Artificial Intelligence for Fast and Accurate 3-Dimensional Tooth Segmentation on Cone-beam Computed Tomography

Lahoud, Pierre; EzEldeen, Mostafa; Beznik, Thomas; Willems, Holger; Leite, André Ferreira; Gerven, Adriaan Van; Jacobs, Reinhilde

doi:10.1016/j.joen.2020.12.020

Cited by 114 publications

(50 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Patients were referred to the radiology centre for CBCT scanning in accordance with clinical indications not related to the study. For the maxilla, an artificial intelligence driven automated tooth segmentation (Lahoud et al, 2021) was performed to segment and generate 3D models of teeth 15 to 25, the same algorithm was applied for segmentation of teeth 36 to 46 on the mandible. The bone tissue from both jaws was segmented by applying a threshold in Mimics Medical software 23.0 (Materialise).…”

Section: Methodsmentioning

confidence: 99%

Dynamic navigation: a laboratory study on the accuracy and potential use of guided root canal treatment

et al. 2021

Self Cite

View full text Add to dashboard Cite

Aim To evaluate 3D accuracy and outcome of a dynamic navigation method for guided root canal treatment of severe pulp canal obliteration (PCO) in 3D printed jaws. Methodology Three operators with different levels of experience in Endodontics performed navigated access cavities, using the Navident system (ClaroNav), in two sets (maxillary and mandibular) of 3D‐printed jaw models with teeth presenting severe PCO. Models were mounted on a phantom to mimic a real clinical situation. After treatment, a postoperative high resolution Cone‐Beam Computer Tomography (CBCT) scan (NewTom) was taken for each model and registered to the preoperative model. All access cavities were then segmented using 3‐Matic Medical software 15.0 (Materialise). Length and volume of each access cavity were measured, and a comparison was done by measuring the distance deviation in mm at the coronal entry point, apical point, vertical deviation, total deviation and angular deviation of the access cavity in comparison with the virtual planning. Additionally, all access cavities were scouted with a size 10 K‐file and inspected on the CBCT to confirm that the canal was located. Descriptive statistics for each parameter were performed. Normality of the data was assessed; data were transformed if needed to make it normally distributed. One‐way analysis of variance (anova) was applied to assess differences between parameters for tooth type, jaw, and operators and corrected for simultaneous hypothesis testing according to Tukey. Significance level was set at .05. Results After training with the system (28 cavities per operator), a total of 132 teeth and 168 access cavities (56 per operator) were prepared. All operators located a total of 156 canals, obtaining an overall success of 93% without a difference between operator experience (p > .05). The mean deviation at the apical point was 0.63 mm (SD 0.35) and was significantly lower in anterior teeth in comparison with molars (p < .05). The mean angular deviation from the planning was 2.81° (SD 1.53). Conclusion Dynamic navigation was an accurate approach for root canal treatment in teeth with severely calcified canals. However, the technique has a learning curve and requires extensive training prior to its use clinically.

show abstract

Section: Methodsmentioning

confidence: 99%

Dynamic navigation: a laboratory study on the accuracy and potential use of guided root canal treatment

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Consequently, the use of software in patient care is a debated topic due to the numerous variables involved in the procedure, making standardization highly difficult [25,44]. Artificial intelligence was recently proposed to automatize the segmentation process [45], but the other steps involved in VTP and FEA also require supplementary software and operator skills, which makes their use in routine clinical practice complex. Indeed, the approximate time required could be considered relatively long, but is in good agreement with the mean time required for maxillofacial VTP [46].…”

Section: Discussionmentioning

confidence: 99%

Decision Support for Removing Fractured Endodontic Instruments: A Patient-Specific Approach

et al. 2021

View full text Add to dashboard Cite

The instrumental fracture is a common endodontic complication that is treated by surgical or non-surgical removal approaches. However, no tool exists to help the clinician to choose between available strategies, and decision-making is mostly based on clinical judgment. Digital solutions, such as Finite Element Analysis (FEA) and Virtual Treatment Planning (VTP), were recently proposed in maxillofacial surgery. The aim of the current study is to present a digital tool to help decide between non-surgical and surgical strategies in a clinical situation of a fractured instrument. Five models have been created: the initial state of the patient, two non-surgical removal strategies using a low or high root canal enlargement, and two surgical removal strategies using a 3- or 6-mm apicoectomy. Results of the VTP found a risk of perforation for the non-surgical strategies and sinus proximity for surgical ones. FEA showed the lowest mechanical risk for the apicoectomy strategy. A 3-mm apicoectomy approach was finally chosen and performed. In conclusion, this digital approach could offer a promising decision support for instrument removal by planning the treatment and predicting the mechanical impact of each strategy, but further investigations are required to confirm its relevance in endodontic practice.

show abstract

“…Most studies have been consistent in their findings that the use of AI programs increases efficiency and minimizes the amount of time clinicians spend on tasks. 8 , 9 Therefore, AI has great potential to improve patient care, but susceptibility to potential biases must be minimized for its successful implementation in healthcare. Healthcare providers, especially those who are less experienced, can over-rely on the data provided by AI programs, leading to inaccurate diagnoses.…”

Section: Background and Signigicancementioning

confidence: 99%

Impact of explainable artificial intelligence assistance on clinical decision-making of novice dental clinicians

et al. 2022

View full text Add to dashboard Cite

Objective Despite artificial intelligence (AI) being used increasingly in healthcare, implementation challenges exist leading to potential biases during the clinical decision process of the practitioner. The interaction of AI with novice clinicians was investigated through an identification task, an important component of diagnosis, in dental radiography. The study evaluated the performance, efficiency, and confidence level of dental students on radiographic identification of furcation involvement (FI), with and without AI assistance. Materials and Methods Twenty-two third- and 19 fourth-year dental students (DS3 and DS4, respectively) completed remotely administered surveys to identify FI lesions on a series of dental radiographs. The control group received radiographs without AI assistance while the test group received the same radiographs and AI-labeled radiographs. Data were appropriately analyzed using the Chi-square, Fischer’s exact, analysis of variance, or Kruskal–Wallis tests. Results Performance between groups with and without AI assistance was not statistically significant except for 1 question where tendency was to err with AI-generated answer (P < .05). The efficiency of task completion and confidence levels was not statistically significant between groups. However, both groups with and without AI assistance believed the use of AI would improve the clinical decision-making. Discussion Dental students detecting FI in radiographs with AI assistance had a tendency towards over-reliance on AI. Conclusion AI input impacts clinical decision-making, which might be particularly exaggerated in novice clinicians. As it is integrated into routine clinical practice, caution must be taken to prevent overreliance on AI-generated information.

show abstract

Artificial Intelligence for Fast and Accurate 3-Dimensional Tooth Segmentation on Cone-beam Computed Tomography

Cited by 114 publications

References 32 publications

Dynamic navigation: a laboratory study on the accuracy and potential use of guided root canal treatment

Dynamic navigation: a laboratory study on the accuracy and potential use of guided root canal treatment

Decision Support for Removing Fractured Endodontic Instruments: A Patient-Specific Approach

Impact of explainable artificial intelligence assistance on clinical decision-making of novice dental clinicians

Contact Info

Product

Resources

About