(273 days)
The Overjet Caries Assist (OCA) is a radiological, automated, concurrent read, computer-assisted detection software intended to aid in the detection and segmentation of caries on bitewing radiographs. The device provides additional information for the dentist to use in their diagnosis of a tooth surface suspected of being carious. The device is not intended as a replacement for a complete dentist's review or that takes into account other relevant information from the image, patient history, and actual in vivo clinical assessment.
Overjet Caries Assist (OCA) is a radiological automated concurrent read computer-assisted detection (CAD) software intended to aid in the detection and segmentation of caries on bitewing radiographs. The device provides additional information for the clinician to use in their diagnosis of a tooth surface suspected of being carious. The device is not intended as a replacement for a complete clinician's review or their clinical judgment that takes into account other relevant information from the image or patient history.
OCA is a software-only device which operates in three layers - a Network Layer, a Presentation Layer, and a Decision Layer (as shown in the data flow diagram below). Images are pulled in from a clinic/dental office, and the Machine Learning model creates predictions in the Decision Layer and results are pushed to the dashboard, which are in the Presentation Layer.
The Machine Learning System within the Decision Layer processes bitewing radiographs and annotates suspected carious lesions. It is comprised of four modules:
- Image Classifier The model evaluates the incoming radiograph and predicts the ● image type between Bitewing and Periapical Radiograph. This classification is used to support the data flow of the incoming radiograph. As part of the classification of the image type any non-radiographs are classified as "junk" and not processed. These include patient charting information, or other non-bitewing or periapical radiographs. OCA shares classifier and Tooth Number modules with the Overjet Dental Assist product cleared under K210187.
- . Tooth Number Assignment module - This module analyzes the processed image and determines what tooth numbers are present and provides a pixel wise segmentation mask for each tooth number.
- Caries module - This module outputs a pixel wise segmentation mask of all carious lesions using an ensemble of 3 U-Net based models. The shape and location of every carious lesion is contained in this mask as the carious lesions' predictions.
- Post Processing The overlap of tooth masks from the Tooth Number . Assignment Module and carious lesions from the Caries Module is used to assign specific carious lesions to a specific tooth. The Image Post Processor module annotates the original radiograph with the carious lesions' predictions.
Acceptance Criteria and Device Performance for Overjet Caries Assist
The Overjet Caries Assist (OCA) is a radiological, automated, concurrent read, computer-assisted detection software intended to aid in the detection and segmentation of caries on bitewing radiographs. The device's performance was evaluated through standalone testing of the AI algorithm and a clinical reader improvement study.
1. Table of Acceptance Criteria and Reported Device Performance
| Measure | Acceptance Criteria (Predicate Device Performance) | Reported Device Performance (Overjet Caries Assist) |
|---|---|---|
| Reader Improvement Study | ||
| Increase in dentist's sensitivity with AI assistance | Approximately 20% increase in sensitivity for the predicate device. For OCA, a greater than 15% increase in dentist's sensitivity was established as acceptance criteria. | Overall reader sensitivity improved from 57.9% to 76.2% (an increase of 18.3 percentage points, satisfying the >15% criterion). |
- Primary caries: 60.5% to 79.4% (18.9 pp improvement).
- Secondary caries: 49.8% to 63.0% (13.2 pp improvement). |
| Specificity with AI assistance | Not explicitly defined as an improvement criterion for the predicate, but overall specificity is a key measure. | Overall reader specificity decreased slightly from 99.3% to 98.4% (a decrease of less than 1%), deemed acceptable by the applicant as the benefit in sensitivity outweighs this slight decrease. |
| AFROC Score (Assisted) | The predicate did not explicitly state an AFROC criterion, but improving diagnostic accuracy is implicit. | AUC increased from 0.593 (unassisted) to 0.649 (assisted), for an increase of 0.057 (statistically significant, p
§ 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.