Evaluating principal component analysis models for representing anatomical changes in head and neck radiotherapy

Perez, R. Argota; Robbins, Jennifer; Green, Andrew; Herk, Marcel van; Korreman, S.; Vásquez-Osorio, Eliana

doi:10.1016/j.phro.2022.04.002

Cited by 4 publications

(1 citation statement)

References 24 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Statistical population models have also been proposed to estimate the anatomical changes of cancer patients during radiotherapy (Ehrhardt et al 2010, Budiarto et al 2011, Szeto 2017, Rigaud 2019, Argota-Perez 2022, Zhang 2022. Most methods do not differentiate between systematic progressive and random day to day changes, so they cannot model the patterns in the systematic changes over treatment.…”

Section: Introductionmentioning

confidence: 99%

Modelling systematic anatomical uncertainties of head and neck cancer patients during fractionated radiotherapy treatment

Nikou,

Thompson,

Nisbet

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Head and neck cancer patients experience systematic anatomical changes as well as random day to day anatomical changes during fractionated radiotherapy treatment. Modelling the expected systematic anatomical changes could aid in creating treatment plans which are more robust against such changes. A patient specific (SM) and population average (AM) model are presented which are able to capture the systematic anatomical changes of some head and neck cancer patients over the course of radiotherapy treatment. Inter- patient correspondence aligned all patients to a model space. Intra- patient correspondence between each planning CT scan and on treatment cone beam CT scans was obtained using diffeomorphic deformable image registration. The stationary velocity fields were then used to develop B-Spline based SMs and AMs. The models were evaluated geometrically and dosimetrically. A leave-one-out method was used to compare the training and testing accuracy of the models. Both SMs and AMs were able to capture systematic changes. The average surface distance between the registration propagated contours and the contours generated by the SM was less than 2mm, showing that the SM are able to capture the anatomical changes which a patient experiences during the course of radiotherapy. The testing accuracy was lower than the training accuracy of the SM, suggesting that the model overfits to the limited data available and therefore also captures some of the random day to day changes. For most patients the AMs were a better estimate of the anatomical changes than assuming there were no changes, but the AMs could not capture the variability in the anatomical changes seen in all patients. No difference was seen in the training and testing accuracy of the AMs. These observations were highlighted in both the geometric and dosimetric evaluations and comparisons. The large patient variability highlights the need for more complex, capable population models.

show abstract