2026-05-31T03:49:16Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/460312026-03-14T00:45:43Zcom_10630_2254col_10630_37953

00925njm 22002777a 4500 dc Jiménez-Partinen, Ariadna author López-Rubio, Ezequiel author Nagib-Raya, Fátima author Palomo-Ferrer, Esteban José author Luque-Baena, Rafael Marcos author 2026-05 In this work, a comprehensive analysis of the impact of intensity value regularization methods on 3D MRI segmentation for three neurological disorders: glioblastoma, multiple sclerosis, and epilepsy, is presented. The experiments were conducted through three architectures: nnU-Net (convolutional neural network), WNet (hybrid combining convolutional and transformer elements), and Primus (transformer-based), considering both FLAIR and T1-weighted images, as well as FLAIR-only scenarios. The statistical analysis conducted underscores the crucial role of intensity regularization in the performance. The results indicate that among the intensity regularization methods tested in this study, KDE, White-stripe, and Z-score standardizations proved to be particularly effective. Furthermore, nnU-Net is the most robust architecture against intensity variability, with small improvements of around 3%. Meanwhile, methods incorporating TF elements are more sensitive to these variations. WNet demonstrates slightly greater gains, around 6%. While Primus can be less stable and underperform compared to nnU-Net and WNet in most cases; nonetheless, it remains a promising and competitive option. Additionally, it has been demonstrated that adding an extra channel does not necessarily guarantee improved performance, while also increasing computational cost. Jiménez-Partinen, Ariadna, López-Rubio, Ezequiel, Nagib-Raya, Fátima, Palomo, Esteban J., Luque-Baena, Rafael M. (2026). Preprocessing strategies and their influence on deep learning-driven MRI segmentation, Pattern Recognition Letters, Volume 203, 2026, Pages 111-118, ISSN 0167-8655, https://doi.org/10.1016/j.patrec.2026.02.030 https://hdl.handle.net/10630/46031 10.1016/j.patrec.2026.02.030 Imágenes por resonancia magnética Esclerosis múltiple Epilepsia Preprocessing strategies and their influence on deep learning-driven MRI segmentation