Application of AI in Radiographic Image Interpretation
Application of AI in Radiographic Image Interpretation
Application of AI in Radiographic Image Interpretation
DEPARTMENT OF RADIOLOGY
CERTIFICATE
Name(s)
Department(s)
JUNE,2024
iii
DECLARATION
Signature
Name:
DEPARTMENT OF RADIOLOGY
IMPACT PARAMEDICAL & HEALTH
INSTITUTE
HIMALAYAN UNIVERSITY
BATCH – 2021-2024
iv
ACKNOWLEDGEMENT
EVEYA GAUR
v
PREFACE
CONTENTS
1. INTRODUCTION
2. AIMS AND OBJECTIVES
3. REVIEW OF LITERATURE
4. …………….
5. MATERIAL AND METHODS
6. OBSERVATION AND RESULTS
7. DISCUSSION
8. SUMMARY
9. CONCLUSION
10. BIBLIOGRAPHY
vii
INTRODUCTION
REVIEW OF LITERATURE
Artificial Intelligence has often been depicted as villain robots ready to take
over the world. But actually AI can save life and improve health care
management around the world.
Based on the literature it is evident that the imminent replacement of the
radiologists by AI is never possible. The common thought that radiologist will
remain a central and crucial cog in diagnostic process of image based
medicine with AI acting as a cognitive companion.
DENTISTRY
Image analysis using AI in dentistry has been applied to various task
such as tooth segmentation/localization.
Deep learning has been used to detect and classify teeth on CBCT
images as well as panoramic images.
Automated CAD outputs can help dentists make clinical decisions and
reduce their charting time by automal filling digital patient records.
(2) Model transparency: one of the major criticisms of deep learning is a lack
of transparency and interpretability. In other words, users (clinicians and
researchers) should be able to understand the “reasoning” of the AI model;
why it renders one verdict and not the other. Model developers and data
scientists must make didactic efforts to teach the users how the models operate
and decide outcomes. Transparency is crucial to defining a modality’s
operational realm and proactively restricting deviations from the model that
can affect image quality and diagnostic interpretability.
(3) Model robustness: one collateral effect of the lack of model transparency
is model instability to adversarial attacks (negligible input variations resulting
in significant changes of the model output) and intrinsic model biases.
Adversarial attack prevention is an oft-discussed topic in AI and they pose a
substantial barrier to the use of AI for image synthesis in critical applications
like diagnostic imaging.97 Careful model design and training considerations
must be taken to avoid adversarial attacks overall if models are trained with
off-the-shelve components.98 In a similar fashion, biases and disparity in
xiii
CARDIAC IMAGING
PAEDIATRIC RADIOLOGY
METHODOLOGY
CONCLUSION