ModalityConverter - AI-based sCT evaluation now available

[ciro.raggio]

The ModalityConverter extension for 3D Slicer has been extended with a new contribution from @PaoloZaffino

A dedicated module named “Synthetic Image Quality Assessment” has been added, along with a new model for slice-wise evaluation of synthetic CT. This enables 2D MAE prediction directly inside 3D Slicer, based on the following study:

Zaffino P. et al., 𝘛𝘰𝘸𝘢𝘳𝘥 𝘊𝘭𝘰𝘴𝘪𝘯𝘨 𝘵𝘩𝘦 𝘓𝘰𝘰𝘱 𝘪𝘯 𝘐𝘮𝘢𝘨𝘦-𝘵𝘰-𝘐𝘮𝘢𝘨𝘦 𝘊𝘰𝘯𝘷𝘦𝘳𝘴𝘪𝘰𝘯 𝘪𝘯 𝘙𝘢𝘥𝘪𝘰𝘵𝘩𝘦𝘳𝘢𝘱𝘺: 𝘈 𝘘𝘶𝘢𝘭𝘪𝘵𝘺 𝘊𝘰𝘯𝘵𝘳𝘰𝘭 𝘛𝘰𝘰𝘭 𝘵𝘰 𝘗𝘳𝘦𝘥𝘪𝘤𝘵 𝘚𝘺𝘯𝘵𝘩𝘦𝘵𝘪𝘤 𝘊𝘰𝘮𝘱𝘶𝘵𝘦𝘥 𝘛𝘰𝘮𝘰𝘨𝘳𝘢𝘱𝘩𝘺 𝘏𝘰𝘶𝘯𝘴𝘧𝘪𝘦𝘭𝘥 𝘜𝘯𝘪𝘵 𝘈𝘤𝘤𝘶𝘳𝘢𝘤𝘺. J. Imaging, 2024, https://doi.org/10.3390/jimaging10120316

We are looking forward to community contributions — if you would like to integrate new models for other modalities, please propose them via the GitHub repository!

More details on GitHub: GitHub - ciroraggio/SlicerModalityConverter: SlicerModalityConverter is an open-source 3D Slicer extension designed for medical image-to-image (I2I) translation. The ModalityConverter module integrates multiple deep learning models trained for different kind of I2I translation, providing a user-friendly interface.