Med Phys
-
Volumetric pancreas segmentation can be used in the diagnosis of pancreatic diseases, the research about diabetes and surgical planning. Since manual delineation is time-consuming and laborious, we develop a deep learning-based framework for automatic pancreas segmentation in three dimensional (3D) medical images. ⋯ We proposed an automatic pancreas segmentation framework and validate in an open dataset. It is found that 2.5D network benefits from multi-level slice interaction and suitable self-supervised learning method for pre-training can boost the performance of neural network. This technique could provide new image findings for the routine diagnosis of pancreatic disease.
-
Technical Note: Optimization of quantitative susceptibility mapping by streaking artifact detection.
In quantitative susceptibility mapping (QSM) using magnetic resonance imaging, image reconstruction methods usually aim at suppressing streaking artifacts. In this study, a streaking detection method is proposed for evaluating and optimizing quantitative susceptibility maps. ⋯ Streaking detection enables direct visualization of streaking patterns in tissue susceptibility maps. It can be applied both for evaluating QSM reconstruction quality and for comparing different reconstruction algorithms. Furthermore, streaking detection can be incorporated into an optimization process of QSM reconstruction. Therefore, we conclude that the proposed method will add value to reconstruction of QSM.