ScatterNet: A convolutional neural network for cone‐beam CT intensity correction

Abstract

Using a deep convolutional neural network for CBCT intensity correction was shown to be feasible in the pelvic region for the first time. Dose calculation accuracy on CBCT <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msub><mml:mrow></mml:mrow> <mml:mi>ScatterNet</mml:mi></mml:msub> </mml:math> was high for VMAT, but unsatisfactory for IMPT. With respect to the reference technique (CBCT <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msub><mml:mrow></mml:mrow> <mml:mi>cor</mml:mi></mml:msub> </mml:math> ), the neural network enabled a considerable increase in speed for intensity correction and might eventually allow for on-the-fly shading correction during CBCT acquisition.