Potential of E-Learning Interventions and Artificial Intelligence-Assisted Contouring Skills in Radiotherapy: The ELAISA Study

Rasmussen ME 1 , Akbarov K 2 , Titovich E 2 , Nijkamp JA 3 , Van Elmpt W 4 , Primdahl H 5 Show all authors , Lassen P 5 , Cacicedo J 6 , Cordero-Mendez L 2 , Uddin AFMK 7 , Mohamed A 8 , Prajogi B 9 , Brohet KE 10 , Nyongesa C 11 , Lomidze D 12 , Prasiko G 13 , Ferraris G 14 , Mahmood H 15 , Stojkovski I 16 , Isayev I 17 , Mohamad I 18 , Shirley L 19 , Kochbati L 20 , Eftodiev L 21 , Piatkevich M 22 , Bonilla Jara MM 23 , Spahiu O 24 , Aralbayev R 25 , Zakirova R 26 , Subramaniam S 27 , Kibudde S 28 , Tsegmed U 29 , Korreman SS 3 , Eriksen JG 1

Affiliations 

  • 1 Experimental Clinical Oncology, Aarhus University Hospital, Aarhus, Denmark
  • 2 International Atomic Energy Agency, Vienna, Austria
  • 3 Department of Clinical Medicine, Aarhus University, Aarhus, Denmark
  • 4 MAASTRO clinic, Maastricht University Medical Centre, Maastricht, the Netherlands
  • 5 Department of Oncology, Aarhus University Hospital, Aarhus, Denmark
  • 6 Department of Radiation Oncology, Cruces University Hospital, Bilbao, Spain
  • 7 Labaid Cancer Hospital and Super Speciality Centre, Dhaka, Bangladesh
  • 8 National Cancer Institute, University of Gezira, Wad Madani, Sudan
  • 9 Cipto Mangunkusumo Hospital, Jakarta, Indonesia
  • 10 Dharmais Cancer Hospital, Jakarta, Indonesia
  • 11 Kenyatta National Hospital, Nairobi, Kenya
  • 12 Tbilisi State Medical University and Ingorokva High Medical Technology University Clinic, Tbilisi, Georgia
  • 13 Nepal Cancer Hospital and Research Center, Lalitpur, Nepal
  • 14 Centro de Radioterapiya dean Funes, Cordoba, Argentina
  • 15 Atomic Energy Cancer Hospital NORI, Islamabad, Pakistan
  • 16 University Clinic of Radiotherapy and Oncology, Skopje, Macedonia
  • 17 National Center of Oncology, Baku, Azerbaijan
  • 18 King Hussein Cancer Center, Amman, Jordan
  • 19 Christian Institute of Health Science and Research, Dimapur, India
  • 20 Hospital Abderrahmen Mami, Ariana, Tunesia
  • 21 Moldavian Oncology Institute, Chisinau, Moldova
  • 22 N. N. Alexandrov National Cancer Centre of Belarus, Minsk, Belarus
  • 23 Hospital México, San José, Costa Rica
  • 24 Mother Tereza Hospital, Tirana, Albania
  • 25 National Centre of Oncology and Hematology, Bishkek, Kyrgyzstan
  • 26 Center of Nuclear Medicine and Oncology, Semey, Kazakhstan
  • 27 Hospital Kuala Lumpur, Kuala Lumpur, Malaysia
  • 28 Uganda Cancer Institute, Kampala, Uganda
  • 29 National Cancer Center of Mongolia, Ulaanbaatar, Mongolia
JCO Glob Oncol, 2024 Aug;10:e2400173.
PMID: 39236283 DOI: 10.1200/GO.24.00173

Abstract

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 AND METHODS: Ninety-seven ROs were randomly assigned to either manual or AI-assisted 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.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

MeSH terms
Similar publications