SlideShare a Scribd company logo
Object Detection on Dental X-ray
Images using Region Based
Convolutional Neural Networks
Rakib Hossen, Minhazul Arefin and Mohammed Nasir Uddin
INTERNATIONAL CONFERENCE ON
MACHINE INTELLIGENCE & DATA
SCIENCE APPLICATIONS
(MIDAS 2021)
Date: December 26-27, 2021
Overview
Problem Statement
Introduction
Objectives
Proposed Methodology
Result
Conclusion
Future Work
Introduction
Add Text
 Object detection is a computer vision technique that
allows us to identify and locate objects in an image or
video.
 Tooth decay, also known as dental caries or cavities,
is the breakdown of teeth due to acids made by
bacteria.
 Root canal is a dental procedure involving the removal
of the soft center of the tooth, the pulp.
Introduction
Add Text
 In 2020, the WHO estimated that about 50% of the world
population is affected by dental caries.
 In some Asian-Pacific countries, the incidence of oral cancer is
within the top 3 of all cancers.
 Dental caries are cavities or holes (a type of structural damage)
in the teeth.
 Root canal causes due to inflammation or infection in the roots of
a tooth.
Problem Statement
Add Text
 Manual feature extraction for the detection of caries and root
canal
 Difficulties in generating hierarchical features
 Inaccurate Region Of Interest (ROI) detection and edge
detection
 Difficulties in training model with good convergence
Objectives
Add Text
 To develop a framework that extracts features efficiently
 To design an efficient deep learning approach that can
aid in the automatic detection of objects in dental X-rays
 To classify the detected objects in the dental x-ray
images into caries and root canal.
Contributions
Add Text
 Using state-of-the-art model
 Parameterizing the four co-ordinates of the detected
object in the multi scale training
 Using 12 anchors in the RPN
Proposed Methodology
Add Text
Image Acquisition
Add Text
Source: Digital Dental Periapical X-Ray Dataset
Two categories: Caries and Root canal
Type: Dental Periapical images
80% for training and 20% for testing
Model pre-training
Add Text
 Pre-train the model on COCO dataset
 Fine tune the model
 Train the model on Digital Dental Periapical
X-Ray Dataset
 Fine tune the model again
Hard negative mining
Add Text
 Boosts performance especially object detection
 Hard negatives are the regions where the network has failed
to make correct prediction
 Fed into the network again as a reinforcement for improving
trained model
 Towards fewer false positives and better classification
performance
Number of anchors
Add Text
 Smaller items such as implants seem to be quite frequent in object
detection tasks
 We uses two conditions to assign a positive label to an anchor
𝐿(𝑝𝑖, 𝑡𝑖) =
1
𝑁𝑐𝑙𝑠
𝑖
𝐿𝑐𝑙𝑠 𝑝𝑖, 𝑝𝑖
∗
+ 𝜆
1
𝑁𝑟𝑒𝑔
𝑖
𝑝𝑖
∗
𝐿𝑟𝑒𝑔 𝑡𝑖, 𝑡𝑖
∗
 A mini-batch has an anchor 𝑖, and 𝑝𝑖 is a projected probability that
anchor 𝑖 will be a real item
Number of anchors
Add Text
 Most Crucial Part in RPN
 Traditional Faster R-CNN uses 9 anchors
 Sometimes fails to detect smaller object
 In this study we used 12 anchors
Multi-scale training
Add Text
 Resizes the images to a random scale
 The detector will be able to learn features across a wide range of sizes
 Improves the performance towards scale invariance
 We compute the bounding box regression by parameterized the four
co-ordinates of the detected object. It is shown in equation:
𝑡𝑝 = (𝑝 − 𝑝𝑎)/𝑟𝑎, 𝑡𝑞 = (𝑞 − 𝑞𝑎)/𝑠𝑎
𝑡𝑟 = 𝑙𝑜𝑔
𝑟
𝑟𝑎
, 𝑡𝑠 = 𝑙𝑜𝑔
𝑠
𝑠𝑎
𝑡𝑝
∗
=
𝑝∗
− 𝑝𝑎
𝑟𝑎
, 𝑡𝑞
∗
=
𝑞∗
− 𝑞𝑎
𝑠𝑎
𝑡𝑟
∗
= 𝑙𝑜𝑔
𝑟∗
𝑟𝑎
, 𝑡𝑠
∗
= 𝑙𝑜𝑔
𝑠∗
𝑠𝑎
Feature Concatenation
Add Text
 Feature concatenation is an effective way to add different features
together to enhance the classification process.
 Features are RoI-pooled and L2-normalized from several lower-level
convolution layers accordingly.
 These characteristics are then concatenated and rescaled as if the
original scale of the features had not been adopted.
 A 1×1 convolution is done to match the original network’s number of
channels.
Feature Concatenation
Add Text
 Features from multiple convolutional layers
 Convolutional layers: lower level & higher level
 Features: ROI pooled & L2 normalized
Object Detection
Add Text
 Assign some labels to an object based on their
features using soft-max classifier
 Detect objects in dental x-rays image
successfully
Result
Add Text
 The overlap between two borders is measured by the IoU.
 The overlap between our anticipated border and the ground reality is
then calculated (the real object boundary).
 Let 𝑛𝑖,𝑗 be the number of pixels of class 𝑖 predicted to belong to class 𝑗,
where there are 𝑛𝑐𝑙 different classes, and let 𝑡𝑖 = 𝑗 𝑛𝑖𝑗 be the total
number of pixels of class 𝑖.
 Mean IoU is defined as:
𝑀𝑒𝑎𝑛𝐼𝑜𝑈 =
1
𝑛𝑐𝑙
𝑖
𝑛𝑖𝑖
𝑡𝑖 + 𝑠𝑢𝑚𝑗 𝑛𝑗𝑖 − 𝑛𝑖𝑖
Result
Add Text
 All ground truth boxes with an IoU ratio
less than 0.3 will be labeled as negative
 Total Loss function per epoc (in thousand)
Comparison
RFCN Resnet 101 68.3% Add Text
GoogleNet Inception V3 55.01% Content Here
SSD Inception V1 73.56% Add Text
Our study 83.45% Content Here
Accuracy Error Rate
Model
Comparison
Conclusion
Add Text
 Successfully detects dental caries and root canal
 Improvement of Faster R-CNN framework for generic
object detection
 Performs better than other standalone methods
 Good convergence with better local minima
Future Works
Add Text
 Will work on huge dataset
 GPU implementation
 To build a real time model that can detect dental objects
from videos considering the clinical parameters
References
Add Text
[1] M. M. Lakshmi and P. Chitra, ”Classification of Dental Cavities from X-ray images
using Deep CNN algorithm,” 2020 4th International Conference on Trends in Electronics
and In-formatics (ICOEI), 2020.
[2]. J.H. Lee, D.H. Kim, S.N. Jeong and S.H. Choi, ”Diagnosis and prediction of period on
tally compromised teeth using a deep learning-based convolutional neural network
algorithm” ,Journal of periodontal implant science, vol. 48, no. 2, pp. 114-123, 2018.
[3]. A.A. Al Kheraif, A.A. Wahba and H. Fouad, ”Detection of dental diseases from
radiographic2d dental image using hybrid graph-cut technique and convolutional neural
network”, Mea-surement, vol. 146, pp. 333-342, 2019.
[4]. Oralhealth, https://www.who.int/news-room/fact-sheets/detail/oral-health. Last
accessed 19 Aug 2021.
[5]. J.-H. Lee, D.-H. Kim, S.-N. Jeong, and S.-H. Choi, “Detection and diagnosis of dental
caries using a deep learning-based convolutional neural network algorithm,” Journal of
dentistry, vol.77, pp. 106–111, 2018.
THANK YOU

More Related Content

What's hot

Moving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNNMoving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNN
NITISHKUMAR1401
 
Morphological operations
Morphological operationsMorphological operations
Super Resolution
Super ResolutionSuper Resolution
Super Resolution
alokahuti
 
Wavelet based image fusion
Wavelet based image fusionWavelet based image fusion
Wavelet based image fusionUmed Paliwal
 
First order logic
First order logicFirst order logic
First order logic
Megha Sharma
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Universitat Politècnica de Catalunya
 
Object Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksObject Detection using Deep Neural Networks
Object Detection using Deep Neural Networks
Usman Qayyum
 
Moving object detection
Moving object detectionMoving object detection
Moving object detection
Raviraj singh shekhawat
 
R-CNN
R-CNNR-CNN
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
Mohamed Loey
 
Medical image analysis
Medical image analysisMedical image analysis
Medical image analysis
Gichelle Amon
 
Semantic nets in artificial intelligence
Semantic nets in artificial intelligenceSemantic nets in artificial intelligence
Semantic nets in artificial intelligence
harshita virwani
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Amr Rashed
 
Image captioning with Keras and Tensorflow - Debarko De @ Practo
Image captioning with Keras and Tensorflow - Debarko De @ PractoImage captioning with Keras and Tensorflow - Debarko De @ Practo
Image captioning with Keras and Tensorflow - Debarko De @ Practo
Debarko De
 
Digital image processing questions
Digital  image processing questionsDigital  image processing questions
Digital image processing questions
Manas Mantri
 
Introduction to image contrast and enhancement method
Introduction to image contrast and enhancement methodIntroduction to image contrast and enhancement method
Introduction to image contrast and enhancement method
Abhishekvb
 
Deep learning ppt
Deep learning pptDeep learning ppt
Deep learning ppt
BalneSridevi
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
Antonio Rueda-Toicen
 

What's hot (20)

Moving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNNMoving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNN
 
Segmentation
SegmentationSegmentation
Segmentation
 
Morphological operations
Morphological operationsMorphological operations
Morphological operations
 
Super Resolution
Super ResolutionSuper Resolution
Super Resolution
 
Wavelet based image fusion
Wavelet based image fusionWavelet based image fusion
Wavelet based image fusion
 
First order logic
First order logicFirst order logic
First order logic
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
 
Object Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksObject Detection using Deep Neural Networks
Object Detection using Deep Neural Networks
 
Moving object detection
Moving object detectionMoving object detection
Moving object detection
 
R-CNN
R-CNNR-CNN
R-CNN
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
Computer Vision Introduction
Computer Vision IntroductionComputer Vision Introduction
Computer Vision Introduction
 
Medical image analysis
Medical image analysisMedical image analysis
Medical image analysis
 
Semantic nets in artificial intelligence
Semantic nets in artificial intelligenceSemantic nets in artificial intelligence
Semantic nets in artificial intelligence
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Image captioning with Keras and Tensorflow - Debarko De @ Practo
Image captioning with Keras and Tensorflow - Debarko De @ PractoImage captioning with Keras and Tensorflow - Debarko De @ Practo
Image captioning with Keras and Tensorflow - Debarko De @ Practo
 
Digital image processing questions
Digital  image processing questionsDigital  image processing questions
Digital image processing questions
 
Introduction to image contrast and enhancement method
Introduction to image contrast and enhancement methodIntroduction to image contrast and enhancement method
Introduction to image contrast and enhancement method
 
Deep learning ppt
Deep learning pptDeep learning ppt
Deep learning ppt
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
 

Similar to Object Detection on Dental X-ray Images using R-CNN

Issues in AI product development and practices in audio applications
Issues in AI product development and practices in audio applicationsIssues in AI product development and practices in audio applications
Issues in AI product development and practices in audio applications
Taesu Kim
 
IRJET - Object Detection using Deep Learning with OpenCV and Python
IRJET - Object Detection using Deep Learning with OpenCV and PythonIRJET - Object Detection using Deep Learning with OpenCV and Python
IRJET - Object Detection using Deep Learning with OpenCV and Python
IRJET Journal
 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET Journal
 
A Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringA Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question Answering
IRJET Journal
 
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET Journal
 
Final Year IEEE Project 2013-2014 - Digital Image Processing Project Title a...
Final Year IEEE Project 2013-2014  - Digital Image Processing Project Title a...Final Year IEEE Project 2013-2014  - Digital Image Processing Project Title a...
Final Year IEEE Project 2013-2014 - Digital Image Processing Project Title a...
elysiumtechnologies
 
Modelling Framework of a Neural Object Recognition
Modelling Framework of a Neural Object RecognitionModelling Framework of a Neural Object Recognition
Modelling Framework of a Neural Object Recognition
IJERA Editor
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
Yogendra Tamang
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
Hiroshi Fukui
 
imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdf
KammetaJoshna
 
IEEE MultiMedia 2016 Title and Abstract
IEEE MultiMedia 2016 Title and AbstractIEEE MultiMedia 2016 Title and Abstract
IEEE MultiMedia 2016 Title and Abstract
tsysglobalsolutions
 
Robust Tracking Via Feature Mapping Method and Support Vector Machine
Robust Tracking Via Feature Mapping Method and Support Vector MachineRobust Tracking Via Feature Mapping Method and Support Vector Machine
Robust Tracking Via Feature Mapping Method and Support Vector Machine
IRJET Journal
 
Off-line English Character Recognition: A Comparative Survey
Off-line English Character Recognition: A Comparative SurveyOff-line English Character Recognition: A Comparative Survey
Off-line English Character Recognition: A Comparative Survey
idescitation
 
ANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNING
ANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNINGANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNING
ANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNING
IRJET Journal
 
Partial Object Detection in Inclined Weather Conditions
Partial Object Detection in Inclined Weather ConditionsPartial Object Detection in Inclined Weather Conditions
Partial Object Detection in Inclined Weather Conditions
IRJET Journal
 
IRJET - Object Detection using Hausdorff Distance
IRJET -  	  Object Detection using Hausdorff DistanceIRJET -  	  Object Detection using Hausdorff Distance
IRJET - Object Detection using Hausdorff Distance
IRJET Journal
 
Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...
Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...
Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...
IRJET Journal
 
IRJET - Face Recognition in Digital Documents with Live Image
IRJET - Face Recognition in Digital Documents with Live ImageIRJET - Face Recognition in Digital Documents with Live Image
IRJET - Face Recognition in Digital Documents with Live Image
IRJET Journal
 
Integrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object TrackingIntegrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object Tracking
ijsrd.com
 

Similar to Object Detection on Dental X-ray Images using R-CNN (20)

Issues in AI product development and practices in audio applications
Issues in AI product development and practices in audio applicationsIssues in AI product development and practices in audio applications
Issues in AI product development and practices in audio applications
 
IRJET - Object Detection using Deep Learning with OpenCV and Python
IRJET - Object Detection using Deep Learning with OpenCV and PythonIRJET - Object Detection using Deep Learning with OpenCV and Python
IRJET - Object Detection using Deep Learning with OpenCV and Python
 
CV _Manoj
CV _ManojCV _Manoj
CV _Manoj
 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
 
A Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringA Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question Answering
 
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
 
Final Year IEEE Project 2013-2014 - Digital Image Processing Project Title a...
Final Year IEEE Project 2013-2014  - Digital Image Processing Project Title a...Final Year IEEE Project 2013-2014  - Digital Image Processing Project Title a...
Final Year IEEE Project 2013-2014 - Digital Image Processing Project Title a...
 
Modelling Framework of a Neural Object Recognition
Modelling Framework of a Neural Object RecognitionModelling Framework of a Neural Object Recognition
Modelling Framework of a Neural Object Recognition
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
 
imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdf
 
IEEE MultiMedia 2016 Title and Abstract
IEEE MultiMedia 2016 Title and AbstractIEEE MultiMedia 2016 Title and Abstract
IEEE MultiMedia 2016 Title and Abstract
 
Robust Tracking Via Feature Mapping Method and Support Vector Machine
Robust Tracking Via Feature Mapping Method and Support Vector MachineRobust Tracking Via Feature Mapping Method and Support Vector Machine
Robust Tracking Via Feature Mapping Method and Support Vector Machine
 
Off-line English Character Recognition: A Comparative Survey
Off-line English Character Recognition: A Comparative SurveyOff-line English Character Recognition: A Comparative Survey
Off-line English Character Recognition: A Comparative Survey
 
ANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNING
ANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNINGANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNING
ANIMAL SPECIES RECOGNITION SYSTEM USING DEEP LEARNING
 
Partial Object Detection in Inclined Weather Conditions
Partial Object Detection in Inclined Weather ConditionsPartial Object Detection in Inclined Weather Conditions
Partial Object Detection in Inclined Weather Conditions
 
IRJET - Object Detection using Hausdorff Distance
IRJET -  	  Object Detection using Hausdorff DistanceIRJET -  	  Object Detection using Hausdorff Distance
IRJET - Object Detection using Hausdorff Distance
 
Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...
Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...
Saliency Based Hookworm and Infection Detection for Wireless Capsule Endoscop...
 
IRJET - Face Recognition in Digital Documents with Live Image
IRJET - Face Recognition in Digital Documents with Live ImageIRJET - Face Recognition in Digital Documents with Live Image
IRJET - Face Recognition in Digital Documents with Live Image
 
Integrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object TrackingIntegrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object Tracking
 

More from Minhazul Arefin

Controlling Home Appliances adopting Chatbot using Machine Learning Approach
Controlling Home Appliances adopting Chatbot using Machine Learning ApproachControlling Home Appliances adopting Chatbot using Machine Learning Approach
Controlling Home Appliances adopting Chatbot using Machine Learning Approach
Minhazul Arefin
 
Natural Language Query to SQL conversion using Machine Learning Approach
Natural Language Query to SQL conversion using Machine Learning ApproachNatural Language Query to SQL conversion using Machine Learning Approach
Natural Language Query to SQL conversion using Machine Learning Approach
Minhazul Arefin
 
Efficient estimation of word representations in vector space (2013)
Efficient estimation of word representations in vector space (2013)Efficient estimation of word representations in vector space (2013)
Efficient estimation of word representations in vector space (2013)
Minhazul Arefin
 
Semantic scaffolds for pseudocode to-code generation (2020)
Semantic scaffolds for pseudocode to-code generation (2020)Semantic scaffolds for pseudocode to-code generation (2020)
Semantic scaffolds for pseudocode to-code generation (2020)
Minhazul Arefin
 
Recurrent neural networks (rnn) and long short term memory networks (lstm)
Recurrent neural networks (rnn) and long short term memory networks (lstm)Recurrent neural networks (rnn) and long short term memory networks (lstm)
Recurrent neural networks (rnn) and long short term memory networks (lstm)
Minhazul Arefin
 
SPoC: search-based pseudocode to code
SPoC: search-based pseudocode to codeSPoC: search-based pseudocode to code
SPoC: search-based pseudocode to code
Minhazul Arefin
 
The rise of “Big Data” on cloud computing
The rise of “Big Data” on cloud computingThe rise of “Big Data” on cloud computing
The rise of “Big Data” on cloud computing
Minhazul Arefin
 

More from Minhazul Arefin (7)

Controlling Home Appliances adopting Chatbot using Machine Learning Approach
Controlling Home Appliances adopting Chatbot using Machine Learning ApproachControlling Home Appliances adopting Chatbot using Machine Learning Approach
Controlling Home Appliances adopting Chatbot using Machine Learning Approach
 
Natural Language Query to SQL conversion using Machine Learning Approach
Natural Language Query to SQL conversion using Machine Learning ApproachNatural Language Query to SQL conversion using Machine Learning Approach
Natural Language Query to SQL conversion using Machine Learning Approach
 
Efficient estimation of word representations in vector space (2013)
Efficient estimation of word representations in vector space (2013)Efficient estimation of word representations in vector space (2013)
Efficient estimation of word representations in vector space (2013)
 
Semantic scaffolds for pseudocode to-code generation (2020)
Semantic scaffolds for pseudocode to-code generation (2020)Semantic scaffolds for pseudocode to-code generation (2020)
Semantic scaffolds for pseudocode to-code generation (2020)
 
Recurrent neural networks (rnn) and long short term memory networks (lstm)
Recurrent neural networks (rnn) and long short term memory networks (lstm)Recurrent neural networks (rnn) and long short term memory networks (lstm)
Recurrent neural networks (rnn) and long short term memory networks (lstm)
 
SPoC: search-based pseudocode to code
SPoC: search-based pseudocode to codeSPoC: search-based pseudocode to code
SPoC: search-based pseudocode to code
 
The rise of “Big Data” on cloud computing
The rise of “Big Data” on cloud computingThe rise of “Big Data” on cloud computing
The rise of “Big Data” on cloud computing
 

Recently uploaded

Courier management system project report.pdf
Courier management system project report.pdfCourier management system project report.pdf
Courier management system project report.pdf
Kamal Acharya
 
The role of big data in decision making.
The role of big data in decision making.The role of big data in decision making.
The role of big data in decision making.
ankuprajapati0525
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
Osamah Alsalih
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
JoytuBarua2
 
ASME IX(9) 2007 Full Version .pdf
ASME IX(9)  2007 Full Version       .pdfASME IX(9)  2007 Full Version       .pdf
ASME IX(9) 2007 Full Version .pdf
AhmedHussein950959
 
Gen AI Study Jams _ For the GDSC Leads in India.pdf
Gen AI Study Jams _ For the GDSC Leads in India.pdfGen AI Study Jams _ For the GDSC Leads in India.pdf
Gen AI Study Jams _ For the GDSC Leads in India.pdf
gdsczhcet
 
Student information management system project report ii.pdf
Student information management system project report ii.pdfStudent information management system project report ii.pdf
Student information management system project report ii.pdf
Kamal Acharya
 
HYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generationHYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generation
Robbie Edward Sayers
 
Vaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdfVaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdf
Kamal Acharya
 
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&BDesign and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Sreedhar Chowdam
 
DESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docxDESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docx
FluxPrime1
 
CME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional ElectiveCME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional Elective
karthi keyan
 
block diagram and signal flow graph representation
block diagram and signal flow graph representationblock diagram and signal flow graph representation
block diagram and signal flow graph representation
Divya Somashekar
 
addressing modes in computer architecture
addressing modes  in computer architectureaddressing modes  in computer architecture
addressing modes in computer architecture
ShahidSultan24
 
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
MdTanvirMahtab2
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
Neometrix_Engineering_Pvt_Ltd
 
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
obonagu
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdf
Kamal Acharya
 
WATER CRISIS and its solutions-pptx 1234
WATER CRISIS and its solutions-pptx 1234WATER CRISIS and its solutions-pptx 1234
WATER CRISIS and its solutions-pptx 1234
AafreenAbuthahir2
 
Halogenation process of chemical process industries
Halogenation process of chemical process industriesHalogenation process of chemical process industries
Halogenation process of chemical process industries
MuhammadTufail242431
 

Recently uploaded (20)

Courier management system project report.pdf
Courier management system project report.pdfCourier management system project report.pdf
Courier management system project report.pdf
 
The role of big data in decision making.
The role of big data in decision making.The role of big data in decision making.
The role of big data in decision making.
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
 
ASME IX(9) 2007 Full Version .pdf
ASME IX(9)  2007 Full Version       .pdfASME IX(9)  2007 Full Version       .pdf
ASME IX(9) 2007 Full Version .pdf
 
Gen AI Study Jams _ For the GDSC Leads in India.pdf
Gen AI Study Jams _ For the GDSC Leads in India.pdfGen AI Study Jams _ For the GDSC Leads in India.pdf
Gen AI Study Jams _ For the GDSC Leads in India.pdf
 
Student information management system project report ii.pdf
Student information management system project report ii.pdfStudent information management system project report ii.pdf
Student information management system project report ii.pdf
 
HYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generationHYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generation
 
Vaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdfVaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdf
 
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&BDesign and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
 
DESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docxDESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docx
 
CME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional ElectiveCME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional Elective
 
block diagram and signal flow graph representation
block diagram and signal flow graph representationblock diagram and signal flow graph representation
block diagram and signal flow graph representation
 
addressing modes in computer architecture
addressing modes  in computer architectureaddressing modes  in computer architecture
addressing modes in computer architecture
 
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdf
 
WATER CRISIS and its solutions-pptx 1234
WATER CRISIS and its solutions-pptx 1234WATER CRISIS and its solutions-pptx 1234
WATER CRISIS and its solutions-pptx 1234
 
Halogenation process of chemical process industries
Halogenation process of chemical process industriesHalogenation process of chemical process industries
Halogenation process of chemical process industries
 

Object Detection on Dental X-ray Images using R-CNN

  • 1. Object Detection on Dental X-ray Images using Region Based Convolutional Neural Networks Rakib Hossen, Minhazul Arefin and Mohammed Nasir Uddin INTERNATIONAL CONFERENCE ON MACHINE INTELLIGENCE & DATA SCIENCE APPLICATIONS (MIDAS 2021) Date: December 26-27, 2021
  • 3. Introduction Add Text  Object detection is a computer vision technique that allows us to identify and locate objects in an image or video.  Tooth decay, also known as dental caries or cavities, is the breakdown of teeth due to acids made by bacteria.  Root canal is a dental procedure involving the removal of the soft center of the tooth, the pulp.
  • 4. Introduction Add Text  In 2020, the WHO estimated that about 50% of the world population is affected by dental caries.  In some Asian-Pacific countries, the incidence of oral cancer is within the top 3 of all cancers.  Dental caries are cavities or holes (a type of structural damage) in the teeth.  Root canal causes due to inflammation or infection in the roots of a tooth.
  • 5. Problem Statement Add Text  Manual feature extraction for the detection of caries and root canal  Difficulties in generating hierarchical features  Inaccurate Region Of Interest (ROI) detection and edge detection  Difficulties in training model with good convergence
  • 6. Objectives Add Text  To develop a framework that extracts features efficiently  To design an efficient deep learning approach that can aid in the automatic detection of objects in dental X-rays  To classify the detected objects in the dental x-ray images into caries and root canal.
  • 7. Contributions Add Text  Using state-of-the-art model  Parameterizing the four co-ordinates of the detected object in the multi scale training  Using 12 anchors in the RPN
  • 9. Image Acquisition Add Text Source: Digital Dental Periapical X-Ray Dataset Two categories: Caries and Root canal Type: Dental Periapical images 80% for training and 20% for testing
  • 10. Model pre-training Add Text  Pre-train the model on COCO dataset  Fine tune the model  Train the model on Digital Dental Periapical X-Ray Dataset  Fine tune the model again
  • 11. Hard negative mining Add Text  Boosts performance especially object detection  Hard negatives are the regions where the network has failed to make correct prediction  Fed into the network again as a reinforcement for improving trained model  Towards fewer false positives and better classification performance
  • 12. Number of anchors Add Text  Smaller items such as implants seem to be quite frequent in object detection tasks  We uses two conditions to assign a positive label to an anchor 𝐿(𝑝𝑖, 𝑡𝑖) = 1 𝑁𝑐𝑙𝑠 𝑖 𝐿𝑐𝑙𝑠 𝑝𝑖, 𝑝𝑖 ∗ + 𝜆 1 𝑁𝑟𝑒𝑔 𝑖 𝑝𝑖 ∗ 𝐿𝑟𝑒𝑔 𝑡𝑖, 𝑡𝑖 ∗  A mini-batch has an anchor 𝑖, and 𝑝𝑖 is a projected probability that anchor 𝑖 will be a real item
  • 13. Number of anchors Add Text  Most Crucial Part in RPN  Traditional Faster R-CNN uses 9 anchors  Sometimes fails to detect smaller object  In this study we used 12 anchors
  • 14. Multi-scale training Add Text  Resizes the images to a random scale  The detector will be able to learn features across a wide range of sizes  Improves the performance towards scale invariance  We compute the bounding box regression by parameterized the four co-ordinates of the detected object. It is shown in equation: 𝑡𝑝 = (𝑝 − 𝑝𝑎)/𝑟𝑎, 𝑡𝑞 = (𝑞 − 𝑞𝑎)/𝑠𝑎 𝑡𝑟 = 𝑙𝑜𝑔 𝑟 𝑟𝑎 , 𝑡𝑠 = 𝑙𝑜𝑔 𝑠 𝑠𝑎 𝑡𝑝 ∗ = 𝑝∗ − 𝑝𝑎 𝑟𝑎 , 𝑡𝑞 ∗ = 𝑞∗ − 𝑞𝑎 𝑠𝑎 𝑡𝑟 ∗ = 𝑙𝑜𝑔 𝑟∗ 𝑟𝑎 , 𝑡𝑠 ∗ = 𝑙𝑜𝑔 𝑠∗ 𝑠𝑎
  • 15. Feature Concatenation Add Text  Feature concatenation is an effective way to add different features together to enhance the classification process.  Features are RoI-pooled and L2-normalized from several lower-level convolution layers accordingly.  These characteristics are then concatenated and rescaled as if the original scale of the features had not been adopted.  A 1×1 convolution is done to match the original network’s number of channels.
  • 16. Feature Concatenation Add Text  Features from multiple convolutional layers  Convolutional layers: lower level & higher level  Features: ROI pooled & L2 normalized
  • 17. Object Detection Add Text  Assign some labels to an object based on their features using soft-max classifier  Detect objects in dental x-rays image successfully
  • 18. Result Add Text  The overlap between two borders is measured by the IoU.  The overlap between our anticipated border and the ground reality is then calculated (the real object boundary).  Let 𝑛𝑖,𝑗 be the number of pixels of class 𝑖 predicted to belong to class 𝑗, where there are 𝑛𝑐𝑙 different classes, and let 𝑡𝑖 = 𝑗 𝑛𝑖𝑗 be the total number of pixels of class 𝑖.  Mean IoU is defined as: 𝑀𝑒𝑎𝑛𝐼𝑜𝑈 = 1 𝑛𝑐𝑙 𝑖 𝑛𝑖𝑖 𝑡𝑖 + 𝑠𝑢𝑚𝑗 𝑛𝑗𝑖 − 𝑛𝑖𝑖
  • 19. Result Add Text  All ground truth boxes with an IoU ratio less than 0.3 will be labeled as negative  Total Loss function per epoc (in thousand)
  • 20. Comparison RFCN Resnet 101 68.3% Add Text GoogleNet Inception V3 55.01% Content Here SSD Inception V1 73.56% Add Text Our study 83.45% Content Here Accuracy Error Rate Model
  • 22. Conclusion Add Text  Successfully detects dental caries and root canal  Improvement of Faster R-CNN framework for generic object detection  Performs better than other standalone methods  Good convergence with better local minima
  • 23. Future Works Add Text  Will work on huge dataset  GPU implementation  To build a real time model that can detect dental objects from videos considering the clinical parameters
  • 24. References Add Text [1] M. M. Lakshmi and P. Chitra, ”Classification of Dental Cavities from X-ray images using Deep CNN algorithm,” 2020 4th International Conference on Trends in Electronics and In-formatics (ICOEI), 2020. [2]. J.H. Lee, D.H. Kim, S.N. Jeong and S.H. Choi, ”Diagnosis and prediction of period on tally compromised teeth using a deep learning-based convolutional neural network algorithm” ,Journal of periodontal implant science, vol. 48, no. 2, pp. 114-123, 2018. [3]. A.A. Al Kheraif, A.A. Wahba and H. Fouad, ”Detection of dental diseases from radiographic2d dental image using hybrid graph-cut technique and convolutional neural network”, Mea-surement, vol. 146, pp. 333-342, 2019. [4]. Oralhealth, https://www.who.int/news-room/fact-sheets/detail/oral-health. Last accessed 19 Aug 2021. [5]. J.-H. Lee, D.-H. Kim, S.-N. Jeong, and S.-H. Choi, “Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm,” Journal of dentistry, vol.77, pp. 106–111, 2018.