Reduced radiation possible with AI prediction of root morphology
NAGOYA, Japan: With the aim of clarifying the relationship between panoramic radiographic appearance and longitudinal CBCT classification of root configurations of the mandibular second molar, researchers from Japan have investigated hundreds of panoramic radiographs and are now planning to develop an artificial intelligence (AI) system to help simplify diagnosis of mandibular second molar root canal configurations on panoramic radiographs in the future.
For the study, Drs Takuma Funakoshi and Takuya Shibata, who both work at the Department of Oral and Maxillofacial Radiology at the Aichi Gakuin University’s School of Dentistry, and their research team examined panoramic radiographs of 1,058 mandibular second molars and classified them into five types according to the number and configuration of the roots.
These molars were also examined with CBCT at four levels between the pulp chamber and the root apex, and axial images perpendicular to the root axis were categorised into three patterns:
- single (fused root with small grooves on both buccal and lingual sides or a round root with one canal);
- double (two separate roots with a trabecular appearance between them); and
- C-shaped (root with a deep groove opening only on the lingual or buccal side relative to the opposite side).
Based on these patterns and their scan levels, the CBCT root morphology appearance in each tooth unit was classified into one of seven groups. The scientists then investigated the relationship between these seven CBCT groups and the five panoramic root types.
It was found that, in panoramic Type 1 and 2 (with separate roots), 85% had roots with a double pattern (Groups II and III) on the CBCT images. In panoramic Type 3 and 4 (with fused roots), 85% had C-shaped CBCT patterns at the lower scan levels.
In an interview with Dental Tribune International, Funakoshi explained what is to be expected in the near future: “This is the first step of our sequential study. Our goal is to utilise a deep learning AI system in diagnosing the mandibular second molar root canal configurations on panoramic radiographs. If an AI system could predict the canal morphology, radiation exposure would be reduced. So, we sought an appropriate clinical classification which was actually effective for endodontic treatment and verified by CBCT. However, we could not find such a classification. Therefore, we decided to create a convenient and useful classification ourselves.”
The study, titled “Cone-beam computed tomography classification of the mandibular second molar root morphology and its relationship to panoramic radiographic appearance”, was published on 13 October 2020 in Oral Radiology, ahead of inclusion in an issue.