Technology

AssistDent® Technology

Powerful AI assisted image analysis to help dentists identify dental decay sooner, in particular enamel-only proximal caries

Technology Technology

AssistDent® Technology

Powerful AI technology assisted bitewing radiograph image analysis to help dentists identify dental decay sooner, in particular enamel-only proximal caries

An Overview of the Tools and Methods our Artificial Intelligence Technology Uses to Help Dentists Achieve Better Detection Rates

1.

We get machine learning algorithms to do what dentists find challenging

AssistDent, an innovative technology developed and patented by Manchester Imaging Limited, uses a range of machine learning algorithms to identify regions of bitewing radiographs which are indicative of enamel-only proximal caries. 

Detection of early enamel interproximal caries by dentists is known to be difficult.  However, once identified and it is at a stage when problematic progress may be prevented (or in some cases reversed), with remedial measures such as cleaning or diet advice, fluoride varnishes and resin infiltration.  A higher-grade caries that has penetrated beyond the enamel into dentine, can be detected with relative ease by dentists and in these cases, preventive action is no longer possible.

2.

We go to great lengths to train AssistDent to the highest standard

For machine learning algorithms to offer clinical gains, the training examples need to be as close to a recognised Gold Standard as possible.  Any false positive examples in the training data will be captured as true positives in the models and result in similar features being erroneously labelled positive in the analysed images.

Manchester Imaging has taken great care to ensure that data used to train the AssistDent® machine learning algorithms are of the highest possible standard.  Five internationally recognised dento-maxillofacial radiologists were instructed to independently identify proximal caries in a set of training images.  A consensus data set from these experts (deemed to be the Gold Standard), was then used to train the AssistDent machine learning models. The result is a software tool which uses the combined expertise from five authoritative dento-maxillofacial radiologists in its learning algorithm and is able to detect the often very subtle patterns indicative of enamel-only proximal caries.

3.

We ensure the AI algorithms are continuously improved

The AssistDent model of machine learning uses offline training, which means that the training exercise is separate from the run-time execution of the software, thus enabling Manchester Imaging to train the models using expert observers.

An alternative model of machine learning is online learning.  In this case, human input into the process at run-time, continually adjusts and improves the models.  This is often used in applications where the intention is to achieve “human-like” performance such as face or object recognition.  In the detection of caries, there is an intention to improve upon general human performance, helping dentists become more like an expert dentomaxillofacial radiologist in practice.

Online training by dentists would result in the models becoming increasingly trained to behave like the dentist and less like the expert.  An automated caries detection system is only worth having if it improves dentists’ performance.

Back To Top

Manchester Imaging Limited

Room E43, Sackville Street Building
Sackville Street
Manchester, M1 3BU
United Kingdom

AssistDent® is a registered trademark of Manchester Imaging Limited in Australia, Canada, European Union, New Zealand, United Kingdom, United States of America. 

© Manchester Imaging 2022 / Privacy Policy / Terms & Conditions

Manchester Imaging Limited

Room E43
Sackville Street Building
Sackville Street
Manchester, M1 3BU
United Kingdom

AssistDent® is a registered trademark of Manchester Imaging Limited in Australia, Canada, European Union, New Zealand, United Kingdom, United States of America. 

© Manchester Imaging 2022 / Privacy Policy / Terms & Conditions