Portal de Periódicos da CAPES

Multi-center external validation of an automated method segmenting and differentiating atypical lipomatous tumors from lipomas using radiomics and deep-learning on MRI

2024; Elsevier BV; Volume: 76; Linguagem: Inglês

10.1016/j.eclinm.2024.102802

2589-5370

Douwe J. Spaanderman, Stefanie Hakkesteegt, David Hanff, A R W Schut, Loes M. Schiphouwer, Melissa Vos, Christina Messiou, Simon Doran, Robin L. Jones, Andrew Hayes, Lorenzo Nardo, Yasser G. Abdelhafez, Atef Moawad, Khaled M. Elsayes, S. Lee, T.M. Link, Wiro J. Niessen, Geert J.L.H. van Leenders, Jacob J. Visser, Stefan Klein, Dirk J. Grünhagen, Cornelis Verhoef, Martijn P. A. Starmans,

Soft tissue tumor case studies

As differentiating between lipomas and atypical lipomatous tumors (ALTs) based on imaging is challenging and requires biopsies, radiomics has been proposed to aid the diagnosis. This study aimed to externally and prospectively validate a radiomics model differentiating between lipomas and ALTs on MRI in three large, multi-center cohorts, and extend it with automatic and minimally interactive segmentation methods to increase clinical feasibility.