Quantification of liver-lung shunt fraction on 3D SPECT/CT images for selective internal radiation therapy of liver cancer using CNN-based segmentations and non-rigid registration
Published in Computer Methods and Programs in Biomedicine, 2023
This paper presents a pipeline for (semi)automatic quantification of liver-lung shunt fraction (LSF) in non-contrast-enhanced CT (nCECT) images. We utilize the Elastix registration technique to deform the liver in the CECT image to the shape of that liver in the nCECT image, then apply a 3D nn-UNet model to segment the deformed liver in CECT. This integrated approach enables reliable liver segmentation and LSF quantification for selective internal radiation therapy (SIRT) planning.
Recommended citation: Manh Ha Luu, Hong Son Mai, Xuan Loc Pham, Le Quoc Anh, Quoc Khanh Le, Theo Van Walsum, Ngoc Ha Le, Daniel Franklin, Vu Ha Le, Adriaan Moelker, et al. "Quantification of liver-Lung shunt fraction on 3D SPECT/CT images for selective internal radiation therapy of liver cancer using CNN-based segmentations and non-rigid registration." Computer Methods and Programs in Biomedicine, 233:107453, 2023.
Download Paper