Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 1
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Towards contrast-and pathology-agnostic clinical fetal brain MRI segmentation using SynthSeg

  • Shang, Ziyao
  • Kaandorp, Misha
  • Payette, Kelly
  • Licandro, Roxane
  • Langs, Georg
  • Aviles Verdera, Jordina
  • Hutter, Jana
  • Menze, Bjoern
  • Kasprian, Gregor
  • Cuadra, Meritxell Bach
  • Jakab, Andras
  • Marina
[EN] Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep Learning providing an automated alternative for this otherwise tedious manual process. However, segmentation performances of Convolutional Neural Networks often suffer from domain shift, where the network fails when applied to subjects that deviate from the distribution with which it is trained on. In this work, we aim to train networks capable of automatically segmenting fetal brain MRIs with a wide range of domain shifts pertaining to differences in subject physiology and acquisition environments, in particular shape-based differences commonly observed in pathological cases. We introduce a novel data-driven train-time sampling strategy that seeks to fully exploit the diversity of a given training dataset to enhance the domain generalizability of the trained networks. We adapted our sampler, together with other existing data augmentation techniques, to the SynthSeg framework, a generator that utilizes domain randomization to generate diverse training data. We ran thorough experimentations and ablation studies on a wide range of training/testing data to test the validity of the approaches. Our networks achieved notable improvements in the segmentation quality on testing subjects with intense anatomical abnormalities (p < 1e-4), though at the cost of a slighter decrease in performance in cases with fewer abnormalities. Our work also lays the foundation for future works on creating and adapting data-driven sampling strategies for other training pipelines., This project was supported by the Swiss National Science Foundation, grant Nr. IZKSZ3_218590 and 10003124, the Adaptive Brain Circuits in Development and Learning Project, University Research Priority Program of the University of Zurich; by the Vontobel Foundation; by the Anna Muller Grocholski Foundation and the Prof. Max Cloetta Foundation.The dHCP data were provided by the developing Human Connectome Project, KCL-Imperial-Oxford Consortium funded by the European Research Council under the European Union Seventh Framework Programme (FP/20072013)/ERC Grant Agreement no [319456]. We are grateful to the families who generously supported this trial.We acknowledge access to the facilities and expertise of the CIBM Center for Biomedical Imaging, a Swiss research center of excellence founded and supported by CHUV, UNIL, EPFL, UNIGE and HUG. This work is supported by Era-net Neuron MULTIFACT - Swiss National Science Foundation (SNSF) grant 31NE30_203977 and SNSF grants 182602 and 215641.The low field KCL data was possible through funding from the UKRI [MR/T018119/1], DFG [502024488] and ERC [101165242]. NDA study DOI: 10.15154/5tzp-xm67.