TY - JOUR
T1 - A multidisciplinary team and multiagency approach for AI implementation: A commentary for medical imaging and radiotherapy key stakeholders
AU - Stogiannos, Nikolaos
AU - Gillan, Caitlin
AU - Precht, Helle
AU - Reis, Claudia
AU - Kumar, Amrita
AU - Oreagan, Tracy
AU - Barnes, Anna
AU - Meades, Richard
AU - Pogose, Michael
AU - Gerggio, Julien
AU - Scurr, Erica
AU - Kumar, Shamie
AU - King, Graham
AU - Rosewarne, David
AU - Jones, Catherine
AU - van Leeuwen, Kicky
AU - Hyde, Emma
AU - Beardmore, Charlotte
AU - Alliende, Juan
AU - El-farra, Samar
AU - Papathanasiou, Stamatia
AU - Berger, Jan
AU - Nash, Jonathan
AU - von Ooijen, Peter
AU - Zelenyanszki, Christiane
AU - Koch, Barbara
AU - Langmack, Keith
AU - Tucker, Richard
AU - Goh, Vicky
AU - Turmezei, Tom
AU - Lip, Gerald
AU - Reyes-Aldasoro, Constantino Carlos
AU - Alonso, Eduardo
AU - Dean, Geraldine
AU - Hirani, Shashivadan P.
AU - Torre, Sofia
AU - Akudjedu, Theophilus N.
AU - Ohene-Botwe, Benard
AU - Khine, Ricardo
AU - O'Sullivan, Chris
AU - Kyratsis, Yiannis
AU - McEntee, Mark
AU - Wheatstone, Peter
AU - Thackray, Yvonne
AU - Cairns, James
AU - Jerome, Derek
AU - Scarsbrook, Andrew
AU - Malamateniou, Christina
PY - 2024
Y1 - 2024
N2 - Artificial Intelligence (AI) algorithms have been recently deployed in different healthcare settings. These tools have shown promise in reducing professionals’ administrative workload, handle electronic health records, aid drug discovery, improve diagnostic services, and analyse complex data [1], [2], [3]. Medical Imaging and Radiotherapy (MIRT) are at the forefront of this digital transformation, as can be seen from the concurrent increase in MIRT-related AI products [4], [5], [6]. In MIRT in particular, AI has shown potential to optimise image acquisition and post-processing, redefine clinical workflows, improve diagnostic accuracy, facilitate automated organ segmentation, image registration and planning in radiotherapy, and personalise patient care [7], [8], [9]. These recent advancements could translate into improved patient outcomes, personalised pathways and treatment plans, and, therefore, deliver precision into healthcare [10,11]. At the same time, concerns about potential risks and safety of AI-enabled software and hardware are raised by both clinical practitioners and patients, which need to be addressed within the design and implementation of AI and balanced against the undoubted benefits [12].
AB - Artificial Intelligence (AI) algorithms have been recently deployed in different healthcare settings. These tools have shown promise in reducing professionals’ administrative workload, handle electronic health records, aid drug discovery, improve diagnostic services, and analyse complex data [1], [2], [3]. Medical Imaging and Radiotherapy (MIRT) are at the forefront of this digital transformation, as can be seen from the concurrent increase in MIRT-related AI products [4], [5], [6]. In MIRT in particular, AI has shown potential to optimise image acquisition and post-processing, redefine clinical workflows, improve diagnostic accuracy, facilitate automated organ segmentation, image registration and planning in radiotherapy, and personalise patient care [7], [8], [9]. These recent advancements could translate into improved patient outcomes, personalised pathways and treatment plans, and, therefore, deliver precision into healthcare [10,11]. At the same time, concerns about potential risks and safety of AI-enabled software and hardware are raised by both clinical practitioners and patients, which need to be addressed within the design and implementation of AI and balanced against the undoubted benefits [12].
U2 - 10.1016/j.jmir.2024.101717
DO - 10.1016/j.jmir.2024.101717
M3 - Journal article
SN - 1939-8654
VL - 55
JO - Journal of Medical Imaging and Radiation Sciences
JF - Journal of Medical Imaging and Radiation Sciences
IS - 4
M1 - 101717
ER -