Dosiomics: Extracting 3D Spatial Features From Dose Distribution to Predict Incidence of Radiation Pneumonitis

Abstract

Radiation pneumonitis (RP) is one of the major toxicities of thoracic radiation therapy. RP incidence has been proven to be closely associated with the dosimetric factors and normal tissue control possibility (NTCP) factors. However, because these factors only utilize limited information of the dose distribution, the prediction abilities of these factors are modest. We adopted the dosiomics method for RP prediction. The dosiomics method first extracts spatial features of the dose distribution within ipsilateral, contralateral, and total lungs, and then uses these extracted features to construct prediction model via univariate and multivariate logistic regression (LR). The dosiomics method is validated using 70 non-small cell lung cancer (NSCLC) patients treated with volumetric modulated arc therapy (VMAT) radiotherapy. Dosimetric and NTCP factors based prediction models are also constructed to compare with the dosiomics features based prediction model. For the dosimetric, NTCP and dosiomics factors/features, the most significant single factors/features are the mean dose, parallel/serial (PS) NTCP and gray level co-occurrence matrix (GLCM) contrast of ipsilateral lung, respectively. And the area under curve (AUC) of univariate LR is 0.665, 0.710 and 0.709, respectively. The second significant factors are V 5 of contralateral lung, equivalent uniform dose (EUD) derived from PS NTCP of contralateral lung and the low gray level run emphasis of gray level run length matrix (GLRLM) of total lungs. The AUC of multivariate LR is improved to 0.676, 0.744, and 0.782, respectively. The results demonstrate that the univariate LR of dosiomics features has approximate predictive ability with NTCP factors, and the multivariate LR outperforms both the dosimetric and NTCP factors. In conclusion, the spatial features of dose distribution extracted by the dosiomics method effectively improves the prediction ability.

Performance of Multiparametric Functional Imaging and Texture Analysis in Predicting Synchronous Metastatic Disease in Pancreatic Ductal Adenocarcinoma Patients by Hybrid PET/MR: Initial Experience

“…GLRLM reflects the comprehensive information of the image grayscale with respect to direction, adjacent interval, and variation amplitude. GLRLM is a set of statistical feature extracted from medical images and applied in radiomics frequently (35)(36)(37). HGRE measures the distribution of sections of high intensity, and its value is expected to be large if the number of sections of high intensity is high.…”

Radiomics for radiation oncologists: are we ready to go?

“…Recently, "dosiomic" analysis has also emerged, as an extension of texture analysis but based on the dose distribution which is planned. 66,83,84 Dosiomic parameters could be interestingly combined to other variables, e.g. clinical factors or radiomic parameters, for the construction of more accurate toxicity prediction models.…”

“…clinical factors or radiomic parameters, for the construction of more accurate toxicity prediction models. It was applied for the prediction of late urinary and digestive toxicity in prostate RT, 83 radiation pneumonitis in thoracic RT 84 and xerostomia in HNC RT. 66 As an example of all this, Scalco et al 77 were able to show significant textural changes with RT (e.g.…”

Clinical and epidemiological observations on individual radiation sensitivity and susceptibility

“…To help physicians in the treatment decision, equivalent uniform dose (EUD) (Niemierko 1997) and normal tissue complication probability (NTCP) (Lyman 1985;Lyman and Wolbarst 1987;Kutcher et al 1991) models were developed and are regularly used (e.g. Henr ıquez and Castrill on 2011; Chaikh et al 2018;Liang et al 2019). However, the algorithmic calculation is not incorporated in the treatment planning systems.…”