Search Results

Overjet Image Enhancement Assist is an image processing software that can be used for image enhancement in dental radiographs viewed in the Overjet device platform. It is an optional tool to be used for image quality enhancement.

The software improves image quality by:

• Reducing Noise: Utilizing a learning-based algorithm for noise reduction in bitewing and periapical images.

• Enhancing Contrast and Sharpness: Applying standard, non-learning based techniques to enhance contrast and sharpness for bitewing, periapical, and panoramic images.

Raw images will be acquired and reviewed using the dental clinics standard imaging acquisition and viewing software. This device is part of the Overjet platform alone, it is not intended to replace their own diagnostic imaging system.

Overjet Image Enhancement is a Software as a Medical Device (SaMD) that enhances dental radiographic images within the Overjet Platform, intended for use by dental providers in clinics or hospitals. It supports routine dental images, including bitewing, periapical, and panoramic images, viewed within the Overjet Platform.

The software enhances image quality by reducing noise with a learning-based algorithm for bitewing and periapical images, and by improving contrast and sharpness using standard, non-learning based techniques. For panoramic images, standard enhancement techniques improve contrast and sharpness without learning-based noise reduction. The enhancement feature can be toggled on and off by the user within the Overjet Platform. AI predictions for findings such as caries, calculus, etc. are run as specified for each FDA cleared device and are run on unenhanced (original) images only. There is no modification to the output of other FDA cleared Overjet devices when the image enhancement feature is applied.

The provided text describes the Overjet Image Enhancement Assist device and its substantial equivalence determination by the FDA. While it states that "Overjet conducted the following performance testing: software verification and validation testing, a study that utilized retrospective data to demonstrate that the software enhanced image quality (quantification report and expert clinical evaluation)," and mentions "All tests passed successfully," it does not provide the specific acceptance criteria or the detailed results of the study that proves the device meets those criteria.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and the reported device performance.
2. Sample size used for the test set and data provenance.
3. Number of experts and their qualifications for ground truth.
4. Adjudication method for the test set.
5. MRMC comparative effectiveness study results.
6. Standalone performance results.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

The document only states the types of tests performed (quantification report for CNR and PSNR, and a Likert expert clinical evaluation) and that "All tests passed successfully," implying that the device met internal, but not explicitly stated, acceptance criteria. It also mentions that the "test methods were highly similar to those of the predicate device."

Ask a specific question about this device

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

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.

Ask a specific question about this device

Overjet Calculus Assist (OCalA) is a radiological automated concurrent-read computer-assisted detection software intended to aid in the detection of interproximal calculus deposits on both bitewing and periapical radiographs. The Overjet Calculus Assist surrounds suspected calculus deposits with a bounding box. The device provides additional information for the dentist to use in their diagnosis of a tooth surface suspected of containing calculus deposits. 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 or patient history. The system is to be used by professionally trained and licensed dentists.

Overjet Calculus Assist is a module within the Overjet Platform. The Overjet Calculus Assist (OCalA) software automatically detects interproximal calculus on bitewing and periapical radiographs. It is intended to aid dentists in the detection of calculus. 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.

Here's an analysis of the acceptance criteria and study findings for the Overjet Calculus Assist device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

While specific acceptance criteria thresholds are not explicitly stated as numerical values in the document (e.g., "Sensitivity must be >= X%"), the document describes the performance testing conducted and implies that these results met the pre-specified requirements. The performance presented is what the FDA reviewed and deemed acceptable for clearance.

• Bitewing: 74.1% (95% CI: 66.2%, 82.0%)
• Periapical: 72.9% (95% CI: 65.3%, 80.5%)
  Specificity:
• Bitewing: 99.4% (95% CI: 99.1%, 99.6%)
• Periapical: 99.6% (95% CI: 99.3%, 99.8%)
  AFROC AUC:
• Bitewing: 0.859 (95% CI: 0.823, 0.894)
• Periapical: 0.867 (95% CI: 0.828, 0.903) |
  | Clinical Performance (Reader Improvement) | Demonstrates superiority of aided reader performance versus unaided reader performance. | Reader Sensitivity (Unassisted vs. Assisted):
• Bitewing: Improved from 74.9% (68.3%, 80.2%) to 84.0% (78.8%, 88.2%)
• Periapical: Improved from 74.7% (69.9%. 79.0%) to 84.4% (78.8%, 89.2%)
  Reader Specificity (Unassisted vs. Assisted):
• Bitewing: Decreased slightly from 98.8% (98.7%, 99.0%) to 98.6% (98.4%, 98.9%)
• Periapical: Decreased slightly from 98.1% (97.8%, 98.4%) to 98.0% (97.7%, 98.4%)
  Reader AFROC AUC (Unassisted vs. Assisted - Average of all readers):
• Bitewing: Increased from 0.840 (0.800, 0.880) to 0.878 (0.844. 0.913) (p-value 0.0055)
• Periapical: Increased from 0.846 (0.808. 0.884) to 0.900 (0.870, 0.929) (p-value 1.47e-05) |

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

• Standalone Test Set:

  • Bitewing Radiographs: 296
  • Periapical Radiographs: 322
  • Total Surfaces (Bitewing): 6,121
  • Total Surfaces (Periapical): 3,595
  • Data Provenance: Not explicitly stated, but subgroup analyses for "sensor" and "clinical site" suggest real-world, diverse data. The document does not specify if the data was retrospective or prospective, or the country of origin.

• Clinical Evaluation (Reader Improvement) Test Set:

  • Bitewing Radiographs: 292 (85 with calculus, 211 without calculus)
  • Periapical Radiographs: 322 (89 with calculus, 233 without calculus)
  • Data Provenance: Not explicitly stated regarding retrospective/prospective or geographical origin.

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

• Ground Truth Establishment for Clinical Evaluation Test Set:
  • Number of Experts: 3 US-licensed dentists formed a consensus for initial labeling. An oral radiologist provided adjudication for non-consensus labels.
  • Qualifications of Experts: "US-licensed dentists" and an "oral radiologist." Specific years of experience or specialization within dentistry beyond "oral radiologist" are not provided.

4. Adjudication Method for the Test Set

• Clinical Evaluation Test Set Adjudication:
  • Ground truth was established by consensus labels of three US-licensed dentists.
  • Non-consensus labels were adjudicated by an oral radiologist. This effectively represents a 3-reader consensus with a 1-reader expert adjudication for disagreements.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, 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. It was described as a "multi-reader, fully crossed reader improvement study."
• Effect Size (Improvement with AI vs. without AI assistance):
  • Sensitivity Improvement:
    • Bitewing: 9.1% (84.0% - 74.9%)
    • Periapical: 9.7% (84.4% - 74.7%)
  • AFROC AUC Improvement (Reader Average):
    • Bitewing: 0.038 (0.878 - 0.840), with a p-value of 0.0055 (statistically significant)
    • Periapical: 0.054 (0.900 - 0.846), with a p-value of 1.47e-05 (statistically significant)
  • Specificity: There was a slight decrease in specificity (0.1-0.2%) when assisted, which is common in CADe systems where increased sensitivity might lead to a minor trade-off in specificity.

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

• Yes, a standalone performance test was conducted.
  • The results are detailed in the "Standalone Testing" section, including sensitivity, specificity, and AFROC AUC for the AI algorithm alone.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

• For both Standalone and Clinical Evaluation Studies:
  • The ground truth was established by expert consensus of US-licensed dentists, with adjudication by an oral radiologist for disagreements. This is a type of "expert consensus" ground truth. The document does not mention pathology or outcomes data.

8. The Sample Size for the Training Set

• The document does not provide the sample size of the training set for the AI model. It only details the test set used for performance evaluation.

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

• The document does not specify how the ground truth for the training set was established. It only describes the ground truth methodology for the test set used in performance validation.

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

• 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

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

Ask a specific question about this device