Unsupervised machine learning based clustering and treatment planning strategy for reducing radiation dermatitis in IMPT of head and neck cancer

Abstract Radiation dermatitis (RD) is a major concern in intensity modulated proton therapy (IMPT) for head and neck cancer (HNC) despite its demonstrated superiority over contemporary photon radiotherapy. In this study, dose surface histogram (DSH) data extracted from forty-four patients of HNC treated with IMPT was used to predict the normal tissue complication probability (NTCP) of skin. Grades of NTCP-skin were clustered using the K-means clustering unsupervised machine learning algorithm (MLA). A new skin-sparing IMPT (IMPT-SS) planning strategy was developed with three major changes and prospectively implemented in twenty HNC patients. Across skin surfaces exposed from 10 (S10) to 70 (S70) GyRBE, the skin's NTCP demonstrated the strongest associations with S50 and S40 GyRBE (0.95 and 0.94). The increase in the NTCP of skin per unit GyRBE is 0.568 for skin exposed to 50 GyRBE as compared to 0.418 for 40 GyRBE. Three distinct clusters were formed, with 41% of patients in G1, 32% in G2, and 27% in G3. The average (±SD) generalised equivalent uniform dose (gEUD) for G1, G2, and G3 clusters was 26.54±6.75, 38.73±1.80, and 45.67±2.20 GyRBE. The corresponding NTCP (%) were 4.97±5.12, 48.12±12.72 and 87.28±7.73 respectively. In comparison to IMPT, new IMPT-SS plans significantly (p<0.01) reduced SX GyRBE, gEUD, and associated NTCP-skin while maintaining identical dose volume indices for target and other organs at risk (OARs). The mean NTCP-skin value for IMPT-SS was 37% lower than that of IMPT. The dose to skin in patients treated prospectively for HNC was reduced by including gEUD for an acceptable radiation dermatitis determined from the local patient population using an unsupervised MLA in the spot map optimization of a new IMPT planning technique. However, the clinical finding of acute skin toxicity must also be related to the observed reduction in skin dose.