Search Results

Overjet Charting Assist is a Medical Image Management and Processing System (MIMPS) intended to detect natural dental structures including detection of tooth anatomy (enamel, pulp), and tooth numbering, as well as dental structures added through past restorative treatments; implants, crowns, endodontic treatment (previous root canal treatment), fillings.

The device is intended to assist dental professionals in producing dental charts based on image analysis. The Overjet Charting Assist detects these findings on bitewing (BW) and periapical (PA) images for patients with primary and/or permanent teeth (Ages 5 and above), and panoramic (Pano) radiographs for patients with only permanent 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.

Overjet Charting Assist 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 interpretation of 2D dental radiographs. The device is intended to detect natural dental structures including detection of tooth anatomy (enamel, pulp), and tooth numbering, as well as dental structures added through past restorative treatments: implants, crowns, endodontic treatment (previous root canal treatment), fillings. The device is intended to assist dental professionals in producing dental charts based on image analysis.

The Overjet Charting Assist detects these findings on bitewing (BW) and periapical (PA) images for patients with primary and/or permanent teeth (Ages 5 and above), and panoramic (Pano) radiographs for patients with only permanent 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.

The provided text does not contain detailed information about the acceptance criteria and the study that proves the device meets the acceptance criteria for "Overjet Charting Assist" (K241684).

The document explicitly states: "Since the device remains unchanged from the Overjet Charting Assist Device cleared under K233590, no additional performance testing was conducted, and the existing data from the previous testing remains applicable."

Therefore, to answer your request, we would need to refer to the K233590 submission. However, based only on the provided text for K241684, I can only extract limited relevant information:

Key Takeaways from the Provided Text (K241684 Submission):

• No New Performance Testing: This submission (K241684) for "Overjet Charting Assist" did not conduct new performance testing. It relies entirely on the testing from the previous clearance, K233590, because "the device remains unchanged."
• PCCP Details Acceptance Criteria for Future Modifications: The Predetermined Change Control Plan (PCCP) outlined for this device states that the "Performance Evaluation Activity" for future algorithm modifications (e.g., re-training the ML model with new data to reduce false positives/negatives) will be "Identical to the acceptance criteria and standalone study protocol for the pre-modified version of the device cleared in K233590. Primary endpoints will be the main acceptance criteria, other endpoints and additional analyses will be conducted and reviewed for any major drop in performance." This strongly suggests that the acceptance criteria for K241684 are those from K233590.
• PCCP Requirement: "If a specific modification fails performance evaluation, failure(s) will be documented, and the modification will not be implemented."

Since the detailed study information (sample size, ground truth, expert qualifications, etc.) for the initial clearance (K233590) is not present in this document (K241684), I cannot provide a complete answer to all your questions.

However, based on the principle of the K241684 submission relying on K233590's data, here's what can be inferred/extracted about the acceptance criteria and study design for the original device, as referenced by the PCCP:

Inferred Information from the Provided Text (Regarding the Study conducted for K233590, as referenced by K241684's PCCP)

1. Table of Acceptance Criteria and Reported Device Performance:

The document states: "Performance Evaluation Activity: Identical to the acceptance criteria and standalone study protocol for the pre-modified version of the device cleared in K233590. Primary endpoints will be the main acceptance criteria, other endpoints and additional analyses will be conducted and reviewed for any major drop in performance."

This means the acceptance criteria and reported device performance exist in the K233590 submission, but are not detailed in this K241684 document.

2. Sample Size Used for the Test Set and Data Provenance:

The document does not specify these details for the K233590 study.

3. Number of Experts Used to Establish Ground Truth and Qualifications:

The document does not specify these details for the K233590 study.

4. Adjudication Method for the Test Set:

The document does not specify this detail for the K233590 study.

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

The document does not specify if an MRMC study was done for K233590, nor does it provide an effect size for human readers' improvement with AI assistance. The focus of the PCCP is on standalone performance evaluation for future modifications.

6. Standalone (Algorithm Only) Performance:

Yes, a standalone study was done. The PCCP explicitly states: "Performance Evaluation Activity: Identical to the acceptance criteria and standalone study protocol for the pre-modified version of the device cleared in K233590." This confirms that a standalone performance evaluation was conducted for the original clearance.

7. Type of Ground Truth Used:

The document does not specify the type of ground truth (e.g., expert consensus, pathology, outcomes data) used for the K233590 study.

8. Sample Size for the Training Set:

The document does not specify this detail for the K233590 study, nor for any future re-training mentioned in the PCCP (it only mentions "re-training the ML model with new data").

9. How the Ground Truth for the Training Set was Established:

The document does not specify this detail for the K233590 study, nor for any future re-training mentioned in the PCCP.

For a complete answer to your questions, the K233590 submission documents would need to be reviewed. The provided document (K241684) serves primarily as a notification for adding a Predetermined Change Control Plan to an already cleared device, stating that no new performance testing was conducted for this specific submission.

Ask a specific question about this device

Overjet Caries Assist-Pediatric (OCA-Ped) is a radiological, automated, concurrent-read, computer-assisted detection (CADe) software intended to aid in the detection and segmentation of caries on bitewing and periapical 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 dentist's review or their clinical judgment that takes into account other relevant information from the image, patient history, or actual in vivo clinical assessment.

The intended patient population of the device is patients aged 4-11 years old that have primary or permanent teeth (primary or mixed dentition) and are indicated for dental radiographs.

Overjet Caries Assist-Pediatric (OCA-Ped) is a radiological, automated, concurrent-read, computer-assisted detection (CADe) software intended to aid in the detection and segmentation of caries on bitewing and periapical 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 their clinical judgment that takes into account other relevant information from the image, patient history, or actual in vivo clinical assessment.

OCA-Ped is a software-only device which operates in three layers: a Network Layer, a Presentation Layer, and a Decision Layer. Images are pulled in from a clinic/dental office, and the Machine Learning model creates predictions in the Decision Laver and results are pushed to the dashboard, which are in the Presentation Layer.

The provided document describes the Overjet Caries Assist-Pediatric (OCA-Ped) device, a computer-assisted detection (CADe) software intended to aid in the detection and segmentation of caries on bitewing and periapical radiographs for patients aged 4-11 years old.

Here's the breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a separate section with specific numerical thresholds. However, it presents the performance metrics from the MRMC reader study and standalone testing, which can be interpreted as demonstrating the device's acceptable performance.

2. Sample Size Used for the Test Set and Data Provenance

• MRMC Test Set: 636 images, each from a unique patient.
• Standalone Test Set: 1190 bitewing and periapical images.
• Data Provenance: "Images were obtained from male and female patients aged 4-11 years." For the Standalone testing, "images were obtained from male and female patients, from a range of distinctly different geographic regions." The document does not specify if the data was retrospective or prospective, nor does it explicitly mention the country of origin, beyond "US licensed dentists" participating in the MRMC study. Given that "US licensed dentists" participated and "distinctly different geographic regions" are mentioned for standalone, it's implied to be US-centric.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Number of Experts: 3
• Qualifications of Experts: General dentists. No specific experience level (e.g., "10 years of experience") is provided, only "3 general dentists."

4. Adjudication Method for the Test Set

• Adjudication Method: Consensus ground truth established by 3 general dentists. The exact process of reaching consensus (e.g., silent read, discussion, majority vote) is not detailed, but it implies agreement among the three experts.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• Yes, an MRMC comparative effectiveness study was done.
• Effect Size of Improvement with AI Assistance:
  • AUC of wAFROC: Averaged across all readers, there was a 7.5% improvement (95% CI: 0.062, 0.088) in assisted readers compared to unassisted readers.
  • Tooth-level Sensitivity: Averaged across all readers, sensitivity increased by 11.8% (95% CI: 0.102, 0.137) when compared to unassisted readers.
  • Tooth-level Specificity: A slight decrease of -0.011 (95% CI: -0.015, -0.008) between assisted and unassisted readers.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done

• Yes, standalone performance testing was done.
  • Tooth-level standalone sensitivity was 83.9% (95% CI: 0.816, 0.860).
  • Tooth-level standalone specificity was 97.5% (95% CI: 0.971, 0.979).
  • Standalone Dice was a mean of 79.0% (95% CI: 0.784, 0.797).

7. The Type of Ground Truth Used

• Ground Truth Type: Expert consensus. Specifically, "consensus reference standard established by 3 general dentists."

8. The Sample Size for the Training Set

• The document does not provide the sample size for the training set. It only describes the test sets used for MRMC and standalone performance evaluation.

9. How the 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 details the ground truth establishment for the test sets.

Ask a specific question about this device

Overiet Charting Assist is a Medical Image Management and Processing System (MIMPS) intended to detect natural dental structures including detection of tooth anatomy (enamel, pulp), and tooth numbering, as well as dental structures added through past restorative treatments: implants, crowns, endodontic treatment (previous root canal treatment), fillings. The device is intended to assist dental professionals in producing dental charts based on image analysis.

The Overiet Charting Assist detects these finding (BW) and periapical (PA) images for patients with primary and/or permanent teeth (Ages 5 and above), and panoramic (Pano) radiographs for patients with only permanent 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.

Overjet Charting Assist 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 interpretation of 2D dental radiographs. The device is intended to detect natural dental structures including detection of tooth anatomy (enamel, pulp), and tooth numbering, as well as dental structures added through past restorative treatments: implants, crowns, endodontic treatment (previous root canal treatment), fillings. The device is intended to assist dental professionals in producing dental charts based on image analysis.

The Overjet Charting Assist detects these findings on bitewing (BW) and periapical (PA) images for patients with primary and/or permanent teeth (Ages 5 and above), and panoramic (Pano) radiographs for patients with only permanent 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.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

Note: The document explicitly states, "All conducted tests produced results that exceeded predefined acceptance criteria," but does not explicitly list numerical thresholds for each criterion. The reported performance metrics are presented as the results that met or exceeded these unstated criteria.

Study Details

1. Sample sizes used for the test set and the data provenance:

   • Test Set Sample Size: 634 images (259 Bitewing, 239 Periapical, 136 Panoramic).
   • Data Provenance: From various clinics across the U.S. (44 distinct clinics). The data includes male and female patients of primary and permanent dentition. The study explicitly states it uses data from all U.S. regions (Southeast, Southwest, Northeast, West). The data collection method (retrospective or prospective) is not explicitly stated, but the mention of "obtained from male and female patients" and "collected from 44 distinct clinics" suggests retrospective collection of existing images.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Number of Experts: Not explicitly stated as a numerical count for each image, but the ground truth was established by "trained dentists."
   • Qualifications of Experts: Described as "trained dentists." No specific years of experience or board certifications are provided.

3. Adjudication method for the test set:

   • The ground truth was established by "majority pixel voting" among trained dentists. This implies a consensus-based adjudication method where multiple experts reviewed the images, and their agreement (or majority vote) determined the ground truth. The exact number of experts involved in each "vote" is not specified (e.g., 2+1, 3+1).

4. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • A formal MRMC comparative effectiveness study demonstrating human reader improvement with AI assistance (vs. without AI) was not explicitly detailed.
   • The study primarily focused on the standalone performance of the device and its ability to reduce manual charting operations. The metric "Mean % Reduction per image in Manual Charting Operations with (95% Cl) when using the OChA device is 80.5% (79.0%, 81.9%)" quantifies the efficiency gain, which is an indirect measure of how much human effort is reduced, rather than a direct measure of improved diagnostic accuracy by human readers with vs without AI assistance.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Yes, a standalone performance evaluation was conducted. The document explicitly states: "Standalone performance of the Overjet Charting Assist device was evaluated..." and "Tooth Level Standalone Analysis for subgroups of past restorative structures...", "Tooth Level Standalone Analysis for subgroups of dental tooth anatomy...", etc.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

   • The ground truth used was expert consensus based on "robust consensus reference standard established by trained dentists via majority pixel voting."

7. The sample size for the training set:

   • The training set sample size is not explicitly mentioned in the provided text. The document describes the test set and its performance evaluation but does not detail the training data or its size.

8. How the ground truth for the training set was established:

   • Since the training set details are not provided, the method for establishing its ground truth is also not stated in this document.

Ask a specific question about this device

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.

Overjet Periapical Radiolucency "PARL" Assist is a module within the Overjet Platform. The Overjet PARL Assist (OPA) software automatically detects periapical radiolucency on periapical radiographs. It is intended to aid dentists in the detection of periapical radiolucency. It should not be used in lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by professionally trained and licensed dentists. Overjet PARL Assist is a software-only device which operates in three layers: a Network Layer, aPresentation Layer, and a Decision Layer. 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.

Here's a detailed breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

Study Details

2. Sample size used for the test set and the data provenance:

• MRMC Reader Study Test Set: 379 periapical radiographs (190 images with at least 1 PARL and 189 images with no PARL).
  • Data Provenance: Images were obtained from various clinical sites across the U.S. from male and female patients aged 12 years and older. (Retrospective, implied, as it's a collected dataset for testing).
• Standalone Performance Testing Test Set: 763 periapical images + 384 additional images, totaling 1147 images.
  • Data Provenance: Images were obtained from various clinical sites across the U.S. from male and female patients aged 12 years and older. (Retrospective, implied).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: 3
• Qualifications of Experts: Endodontists (specific experience/years not detailed, but their specialty implies relevant expertise).

4. Adjudication method for the test set:

• Adjudication Method: Consensus reference standard established by 3 endodontists. (This implies all three experts agreed on the ground truth for each case; no specific 2+1 or 3+1 method is explicitly stated, but "consensus" suggests agreement among all three).

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• MRMC Comparative Effectiveness Study: Yes, an MRMC fully crossed reader improvement study was conducted.
• Effect Size / Improvement with AI Assistance:
  • Image-level AUC: 4.8% (95% CI: 0.030, 0.066) improvement in assisted readers compared to unassisted readers.
  • Image-level sensitivity: Average increase of 13.6% (0.110, 0.165) for assisted readers.
  • Image-level specificity: Decreased by 7.1% from 83.2% to 76.1% (-0.071 difference, Cls (-0.099, -0.042)).
  • Instance (polygon) level sensitivity: Average increase of 16.2% (0.125, 0.194) for assisted readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Standalone Performance Testing: Yes, standalone performance of the Overjet PARL Assist device was evaluated.

7. The type of ground truth used:

• Ground Truth Type: Expert consensus from 3 endodontists.

8. The sample size for the training set:

• The document does not explicitly state the sample size for the training set. It only provides details for the test sets used in the MRMC reader study and standalone performance testing.

9. How the ground truth for the training set was established:

• The document does not explicitly state how the ground truth for the training set was established. It only describes the ground truth establishment for the test sets via consensus of 3 endodontists.

Ask a specific question about this device

Overjet Caries Assist (OCA) is a radiological, automated, concurrent-read, computer-assisted detection (CADe) software intended to aid in the detection and segmentation of caries on bitewing and periapical 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 their clinical judgment that takes into account other relevant information from the image, patient history, or actual in vivo clinical assessment.

Overjet Caries Assist (OCA) is a radiological, automated, concurrent-read, computer-assisted detection (CADe) software intended to aid in the detection and segmentation of caries on bitewing and periapical 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 their clinical judgment that takes into account other relevant information from the image, patient history, or actual in vivo clinical assessment.

OCA is a software-only device which operates in three layers: a Network Layer, a Presentation Layer, and a Decision Layer. 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 with the Decision Layer processes bitewing and periapical radiographs and annotates suspected carious lesions. It is comprised of four modules:

• Image Preprocessor Module
• Tooth Number Assignment Module
• Caries Module
• Post Processing

This document describes the Overjet Caries Assist (OCA) device, a computer-assisted detection (CADe) software intended to aid dentists in the detection and segmentation of caries on bitewing and periapical radiographs.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state numerical acceptance criteria for sensitivity or specificity in a "table" format as initial goals. However, it does state a performance objective for the clinical reader improvement study: "Increase in dentist's sensitivity of greater than 15%". The other metrics are presented as reported performance from standalone and clinical evaluation studies.

2. Sample Size for Test Set and Data Provenance:

• Standalone Testing:

  • Sample Size: 1,293 Bitewing images (27,920 surfaces) and 1,314 Periapical images (16,254 surfaces).
  • Data Provenance: Not explicitly stated regarding country of origin. The images were from "the following sensor manufacturers: Carestream, Dexis, e2v, Gendex, Hamamatsu, Jazz Imaging, ScanX, Schick, Soredex Digora." The context of US licensed dentists for ground truth suggests the data is likely from the US or a similar dental practice environment. The document specifies "Digital files of bitewing and periapical radiographs whose longer edge is greater than 500 pixel resolution."
  • Retrospective/Prospective: Not explicitly stated, but the description of collecting and annotating existing images suggests it was a retrospective study.

• Clinical Evaluation (Reader Improvement Study):

  • Sample Size: 330 bitewing images (94 containing caries / 236 without caries) and 330 periapical images (94 containing caries / 236 without caries).
  • Data Provenance: Not explicitly stated regarding country of origin, but the "US licensed dentists" implies the study was conducted within the US.
  • Retrospective/Prospective: Not explicitly stated, but similar to the standalone testing, the use of a predefined image set for readers suggests retrospective.

3. Number of Experts and Qualifications for Ground Truth:

• Standalone Testing: Ground truth established by consensus of three US licensed dentists. Non-consensus labels were adjudicated by an oral radiologist. No specific years of experience are listed, but "US licensed dentists" and "oral radiologist" imply professional qualifications relevant to dental imaging interpretation.
• Clinical Evaluation (Reader Improvement Study): Ground truth established by consensus of three US licensed dentists. Non-consensus labels were adjudicated by an oral radiologist. (Same as standalone testing).

4. Adjudication Method for the Test Set:

• Standalone Testing & Clinical Evaluation: The method described is consensus of three experts, with a fourth expert (oral radiologist) adjudicating non-consensus cases. This can be described as a "3+1 adjudication" method, where the "1" is specifically for tie-breaking or resolving disagreements among the initial three.

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

• Yes, a MRMC study was done. This is detailed under "Clinical Evaluation - Reader Improvement."
• Effect Size / Reader Improvement:
  • Bitewing Images:
    • Overall reader sensitivity improved from 64.6% (unassisted) to 78.5% (assisted). This is an absolute increase of 13.9 percentage points.
    • Weighted AFROC AUC increased from 0.729 (unassisted) to 0.785 (assisted), an increase of 0.055. This increase was statistically significant (p < 0.001).
    • Mean Dice scores increased from 0.67 (unassisted) to 0.76 (assisted) for primary caries. Similar increases were observed for other caries types.
  • Periapical Images:
    • Overall reader sensitivity improved from 65.6% (unassisted) to 79.0% (assisted). This is an absolute increase of 13.4 percentage points.
    • Weighted AFROC AUC increased from 0.799 (unassisted) to 0.848 (assisted), an increase of 0.050. This increase was statistically significant (p < 0.001).
    • Mean Dice scores increased from 0.73 (unassisted) to 0.80 (assisted) for primary caries. Similar increases were observed for other caries types.

The document concludes that the increase in wAFROC numbers clearly demonstrates improvement in caries detection by dentists when aided by Overjet Caries Assist, aligned with increases in sensitivity and minimal decrease in specificity.

6. Standalone (Algorithm Only) Performance Study:

• Yes, a standalone performance study was done. This is detailed under "Standalone Testing." The results for the algorithm's sensitivity, specificity, and Dice scores are provided for both bitewing and periapical images.

7. Type of Ground Truth Used:

• Expert Consensus. For both standalone and clinical evaluation studies, the ground truth was "established by consensus of labels of three US licensed dentists, and non-consensus labels were adjudicated by an oral radiologist."

8. Sample Size for the Training Set:

• The document does not explicitly state the sample size for the training set. It describes the "Machine Learning model" and its components but does not provide details about the data used for training.

9. How the Ground Truth for the Training Set Was Established:

• The document does not explicitly state how the ground truth for the training set was established. It only details the ground truth establishment for the test sets used in standalone and clinical performance evaluations.

Ask a specific question about this device

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

2. Sample Size and Data Provenance for the Test Set

• Sample Size for Test Set: 352 bitewing radiographs (104 containing caries / 248 without caries).
• Data Provenance: Not explicitly stated in the provided text (e.g., country of origin). However, given the context of U.S. FDA clearance and the use of US-licensed dentists, it is likely that the data is either from the US or representative of populations seen in the US. The type of data is retrospective, as existing radiographs were used.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three US-licensed dentists for initial consensus, and one Dental Radiologist for adjudication of non-consensus labels.
• Qualifications of Experts: All experts were US-licensed dentists. The adjudicating expert was specifically a Dental Radiologist. No further details on years of experience were provided.

4. Adjudication Method for the Test Set

The adjudication method used was a "3+1" approach. Ground truth was initially established by the consensus labels of three US-licensed dentists. Any non-consensus labels were then adjudicated by a Dental Radiologist.

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

Yes, an MRMC comparative effectiveness study was conducted.

• Effect Size of Human Readers Improvement with AI vs. without AI assistance:
  • Sensitivity: Overall reader sensitivity improved by 18.3 percentage points (from 57.9% unassisted to 76.2% assisted).
    • For primary caries, sensitivity improved by 18.9 percentage points (60.5% unassisted to 79.4% assisted).
    • For secondary caries, sensitivity improved by 13.2 percentage points (49.8% unassisted to 63.0% assisted).
  • Specificity: Overall reader specificity decreased slightly by 0.9 percentage points (from 99.3% unassisted to 98.4% assisted).
  • AFROC AUC: The average AUC for all readers increased by 0.057 (from 0.593 unassisted to 0.649 assisted). This increase was statistically significant (p < 0.001).
  • Average Dice Scores for Segmentation:
    • Primary caries: Mean Dice scores improved from 0.67 unassisted to 0.69 assisted.
    • Secondary caries: Mean Dice scores improved from 0.65 unassisted to 0.74 assisted. (Note: These segmentation improvements were not statistically significant).

6. Standalone (Algorithm Only) Performance

Yes, standalone performance (algorithm only without human-in-the-loop) was conducted.

• Overall standalone sensitivity: 72.0% (95% CI: 62.9%, 81.1%)
• Overall standalone specificity: 98.1% (95% CI: 97.7%, 98.5%)
• Lesion Segmentation (Dice Score):
  • Primary caries: Mean Dice score of 0.69
  • Secondary caries: Mean Dice score of 0.75

7. Type of Ground Truth Used

The ground truth used was expert consensus complemented by expert adjudication. Specifically, a consensus of three US-licensed dentists, with non-consensus cases adjudicated by a Dental Radiologist.

8. Sample Size for the Training Set

The sample size for the training set is not provided in the excerpt. The document only mentions "training data" in the context of the algorithm's capability to learn during its operation, but not a specific size for its initial training.

9. How the Ground Truth for the Training Set was Established

The method for establishing ground truth for the training set is not explicitly detailed in the provided text. It generally states that the algorithm "has been trained," but does not provide information on how the ground truth for that training was established.

Ask a specific question about this device

Overjet Dental Assist is a radiological semi-automated image processing software device intended to aid dental professionals in the measurements of mesial and distal bone levels associated with each tooth from bitewing and periapical radiographs.

It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by trained professionals including, but not limited to, dentists and dental hygienists.

Overjet Dental Assist developed by Overjet Inc, is a radiological semi automated image processing software device intended to aid dental professionals in the measurements of mesial and distal bone levels associated with each tooth from bitewing and periapical radiographs.

Overjet Dental Assist is a cloud native Software as a Medical Device that allows users to automate the measurement of interproximal bone levels for bitewing and periapical radiographs, review associated radiographs, view annotations, modify annotations.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Note regarding "Periapical Root Length": While the acceptance criteria for sensitivity, specificity, and mean absolute difference are explicitly stated for bone level measurements, the document also reports performance for "Periapical Root Length" with similar metrics and a mean absolute difference. It's reasonable to infer a similar acceptance criterion for MAE for this measurement type.

2. Sample Sizes and Data Provenance

• Test Set (Clinical Testing):

  • Sample Size: 65 bitewing and 96 periapical radiographs from 63 subjects.
  • Data Provenance: Retrospective clinical subject data from patients in the United States, 22 years old or older, without primary teeth. No information about ethnicity was available.

• Test Set (Bench Testing):

  • Sample Size: 2234 bitewing radiographs and 6543 periapical radiographs.
  • Data Provenance: Not explicitly stated, beyond being "ground truth data set utilizing Object Keypoint Similarity assessment." The context suggests this is also retrospective imaging data.

• Training Set (not explicitly called out as such here, but implied as distinct from the validation sets):

  • Sample Size: Not explicitly stated in the provided text.
  • Data Provenance: Not explicitly stated.

3. Number of Experts to Establish Ground Truth for Test Set & Qualifications

• Number of Experts: 3 US licensed dentists for initial labeling, plus 2 US Dental Radiologists for adjudication.
• Qualifications of Experts: US licensed dentists; US Dental Radiologists. No specific years of experience are mentioned.

4. Adjudication Method for the Test Set

• Clinical Testing: The adjudication method was "initial measurements by three US licensed dentists, which were then adjudicated by two US Dental Radiologists." This can be interpreted as a form of expert consensus and review. It's not a standard 2+1 or 3+1, but a multi-expert review process.

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

• No explicit MRMC comparative effectiveness study was done to quantify the improvement of human readers with AI assistance versus without. The study focuses on standalone performance against expert-derived ground truth. The document does state, "The overall sensitivity of 88% was consistent with the performance of the three ground truth dentists," which indirectly compares the device's sensitivity to human performance on a specific metric, but this is not a formal MRMC study of human reading with and without AI.

6. Standalone Performance Study

• Yes, a standalone study was done. The entire "Clinical Testing" section describes the device's performance (sensitivity, specificity, mean absolute difference) when compared against an expert-established ground truth. The device results are reported directly without human intervention in the reported metrics.

7. Type of Ground Truth Used

• Expert Consensus. For the clinical testing, the ground truth was established by three US licensed dentists using a measurement tool, whose measurements were then adjudicated by two US Dental Radiologists. For the bench testing, it mentions "labeled keypoints," implying expert labeling.

8. Sample Size for the Training Set

• Not explicitly stated in the provided text. The document refers to "the Overjet met acceptable performance criteria with the following results:" and then lists results for "Bench Testing" and "Clinical Testing," which are typically considered validation/test sets, not the training set itself.

9. How Ground Truth for Training Set Was Established

• Not explicitly stated in the provided text, as the size and provenance of the training set itself are not detailed. It can be inferred that similar expert labeling processes would have been used to establish ground truth for training data, but this is not confirmed.

Ask a specific question about this device