Unsupervised Skull Segmentation via Contrastive MR-to-CT Modality Translation

Kamil Kwarciak, Mateusz Daniol, Daria Hemmerling, Marek Wodzinski; Proceedings of the Asian Conference on Computer Vision (ACCV) Workshops, 2024, pp. 160-174

The skull segmentation from CT scans can be seen as an already solved problem. However, in MR this task has a significantly greater complexity due to the presence of soft tissues rather than bones. Capturing the bone structures from MR images of the head, where the main visualization objective is the brain, is very demanding. The attempts that make use of skull stripping seem to not be well suited for this task and fail to work in many cases. On the other hand, supervised approaches require costly and time-consuming skull annotations. To overcome the difficulties we propose a fully unsupervised approach, where we do not perform the segmentation directly on MR images, but we rather perform a synthetic CT data generation via MR-to-CT translation and perform the segmentation there. We claim that translating the process to the CT modality is essential, as it significantly simplifies the overall procedure by transforming the complex segmentation in MR into a more straightforward segmentation in CT.We address many issues associated with unsupervised skull segmentation including the unpaired nature of MR and CT datasets (contrastive learning), low resolution and poor quality (super-resolution), and generalization capabilities. We demonstrate the effectiveness of our methodology through a quantitative analysis using Dice and Surface Dice metrics on the validation dataset, as well as on the test set to highlight its adaptability to new datasets. The research has a significant value for downstream tasks requiring skull segmentation from MR volumes such as craniectomy or surgery planning and can be seen as an important step towards the utilization of synthetic data in medical imaging.