TY - JOUR
T1 - Potential of E-Learning Interventions and Artificial Intelligence-Assisted Contouring Skills in Radiotherapy
T2 - The ELAISA Study
AU - Rasmussen, Mathis Ersted
AU - Akbarov, Kamal
AU - Titovich, Egor
AU - Nijkamp, Jasper Albertus
AU - Van Elmpt, Wouter
AU - Primdahl, Hanne
AU - Lassen, Pernille
AU - Cacicedo, Jon
AU - Cordero-Mendez, Lisbeth
AU - Uddin, A F M Kamal
AU - Mohamed, Ahmed
AU - Prajogi, Ben
AU - Brohet, Kartika Erida
AU - Nyongesa, Catherine
AU - Lomidze, Darejan
AU - Prasiko, Gisupnikha
AU - Ferraris, Gustavo
AU - Mahmood, Humera
AU - Stojkovski, Igor
AU - Isayev, Isa
AU - Mohamad, Issa
AU - Shirley, Leivon
AU - Kochbati, Lotfi
AU - Eftodiev, Ludmila
AU - Piatkevich, Maksim
AU - Bonilla Jara, Maria Matilde
AU - Spahiu, Orges
AU - Aralbayev, Rakhat
AU - Zakirova, Raushan
AU - Subramaniam, Sandya
AU - Kibudde, Solomon
AU - Tsegmed, Uranchimeg
AU - Korreman, Stine Sofia
AU - Eriksen, Jesper Grau
PY - 2024/9/1
Y1 - 2024/9/1
N2 - PURPOSE Most research on artificial intelligence–based auto-contouring as template (AI-assisted contouring) for organs-at-risk (OARs) stem from high-income countries. The effect and safety are, however, likely to depend on local factors. This study aimed to investigate the effects of AI-assisted contouring and teaching on contouring time and contour quality among radiation oncologists (ROs) working in low- and middle-income countries (LMICs). MATERIALS Ninety-seven ROs were randomly assigned to either manual or AI-assisted AND METHODS contouring of eight OARs for two head-and-neck cancer cases with an in-between teaching session on contouring guidelines. Thereby, the effect of teaching (yes/no) and AI-assisted contouring (yes/no) was quantified. Second, ROs completed short-term and long-term follow-up cases all using AI assistance. Contour quality was quantified with Dice Similarity Coefficient (DSC) between ROs’ contours and expert consensus contours. Groups were compared using absolute differences in medians with 95% CIs. RESULTS AI-assisted contouring without previous teaching increased absolute DSC for optic nerve (by 0.05 [0.01; 0.10]), oral cavity (0.10 [0.06; 0.13]), parotid (0.07 [0.05; 0.12]), spinal cord (0.04 [0.01; 0.06]), and mandible (0.02 [0.01; 0.03]). Contouring time decreased for brain stem (–1.41 [–2.44; –0.25]), mandible (–6.60 [–8.09; –3.35]), optic nerve (–0.19 [–0.47; –0.02]), parotid (–1.80 [–2.66; –0.32]), and thyroid (–1.03 [–2.18; –0.05]). Without AI-assisted contouring, teaching increased DSC for oral cavity (0.05 [0.01; 0.09]) and thyroid (0.04 [0.02; 0.07]), and contouring time increased for mandible (2.36 [–0.51; 5.14]), oral cavity (1.42 [–0.08; 4.14]), and thyroid (1.60 [–0.04; 2.22]). CONCLUSION The study suggested that AI-assisted contouring is safe and beneficial to ROs working in LMICs. Prospective clinical trials on AI-assisted contouring should, however, be conducted upon clinical implementation to confirm the effects.
AB - PURPOSE Most research on artificial intelligence–based auto-contouring as template (AI-assisted contouring) for organs-at-risk (OARs) stem from high-income countries. The effect and safety are, however, likely to depend on local factors. This study aimed to investigate the effects of AI-assisted contouring and teaching on contouring time and contour quality among radiation oncologists (ROs) working in low- and middle-income countries (LMICs). MATERIALS Ninety-seven ROs were randomly assigned to either manual or AI-assisted AND METHODS contouring of eight OARs for two head-and-neck cancer cases with an in-between teaching session on contouring guidelines. Thereby, the effect of teaching (yes/no) and AI-assisted contouring (yes/no) was quantified. Second, ROs completed short-term and long-term follow-up cases all using AI assistance. Contour quality was quantified with Dice Similarity Coefficient (DSC) between ROs’ contours and expert consensus contours. Groups were compared using absolute differences in medians with 95% CIs. RESULTS AI-assisted contouring without previous teaching increased absolute DSC for optic nerve (by 0.05 [0.01; 0.10]), oral cavity (0.10 [0.06; 0.13]), parotid (0.07 [0.05; 0.12]), spinal cord (0.04 [0.01; 0.06]), and mandible (0.02 [0.01; 0.03]). Contouring time decreased for brain stem (–1.41 [–2.44; –0.25]), mandible (–6.60 [–8.09; –3.35]), optic nerve (–0.19 [–0.47; –0.02]), parotid (–1.80 [–2.66; –0.32]), and thyroid (–1.03 [–2.18; –0.05]). Without AI-assisted contouring, teaching increased DSC for oral cavity (0.05 [0.01; 0.09]) and thyroid (0.04 [0.02; 0.07]), and contouring time increased for mandible (2.36 [–0.51; 5.14]), oral cavity (1.42 [–0.08; 4.14]), and thyroid (1.60 [–0.04; 2.22]). CONCLUSION The study suggested that AI-assisted contouring is safe and beneficial to ROs working in LMICs. Prospective clinical trials on AI-assisted contouring should, however, be conducted upon clinical implementation to confirm the effects.
KW - Humans
KW - Artificial Intelligence
KW - Organs at Risk/radiation effects
KW - Head and Neck Neoplasms/radiotherapy
KW - Female
KW - Male
KW - Radiotherapy Planning, Computer-Assisted/methods
KW - Radiation Oncologists/education
KW - Adult
KW - Middle Aged
U2 - 10.1200/GO.24.00173
DO - 10.1200/GO.24.00173
M3 - Article
SN - 2687-8941
VL - 10
SP - 2400173
JO - JCO Global Oncology
JF - JCO Global Oncology
M1 - e2400173
ER -