Restriction lift date: 2027-01-15
AI in computed tomography
Loading...
Files
Date
2025-01-15
Authors
McEntee, Mark
Mussmann, Bo
Ohene-Botwe, Benard
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Nature
Published Version
Abstract
This chapter explores some of the recent advancements in computed tomography (CT), driven by Artificial Intelligence (AI), and their transformative impact on various aspects of CT practice. From workflow optimisation to patient preparation, AI-powered innovations are enhancing efficiency and accuracy. In particular, AI improves patient positioning and alignment by precisely detecting body contours, thereby optimising scanning precision. While AI may not always generate fully personalised protocols, it integrates individual patient characteristics to recommend optimised scanning parameters. Furthermore, AI plays a crucial role in radiation protection, particularly through the optimisation of techniques, low-dose CT scanning, and advanced dose tracking systems that enhance patient safety. AI-driven scan range optimisation tools help define precise scan boundaries without compromising image quality, leveraging patient anatomy and predefined parameters. Additionally, AI-guided needle-tracking systems have significantly improved the accuracy of CT-guided biopsies and spinal injections by providing real-time navigation for precise lesion targeting. Beyond image acquisition, AI has also revolutionised data processing and image reconstruction. By reducing noise, correcting artefacts, and enhancing segmentation, AI contributes to more accurate and reliable imaging. Moreover, AI-assisted diagnostic models streamline clinical workflows, improving efficiency by facilitating abnormality detection, triaging, and quantification. The integration of AI with emerging technologies such as photon-counting CT, radiomics, and radiogenomics further underscores its potential to advance precision imaging and personalised medicine. Despite these transformative benefits, several challenges remain in AI implementation. Issues related to data quality, clinical integration, and ethical considerations must be addressed to fully harness AI’s potential in CT. Overcoming these challenges will be crucial to ensuring seamless adoption into clinical practice and maximising the benefits of AI-driven innovations in medical imaging.
Description
Keywords
Artificial Intelligence (AI) , Computed tomography (CT) , [Medicine]
Citation
McEntee, M, Mussmann, B & Ohene-Botwe, B 2025, AI in computed tomography. in C Malamateniou, M Hardy, K Knapp & A Ramlaul (eds), Artificial Intelligence for Radiographers - Basic Principles, Clinical Applications and Implementation Considerations. 1 edn, Springer Nature, pp. 119-146. https://doi.org/10.1007/978-3-032-05080-9_6
Link to publisher’s version
Collections
Copyright
© 2026, the Editors and the Authors, under exclusive license to Springer Nature Switzerland AG.