System and method for error detection in dental imaging

The system addresses inefficiencies in panoramic dental imaging by automating error detection using a network-based approach, enhancing diagnostic accuracy and reducing costs through rapid error identification and correction.

WO2025191278A1PCT designated stage Publication Date: 2025-09-18VOXEL3DI LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/GB2025/050526
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-03-15
Filing Date
2025-03-14
Publication Date
2025-09-18

AI Technical Summary

Technical Problem

Current dental imaging systems lack automated error detection in panoramic radiographs, leading to inefficiencies, potential misdiagnoses, increased healthcare costs, and patient anxiety due to manual error correction by healthcare professionals.

Method used

A system utilizing a backbone network, feature pyramid network, regional proposal network, and Fast R-CNN for automated error detection in panoramic dental images, converting images to byte arrays, extracting critical features, generating feature maps, and classifying errors with bounding boxes.

Benefits of technology

Automated error detection in panoramic dental images reduces diagnostic time, enhances accuracy, and minimizes misdiagnoses by providing immediate feedback on image viability and correction instructions, thus improving patient care and reducing healthcare costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure GB2025050526_18092025_PF_FP_ABST
    Figure GB2025050526_18092025_PF_FP_ABST
Patent Text Reader

Abstract

A system and method for error detection in dental imaging. The method for detecting errors in a dental panoramic image, comprising converting a dental panoramic image into a byte array. Identifying and extracting critical features from the byte array. Generating a plurality of feature map layers. Generating region proposals for potential errors within each feature map layer. Extracting fixed sized features from the region proposals. Classifying features within each region proposal. Regressing bounding boxes around classified error. Outputting the image with bounding boxes indicating errors within the image, and outputting an indication whether image is viable based on the errors.
Need to check novelty before this filing date? Find Prior Art