Review Article

Artificial Intelligence in Endodontics: A Narrative Review

Parvathi Sudeep, Paras M. Gehlot, Brindha Murali, Annapoorna B. Mariswamy
Department of Conservative Dentistry and Endodontics, JSS Dental College and Hospital, JSS Academy of Higher Education and Research (JSSAHER), JSS Medical
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

Institutions Campus, Mysuru, Karnataka, India

Abstract
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

Aim: With the help of developments in artificial intelligence (AI), picture archiving systems, and computer-aided diagnostic systems,
dentists have been able to augment the quality of treatment and ensure a favorable outcome, by improving and facilitating the delivery
of appropriate dental care. There has been a breakthrough in designing the diagnosis, treatment plans, and predicting prognoses recently,
which has helped to explore newer options for better treatment. Materials and Methods: A literature search was conducted using
MeSH terms in a variety of databases, including PubMed, Cochrane, Scopus, and Web of Science, to gather information on “Artificial
intelligence (AI) in endodontics.” Unpublished data, literature written in other languages, and articles with only abstracts were discarded.
Forty-one relevant articles were included. Results: Since there were not many papers referring to AI in endodontics, papers published
relating to AI in dentistry were also referred. The search showed that the use of AI in dentistry, specifically in endodontics, has enormous
promise. Although useful, AI has its disadvantages as well as the need for long-term studies. Conclusion: AI, consisting of a sequence
of algorithms, work on a concept that mimics the human brain and thinking. AI in endodontics has been used widely in locating apical
foramina, identifying periapical pathologies, diagnosis of vertical root fractures, evaluating the outcome of regenerative procedures and
retreatments, and assessment of root morphologies and difficulties associated with canal preparations. Being a potential game changer
and beginning something called a “fourth industrial revolution,” AI has what it takes to revolutionize endodontics with time.

Keywords: Artificial Intelligence, Deep Learning, Endodontics, Machine Learning, Neural Networks
Received: 06-12-2022, Revised: 12-01-2023, Accepted: 13-01-2023, Published: 28-04-2023.

Introduction “Father of Artificial intelligence,” organized a conference

in Dartmouth, which paved the way for the extensive
Digitalization in dentistry has increased remarkably over
research on AI, from 1950s to 1970’s.[5]
the last two decades. In most developing countries, the
shortage of medical and dental professionals demands the AI can be described as “a field of science and engineering
need for technology, especially artificial intelligence (AI) concerned with the computational understanding of what
software. This can reduce expenses, time, the need for human is commonly called intelligent behavior, and with the
knowledge, and the number of medical errors.[1] A model creation of artefacts that exhibit such behavior.”[6]
designed to work almost identically to the human brain has Today, dentistry has abundant data which are acquired
been an enigma for a lot of researchers and scientists over from a patient at each step of the treatment process.
the years. Their constant effort and hard work resulted in This poses a challenge for obtaining, examining, and
the evolution of “Artificial Intelligence.”[2] The term AI, utilizing the knowledge gained. The vast amount of
explains how, through technology, a machine or software,
may replicate human intellect to do particular tasks.[3]
Address for correspondence: Dr. Paras M. Gehlot,
In 1955, John McCarthy coined a term which explained Department of Conservative Dentistry and Endodontics, JSS Dental College
the possibility of machines to carry out activities that and Hospital, JSS Academy of Higher Education and Research (JSSAHER),
JSS Medical Institutions Campus, Sri Shivarathreeshwara Nagara, Mysuru
can be encompassed within “intelligent” tasks.[4] In
570015, Karnataka, India.
the year 1956, McCarthy, also widely recognized as the E-mail: [email protected]

This is an open access journal, and articles are distributed under the terms of the
Access this article online
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License, which allows
Quick Response Code: others to remix, tweak, and build upon the work non-commercially, as long as
Website: appropriate credit is given and the new creations are licensed under the identical terms.
www.jioh.org
For reprints contact: [email protected]

DOI: How to cite this article: Sudeep P, Gehlot PM, Murali B, Mariswamy
10.4103/jioh.jioh_257_22 AB. Artificial intelligence in endodontics: A narrative review. J Int
Oral Health 2023;15:134-41.

      
134 134
© 2023 Journal of International Oral Health | Published by Wolters Kluwer - Medknow
 Sudeep, et al.: Artificial intelligence in endodontics

acquired knowledge can be deemed necessary to solve databases were utilized for identifying the articles with the
complex clinical problems. The evolution of AI will likely required information.
not replace dentists, but would be a perfect addition to
accentuate their expertise and support them. This can Materials and Methods
indeed help a dentist to adapt to a new level of accuracy
The databases of PubMed/Medline and other sources
in diagnosis and prediction of outcomes, thus, rendering
which related with AI in endodontics, were thoroughly
better patient experience and treatment success.[7]
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

searched from August 2021 to September 2022. The

The lack of standardization of treatment protocols can also following MeSH and keywords were used in the search:
pose a problem when newer technologies are used. Hence, “Artificial intelligence, Deep learning, Endodontics,
the use of AI can also be beneficial in understanding and Machine learning, and Neural networks.”
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

identifying conditions wherein the said technology can be

applied. Eligibility criteria
To understand how AI can be utilized, key aspects such The PICOS principles were followed while choosing the
inclusion criterion. The articles searched and included
as machine learning (ML), neural networks (NN), and
were the following:
genetic algorithms have to be acknowledged. Previous
- All English-language papers with full-text abstracts
studies on the use of AI in dentistry explains how AI
- Articles discussing the relationship between AI and
can be an advantage in the various aspects of patient
applications in endodontics
management and treatment strategies.
- Articles published since the use of AI in dentistry
The purpose of this narrative review was to understand about - Studies (in vitro and in vivo) that explored the use of AI
the application of AI in endodontics and the effects that any in endodontics
future advancements in this area might have in this field of The exclusion criterion included case series/reports, articles
dentistry. In light of the paucity of research in this area, the written in languages other than English, unpublished
review here is based on articles taken from internationally data, and unrelated studies. Dual publications were also
published research literature and review articles, based on a turned down. Possible outcomes were presented once the
specific set of key words which emphasized on the published data were examined and compared with each particular
information about AI, its various applications in the field of paper under debate. On the retrieved data, no statistical
Endodontics and regarding its limitations as well. Computer analysis was performed [Figure 1].

Search strategy
N = 251

Articles from PubMed Articles from other sources

x = 79 (Scopus, Cochrane, Web of Science)
y = 172

After exclusion of Duplicates and Foreign languages

z = 62

Number of articles
excluded (21)

Reasons for exclusion

Full text articles included
1. Full text not available n = 41
(14)
Articles on AI in dentistry
2. Editorials (7)
n = 22

Articles on AI in endodontics
n = 19

Figure 1: PRISMA flowchart

      Journal of International Oral Health ¦ Volume 15 ¦ Issue 2 ¦ March-April 2023 135  

 Sudeep, et al.: Artificial intelligence in endodontics

Results Discussion
Study recognition and preference AI methodologies used in dentistry
The initial electronic and manual search yielded 251 The composition of the technology used in AI consists
results the PubMed, Scopus, Cochrane and Web of of a neural network pattern almost identical to human
Science databases (2021–2022). On initial screening and brains.[8] This neural design imitates human thinking,
application of inclusion criteria 62 articles were chosen and is composed of firmly interconnected neurons.
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

based on name, abstract, and whole text. Finally, the To solve specific problems, these work together as a
narrative reviews, comprehensive reviews, umbrella “data-processing system.”[9] There has been amazing
reviews, and clinical trials that met the criteria were developments in the application of neural networks in
chosen. dentistry over the years.
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

Conventional computer programs such as “expert

Characteristics of included studies systems” use complicated formulas and numerical models
Randomized controlled trials, in vitro and in vivo research, to accomplish computing and achieve an array of plans
and reviews were all included. Forty-one papers that formulated on the given programming patterns. At
met the requirements for inclusion were included in our present, AI research has entered a distinct field of study
review. Out of these, 22 papers covered AI in dentistry known as “machine learning (ML).”[10] There are other
and 19 papers examined the applications of AI in key areas of research included in AI as well [Figure 2].
endodontics.
Machine learning
Assessment and quality of proof in studies included Machine learning is an AI subset, that uses algorithms
The literature that is currently available in the research to anticipate outcomes based on a dataset.[3] These
(reviews, in vitro, and in vivo) all agree about the beneficial algorithms are used to discover data’s inherent statistical
impact of application of AI in the various fields of patterns and structures.[11] Machine learning aims to make
dentistry. On this topic though, there were no meta- it easier for machines to learn from and solve issues from
analyses and the number of clinical trials appears to be large data sets without the need for human intervention.[3]
negligible. Future clinical research is crucial to understand For training, ML makes use of computational tools and
how AI can be applied in every aspect of dentistry and data (experience). It does so to assess the data presented
especially, endodontics. Almost all studies employ the as input and to process the knowledge gained from former
best practices, and all relevant findings are presented in a experiences. “Experience gathering” or “active learning”
consistent, verified, and reliable manner. is at the heart of machine learning. In practice, this

Figure 2: Artificial intelligence (AI) in dentistry

      
136 136  Journal of International Oral Health ¦ Volume 15 ¦ Issue 2 ¦ March-April 2023
 Sudeep, et al.: Artificial intelligence in endodontics

means that computers learn from their incoming data and estimate the dose that is mobile with respect to anatomy,
improve their properties by learning from their mistakes, such as in patients with head and neck cancer.[17]
all without the requirement for complex programming or
the building of a numerical model.[12] Deep learning
In a neural network, the number of neurons, levels or eras; Deep learning is a part of ML that process information
membership function selections in fuzzy logic; the size using a deep neural network with multiple computational
layers. To enhance feature identification, deep learning is
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

of the population, selection methods, rate of mutations,

utilized to develop a computational model that detects
and crossovers in optimization techniques; and hybrid
patterns automatically.[18] They employ simple features
techniques that use fuzzy logic or neural network or both
such as line, edge, and texture to study complex systems,
inevitably necessitate parametric tweaking related to the
pathologies, or entire organs.[19,20] The difference between
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

objective scheme.[13] Various ML models, such as the

deep learning and NNs is similar to that between feed
“Genetic Algorithm (GA),” “Artificial Neural Network
forward NNs and feed backward NNs. Deep learning has
(ANN),” and “Support Vector Machine (SVM),” may
a more complicated technique of connecting layers, as
“learn” and “be trained” from provided data to perform
well as a higher number of neurons than other networks
a variety of tasks.[14]
to demonstrate sophisticated programs, more processing
capacity to train, and a preprogrammed character
Neural networks recognition feature.[21]
A prominent sort of ML model is neural networks, which
are made up of a series of algorithms that calculate signals
Clinical decision support systems (CDSS)
using artificial neurons. Its goal is to develop neural
“Any computer system that aids healthcare providers
networks that mimic the human brain.[3]
in making clinical choices by handling clinical data or
Artificial neural networks are a collection of a configurable medical knowledge” is referred to as a CDSS.[22] The
number of “artificial neurons or nodes” that are connected inference engine (IE), knowledge base (KB), explanation
in a systematic layering structure that includes an input module, and working memory are the four essential
sequence, one or maybe more hidden units, and an output components of most CDSS.[16] Any such system’s primary
vector. With the exception of the input nodes, each component is the IE, which stores information about the
neuron receives numerous weighted inputs and produces patient and draws conclusions about specific illnesses
an output that is usually an arbitrary expression of the from it. The knowledge used by IE is represented by the
inputs.[15] By altering these weights regularly, a neural knowledge base and tools that have been built to aid in
network “learns.” the accumulation and elaboration of this knowledge.
The working memory is the database where the acquired
Their capacity to apply what they’ve learned from previous
data are saved or may take the shape of a signal. The
representative cases, analyze non-linear data, deal with
final component, the explanation module, is in charge of
unspecific data, and generalize; allowing the model to
justifying the IE’s conclusions when applying the KB’s
be exposed to new information, has made them a very
information to patient data and records in the working
appealing investigative tool. They have been employed
memory.[23]
in clinical diagnosis, radiology and histopathology
image processing, intensive care data interpretation, and
waveform analysis.[7]
Fuzzy logic
The branch of logic known as fuzzy logic recognizes and
“Convolutional neural networks (CNNs)” for image proves that everything is a matter of degree.[16] It offers
classifications and “dilated convolutional neural networks quite useful explanation for a hazy problem. Fuzzy logic
(DCNNs)” for sematic scene partitions are two types of is a very simple ML technique that is also flexible to use.
ANN that have recently gained popularity.[16] The two
The following are the four major components of the fuzzy
primary types of CNNs used for volumetric prediction
logic system:
in particular are “Tiramisu” and DCNNs. “U-net” and
other Tiramisu-based models are particularly good at (i) “Rule Basse,” (ii) “Fuzzification,” (iii) “Inference
estimating dosage ratios that are spatially compatible with Engine,” and (iv) “Defuzzification.”[2]
anatomy, such as the prostate dose volume. DCNNs also Fuzzy logic aims to emulate human reasoning abilities
utilize the complexities that bypass information during when dealing with unclear issues.
the encoding process to help broaden their perspectives
and visual field.
Evolutionary computation
DCNNs are likely to become more common in the Evolutionary computation is a disputed dynamic
prediction of the amount of exposure for head and neck programming strategy for general-purpose problems based
intensity modulated radiation therapy as they can help on the generally accepted “neo-Darwinian” perspective,

      Journal of International Oral Health ¦ Volume 15 ¦ Issue 2 ¦ March-April 2023 137  

 Sudeep, et al.: Artificial intelligence in endodontics

which incorporates basic Darwinian evolutionary theory, Periapical pathologies

Weismann’s selectionism, and Mendel’s genetics. The Radiographically, periapical pathosis can be detected
genetic algorithm is the most extensively used evolutionary as periapical radiolucencies. On periapical radiographs,
algorithm.[24] It uses various methods including mutation, panoramic radiographs, and cone-beam computed
inheritance, selection, and crossover to find a better remedy. tomography scans (CBCT), apical periodontitis is
The key advantage of genetic algorithms over traditional frequently discovered as an unintentional finding. CBCT
methods is that they are based on conflict resolutions rather produces high-resolution three-dimensional (3D) images
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

than numerical correlations, as used by traditional methods. that are free of the deformation and superimposition
It is simple to use despite being a powerful upgrading of bone and dental structures that might occur with
device, because it is based on normal standards.[2] traditional radiography.[26] A dentist knows that it is always
crucial to have a dependable instrument that can assist
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

Hybrid intelligent systems in making informed selections and treatment planning.

Each AI technique has its own set of advantages and A study looked at how an AI-based CNN model may
disadvantages. Combining systems enable common sense be used to detect periapical lesions on radiographs, and
to be accommodated, knowledge to be extracted from found that the model performed well, with high sensibility
original assets, “human-like” cognitive mechanisms to and intermediate precision. For dentists, this approach
be used, ambiguity and inaccuracy to be dealt with, could be very useful in identifying and detecting periapical
and learning to keep up with the rapidly evolving and lesions.[27]
unfamiliar environment. Developing fuzzy systems
Another model’s accuracy in recognizing periapical
for ANNs and vice versa, and Genetic Algorithms for
diseases on CBCT images was astounding, with a 92.8%
autonomously instructing and designing NNA structures
accuracy rate.[28] An AI-based model was utilized in another
are just a few of the hybrid systems accessible.[7]
investigation to detect the existence of a periapical lesion.
There were unexpected findings, with a mean accuracy of
Endodontics and applications of AI [Figure 3] roughly 77.2%, and the authors stated that the reference
Identification and diagnosis method was better than this approach, but that the results
AI has been used to detect and diagnose a wide range may be improved in future work utilizing optimization
of physiological and pathological abnormalities in the techniques.[29]
teeth.[25] AI has also been shown in studies to be an effective
tool for understanding and spotting anomalies, as well as Setzer et al.[30] concluded that a DL algorithm trained in a
for formulating the required treatment strategies. constrained CBCT setting produced high lesion detection
accuracy. Enhanced versions of AI may improve overall
voxel-matching accuracy, thus, revealing an accuracy of
93% for this study.
Endres et al.[31] found that the rate of detection of
periapical radiolucencies by 24 oral and maxillofacial
surgeons was similar to using a DL algorithm model. The
experiments revealed that adopting AI systems can lessen
the differences between examiners and bias.
Poswar et al.[32] analyzed the variations in gene expression
between a periapical cyst and a periapical granuloma
using a “multilayer perceptron neural network” for gene
categorization. The research had its own set of constraints.
Zheng et al.[33] compared a morphologically restricted
Dense U-Net with known clinical image analysis
approaches in terms of lesion diagnosis efficiency and dice
coefficient indices of a multilabel segmentation. Despite
the small size of the sample, the researchers found that the
novel deep learning strategy increased CBCT segmentation
and the precision of pathological identification.

Root fractures
“Vertical root fractures (VRFs)” are a very uncommon
occurrence in endodontically treated teeth. VRFs
Figure 3: Artificial intelligence models in endodontics are found in 3.7%–30.8% of teeth that have received

      
138 138  Journal of International Oral Health ¦ Volume 15 ¦ Issue 2 ¦ March-April 2023
 Sudeep, et al.: Artificial intelligence in endodontics

endodontic therapy, according to studies.[34] Determining the working length and demonstrated an outstanding
VRFs on radiographs is difficult and may necessitate the accuracy of 96%, which is higher than the accuracy of
use of more advanced technology. expert endodontists (76%). These findings matched those
Johari et al.[35] performed research on the creation of an of another study by the same author and his associates,
AI-based model utilizing a PNN framework for detecting who used feature extraction processes from radiographs
VRFs on both intact and endodontically treated teeth using before processing the data with an ANN. The study found
that finding the minor apical foramen was 93% accurate.[43]
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

periapical radiographs and CBCT images. In comparison

to periapical radiographs, the model demonstrated to be
quite effective in diagnosing VRFs on CBCT images, with Re-treatment predictions
an accuracy of 96.6%. CBS stands for “case-based reasoning,” which defines
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

the practice of coming up with solutions to queries

CNNs, according to Fukuda et al.,[36] could be a viable and doubts based on previous encounters with similar
approach for detecting and measuring VRFs on challenges.[40] Campo et al.[44] used CBS to predict the
panoramic radiographs. In a study by Kositbowornchai results of nonsurgical root canal retreatment, as well as the
et al.,[37] who employed a probabilistic neural network associated risks and benefits. The system gave the data on
design to determine if a tooth root was sound or had a whether or not retreatment should be conducted, and also
vertical root fracture, the accuracy was 95.7%. provided the statistics on the efficiency of the procedure
done earlier, the risks involved, and the recall periods. The
Root canal and root morphology system’s merit is that it may be able to properly forecast the
For a successful non-surgical root canal therapy, dentists retreatment outcome. But the technique had a drawback
must first understand and identify root canal anatomy of relying too much on the data’s information, and not
and root morphologies. AI can assist in recognizing any analyzing possibilities from every perspective.
morphological irregularities as well as identifying errors
in locating new canals.
Regenerative endodontic procedures
On panoramic radiographs, Hiraiwa et al.[38] investigated Using the neuro-fuzzy inference technique, Bindal et al.
the diagnostic efficacy of a DL system for categorization of examined dental pulp stem cells in multiple rejuvenation
the root morphology of mandibular first molars. On CBCT treatment modalities. This approach predicted the result
images, distal roots were investigated for the occurrence of of a simulated clinical scenario by assessing the stem
a single or additional root. For determining whether distal cell vitality after bacterial lipopolysaccharide treatment.
roots were solitary or had supplementary roots, the DL Throughout several regenerative regimens, the neuro-
system exhibited a diagnostic reliability of 86.9%. fuzzy interpretation method was employed to predict cell
Lahoud et al. used the CNN technique to automate viability, following microbial infection. The researchers
3-dimensional tooth segmentation. In a rapid, efficient, used neuro-fuzzy inferencing, which could be adjustable,
and reliable clinical benchmark, the authors analyzed 433 to test the outcome’s accuracy in forecasting stem cell
CBCT radiographic segmentations of teeth and found survival after pathogenic invasion.[40,45]
that AI performed as well as a human operator but at a
considerably quicker pace.[39,40] Shortcomings and gaps in AI and endodontics
Though AI has been found to be beneficial in a lot of
Working length determinations aspects, there have been downfalls associated with it, due to
The selection of the correct working length (WL) is which it has not been widely implemented in endodontics.
critical to ensuring successful root canal treatment Some of the shortcomings and disadvantages associated
outcomes. Instrumentation beyond the apical foramen, include the following:[40,46]
flare-ups, periapical foreign body reactions, and poor i. The health care system requires a standard
microbiological control are all common consequences programming technology for organizing appointments,
of inadequate WL determination.[41] Finding the apical managing patients and for periodic recall. This system
foramen and estimating the WL can be done in a variety also has to be updated regularly to keep up to the
of ways, including radiography, digital tactile sense, and changes occurring in the healthcare sector.
patient’s responses to a file or paper point.[42] The use ii. The cost of setting up an AI based system in
of digital technology has demonstrated both benefits in independent clinics would not be feasible.
terms of finding the apical foramen and drawbacks in iii. The availability of patient data using the individual
terms of mistakes. As a result, investigations on the use of health records can prove to be useful in informing
ANN to estimate the correct WL of teeth have been done.
the dentists about adverse reactions in respect to the
In a human cadaver model, Saghiri et al.[41] used an use of certain drugs and/or the adjustments required
artificial neural network (ANN) method to determine in the treatment protocol. But this can also be a

      Journal of International Oral Health ¦ Volume 15 ¦ Issue 2 ¦ March-April 2023 139  

 Sudeep, et al.: Artificial intelligence in endodontics

disadvantage, as misuse of information can also occur Ethical policy and Institutional Review board statement
through the AI channels. Not applicable.
iv. There is no protocol that has been devised yet to
provide a precise diagnosis, that would affect the Patient declaration of consent
prediction of outcomes or determination of the Not applicable.
prognosis. The clarity of this diagnosis would be
based on the clinical findings. Data availability statement
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

v. Dynamic navigations in endodontic surgery can be Not applicable.

improved with the help of AI. Very minimal number
of studies look into these techniques and it is highly
recommended that further studies be done to check and References
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

1. Machoy ME, Szyszka-Sommerfeld L, Vegh A, Gedrange T,

assess robotically guided placement in endodontics.
Woźniak K, Woźniak K. The ways of using machine learning in
vi. The complexity of the applications can be dentistry. Adv Clin Exp Med 2020;29:375-84.
misinterpreted by individuals and dentists who have 2. Tandon D, Rajawat J. Present and future of artificial intelligence in
not been trained in AI. dentistry. J Oral Bio Craniofacial Res 2020;10:391-6.
3. Khanagar SB, Ehaideb AA, Maganur PC, Vishwanathaiah S, Patil S,
vii. Data in endodontics can be often used for both Baeshen HA, et al. Developments, application, and performance of
education and evaluation, leading to “data snooping artificial intelligence in dentistry—A systematic review. J Dent Sci
bias.” 2021;19:508-22.
viii. The results of AI in endodontics are not readily 4. Rajaraman V. John McCarthy father of artificial intelligence. Reson.
2014;19:198-207.
significant as AI can give a single outcome as an 5. National Research Council. Funding a Revolution: Government
answer, where multiple outcomes could be present. Support for Computing Research. Washington, DC: The National
Academies Press, 1999.
The limitation of this review is the constrained search 6. Shapiro SC. Artificial intelligence. In: Shapiro SC, editor.
period (August 2021 to September 2022). Also, papers Encyclopedia of Artificial Intelligence. Vol. 1. New York: Wiley,
with abstracts only and published in foreign languages 1992.
7. Ramesh AN, Kambhampati C, Monson JRT, Drew PJ. Artificial
were not included. It is interesting to note that, a few more intelligence in medicine. Ann R Coll Surg Engl 2004;86:334-8.
articles related to AI in endodontics have been added to 8. Brickley MR, Shepherd JP, Armstrong RA. Neural networks: A new
the literature lately. technique for development of decision support systems in dentistry.
J Dent 1998;26:305-9.
9. Tripathy M, Maheshwari RP, Verma HK. Power transformer
Conclusion differential protection based on optimal probabilistic neural
network. IEEE Trans Power Del 2010;25:102-12.
With inter-disciplinary dentistry becoming more popular 10. Ren R, Luo H, Su C, Yao Y, Liao W. Machine learning in dental,
in the coming decades, it is indeed important to assess the oral and craniofacial imaging: A review of recent progress. PeerJ
worth of AI and its applications in endodontics. The fate of 11459:1.
Endodontics, which is a highly researched subject, can be 11. Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry:
Chances and challenges. J Dent Res 2020;99:769-74.
changed by the incorporation of modified bioengineering 12. Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for
components like AI. The impact of AI in integrating the medical imaging. Radiographics 2017;37:505-15.
various areas of knowledge can prove to be beneficial in 13. Kareem SA, Pozos-Parra P, Wilson N. An application of belief
upgrading patient care. The combination of conventional merging for the diagnosis of oral cancer. Appl Soft Comput J
2017;61:1105-12.
methodologies with AI technology can help in minimizing 14. Tan MS, Tan JW, Chang S-W, Yap HJ, Abdul Kareem S, Zain RB.
the potential errors in interpretation and can indefinitely, A genetic programming approach to oral cancer prognosis. PeerJ
be adopted into routine clinical practice with ease. 2016;4:e24822482.
15. Nayak GS, Kamath S, Pai KM, Sarkar A, Ray S, Kurien J, et al.
Principal component analysis and artificial neural network analysis
Acknowledgement of oral tissue fluorescence spectra: Classification of normal
Nil. premalignant and malignant pathological conditions. Biopolymers
2006;82:152-66.
16. Shilpi S. Artificial intelligence in dentistry: The current concepts and
Financial support and sponsorship a peek into the future. Int J Contemp Med 2019;6:L5-9.
Nil. 17. Kearney V, Chan JW, Valdes G, Solberg TD, Yom SS. The application
of artificial intelligence in the IMRT planning process for head and
Conflicts of interest neck cancer. Oral Oncol 2018;87:111-6.
18. Akst J. A primer: Artificial intelligence versus neural networks.
There are no conflicts of interest. Inspiring Innovation: The Scientist Exploring Life 2019. p. 65802.
19. Rabun al JR, Dorado J. Artificial neural networks in real-life
Authors contributions applications. IGI Global: Hershey 2005;1:166-346.
20. Yaji A, Prasad S, Pai A. Artificial intelligence in dento-maxillofacial
PS and PG conceived the idea and study design. PS
radiology. Acta Sci Dent Sci 2019;3:116-21.
performed the literature search and the extraction of 21. Abiodun OI, Jantan A, Omolara AE, Dada KV, Mohamed NAE,
data. PS drafted the article. PG, BM and AM reviewed Arshad H. State-of-the-art in artificial neural network applications:
the article. A survey. Heliyon 2018;4:e00938.

      
140 140  Journal of International Oral Health ¦ Volume 15 ¦ Issue 2 ¦ March-April 2023
 Sudeep, et al.: Artificial intelligence in endodontics

22. Khalifa M. Clinical decision support: Strategies for success. Proc 34. Fuss Z, Lustig J, Katz A, Tamse A. An evaluation of endodontically
Comput Sci 2014;37:422-7. treated vertical root fractured teeth: Impact of operative procedures.
23. Zhang B, Wu Y, Lu J, Du K. Evolutionary computation and its J Endod 2001;27:46-8.
applications in neural and fuzzy systems. Appl Comput Intell Soft 35. Johari M, Esmaeili F, Andalib A, Garjani S, Saberkari H. Detection
Comput 2011;2011:1-20. of vertical root fractures in intact and endodontically treated
24. Tripathi P, Malathy C, Prabhakaran M. Genetic algorithms based premolar teeth by designing a probabilistic neural network: An ex
approach for dental caries detection using back propagation neural vivo study. Dentomaxillofac Radiol 2017;46:20160107.
network. Int J Recent Technol Eng 2019;8:2277-3878. 36. Fukuda M, Inamoto K, Shibata N, Ariji Y, Yanashita Y, Kutsuna S,
25. Umer F, Habib S. Critical analysis of artificial intelligence in et al. Evaluation of an artificial intelligence system for detecting
Downloaded from http://journals.lww.com/jioh by BhDMf5ePHKav1zEoum1tQfN4a+kJLhEZgbsIHo4XMi0hCywCX1AW

endodontics: A scoping review. J Endod 2022;48:152-60. vertical root fracture on panoramic radiography. Oral Radiol
26. AAmerican Association of Endodontists, American Academy of 2019;36:337-343.
Oral and Maxillofacial Radiology. Use of cone-beam computed 37. Kositbowornchai S, Plermkamon S, Tangkosol T. Performance of
tomography in endodontics Joint Position Statement of the an artificial neural network for vertical root fracture detection: An
nYQp/IlQrHD3i3D0OdRyi7TvSFl4Cf3VC4/OAVpDDa8KKGKV0Ymy+78= on 06/11/2024

American Association of Endodontists and the American Academy ex vivo study. Dent Traumatol 2013;29:151-5.
of Oral and Maxillofacial Radiology. Oral Surg Oral Med Oral 38. Hiraiwa T, Ariji Y, Fukuda M, Kise Y, Nakata K, Katsumata A,
Pathol Oral Radiol Endod 2011;111:234-7. et al. A deep-learning artificial intelligence system for assessment
27. Ekert T, Krois J, Meinhold L, Elhennawy K, Emara R, Golla T, of root morphology of the mandibular first molar on panoramic
et al. Deep learning for the radiographic detection of apical lesions. radiography. Dentomaxillofac Radiol 2019;48:20180218.
J Endod 2019;45:917-922.e5. 39. Lahoud P, EzEldeen M, Beznik T, Willems H, Leite A, Van Gerven A,
28. Orhan K, Bayrakdar IS, Ezhov M, Kravtsov A, Özyürek T. Evaluation et al. Artificial intelligence for fast and accurate 3-dimensional
of artificial intelligence for detecting periapical pathosis on cone- tooth segmentation on cone-beam computed tomography. J Endod
beam computed tomography scans. Int Endod J 2020;53:680-9. 2021;47:827-35.
29. Mahmoud YE, Labib SS, Hoda MO. Clinical prediction of teeth 40. Aminoshariae A, Kulild J, Nagendrababu V. Artificial intelligence
periapical lesion based on machine learning techniques—An in endodontics: Current applications and future directions. J Endod
experimental study. Proceedings of Second International Conference 2021;47:1352-7.
on Digital Information Processing, Data Mining, and Wireless 41. Saghiri MA, Garcia-Godoy F, Gutmann JL, Lotfi M, Asgar K.
Communications (DIPDMWC 2015), Dubai, UAE, 2015. The reliability of artificial neural network in locating minor apical
30. Setzer FC, Shi KJ, Zhang Z, Yan H, Yoon H, Mupparapu M, et al. foramen: A cadaver study. J Endod 2012;38:1130-4.
Artificial intelligence for the computer-aided detection of periapical 42. Seidberg B, Alibrandi B, Fine H, Logue B. Clinical investigation of
lesions in cone-beam computed tomographic images. J Endod measuring working lengths of root canals with an electronic device
2020;46:987-93. and with digital-tactile sense. J Am Dent Assoc 1975;90:379-87.
31. Endres MG, Hillen F, Salloumis M, Sedaghat AR, Niehues SM, 43. Saghiri MA, Asgar K, Boukani KK, Lotfi M, Aghili H, Delvarani A,
Quatela O, et al. Development of a deep learning algorithm for et al. A new approach for locating the minor apical foramen using an
periapical disease detection in dental radiographs. Diagnostics artificial neural network. Int Endod J 2012;45:257-65.
(Basel) 2020;10:430. 44. Campo L, Aliaga IJ, De Paz JF, García AE, Bajo J, Villarubia G,
32. Poswar Fde O, Farias LC, Fraga CA, Bambirra W, Brito- et al. Retreatment predictions in odontology by means of CBR
Júnior M, Sousa-Neto MD, et al. Bioinformatics, interaction systems. Comput Intell Neurosci 2016;2016:7485250.
network analysis, and neural networks to characterize gene 45. Bindal P, Bindal U, Lin CW, Kasim NHA, Ramasamy TSA,
expression of radicular cyst and periapical granuloma. J Endod Dabbagh A, et al. Neuro-fuzzy method for predicting the viability
2015;41:877-83. of stem cells treated at different time-concentration conditions.
33. Zheng Z, Yan H, Setzer FC, Shi KJ, Mupparapu M, Li J. Technol Health Care 2017;25:1041-51.
Anatomically constrained deep learning for automating dental 46. Chen YW, Stanley K, Att W. Artificial intelligence in dentistry:
CBCT segmentation and lesion detection. IEEE Trans Autom Sci Current applications and future perspectives. Quintessence Int
Eng 2021;18:603-14. 2020;51:248-57.

      Journal of International Oral Health ¦ Volume 15 ¦ Issue 2 ¦ March-April 2023 141