SURENDERA DENTAL COLLEGE & RESEARCH INSTITUTE.
Department of Oral Medicine and Radiology
INTER DEPARTMENT MEET 2022
Artificial Intelligence
Boon or Curse ….???
CONTENT
• Introduction
• History
• Classification
• How does AI work?
• Role of AI in dentistry.
• Current Scenario and Future Prospects
• Conclusion
• References
INTRODUCTION
Ever since the field of science has originated,
researchers and technologists have been busy in
solving the complexity of the human brain that is a
maze of neurons interconnected with each other and
transmitting signals to the whole body.
Artificial intelligence (AI) are machines that are
able to mimic the cognitive functions of humans
to perform tasks of problem-solving and
learning.
HISTORY
Slide Title
Alan Turing (British mathematician, 1936) was one of the most
important visionary and theoretician, proved that a universal
calculator—known as the Turing machine—is possible [13].
Turing’s central insight is that such a machine is capable of solving
any problem as long as it may be represented and solved by an
algorithm.
Newell and Simon (1955) designed “The Logic Theorist” which is
considered to be the first AI program which marks the development
of modern AI.
John McCarthy in 1965 coined the term ‘artificial intelligence
Slide Title
CLASSIFICATION
HOW DOES AI
WORK?
Slide Title
Artificial
Intelligence
(AI)
Machine
Learning
1. Genetic algorithms
2. Artificial Neural Networks
(ANN)
3. Fuzzy Logic
Deep
Learning -Subset of ML
-Focus on lines, edges,
corners
Machine Learning
 Algorithms are applied to perform tasks by learning patterns from
data.
 Machine learning technique involves parameter adjustment with
regards to underlying technique such as,
o number of neurons,
o layers in a neural network technique;
o population size,
o rate of mutation and
o crossing over rate in genetic algorithms technique etc
Deep learning
 A complex multilayer system.
 This system has a complex arrangement of layers and a greater
number of interconnected neurons which makes it capable of
visualizing simple features like
o lines,
o edges,
o corners and
o macroscopic patterns in a hierarchical structure
Slide Title
Slide Title
Schematic representation of the architecture of neural networks. Artificial neural networks are structures used in machine
learning. They contain many small communicating units called neurons, which are organized in layers. a. Shallow neural
networks are composed of an input layer, a few hidden layers and an output layer. b. Deep neural networks have an input
layer, multiple hidden layers and an output layer. c. Convolutional neural networks use filters to scan a small neighbourhood
of inputs.
Slide Title
Role of Artificial
Intelligence in Dentistry…
Slide Title
AI in general dentistry
 book a patient's appointment in the clinic
 taking proper medical and dental history of the patient
 managing insurance as well as assisting the dental surgeon in adequate
diagnosis and treatment planning
 works by warning the dental professional about the habitual details of
patients like use of tobacco or alcohol and medical history of the patient
 follow up and online emergency health consultancy.
Artificial intelligence and diagnostic
dentistry
 Proper diagnosis of any disease is the basis for successful
treatment.
 Example: Internal derangement of temporomandibular joints
where clinical and radiological diagnosis is considered as gold
standard.
Slide Title
Kim et al. 2009 used Artificial neural network to build a model that can predict
toothache on the basis of association between toothache and daily toothbrushing frequency,
toothbrushing time, use of dental floss, toothbrush replacement pattern, undergoing scaling and
other factors like diet and exercise. This model recognizes adequate eating habits, oral hygiene,
and stress prevention as the most important factors in preventing toothaches
Slide Title
Nieri et. al 2008 used Bayesian network analysis to identify relationships between various
factors affecting the diagnosis and final treatment outcome of impacted maxillary canines
Artificial intelligence
and radiology
 AI provides the additional capability to learn more to be a dental
professional.
 When integrated with imaging methods like MRI and cone beam
computed tomography.
 ML algorithms can detect an abnormal or normal lymph node in
head and neck image.
Slide Title
Slide Title
Artificial intelligence in
Conservative &
Endodontics

Slide Title
Slide Title
Artificial intelligence and
Cosmetic Dentistry
 DSD (Digital smile design)
 DTS Pro (Digital treatment simulation)
 Planmeca Romexis Digital smile design
These software’s make use of AI & ML to help dentist design
smile in a minute.
Artificial intelligence and
orthodontics
 3D scans and virtual models are useful in assessing craniofacial and dental
abnormalities
 AI decides how the teeth or tooth of the patients should be moved, how much
pressure should be applied and even also recognize the pressure points for that
specific tooth/teeth.
 The AI conjugated aligners not only provide precise treatment but also reduces
the chances of error and time for treatment.
Slide Title
Slide Title
Slide Title
Artificial intelligence and
restorative/prosthetic dentistry
 provide perfect prosthesis to the patient
 Also, CAD/CAM based systems are used in dentistry to attain finished dental
restorations with great precision.
 3D scans
Slide Title
Slide Title
Slide Title
Artifical intelligence in Oral
Pathology
 Detection and diagnosis of oral lesions is of crucial importance indental practices because
early detection significantly improves prognosis. As some oral lesions can be precancerous or
cancerous in nature, it is important to make an accurate diagnosis and prescribe appropriate
treatment of the patient.
 CNN has been shown to be a promising aid throughout the process of diagnosis of head and
neck cancer lesions. With specificity and accuracy at 78–81.8% and 80–83.3%, respectively
(compared with those of specialists, which were 83.2% and 82.9% respectively), CNN shows
great potential for detecting tumoural tissues in tissue samples or on radiographs.
Head and Neck Cancer
Artificial intelligence in
periodontics.
 In periodontics AI is used to diagnose the two types of periodontics- Aggressive and
Chronic, which aid in determining the treatment plan to a large extent.
 Papatanopoulos and colleagues have used ANN technology to distinguish between
Aggressive Periodontitis and Chronic types by using immunological parameters such as
Leukocytes, IgG antibody titers, and interleukins.
 ANN was used to identify these parameters which helped in differentiating Aggressive
Periodontitis from Chronic Periodontitis having 90-98% accuracy
S. Sachdeva et al. / Artificial intelligence in periodontics Journal of Cellular
Biotechnology 7 (2021) 119–124
Slide Title
Challenges of AI
Slide Title
o The management and sharing of clinical data are major challenges in the
implementation of AI systems in health care.
o Personal data from patients are necessary for initial training of AI
algorithms, as well as ongoing training, validation and improvement.
o Furthermore, the development of AI will prompt data sharing among
different institutions and, in some cases, across national boundaries. To
integrate AI into clinical operations, systems must be adapted to protect
patient confidentiality and privacy.
Current Scenario
and Future
Prospects
The survey by Jaideep Sur et al(2020) of the 250 participating dentists
regarding awareness about artificial intelligence shows following results-
Slide Title
Slide Title
Slide Title
Benefits of AI in dentistry
 Performing tasks in almost no time.
 Logical and feasible decisions which
results in an accurate diagnosis.
 Procedures can be standardized
Shortcomings of AI use in dentistry
 Mechanism/system complexity
 Costly setup
 Adequate training is required
 Data is often used for both
training and testing, leading to
“data snooping bias”.
 The outcomes of AI in dentistry
are not readily applicable.
CONCLUSION
Slide Title
The AI-powered program helps dental
practitioners analyze radiographs more accurately and
consistently. It doesn’t replace dentists’ expertise but
instead helps them to identify problems and potential
treatments with even greater speed and precision.
Bridging the gap to build a better & comfortable future…
THANK YOU.
Slide Title

Artificial Intelligence. IDM.pptx

  • 1.
    SURENDERA DENTAL COLLEGE& RESEARCH INSTITUTE. Department of Oral Medicine and Radiology INTER DEPARTMENT MEET 2022
  • 2.
  • 3.
    CONTENT • Introduction • History •Classification • How does AI work? • Role of AI in dentistry. • Current Scenario and Future Prospects • Conclusion • References
  • 4.
  • 5.
    Ever since thefield of science has originated, researchers and technologists have been busy in solving the complexity of the human brain that is a maze of neurons interconnected with each other and transmitting signals to the whole body.
  • 6.
    Artificial intelligence (AI)are machines that are able to mimic the cognitive functions of humans to perform tasks of problem-solving and learning.
  • 7.
  • 8.
    Slide Title Alan Turing(British mathematician, 1936) was one of the most important visionary and theoretician, proved that a universal calculator—known as the Turing machine—is possible [13]. Turing’s central insight is that such a machine is capable of solving any problem as long as it may be represented and solved by an algorithm. Newell and Simon (1955) designed “The Logic Theorist” which is considered to be the first AI program which marks the development of modern AI. John McCarthy in 1965 coined the term ‘artificial intelligence
  • 9.
  • 10.
  • 12.
  • 13.
  • 15.
    Artificial Intelligence (AI) Machine Learning 1. Genetic algorithms 2.Artificial Neural Networks (ANN) 3. Fuzzy Logic Deep Learning -Subset of ML -Focus on lines, edges, corners
  • 16.
    Machine Learning  Algorithmsare applied to perform tasks by learning patterns from data.  Machine learning technique involves parameter adjustment with regards to underlying technique such as, o number of neurons, o layers in a neural network technique; o population size, o rate of mutation and o crossing over rate in genetic algorithms technique etc
  • 17.
    Deep learning  Acomplex multilayer system.  This system has a complex arrangement of layers and a greater number of interconnected neurons which makes it capable of visualizing simple features like o lines, o edges, o corners and o macroscopic patterns in a hierarchical structure
  • 18.
  • 19.
    Slide Title Schematic representationof the architecture of neural networks. Artificial neural networks are structures used in machine learning. They contain many small communicating units called neurons, which are organized in layers. a. Shallow neural networks are composed of an input layer, a few hidden layers and an output layer. b. Deep neural networks have an input layer, multiple hidden layers and an output layer. c. Convolutional neural networks use filters to scan a small neighbourhood of inputs.
  • 20.
  • 21.
  • 22.
  • 23.
    AI in generaldentistry  book a patient's appointment in the clinic  taking proper medical and dental history of the patient  managing insurance as well as assisting the dental surgeon in adequate diagnosis and treatment planning  works by warning the dental professional about the habitual details of patients like use of tobacco or alcohol and medical history of the patient  follow up and online emergency health consultancy.
  • 24.
    Artificial intelligence anddiagnostic dentistry  Proper diagnosis of any disease is the basis for successful treatment.  Example: Internal derangement of temporomandibular joints where clinical and radiological diagnosis is considered as gold standard.
  • 25.
    Slide Title Kim etal. 2009 used Artificial neural network to build a model that can predict toothache on the basis of association between toothache and daily toothbrushing frequency, toothbrushing time, use of dental floss, toothbrush replacement pattern, undergoing scaling and other factors like diet and exercise. This model recognizes adequate eating habits, oral hygiene, and stress prevention as the most important factors in preventing toothaches
  • 26.
    Slide Title Nieri et.al 2008 used Bayesian network analysis to identify relationships between various factors affecting the diagnosis and final treatment outcome of impacted maxillary canines
  • 27.
    Artificial intelligence and radiology AI provides the additional capability to learn more to be a dental professional.  When integrated with imaging methods like MRI and cone beam computed tomography.  ML algorithms can detect an abnormal or normal lymph node in head and neck image.
  • 28.
  • 29.
  • 30.
  • 31.
  • 32.
  • 33.
    Artificial intelligence and CosmeticDentistry  DSD (Digital smile design)  DTS Pro (Digital treatment simulation)  Planmeca Romexis Digital smile design These software’s make use of AI & ML to help dentist design smile in a minute.
  • 34.
    Artificial intelligence and orthodontics 3D scans and virtual models are useful in assessing craniofacial and dental abnormalities  AI decides how the teeth or tooth of the patients should be moved, how much pressure should be applied and even also recognize the pressure points for that specific tooth/teeth.  The AI conjugated aligners not only provide precise treatment but also reduces the chances of error and time for treatment.
  • 35.
  • 36.
  • 37.
  • 38.
    Artificial intelligence and restorative/prostheticdentistry  provide perfect prosthesis to the patient  Also, CAD/CAM based systems are used in dentistry to attain finished dental restorations with great precision.  3D scans
  • 39.
  • 40.
  • 41.
  • 42.
    Artifical intelligence inOral Pathology  Detection and diagnosis of oral lesions is of crucial importance indental practices because early detection significantly improves prognosis. As some oral lesions can be precancerous or cancerous in nature, it is important to make an accurate diagnosis and prescribe appropriate treatment of the patient.  CNN has been shown to be a promising aid throughout the process of diagnosis of head and neck cancer lesions. With specificity and accuracy at 78–81.8% and 80–83.3%, respectively (compared with those of specialists, which were 83.2% and 82.9% respectively), CNN shows great potential for detecting tumoural tissues in tissue samples or on radiographs.
  • 43.
  • 44.
    Artificial intelligence in periodontics. In periodontics AI is used to diagnose the two types of periodontics- Aggressive and Chronic, which aid in determining the treatment plan to a large extent.  Papatanopoulos and colleagues have used ANN technology to distinguish between Aggressive Periodontitis and Chronic types by using immunological parameters such as Leukocytes, IgG antibody titers, and interleukins.  ANN was used to identify these parameters which helped in differentiating Aggressive Periodontitis from Chronic Periodontitis having 90-98% accuracy S. Sachdeva et al. / Artificial intelligence in periodontics Journal of Cellular Biotechnology 7 (2021) 119–124
  • 45.
  • 46.
  • 47.
    Slide Title o Themanagement and sharing of clinical data are major challenges in the implementation of AI systems in health care. o Personal data from patients are necessary for initial training of AI algorithms, as well as ongoing training, validation and improvement. o Furthermore, the development of AI will prompt data sharing among different institutions and, in some cases, across national boundaries. To integrate AI into clinical operations, systems must be adapted to protect patient confidentiality and privacy.
  • 48.
  • 49.
    The survey byJaideep Sur et al(2020) of the 250 participating dentists regarding awareness about artificial intelligence shows following results-
  • 53.
  • 54.
  • 55.
    Slide Title Benefits ofAI in dentistry  Performing tasks in almost no time.  Logical and feasible decisions which results in an accurate diagnosis.  Procedures can be standardized Shortcomings of AI use in dentistry  Mechanism/system complexity  Costly setup  Adequate training is required  Data is often used for both training and testing, leading to “data snooping bias”.  The outcomes of AI in dentistry are not readily applicable.
  • 56.
  • 57.
    Slide Title The AI-poweredprogram helps dental practitioners analyze radiographs more accurately and consistently. It doesn’t replace dentists’ expertise but instead helps them to identify problems and potential treatments with even greater speed and precision.
  • 58.
    Bridging the gapto build a better & comfortable future… THANK YOU.
  • 59.