (20.6%), and 60 from unknown devices (12.0%).
Below is a table describing the composition of the dataset with respect to presence of periapical radiolucencies.
Table 2 - Summary of image characteristics.
| | Total
N=500 |
|---|---|
| Overall status, n (%) | |
| Normal | 380 (76.0) |
| Abnormal | 120 (24.0) |
| Number of lesions on abnormal images | |
| Total, n | 151 |
| Mean (SD) | 1.3 (0.46) |
| Median (range) | 1.0 (1, 3) |
| Lesion size on abnormal images (percent of image pixels) | |
| Mean (SD) | 2.8 (3.02) |
| Median (range) | 1.7 (0, 17) |
Source table: S_IMG_ALL.rtf
Page 11
Standalone Testing
The clinical study design consisted of one non-inferiority trial: comparing the ability of Second Opinion PC (polygonal localization) and Second Opinion (bounding box localization) to identify periapical radiolucencies. The 500 unique unannotated images were analyzed by both Second Opinion and Second Opinion PC. The results for each image were grouped into one of two categories:
- Non-Lesion Localization (NL): A predicted region which does not overlap with a ground truth region at or above a specified Jaccard index
- Lesion Localization (LL): A predicted region which does overlap with a ground truth region at or above a specified Jaccard index
The Jaccard Index used for the study was 0.4. The primary performance comparison of Second Opinion PC Second Opinion was conducted using wAFROC-FOM. A secondary analysis was carried out using HR-ROC-AUC.
There were a total number of lesion localizations (mean per image) of 99 (1.1) and 116 (1.2) by Second Opinion and Second Opinion PC respectively resulting from the non-inferiority study. The Obuchowski-Rockette analysis of jackknife and ANOVA estimate of the FOM difference between Second Opinion devices showed the estimated difference (95% CI) was 0.15 (0.10, 0.21). The lower bound of the 95% CI exceeded -0.05 showing Second Opinion PC was non-inferior to Second Opinion at the 5% level of significance. The wAFROC-FOM, 95% CI for Second Opinion PC was 0.85 (0.81, 0.89) and HR-ROC-AUC, 95% CI was 0.93 (0.90, 0.96). The null hypothesis was rejected.
The HR-ROC analysis further supports that Second Opinion PC's periapical radiolucencies detection is non-inferior to that of Second Opinion. Second Opinion PC demonstrated a lesion level sensitivity (95% CI) of 77% (69%, 84%) and average false positives per image (95% CI) of 0.28 (0.23, 0.33).
13. Comparison to Predicate Clinical Outcomes
The predicate, Second Opinion, underwent a similar standalone study wherein bounding boxes were used for both detection and ground truth representation of periapical radiolucencies. This standalone testing demonstrated that Second Opinion performed comparably to unaided readers in detecting periapical radiolucencies:
- A Jaccard Index of 0.4 corresponds to an overlap area between the device's outputs and truth of 57% in theory. Using Jaccard Index of 0.4 leads to the device's standalone performance wAFROC-FOM 95% CI (0.75, 0.84) for periapical radiolucencies.
- The device exhibited equivalent standalone HR-AUC performance for both
Page 12
Jaccard Indexes of 0.4 and 0.5 with 95% CIs of (0.82, 0.89) for PRs.
The secondary predicate, Overjet Periapical Radiolucency Assist, conducted a standalone evaluation on 763 periapical images where ground truth data was represented as surfaces. The data was split with 326 images with PARL and 437 with no PARL. Overall standalone sensitivity was 88% (84.7%, 91.4%). When broken down further, Image Level Standalone Sensitivity and Specificity by sensor category is as follows:
- Dexis - Sensitivity: 0.867 (0.800, 0.933) Specificity: 0.885 (0.827, 0.942)
- E2v - Sensitivity: 0.861 (0.785, 0.937) Specificity: 0.804 (0.728, 0.875)
- Gendex - Sensitivity: 0.889 (0.815, 0.951) Specificity: 0.793 (0.712, 0.865)
- Schick - Sensitivity: 0.908 (0.836, 0.961) Specificity: 0.891 (0.827, 0.945)
14. Conclusions
Based on the information presented above, Second Opinion PC and its primary predicate device, Second Opinion, are deemed to have similar intended uses as devices which aid in the detection of periapical radiolucencies that can appear in dental radiographic images. Second Opinion PC's performance data demonstrate that the device effectively performs as well as the primary predicate device.
As Second Opinion PC raises no new or different questions of safety or effectiveness, performs in accordance with its specifications, meets user needs, meets the intended use and therefore was found substantially equivalent to the predicate devices.