Application of AI in Radiographic Image Interpretation

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 17

i

APPLICATION OF AI IN RADIOGRAPHIC IMAGE


INTERPRETATION CHALLENGES AND OPPORTUNITIES

A Thesis Submitted In Partial Fulfillment of the Requirements for the Degree


Of Bachelor in Radiology and Imaging Technology

SUBMITTED BY: EVEYA GAUR


to the

DEPARTMENT OF RADIOLOGY

IMPACT PARAMEDICAL & HEALTH INSTITUTE


HIMALAYAN UNIVERSITY
BATCH – 2021-2024
ii

CERTIFICATE

It is certified that the work contained in the thesis titled


“Application of AI in radiographic image interpretation challenges
and opportunities” by “EVEYA GAUR” has been carried out under
my/our supervision and that this work has not been submitted
elsewhere for a degree.

Signature of the Supervisor(s)

Name(s)
Department(s)

JUNE,2024
iii

DECLARATION

This is to certify that the thesis titled Application of AI in radiographic image


interpretation challenges and opportunities has been authored by me. It presents
the research conducted by me under the supervision of Miss.Deepti Saroha faculty of
Radiology in the Department of Radiology at Impact Paramedical and Health Institute,
New Delhi. To the best of my knowledge, it is an original work, both in terms of research
content and narrative, and has not been submitted elsewhere, in part or in full, for a
degree. Further, due credit has been attributed to the relevant state-of-the-art and with
appropriate citations and acknowledgements, in line with established norms and practices.

Signature

Name:

DEPARTMENT OF RADIOLOGY
IMPACT PARAMEDICAL & HEALTH
INSTITUTE
HIMALAYAN UNIVERSITY
BATCH – 2021-2024
iv

ACKNOWLEDGEMENT

I would like to thank my supervisor Ms.Deepti Saroha for her invaluable


supervision and support during my BSC degree. My gratitude extends to
Director Dr Archana Aravindan who gave me the golden opportunity to do
this research work and finally my dissertation. I would like to express my
gratitude to my colleague Mr. Rohit Singhal for his treasured support which
was really influential in shaping my research methods. I would like to also
thank my family for there encouragement and support throughout my studies.

EVEYA GAUR
v

PREFACE

“Application of Ai in Radiographic Image Interpretation: CHALLENGES


AND OPPORTUNITIES” is a dissertation that I have made during my
internship period. The main challenge for me is to understand the main
concept of different AI tools in their respective field of functioning and then
integrating them to create my own theory. I have gone through my articles for
a brief introductions and to review the conclusions of various authors and also
compared some of these articles in about their recommendations in AI. It was
very interesting for me to explore various AI tools as I countered many new
topics. I have also learned about machine learning, deep learning and CAD.
vi

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

Artificial intelligence (AI) has been defined as a branch of computer science


dealing with the capability and simulation of a machine to imitate intelligent
human behaviour. Diagnostic radiology, being a computer-based service, is
unsurprisingly at the forefront of the discussion of the use of AI in medicine.
There are however differing schools of thought regarding its use; namely, will
AI eventually replace the radiologist? Or indeed will it ever be fully capable
of replacing radiology as a speciality, but rather be used as an aid to the
profession whereby a human’s input will always be required? Furthermore,
what will the legal implications of AI in radiology mean to the profession?
Who will be liable for missed diagnoses? Is it possible that the introduction of
AI to radiology will in fact make the profession busier?
viii

AIM AND OBJECTIVE

The main aim of this dissertation is to enhance the advantages of AI in the


field of radiology and conquering the challenges of introducing AI in
radiographic image interpretation.
AI have already found its place in various modalities and treatment plans. The
study shows that AI has wide range of algorithms and provides outcomes in
the most precise manner possible to detect diseases like cancer.
This dissertation is based on authentic discoveries and research, it also
objectify the application of AI in radiographic image interpretation for a
smooth working and early detection of pathologies
ix

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.

 Radiographic imaging is very useful in the dental field, both for


diagnostic purposes and to ensure proper treatment. In implant,
orthodontic, and oral surgery, radiographic images are quantitatively
analysed as part of treatment planning. Artificial intelligence is of
considerable value in these fields. OMF radiologists, as professionals
who understand the basic principles and characteristics of radiographic
imaging and have the ability to read radiographs and interpret them in
terms of various diseases, continue to play an important role in artificial
intelligence-related research.

 Panoramic radiographs provide important information for diagnosing


osteopenia and osteoporosis,40 and osteoporosis in postmenopausal
females was determined using the reduction in mandibular cortical
x

width (MCW) and the degree of erosion of the mandibular lower


cortex.Using MCW and mandibular cortical erosion findings of
panoramic radiographs, artificial intelligence studies were conducted to
diagnose osteoporosis. It is expected that artificial intelligence models
will be clinically applied to diagnose osteopenia and osteoporosis.

ORAL AND MAXILLOFACIAL RADIOLOGY


BASED ON A STUDY-:
 Objectives: The distal root of the mandibular first molar occasionally
has an extra root, which can directly affect the outcome of endodontic
therapy. In this study, we examined the diagnostic performance of a
deep learning system for classification of the root morphology of
mandibular first molars on panoramic radiographs. Dental cone-beam
CT (CBCT) was used as the gold standard.
 Methods: CBCT images and panoramic radiographs of 760 mandibular
first molars from 400 patients who had not undergone root canal
treatments were analysed. Distal roots were examined on CBCT images
to determine the presence of a single or extra root. Image patches of the
roots were segmented from panoramic radiographs and applied to a
deep learning system, and its diagnostic performance in the
classification of root morphology was examined.
 Results: Extra roots were observed in 21.4% of distal roots on CBCT
images. The deep learning system had diagnostic accuracy of 86.9% for
the determination of whether distal roots were single or had extra roots.
 Conclusions: The deep learning system showed high accuracy in the
differential diagnosis of a single or extra root in the distal roots of
mandibular first molars

CHEST AND LUNGS

 While AI is still an emerging discipline in functional lung imaging,


there are clear and tangible opportunities worth mentioning:
xi

(1) Multifunctional assessment: AI has the potential to unleash the power


of multiple functional assessments under a single imaging platform.
Currently, ventilation and perfusion imaging require the use of different
imaging contrast agents in CT. One potential integrated solution could be
the emerging combination of 4D CBCT and simulated dual-energy
imaging for functional imaging. The benefits of synthetic multifunctional
assessment include reduced radiological tests that require hard-to-obtain
radioactive contrast agents, reduced radiation exposure, and improved care
delivery as imaging synthesis is performed without the patient as part of
the radiological and clinical evaluation. However, realizing these
opportunities will require an extensive validation process to define the
interval confidence in which the synthetic images are consistent with the
underlying functional ground truth. The outcome of the validation studies
will also determine the potential of AIenabled synthetic imaging for
clinical adoption and whether it could eventually be circumscribed to
narrower clinical scenarios where an initial triage based on a sub optimal
approach might be useful
(2) Clinical translation to low footprint radiological setups: current
functional imaging relies on advanced modalities that require specialized
equipment like hyperpolarizers. The potential use of AI-driven image-to-
image translation could bring the benefit of functional information to
standard radiological imaging modalities that are available in primary and
secondary care facilities.

(3) Novel biomarkers: functional modalities provide voluminous


multiparametric data that need to be laboriously synthesized into specific
markers of disease. AI provides an alternative computational approach to
define novel biomarkers of the disease. Supervised CNNs can be used to
extract relevant image features that are associated with a specific outcome.
Unsupervised autoencoder techniques can also be applied for
dimensionality reduction to define novel biomarkers from multipara metric
imaging sources.
(4) Unravelling lung structure and function: the relationship between
structure and function of the lung has been welldescribed, but we are still
limited in linking the structural changes to the functional impairment and
xii

achieving a better characterization of the disease. Studies that combine


structural and functional modalities83,96 can take advantage of AI as an
exploratory tool to gain further insight into the structure–function
relationship.
 Despite the exciting and compelling preliminary evidence promising a
more significant and elaborate role for AI in pulmonary functional
imaging, several challenges remain that need to be carefully evaluated
and resolved before realizing AI as a reliable component of clinical
functional lung imaging:
(1) Validation: data-driven approaches require rigorous validation studies to
gauge the generality and robustness of the methods. Until now, most of the
studies that apply AI to functional lung imaging were performed with small
datasets. Although they provide early evidence of what AI can do, they lack
the rigor needed to qualify as bonafide approaches. Large databases on diverse
populations will be required to train and validate the techniques before
translating them into clinical use.

(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

functional expression may be translated into AI systems trained with imaging


data in which those underlying biases exist.99 Understanding the specific
performance characteristics of each model is crucial to move beyond the
preclinical scenario and successfully introduce it into clinical practice.

(4) Unlocking data silos: the unresolved complexities of functional imaging


imply that the number of training cases is limited compared to Training
sample size is a key factor in deep learning that depends on the specific
characteristics of the problem begin addressed and the model that is used.
Unlocking the available data silos is paramount for implementing new data-
driven advances in functional lung imaging. Open data repositories and
challenges like VAMPIRE79 are crucial for developing machine
learningcentric approaches that improve functional lung imaging quality and
performance reasonably and reproducibly. Issues about data integrity and
privacy could be overcome with federated solutions that enable de-centralized
AI modelling to exploit pan-institutional datasets.
 Chest X-rays are the most commonly performed diagnostic
examinations. An artificial intelligence (AI) system that evaluates the
images fast and accurately help reducing workflow and management of
the patients. An automated assistant may reduce the time of
interpretation in daily practice.

 Although, the AI algorithm diagnostic accuracy were higher than the


residents as per article, the radiology residents did not change their final
decisions after reviewing AI recommendations. In order to benefit from
these tools, the recommendations of the AI system must be more
precise to the user.

CARDIAC IMAGING

 Cardiac AI algorithms have been developed for image detection,


segmentation, and classification, as well as recently available advanced
xiv

algorithms, which can significantly improve the clinical application in


cardiac imaging. In the past few years, numerous studies have shown
the great potential of AI in the diagnosis of CAD and cardiomyopathy,
and the assessment of cardiac function, as well as the prediction of
prognosis. Recently, cardiac AI exhibits its ability to outperform human
perception in several specific cardiac fields.

 CMR plays an increasingly important role in the diagnosis, treatment


planning, and prognosis of cardiomyopathy.5,35,61–66 Baessler et al
used radiomic analysis and machine learning to detect hypertrophied
cardiomyopathy on non-enhanced CMR of 62 patients.61 Four radiomic
features were identified with 100% sensitivity and 90% specificity.
Changes in heart tissue can be measured with extremely high accuracy
without enhancement.

 The diagnosis of myocardial infarction (MI) by machine learning is


mainly realized in cardiac MR (CMR)

PAEDIATRIC RADIOLOGY

 This article has highlighted several areas where AI could improve


clinical paediatric radiology practice, and taken together, the multitude
of research studies suggest an optimistic, exciting and positive future.
Nevertheless, readers should remain cautious of the dangers that
expedited implementation of AI tools could bring. While many of these
are generic and affect all aspects of healthcare (i.e., data security, legal,
ethical and implementation considerations, standardisation of clinical
terminologies),82–85 there are two areas of caution specific to
paediatric imaging: the temptation to apply AI software designed for
adults to children unmodified, and the potential lack of acceptability
amongst parents and carers. The first area of caution relates to the
dangers of improper external validation of algorithms in children, and
ignorance.
xv

Artificial intelligence (AI) has received widespread and growing interest in


healthcare, as a method to save time, cost and improve efficiencies. The high-
performance statistics and diagnostic accuracies reported by using AI
algorithms (with respect to predefined reference standards), particularly from
image pattern recognition studies, have resulted in extensive applications
proposed for clinical radiology, especially for enhanced image interpretation.
Whilst certain sub-speciality areas in radiology, such as those relating to
cancer screening, have received wide-spread attention in the media and
scientific community, children’s imaging has been hitherto neglected. In this
article, we discuss a variety of possible ‘use cases’ in paediatric radiology
from a patient pathway perspective where AI has either been implemented or
shown early-stage feasibility, while also taking inspiration from the adult
literature to propose potential areas for future development. We aim to
demonstrate how a ‘future, enhanced paediatric radiology service’ could
operate and to stimulate further discussion with avenues for research
xvi

METHODOLOGY

The methodology adopted in this study to assess the knowledge of AI in


radiographic image interpretation. From the basic idea of the accuracy in
diagnosis by AI to the future of AI in radiographic image interpretation .
This is self-analysed
xvii

CONCLUSION

You might also like