Smile Dx®

Smile Dx® is a computer-assisted detection software designed to enhance the diagnostic capabilities of dentists by analyzing digital bitewing and periapical radiographs. It leverages machine learning algorithms to detect and segment dental findings and measure bone levels, with clinical studies demonstrating improved sensitivity for caries and periapical radiolucencies without compromising specificity, thereby aiding in comprehensive dental radiographic assessment.

Cube Click, Inc. has developed Smile Dx®, a computer-assisted detection software designed to assist licensed dentists in analyzing digital bitewing and periapical radiographs of permanent teeth. This software has undergone a thorough review and has been determined to be substantially equivalent to other commercially available devices with similar functions, enabling its marketing and distribution. It is important to note that Smile Dx® is intended as an aid to a dentist's review, not as a replacement for their comprehensive clinical judgment.Smile Dx® utilizes machine learning algorithms to aid in the detection and segmentation of various suspected dental findings, including caries, periapical radiolucencies, restorations, and normal dental anatomy. The software also assists dentists in precisely measuring mesial and distal bone levels. Performance testing, including standalone evaluations and a multi-reader, multi-case clinical study, demonstrated that the device significantly improved reader sensitivity for detecting both caries and periapical radiolucencies, without compromising specificity, thereby supporting its effectiveness in enhancing dental radiographic assessment.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does Smile Dx® compare in performance to other commercially available CAD software in a real-world clinical setting beyond the controlled study?; What is the specific training data used for the machine learning algorithms, and how does its diversity impact the software's performance across different patient demographics or image qualities?; Are there any specific types of dental findings or radiographic artifacts where Smile Dx®'s performance is less robust, and how are these limitations communicated to clinicians?; What is the long-term impact of using Smile Dx® on dentist workflow efficiency and diagnostic accuracy, particularly regarding false positives or negatives?; Has the software been evaluated for its ability to track the progression or regression of dental conditions over time, leveraging its detection and measurement capabilities?