Poster + Paper
3 April 2023 Can a single image processing algorithm work equally well across all phases of DCE-MRI
Author Affiliations +
Conference Poster
Abstract
Image segmentation and registration are said to be challenging when applied to dynamic contrast enhanced MRI sequences (DCE-MRI). The contrast agent causes rapid changes in intensity in the region of interest and elsewhere, which can lead to false positive predictions for segmentation tasks and confound the image registration similarity metric. While it is widely assumed that contrast changes increase the difficulty of these tasks, to our knowledge no work has quantified these effects. In this paper we examine the effect of training with different ratios of contrast enhanced (CE) data on two popular tasks: segmentation with nnU-Net and Mask R-CNN and registration using VoxelMorph and VTN. We experimented further by strategically using the available datasets through pretraining and fine tuning with different splits of data. We found that to create a generalisable model, pretraining with CE data and fine tuning with non-CE data gave the best result. This interesting find could be expanded to other deep learning based image processing tasks with DCE-MRI and provide significant improvements to the models’ performance.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Adam G. Tattersall, Keith A. Goatman, Lucy E. Kershaw, Scott I. K. Semple, and Sonia Dahdouh "Can a single image processing algorithm work equally well across all phases of DCE-MRI", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 124642X (3 April 2023); https://doi.org/10.1117/12.2654228
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Kidney

Image registration

Prostate

Image processing

Magnetic resonance imaging

Contrast agents

Back to Top