Random forest algorithm for precision dose prediction in brain cancer radiotherapy

Luqyana Adha Azwat; Prawito Prajitno; Dwi Seno Kuncoro Sihono; Dewa Ngurah Yudhi Persada

doi:10.31258/jkfi.21.2.%p

Random forest algorithm for precision dose prediction in brain cancer radiotherapy

Luqyana Adha Azwat, Prawito Prajitno, Dwi Seno Kuncoro Sihono, Dewa Ngurah Yudhi Persada

Abstract

Improving dose optimization during clinical planning using the Treatment Planning System (TPS) for radiotherapy patients is crucial, yet executing this process can be time-consuming and reliant on the expertise of medical physicists. This research focuses on dose prediction employing machine learning for the Planning Target Volume (PTV) and Organ at Risk (OAR) in cases of brain cancer treated with the Volumetric Modulated Arc Therapy (VMAT) planning technique. Utilizing DICOM planning data from brain cancer cases, this study utilizes extracted radiomic and dosiomic values as inputs and outputs for the research, employing a random forest algorithm model. Evaluation of the model reveals its effectiveness in predicting doses for PTV in brain cancer and OAR, with predicted Homogeneity Index (HI) and Conformity Index (CI) values of 0.14±0.04 and 0.95±0.01, respectively, compared to clinical values of 0.14±0.13 and 0.94±0.13. Thus, the random forest model demonstrates proficiency in predicting doses for brain cancer PTV and OAR, with an Mean Square Error (MSE) value of 0.017.

Keywords

Mean square error; OAR; PTV; p-value; random forest

References

H. Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and

Mortality Worldwide for 36 Cancers in 185 Countries,” CA Cancer J Clin, vol. 71, no. 3, pp.

–249, May 2021, doi: 10.3322/CAAC.21660.

M. Kurniawan, A. R. Ganiem, and W. Wiratman, “Pedoman Praktik Klinis Neurologi 2023,”

W. F. A. R. Verbakel, J. P. Cuijpers, D. Hoffmans, M. Bieker, B. J. Slotman, and S. Senan, “Volumetric Intensity-Modulated Arc Therapy Vs. Conventional IMRT in Head-and-Neck Cancer: A Comparative Planning and Dosimetric Study,” Int J Radiat Oncol Biol Phys, vol. 74, no. 1, pp. 252–259, May 2009, doi: 10.1016/j.ijrobp.2008.12.033.

M. Van Herk, P. Remeijer, C. Rasch, and J. V. Lebesque, “The probability of correct target dosage: dose-population histograms for deriving treatment margins in radiotherapy,” International Journal of Radiation Oncology*Biology*Physics, vol. 47, no. 4, pp. 1121–1135, Jul. 2000, doi: 10.1016/S0360-3016(00)00518-6.

M. Savargiv, B. Masoumi, and M. R. Keyvanpour, “A new random forest algorithm based on learning automata,” Comput Intell Neurosci, vol. 2021, 2021, doi: 10.1155/2021/5572781.

A. D. Purwanto, K. Wikantika, A. Deliar, and S. Darmawan, “Decision Tree and Random Forest Classification Algorithms for Mangrove Forest Mapping in Sembilang National Park, Indonesia,” Remote Sens (Basel), vol. 15, no. 1, Jan. 2023, doi: 10.3390/rs15010016.

Y. Song et al., “Dose prediction using a deep neural network for accelerated planning of rectal cancer radiotherapy,” Radiother Oncol, vol. 149, pp. 111–116, Aug. 2020, doi:

1016/J.RADONC.2020.05.005.

H. G. Menzel, “The international commission on radiation units and measurements,” J ICRU, vol. 10, no. 1, pp. 1–106, 2010, doi: 10.1093/jicru/ndq001.

I. Commission on Radiological Units, “REPORT OF THE INTERNATIONAL COMMISSION ON RADIOLOGICAL UNITS AND MEASUREMENTS (ICRU) 1956 Handbook 62 United States Department of Commerce National Bureau of Standards.”

DOI: http://dx.doi.org/10.31258/jkfi.21.2.%25p