Consistency in contouring of organs at risk by artificial intelligence vs oncologists in head and neck cancer patients

Authors

  • Camilla Panduro Nielsen a Laboratory of Radiation Physics, Odense University Hospital, Odense, Denmark; b Institute of Clinical Research, University of Southern Denmark, Odense, Denmark
  • Ebbe Laugaard Lorenzen a Laboratory of Radiation Physics, Odense University Hospital, Odense, Denmark; b Institute of Clinical Research, University of Southern Denmark, Odense, Denmark
  • Kenneth Jensen d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark
  • Nis Sarup a Laboratory of Radiation Physics, Odense University Hospital, Odense, Denmark
  • Carsten Brink a Laboratory of Radiation Physics, Odense University Hospital, Odense, Denmark; b Institute of Clinical Research, University of Southern Denmark, Odense, Denmark
  • Bob Smulders d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark; e Department of Oncology, Rigshospitalet, University Hospital of Copenhagen, Copenhagen, Denmark
  • Anne Ivalu Sander Holm f Department of Oncology, Aarhus University Hospital, Aarhus N, Denmark
  • Eva Samsøe d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark; g Department of Oncology, Zealand University Hospital, Naestved, Denmark
  • Martin Skovmos Nielsen h Department of Oncology, Aalborg University Hospital, Aalborg, Denmark
  • Patrik Sibolt i Department of Oncology, University Hospital Herlev, Herlev, Denmark
  • Peter Sandegaard Skyt d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark
  • Ulrik Vindelev Elstrøm d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark
  • Jørgen Johansen c Department of Oncology, Odense University Hospital, Odense, Denmark
  • Ruta Zukauskaite b Institute of Clinical Research, University of Southern Denmark, Odense, Denmark; c Department of Oncology, Odense University Hospital, Odense, Denmark
  • Jesper Grau Eriksen f Department of Oncology, Aarhus University Hospital, Aarhus N, Denmark; h Department of Oncology, Aalborg University Hospital, Aalborg, Denmark
  • Mohammad Farhadi g Department of Oncology, Zealand University Hospital, Naestved, Denmark
  • Maria Andersen h Department of Oncology, Aalborg University Hospital, Aalborg, Denmark
  • Christian Maare i Department of Oncology, University Hospital Herlev, Herlev, Denmark
  • Jens Overgaard j Department of Experimental Clinical Oncology, Aarhus University Hospital, Denmark
  • Cai Grau d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark
  • Jeppe Friborg d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark; e Department of Oncology, Rigshospitalet, University Hospital of Copenhagen, Copenhagen, Denmark
  • Christian Rønn Hansen a Laboratory of Radiation Physics, Odense University Hospital, Odense, Denmark;b Institute of Clinical Research, University of Southern Denmark, Odense, Denmark; d Danish Centre of Particle Therapy, Aarhus University Hospital, Aarhus, Denmark

DOI:

https://doi.org/10.1080/0284186X.2023.2256958

Keywords:

AI, contouring, organs at risk, head and neck cancer, proton treatment

Abstract

Background

In the Danish Head and Neck Cancer Group (DAHANCA) 35 trial, patients are selected for proton treatment based on simulated reductions of Normal Tissue Complication Probability (NTCP) for proton compared to photon treatment at the referring departments. After inclusion in the trial, immobilization, scanning, contouring and planning are repeated at the national proton centre. The new contours could result in reduced expected NTCP gain of the proton plan, resulting in a loss of validity in the selection process. The present study evaluates if contour consistency can be improved by having access to AI (Artificial Intelligence) based contours.

Materials and Methods

The 63 patients in the DAHANCA 35 pilot trial had a CT from the local DAHANCA centre and one from the proton centre. A nationally validated convolutional neural network, based on nnU-Net, was used to contour OARs on both scans for each patient. Using deformable image registration, local AI and oncologist contours were transferred to the proton centre scans for

Downloads

Download data is not yet available.

Downloads

Additional Files

Published

2023-11-02

How to Cite

Panduro Nielsen, C., Laugaard Lorenzen, E., Jensen, K., Sarup, N., Brink, C., Smulders, B., … Rønn Hansen, C. (2023). Consistency in contouring of organs at risk by artificial intelligence vs oncologists in head and neck cancer patients. Acta Oncologica, 62(11), 1418–1425. https://doi.org/10.1080/0284186X.2023.2256958

Issue

Vol. 62 No. 11 (2023): Acta Oncologica

Section

Articles