International Journal of Advances in Medicine | November-December 2025 | Vol 12 | Issue 6 Page 621
International Journal of Advances in Medicine
Vadlapudi V et al. Int J Adv Med. 2025 Nov;12(6):621-626
http://www.ijmedicine.com
pISSN 2349-3925 | eISSN 2349-3933
Review Article
Artificial intelligence in medical imaging: bridging innovation, ethics,
and clinical impact
Varahalarao Vadlapudi
1
*, Dowluru S. V. G. K. Kaladhar
2
INTRODUCTION
Medical imaging techniques such as X-ray, computed
tomography (CT), magnetic resonance imaging (MRI),
ultrasound, positron emission tomography (PET), and
digital pathology remain fundamental to modern
healthcare, providing critical information for diagnosis,
treatment planning, and patient monitoring. The increasing
demand for image interpretation, coupled with the growing
complexity and volume of imaging data, places a
considerable burden on radiologists and clinicians. AI has
emerged as a transformative solution, offering automated
approaches that augment human expertise and streamline
clinical workflows.
1,2
AI refers to computational systems
that mimic human cognition-such as perception,
reasoning, and decision-making. Within AI, ML enables
algorithms to recognize patterns from data without explicit
programming, while DL leverages multilayered neural
networks to autonomously extract hierarchical features
from raw input. In radiology, convolutional neural
networks (CNNs) have become the predominant DL
architecture,
excelling
in
image
classification,
segmentation, and diagnostic tasks.
3,4
Radiomics, which
converts images into quantitative descriptors, further
enhances these models by uncovering features beyond
human visual interpretation
5
. Recent developments
illustrate the clinical potential of AI across specialties. For
example, DL has improved detection and characterization
of ophthalmic disorders, enhanced corneal disease
management, and enabled prediction of surgical outcomes
using
generative
adversarial
networks
(GANs).
6-9
Similarly, AI applications in oncology, neurology, and
gastrointestinal
imaging
are
advancing
diagnostic
precision and prognostic assessment.
10-13
Despite this
ABSTRACT
Medical imaging is essential for diagnosis, treatment planning, and disease monitoring. The integration of artificial
intelligence (AI), particularly machine learning (ML) and deep learning (DL), is revolutionizing this field by automating
image analysis and improving diagnostic performance. This review synthesizes recent advancements in AI applications
for medical imaging, with a focus on radiology, oncology, and digital pathology. Core methodologies, including image
classification, segmentation, reconstruction, and multimodal integration, are examined alongside emerging approaches
such as federated learning and explainable AI. AI models demonstrate strong potential in enhancing diagnostic
accuracy, reducing variability, and improving workflow efficiency. However, key barriers remain, including data
quality limitations, algorithmic bias, lack of interpretability, and regulatory challenges. Novel strategies, including
cross-modality fusion and privacy-preserving frameworks, are being explored to address these issues and improve
generalizability. AI-driven medical imaging tools are poised to advance personalized care and clinical decision-making.
Achieving widespread adoption will require fairness, transparency, clinician engagement, and rigorous real-world
validation to ensure safe and effective integration into healthcare practice.
Keywords:
Artificial intelligence, Machine learning, Deep learning
1
Diabetomics Medical Private Limited, Muppireddypally Village, Medak, Telangana, India
2
Department of Microbiology and Bioinformatics, UTD, Atal Bihari Vajpayee University, Bilaspur, Chhattisgarh, India
Received:
27 August 2025
Accepted:
11 October 2025
*Correspondence:
Dr. Varahalarao Vadlapudi,
E-mail: vvraophd@gmail.com
Copyright:
© the author(s), publisher and licensee Medip Academy. This is an open-access article distributed under
the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial
use, distribution, and reproduction in any medium, provided the original work is properly cited.
DOI: https://dx.doi.org/10.18203/2349-3933.ijam20253360
Vadlapudi V et al. Int J Adv Med. 2025 Nov;12(6):621-626
International Journal of Advances in Medicine | November-December 2025 | Vol 12 | Issue 6 Page 622
progress, clinical implementation faces persistent barriers
such as algorithmic bias, limited generalizability,
interpretability challenges, and evolving regulatory
standards. This review provides an integrated overview of
current methodologies, applications, and future directions
for AI in medical imaging, with a focus on both
opportunities and translational hurdles.
METHODOLOGICAL
FOUNDATIONS
AND
TECHNIQUES
ML in imaging early
ML applications in imaging relied on handcrafted features
and statistical models such as support vector machines and
random forests. Radiomics exemplifies this approach by
extracting quantitative features from images to reveal
patterns beyond human perception.
14
While useful, these
approaches often lacked scalability and were limited by
dependence on manual feature engineering.
DL architectures
DL, particularly CNN-based architectures, overcame these
challenges by learning representations directly from data.
Networks such as ResNet, DenseNet, and U-Net are now
standard tools for classification and segmentation tasks.
15
DL approaches have been shown to produce encouraging
results on histopathology images in various studies.
16
More
advanced variants, including attention-guided CNNs and
recurrent neural networks, provide contextual and
temporal insights into imaging data. The concept of a
convolutional neural network (CNN) to recognize
handwritten digits, paving the way for the use of deep
neural networks in imaging.
17
CNN algorithms enhance
image analysis and reduce variability. The rising incidence
of pancreatic diseases, including acute and chronic
pancreatitis and various pancreatic neoplasms, poses a
significant global health challenge. CNNs, have been
effective in detecting and differentiating between benign
and malignant lesions. DL algorithms have also been used
to predict survival time, recurrence risk, and therapy
response in pancreatic cancer patients.
Radiomics and AI synergy radiomics approaches
Extracting quantitative features from imaging modalities
such as CT, MRI, and endoscopic ultrasound, have
enhanced the accuracy of these DL models.
18
Combining
AI and radiomics improved the breast ultrasound.
19
Radiomic models may aid various processes in breast
cancer research.
20
Combining radiomics with DL has
enabled predictive models that integrate imaging
phenotypes with genomic or molecular data-a field termed
radiogenomics. These approaches show promise in
oncology, where they can predict therapeutic outcomes
and patient survival.
21
Recent advancements in radiomics
and AI offer novel solutions by integrating ML algorithms
and quantitative imaging features to enhance prognostic
precision and diagnostics.
22
High-quality AI models
trained
on
radiomics
data
demonstrate
superior
performance and helping physicians and patients in the
study on thoracic trauma.
23
Explainable and interpretable
AI interpretability is critical for clinical use. Visualization
tools such as saliency maps, Grad-CAM, and attention
mechanisms provide insights into model decision-
making.
24
Nonetheless, the black-box nature of DL
remains a barrier to clinician confidence.
Emerging approach novel
Strategies such as federated learning enable collaborative
model training across institutions while preserving patient
data privacy.
25
Additionally, uncertainty quantification
and model calibration are becoming important for
enhancing reliability and clinical safety.
CLINICAL APPLICATIONS OF AI IN MEDICAL
IMAGING
Disease detection and diagnosis
DL systems have demonstrated expert-level performance
in disease recognition tasks. For instance, algorithms now
match ophthalmologists in detecting diabetic retinopathy
from fundus photographs and achieve high sensitivity in
identifying
pulmonary
nodules
on
chest
CT.
26,27
Computer-aided diagnosis (CAD) powered by AI is
increasingly incorporated into radiology workflows to
support clinical decision-making. In neurology, AI-based
methods are being developed for the early identification of
neurodegenerative disorders such as Parkinson’s and
Alzheimer’s disease, offering potential for timely
intervention and improved patient outcomes.
28
Oncology and digital pathology
Oncology is one of the most active areas for AI
deployment. DL has shown remarkable accuracy in breast
cancer detection and prognosis, utilizing both radiographic
and histopathological data. Whole-slide histopathology
imaging has been transformed through DL, enabling tumor
subtype classification, prediction of genetic mutations, and
survival outcome modeling.
29
In clinical oncology, AI
tools are increasingly applied to forecast therapeutic
responses and stratify patients, reinforcing the promise of
precision medicine.
Image reconstruction and enhancement
AI techniques are also advancing image acquisition and
post-processing. In PET, DL-based methods improve
image reconstruction, compensate for noise, and enhance
resolution.
30,31
In MRI and CT, these approaches reduce
radiation exposure and scan times while maintaining
diagnostic quality.
32
Ultrasound imaging has similarly
Vadlapudi V et al. Int J Adv Med. 2025 Nov;12(6):621-626
International Journal of Advances in Medicine | November-December 2025 | Vol 12 | Issue 6 Page 623
benefited, with AI-powered denoising methods producing
clearer and more interpretable images.
Multimodal integration
The integration of multiple imaging modalities, alongside
genomic and clinical data, is driving personalized
medicine. For example, combining MRI and PET provides
complementary information that enhances diagnostic
accuracy. AI has also revealed associations between
genetic mutations and morphologic features captured in
pathology slides, linking imaging phenotypes to molecular
mechanisms.
33,34
Such multimodal frameworks enable
more comprehensive patient profiling and improve
prognostic modeling.
Specialty-specific applications
Beyond oncology and radiology AI has shown promise
across numerous specialties. In ophthalmology, it aids in
detecting retinal disorders; in cardiology, it supports
echocardiographic analysis; and in pulmonology, it
contributes to the diagnosis of COVID-19 from chest CT
scans.
35
Furthermore, multimodal DL has enabled
integrative analyses of histopathology slides and genomic
datasets across diverse cancer types, opening new avenues
for biomarker discovery and translational research.
36,37
CHALLENGES AND LIMITATIONS
Data quality and bias
AI effectiveness is constrained by the quality and diversity
of training datasets. AI algorithms are prone to bias at
multiple stages of model development.
38
AI in healthcare
gains momentum, it brings forth profound ethical
challenges that demand careful consideration. The primary
concerns use of AI in healthcare includes responsibility
privacy trust, bias, cybersecurity, transparency, and data
quality.
39-41
Inadequate representation of populations can
introduce
biases,
potentially
exacerbating
health
disparities.
42
Generalizability and reproducibility models
Developed on single-center datasets often struggle to
generalize across different populations or institutions due
to variations in scanners, imaging protocols, and
annotation
standards.
Beyond
diagnostic
imaging,
artificial intelligence has also been explored for predicting
clinical outcomes. For example, ML approaches designed
to identify large vessel occlusions and viable brain tissue
are crucial in extending the treatment window, thereby
improving both patient prognosis and healthcare cost
efficiency. However, for such models to be reliable, they
must be reproducible-meaning the algorithms, underlying
code, and datasets should be accessible, well-documented,
and free of errors. At present, the absence of standardized
reporting practices and the limited public availability of
source code and clinical datasets pose significant
challenges.
These
limitations
not
only
hinder
reproducibility but also conflict with the ethical principles
of transparency and accountability in AI research.
43
Interpretability and trust
Interpretability trust are critical parameters to developing
transparent AI models that clinicians can trust for reliable
decision support.
44
The opaque decision-making of DL
models undermines clinical trust. While explainable AI
methods are progressing, achieving fully transparent
models remains a challenge.
Regulatory and ethical considerations
Clinicians acknowledge that the rapid development and
applications of AI in medical highlighting significant
progress and innovation. Ethical challenges, such as data
security, fairness, system bias, patient privacy and
regulatory gaps are the potential for AI to replace human
practitioners.
45
The regulatory landscape for AI in
healthcare is evolving. Although several AI-based imaging
systems have received FDA approval, questions of
liability, patient consent, and data security remain
unsettled.
46
FUTURE DIRECTIONS
Federated and privacy-preserving
AI conventional centralized AI models require pooling
sensitive
patient
data,
raising
concerns
about
confidentiality. Federated learning (FL) addresses this by
enabling multiple institutions to collaboratively train
models without exchanging raw data, maintaining privacy
while achieving performance comparable to centralized
approaches. Advanced methods integrate FL with
differential privacy, secure multiparty computation, and
homomorphic encryption to further reduce risks of data
leakage.
47,48
These frameworks promote cross-institutional
collaboration, enhance model generalizability, and align
with regulatory compliance.
Trustworthy and explainable
AI for AI systems to be widely adopted, they must not only
perform accurately but also provide transparency and
reliability. DL models are prone to overconfidence in
uncertain scenarios and vulnerable to adversarial attacks,
which undermines clinical trust. Incorporating uncertainty
quantification and interpretability tools can provide
confidence estimates alongside predictions, making
outputs more reliable for clinical use.
49,50
This shift toward
explainable AI is crucial for clinician acceptance.
Multimodal and multiscale models
The future of AI in imaging is expected to converge
diverse data sources-radiology, pathology, and genomics-
into unified predictive frameworks. Multimodal DL
Vadlapudi V et al. Int J Adv Med. 2025 Nov;12(6):621-626
International Journal of Advances in Medicine | November-December 2025 | Vol 12 | Issue 6 Page 624
approaches
have
already
demonstrated
superior
performance
compared
with
unimodal
systems,
particularly for tasks such as automated reporting,
outcome prediction, and CAD.
51,52
In addition, multiscale
models that link imaging at cellular, organ, and
physiological levels hold promise for patient-specific
simulations, such as tailored cardiac models for therapy
planning. Despite their potential, barriers such as data
heterogeneity, interpretability, and generalizability remain
pressing challenges.
Clinical translation and regulation
Although numerous high-performing AI algorithms have
been published, relatively few have been integrated into
routine clinical practice. Bridging this gap requires
adherence to robust validation protocols, prospective
trials, and standardized reporting frameworks such as
CONSORT-AI and SPIRIT-AI. Once beyond initial
development, models must demonstrate clinical validity
(accuracy in real-world settings), clinical utility (impact on
patient care), and usability (integration into daily
workflows) before they can be reliably deployed.
53
Human-AI collaboration
The trajectory of medical AI suggests a collaborative
future rather than replacement of clinicians. Recent studies
show that radiologists supported by large language models
(LLMs), such as GPT-4, achieve modest improvements in
diagnostic performance, underscoring the role of AI as a
clinical assistant rather than a substitute.
54
Applications in
breast cancer screening already demonstrate how human–
AI interaction can improve accuracy, efficiency, and
patient experience.
55
By reducing workload and enhancing
diagnostic consistency, AI will increasingly function as a
complementary partner to clinicians.
CONCLUSION
Artificial intelligence, particularly ML and DL, is
reshaping medical imaging by enhancing automation,
diagnostic accuracy, and understanding of disease
processes. Its applications in radiology, oncology, and
pathology highlight its ability to improve clinical
efficiency and support precision medicine. Nonetheless,
widespread clinical deployment is constrained by
challenges, including limited data diversity, model
interpretability,
potential
biases,
and
regulatory
uncertainties. Emerging strategies such as federated
learning, explainable AI, and multimodal integration are
critical to addressing these barriers and ensuring reliable
real-world adoption. Multiscale frameworks that combine
imaging, molecular, and clinical data are particularly
promising for building comprehensive patient profiles and
advancing personalized care. However, successful
translation requires more than technological innovation-it
must
also
prioritize
fairness,
transparency,
interoperability, and rigorous prospective validation.
Ultimately, the future of AI in medical imaging lies in
collaborative human-AI models that complement rather
than replace clinical expertise. By integrating ethical
responsibility,
clinician
engagement,
and
robust
validation, AI-driven imaging solutions can achieve safe,
effective, and equitable integration into healthcare
practice.
Funding: No funding sources
Conflict of interest: None declared
Ethical approval: The study was approved by the
Institutional Ethics Committee
REFERENCES
1.
Sorantin E, Grasser MG, Hemmelmayr A, Tschauner
S, Hrzic F, Weiss V, et al. The augmented
radiologist: artificial intelligence in the practice of
radiology. Pediatr Radiol. 2022;52(11):2074–86.
2.
Gore JC. Artificial intelligence in medical imaging.
Magn Reson Imaging. 2020;68:A1–4.
3.
LeCun Y, Bengio Y, Hinton G. Deep learning.
Nature. 2015;521:436–44.
4.
Esteva A, Kuprel B, Novoa RA. Dermatologist-level
classification of skin cancer with deep neural
networks. Nature. 2017;542:115–8.
5.
Giger ML. Machine learning in medical imaging. J
Am Coll Radiol. 2018;15(3 Pt B):512–20.
6.
Gurnani B, Kaur K, Lalgudi VG, Kundu G, Mimouni
M, Liu H, et al. Role of artificial intelligence,
machine learning and deep learning models in
corneal disorders—a
narrative
review.
J
Fr
Ophtalmol. 2024;47(7):104242.
7.
Saeed AQ, Sheikh Abdullah SNH, Che-Hamzah J,
Abdul Ghani AT. Accuracy of using generative
adversarial networks for glaucoma detection:
systematic review and bibliometric analysis. J Med
Internet Res. 2021;23(9):e27414.
8.
Khan ZK, Umar AI, Shirazi SH, Rasheed A, Qadir
A, Gul S. Image-based analysis of meibomian gland
dysfunction using conditional generative adversarial
neural
network.
BMJ
Open
Ophthalmol.
2021;6(1):e000436
9.
Waisberg E, Ong J, Kamran SA, Masalkhi M,
Paladugu P, Zaman N, et al. Generative artificial
intelligence in ophthalmology. Surv Ophthalmol.
2025;70(1):1–11.
10.
Avanzo M, Porzio M, Lorenzon L, Milan L,
Sghedoni R, Russo G, et al. Artificial intelligence
applications in medical imaging: a review of the
medical physics research in Italy. Phys Med.
2021;83:221–41.
11.
Rondina J, Nachev P. Artificial intelligence and
stroke imaging. Curr Opin Neurol. 2025;38(1):40–6.
12.
Loper MR, Makary MS. Evolving and novel
applications of artificial intelligence in abdominal
imaging. Tomography. 2024;10(11):1814–31.
13.
Ramai D, Collins B, Ofosu A, Mohan BP, Jagannath
S, Tabibian JH, et al. Deep learning methods in the
imaging of hepatic and pancreaticobiliary diseases. J
Clin Gastroenterol. 2025;59(5):405–11.
Vadlapudi V et al. Int J Adv Med. 2025 Nov;12(6):621-626
International Journal of Advances in Medicine | November-December 2025 | Vol 12 | Issue 6 Page 625
14.
Lambin P, Rios-Velazquez E, Leijenaar R.
Radiomics: extracting more information from
medical images using advanced feature analysis. Eur
J Cancer. 2012;48:441–6.
15.
Ronneberger O, Fischer P, Brox T. U-Net:
convolutional networks for biomedical image
segmentation. In: MICCAI 2015. Springer; 2015. p.
234–41.
16.
Sirinukunwattana K, Ahmed Raza SE, Tsang YW,
Snead DR, Cree IA, Rajpoot NM. Locality sensitive
deep learning for detection and classification of
nuclei in colon cancer histology images. IEEE Trans
Med Imaging. 2016;35(5):1196–206.
17.
Avanzo M, Stancanello J, Pirrone G, Drigo A, Retico
A. The evolution of artificial intelligence in medical
imaging: from computer science to machine and deep
learning. Cancers (Basel). 2024;16(21):3702.
18.
Podină N, Gheorghe EC, Constantin A, Cazacu I,
Croitoru V, Gheorghe C, et al. Artificial intelligence
in pancreatic imaging: a systematic review. United
European Gastroenterol J. 2025;13(1):55–77.
19.
Bahl M. Combining AI and radiomics to improve the
accuracy
of
breast
US.
Radiology.
2024;312(3):e241795.
20.
Qi YJ, Su GH, You C, Zhang X, Xiao Y, Jiang YZ,
et al. Radiomics in breast cancer: current advances
and
future
directions.
Cell
Rep
Med.
2024;5(9):101719.
21.
Gillies RJ, Kinahan PE, Hricak H. Radiomics:
images are more than pictures, they are data.
Radiology. 2016;278:563–77.
22.
Peng D, Huang W, Liu R, Zhong W. From pixels to
prognosis: radiomics and AI in Alzheimer's disease
management. Front Neurol. 2025;16:1536463.
23.
Hefny AF, Almansoori TM, Smetanina D, Morozova
D, Voitetskii R, Das KM, et al. Streamlining
management in thoracic trauma: radiomics- and AI-
based assessment of patient risks. Front Surg.
2024;11:1462692.
24.
Selvaraju RR, Cogswell M, Das A. Grad-CAM:
visual explanations from deep networks via gradient-
based localization. Proc IEEE ICCV. 2017:618–26.
25.
Sheller MJ, Edwards B, Reina GA. Federated
learning in medicine: facilitating multi-institutional
collaborations without sharing patient data. Sci Rep.
2020;10:12598.
26.
Gulshan V, Peng L, Coram M. Development and
validation of a deep learning algorithm for detection
of diabetic retinopathy in retinal fundus photographs.
JAMA. 2016;316:2402–10
27.
Ardila D, Kiraly AP, Bharadwaj S, et al. End-to-end
lung cancer screening with three-dimensional deep
learning on low-dose chest CT. Nat Med.
2019;25:954–61.
28.
Reddy A, Reddy RP, Roghani AK, Garcia RI,
Khemka S, Pattoor V, et al. Artificial intelligence in
Parkinson's disease: early detection and diagnostic
advancements. Ageing Res Rev. 2024;99:102410.
29.
Coudray N, Ocampo PS, Sakellaropoulos T.
Classification and mutation prediction from non–
small cell lung cancer histopathology images using
deep learning. Nat Med. 2018;24:1559–67.
30.
Wang T, Lei Y, Fu Y, Curran WJ, Liu T, Nye JA, et
al. Machine learning in quantitative PET: a review of
attenuation
correction
and
low-count
image
reconstruction methods. Phys Med. 2020;76:294–
306.
31.
Reader AJ, Pan B. AI for PET image reconstruction.
Br J Radiol. 2023;96(1150):20230292.
32.
Hammernik K, Klatzer T, Kobler E. Learning a
variational network for reconstruction of accelerated
MRI data. Magn Reson Med. 2018;79:3055–71.
33.
Lipkova J, Chen RJ, Chen B, Lu MY, Barbieri M,
Shao D, et al. Artificial intelligence for multimodal
data
integration
in
oncology.
Cancer
Cell.
2022;40(10):1095–110.
34.
He X, Liu X, Zuo F, Shi H, Jing J. Artificial
intelligence-based multi-omics analysis fuels cancer
precision
medicine.
Semin
Cancer
Biol.
2023;88:187–200.
35.
Chan JF, Zhang AJ, Yuan S, Poon VK, Chan CC, Lee
AC, et al. Simulation of the clinical and pathological
manifestations of COVID-19 in a golden Syrian
hamster model. Clin Infect Dis. 2020;71(9):2428–46.
36.
Chen RJ, Lu MY, Williamson DFK, Chen TY,
Lipkova J, Noor Z, et al. Pan-cancer integrative
histology-genomic analysis via multimodal deep
learning. Cancer Cell. 2022;40(8):865–78.e6.
37.
Beck AH, Sangoi AR, Leung S, Marinelli RJ, Nielsen
TO, van de Vijver MJ, et al. Systematic analysis of
breast cancer morphology uncovers stromal features
associated
with
survival.
Sci
Transl
Med.
2011;3(108):108ra113.
38.
Tejani AS, Ng YS, Xi Y, Rayan JC. Understanding
and mitigating bias in imaging artificial intelligence.
Radiographics. 2024;44(5):e230067.
39.
Jeyaraman M, Balaji S, Jeyaraman N, Yadav S.
Unraveling the ethical enigma: artificial intelligence
in healthcare. Cureus. 2023;15(8):e43262.
40.
Sallam M. ChatGPT utility in healthcare education,
research, and practice: systematic review on the
promising
perspectives
and
valid
concerns.
Healthcare (Basel). 2023;11(6):887.
41.
Prakash S, Balaji JN, Joshi A, Surapaneni KM.
Ethical conundrums in the application of artificial
intelligence in healthcare—a scoping review of
reviews. J Pers Med. 2022;12(11):1914.
42.
Parikh RB, Obermeyer Z, Navathe AS. Regulation of
predictive
analytics
in
medicine.
Science.
2019;363:810–2.
43.
Romoli M, Caliandro P. Artificial intelligence,
machine learning, and reproducibility in stroke
research. Eur Stroke J. 2024;9(3):518–20.
44.
Shool S, Adimi S, Saboori Amleshi R, Bitaraf E,
Golpira R, Tara M. A systematic review of large
language model evaluations in clinical medicine.
BMC Med Inform Decis Mak. 2025;25(1):117.
45.
Alfaraj A, Nagai T, AlQallaf H, Lin WS. Race to the
moon or the bottom? Applications, performance, and
ethical considerations of artificial intelligence in
Vadlapudi V et al. Int J Adv Med. 2025 Nov;12(6):621-626
International Journal of Advances in Medicine | November-December 2025 | Vol 12 | Issue 6 Page 626
prosthodontics and implant dentistry. Dent J (Basel).
2024;13(1):13.
46.
Topol
EJ.
High-performance
medicine:
the
convergence of human and artificial intelligence. Nat
Med. 2019;25:44–56.
47.
Nakayama-Kamada C, Enatsu R, Fukumura S,
Kuribara T, Ochi S, Mikuni N. A case of paroxysmal
kinesigenic dyskinesia suspected to be reflex
epilepsy. Nagoya J Med Sci. 2021;83(2):361–5.
48.
Baber R. Treating menopausal women: have we lost
our
way? Aust
N
Z
J
Obstet
Gynaecol.
2021;61(4):493–5.
49.
Lambert B, Forbes F, Doyle S, Dehaene H, Dojat M.
Trustworthy clinical AI solutions: a unified review of
uncertainty quantification in deep learning models
for medical image analysis. Artif Intell Med.
2024;150:102830.
50.
Zbrzezny AM, Grzybowski AE. Deceptive tricks in
artificial
intelligence:
adversarial
attacks
in
ophthalmology. J Clin Med. 2023;12(9):3266.
51.
Sun Z, Lin M, Zhu Q, Xie Q, Wang F, Lu Z, et al. A
scoping review on multimodal deep learning in
biomedical images and texts. J Biomed Inform.
2023;146:104482.
52.
Warner E, Lee J, Hsu W, Syeda-Mahmood T, Kahn
CE Jr, Gevaert O, Rao A. Multimodal machine
learning in image-based and clinical biomedicine:
survey
and
prospects.
Int
J
Comput
Vis.
2024;132(9):3753–69.
53.
Kann BH, Hosny A, Aerts HJWL. Artificial
intelligence for clinical oncology. Cancer Cell.
2021;39(7):916–27.
54.
Kim SH, Wihl J, Schramm S, Berberich C,
Rosenkranz E, Schmitzer L, et al. Human-AI
collaboration in large language model-assisted brain
MRI differential diagnosis: a usability study. Eur
Radiol. 2025;35(9):5252–63.
55.
Frazer HML, Peña-Solorzano CA, Kwok CF, Elliott
MS, Chen Y, Wang C, et al. Comparison of AI-
integrated pathways with human-AI interaction in
population mammographic screening for breast
cancer. Nat Commun. 2024;15(1):7525.
Cite this article as:
Vadlapudi V, Kaladhar DSVGK.
Artificial intelligence in medical imaging: bridging
innovation, ethics, and clinical impact. Int J Adv Med
2025;12:621-6.
