A Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data
This toolkit addresses data privacy and computational efficiency issues for researchers and practitioners using self-supervised learning in 3D medical imaging, though it is incremental as it builds on existing segmentation methods.
The study tackled the problem of preprocessing 3D medical imaging data for self-supervised learning by developing an open-source toolkit that segments foreground and anonymization areas, achieving mean Dice scores over 98.5 for anonymization and over 99.5 for foreground segmentation.
This study presents an open-source toolkit to address critical challenges in preprocessing data for self-supervised learning (SSL) for 3D medical imaging, focusing on data privacy and computational efficiency. The toolkit comprises two main components: a segmentation network that delineates foreground regions to optimize data sampling and thus reduce training time, and a segmentation network that identifies anonymized regions, preventing erroneous supervision in reconstruction-based SSL methods. Experimental results demonstrate high robustness, with mean Dice scores exceeding 98.5 across all anonymization methods and surpassing 99.5 for foreground segmentation tasks, highlighting the efficacy of the toolkit in supporting SSL applications in 3D medical imaging for both CT and MRI images. The weights and code is available at https://github.com/MIC-DKFZ/Foreground-and-Anonymization-Area-Segmentation.