277719 20250406001045.0 10.1162/imag_a_00446 doi pmid:40109899 pmid pmc:PMC11917724 pmc altmetric:173808095 altmetric DZNE-2025-00445 English 610 Pollak, Clemens P:(DE-2719)2814183 0 First author dzne FastSurfer-LIT: Lesion inpainting tool for whole-brain MRI segmentation with tumors, cavities, and abnormalities. Cambridge, MA 2025 MIT Press article DRIVER Output Types/Journal article DataCite Journal Article journal journal PUB:(DE-HGF)16 1743584083_9485 PUB:(DE-HGF) ARTICLE BibTeX JOURNAL_ARTICLE ORCID Journal Article 0 EndNote Resection cavities, tumors, and other lesions can fundamentally alter brain structure and present as abnormalities in brain MRI. Specifically, quantifying subtle neuroanatomical changes in other, not directly affected regions of the brain is essential to assess the impact of tumors, surgery, chemo/radiotherapy, or drug treatments. However, only a limited number of solutions address this important task, while many standard analysis pipelines simply do not support abnormal brain images at all. In this paper, we present a method to perform sensitive neuroanatomical analysis of healthy brain regions in the presence of large lesions and cavities. Our approach called 'FastSurfer Lesion Inpainting Tool' (FastSurfer-LIT) leverages the recently emerged Denoising Diffusion Probabilistic Models (DDPM) to fill lesion areas with healthy tissue that matches and extends the surrounding tissue. This enables subsequent processing with established MRI analysis methods such as the calculation of adjusted volume and surface measurements using FastSurfer or FreeSurfer. FastSurfer-LIT significantly outperforms previously proposed solutions on a large dataset of simulated brain tumors (N = 100) and synthetic multiple sclerosis lesions (N = 39) with improved Dice and Hausdorff measures, and also on a highly heterogeneous dataset with lesions and cavities in a manual assessment (N = 100). Finally, we demonstrate increased reliability to reproduce pre-operative cortical thickness estimates from corresponding post-operative temporo-mesial resection surgery MRIs. The method is publicly available at https://github.com/Deep-MI/LIT and will be integrated into the FastSurfer toolbox. 354 - Disease Prevention and Healthy Aging (POF4-354) G:(DE-HGF)POF4-354 POF4-354 POF IV 0 Dataset connected to CrossRef, PubMed, , Journals: pub.dzne.de brain filling Other inpainting Other lesion Other segmentation Other software Other tumor Other Kügler, David P:(DE-2719)2814290 1 dzne Bauer, Tobias P:(DE-2719)9002598 2 dzne Rüber, Theodor 3 Reuter, Martin P:(DE-2719)2812134 4 Last author dzne 10.1162/imag_a_00446 Vol. 3, p. imag_a_00446 PERI:(DE-600)3167925-0 imag_a_00446 Imaging neuroscience 3 2025 2837-6056 OpenAccess http://pub.dzne.de/record/277719/files/DZNE-2025-00445.pdf OpenAccess pdfa http://pub.dzne.de/record/277719/files/DZNE-2025-00445.pdf?subformat=pdfa oai:pub.dzne.de:277719 openaire open_access VDB driver dnbdelivery Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 0 P:(DE-2719)2814183 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 1 P:(DE-2719)2814290 External Institute I:(DE-HGF)0 Extern 2 P:(DE-2719)9002598 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 4 P:(DE-2719)2812134 DE-HGF Gesundheit Neurodegenerative Diseases G:(DE-HGF)POF4-350 G:(DE-HGF)POF4-354 G:(DE-HGF)POF4 G:(DE-HGF)POF4-300 G:(DE-HGF)POF Disease Prevention and Healthy Aging 0 2025 Creative Commons Attribution CC BY 4.0 LIC:(DE-HGF)CCBY4 HGFVOC DBCoverage StatID:(DE-HGF)0501 StatID DOAJ Seal 2024-09-26T09:40:26Z DBCoverage StatID:(DE-HGF)0500 StatID DOAJ 2024-09-26T09:40:26Z OpenAccess StatID:(DE-HGF)0510 StatID Peer Review StatID:(DE-HGF)0030 StatID DOAJ : Anonymous peer review 2024-09-26T09:40:26Z Article Processing Charges StatID:(DE-HGF)0561 StatID 2025-01-02 DBCoverage StatID:(DE-HGF)0300 StatID Medline 2025-01-02 Fees StatID:(DE-HGF)0700 StatID 2025-01-02 I:(DE-2719)1040310 AG Reuter Artificial Intelligence in Medicine 0 journal VDB UNRESTRICTED I:(DE-2719)1040310 FullTexts