Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 47 min ago
Peer-reviewedCC BYDigital Health

Systematic review of sustainable AI implementation in medical imaging: Challenges, strategies, and future directions

8 more authors

Abstract

Background Artificial Intelligence (AI) in medical imaging has the potential to provide a competitive edge through early diagnosis, prognosis, and patient management. There is high optimism about diagnostic imaging AI utilisation; however, scarce empirical evidence exists assessing antecedents of sustainable adoption in real-world hospital settings. This systematic review aims to provide an integrative model that explains factors relevant to the sustainable deployment of AI in medical imaging across three implementation layers (macro, meso, and micro). Methods A systematic literature review was conducted in accordance with PRISMA guidelines. Seven databases (IEEE Xplore, Web of Science, ScienceDirect, Scopus, Embase, PsycINFO, and Medline) were searched for English-language empirical studies published between 2020-2025 examining AI implementation in medical imaging. The extracted data was analysed with thematic analysis to identify key themes. Results From the search results, 89 peer-reviewed journal articles were included in the review. The findings indicated that the majority of studies focused on technical challenges and clinical and operational barriers to sustainable AI deployment in medical imaging. Limited attention was paid to ethical, regulatory, structural, communication, and patient attitudinal factors. Findings were synthesised into a three-layered sustainability model describing macro-level (e.g., governance, policy, ethics), meso-level (e.g., performance, workforce capacity development), and micro-level (e.g., operational efficiency, cost, well-being) factors of sustainability. Conclusions This review presents a model for sustainable AI adoption in medical imaging that can inform clinicians, policymakers, and industry stakeholders when considering implementation, monitoring, and scalable integration, while highlighting areas where further empirical evidence is needed.

Related

  1. First Year Implementation and Performance of the Republic of Korea’s National Antimicrobial Stewardship Program Pilot: Policy Directions for Sustainable Expansion
    Young-Il Jeong, Yeo Won Jin, In Kyoung Kim +3
    Public Health Weekly ReportPeer-reviewedCC BY 4.0Full textInfectious diseasePMC
  2. Virtual Reality in Surgical Education: Evidence, Applications, Implementation Challenges, and Future Directions.
    Peng Huang, Jia-Xing Zeng, Zhi-Jun Zhan +2
    Advances in medical education and practicePeer-reviewedCC BY-NCFull textSurgery & anaesthesiaEurope PMCPMC
  3. Competency Based Education in Anesthesia and Intensive Care Medicine: Educational Innovations, Implementation Challenges, and Future Directions
    Ibrahim Abdullahi Mohamed, Najma Abdullahi Mohamed
    Advances in Medical Education and PracticePeer-reviewedCC BY-NC 4.0Full textEpidemiology & public healthPMCEurope PMC
  4. Climate change and malaria in Rwanda: multi-sectoral expert insights on adaptation strategies, capacity needs and implementation challenges
    Felix K. Rubuga, Gashaija Absolomon, Arnold S. Mmbando +5
    BMC Public HealthPeer-reviewedCC BY-NC-ND 4.0Pharmacology & toxicologyCrossref
  5. Implementation strategies, outcomes and determinants of integrated care for cardiometabolic conditions and mental, neurological and substance use disorders: protocol for a mixed-methods systematic review
    Emma Jeltje Blinker, Gordon Kwasi Ampomah Amoh, Samuel Ankamah +6
    BMJ OpenPeer-reviewedCC BY 4.0Full textGeneral medicineCrossrefEurope PMC
BibTeX
@article{brough2026systematic,
  title = {{Systematic review of sustainable AI implementation in medical imaging: Challenges, strategies, and future directions}},
  author = {Paula Brough and Khondker Mohammad Zobair and Javad Pool and Natalie Haskell and Luke Houghton and Paul Scuffham and Jennifer Loy and Ashlea Troth and Salim Memon and Rachael Smithson and Maria Khan and Brooke Murphy and Letisha Living and Leanne Du and John Richards and Jennifer Dolkens and Matthew Aitken and Jason Zhang and John Grieve and Sandeep Bhuta},
  journal = {Digital Health},
  year = {2026},
  month = nov,
  doi = {10.1177/20552076261500355},
  url = {https://doi.org/10.1177/20552076261500355},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Systematic review of sustainable AI implementation in medical imaging: Challenges, strategies, and future directions
AU  - Paula Brough
AU  - Khondker Mohammad Zobair
AU  - Javad Pool
AU  - Natalie Haskell
AU  - Luke Houghton
AU  - Paul Scuffham
AU  - Jennifer Loy
AU  - Ashlea Troth
AU  - Salim Memon
AU  - Rachael Smithson
AU  - Maria Khan
AU  - Brooke Murphy
AU  - Letisha Living
AU  - Leanne Du
AU  - John Richards
AU  - Jennifer Dolkens
AU  - Matthew Aitken
AU  - Jason Zhang
AU  - John Grieve
AU  - Sandeep Bhuta
PY  - 2026
DA  - 2026/11/13
JO  - Digital Health
DO  - 10.1177/20552076261500355
UR  - https://doi.org/10.1177/20552076261500355
AB  - Background Artificial Intelligence (AI) in medical imaging has the potential to provide a competitive edge through early diagnosis, prognosis, and patient management. There is high optimism about diagnostic imaging AI utilisation; however, scarce empirical evidence exists assessing antecedents of sustainable adoption in real-world hospital settings. This systematic review aims to provide an integrative model that explains factors relevant to the sustainable deployment of AI in medical imaging across three implementation layers (macro, meso, and micro). Methods A systematic literature review was conducted in accordance with PRISMA guidelines. Seven databases (IEEE Xplore, Web of Science, ScienceDirect, Scopus, Embase, PsycINFO, and Medline) were searched for English-language empirical studies published between 2020-2025 examining AI implementation in medical imaging. The extracted data was analysed with thematic analysis to identify key themes. Results From the search results, 89 peer-reviewed journal articles were included in the review. The findings indicated that the majority of studies focused on technical challenges and clinical and operational barriers to sustainable AI deployment in medical imaging. Limited attention was paid to ethical, regulatory, structural, communication, and patient attitudinal factors. Findings were synthesised into a three-layered sustainability model describing macro-level (e.g., governance, policy, ethics), meso-level (e.g., performance, workforce capacity development), and micro-level (e.g., operational efficiency, cost, well-being) factors of sustainability. Conclusions This review presents a model for sustainable AI adoption in medical imaging that can inform clinicians, policymakers, and industry stakeholders when considering implementation, monitoring, and scalable integration, while highlighting areas where further empirical evidence is needed.
SN  - 2055-2076
ER  -