Buch, Englisch, 133 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 236 g
Second MICCAI Challenge, LISA 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 27, 2025, Proceedings
Buch, Englisch, 133 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 236 g
Reihe: Lecture Notes in Computer Science
ISBN: 978-3-032-14416-4
Verlag: Springer
This open access book constitutes the proceedings of the LISA 2025 Challenge, held in conjunction with MICCAI 2025 in Daejeon, South Korea, during September 27, 2025.
The LISA Challenge serves as a benchmarking platform for developing evaluating automatic image analysis and machine learning algorithms.
The 11 full papers included in the book were carefully reviewed and selected from 14 final submissions.The papers are organized in topical sections as follows: Task 1 - Automatic Ultra-Low Field MR Image Quality Assessment; Task 2b - Automatic Basal Ganglia Segmentation from Ultra-Low Field MRI; Tasks 2a and 2b - Automatic Hippocampal and Basal Ganglia Segmentation form Ultra-Low Field MRI; and Tasks 1, 2a and 2b Combined.
Zielgruppe
Research
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
.- Task 1 - Automatic Ultra-Low Field MR Image Quality Assessment
.- BRIQA: Balanced Reweighting in Image Quality Assessment of Pediatric Brain MRI.
.- Robust Multi-Label Classification of MRI Artifacts in Low-Field Neonatal Brain Imaging via View-Conditional Dual Task Learning.
.- Task 2b - Automatic Basal Ganglia Segmentation from Ultra-Low Field MRI
.- Towards Robust Basal Ganglia Segmentation in Ultra-Low-Field Pediatric MRI via an Optimized MS-TCNet.
.- Tasks 2a and 2b - Automatic Hippocampal and Basal Ganglia Segmentation form Ultra-Low Field MRI
.- Segmenting Brain Regions in Low Field Pediatric Brain MR Images using (symmetric) nnU-Net ResEnc.
.- Segmenting infant brains across magnetic fields: Domain randomization and annotation curation in ultra-low field MRI.
.- Enforcing Anatomical Symmetry with Euclidean Distance Transforms for Low-Field MRI Bilateral Structure Segmentation.
.- Coordinate Transformations Make Segmentation Models More Data-Efficient.
.- Atlas-Augmented Semantic Segmentation for Robust Ultra-Low-Field Pediatric Brain Imaging.
.- Automated Pediatric Brain Hippocampal and Basal Ganglia Segmentation in Ultra-Low Field Magnetic Resonance Images.
.- Tasks 1, 2a and 2b Combined
.- Application of Vision Transformers to Multi-Task Learning in the LISA 2025 MRI Challenge.
.- Automatic Quality Assurance and Subcortical Brain Segmentation in Pediatric Ultra-Low-Field MRI: Exploring Ordinal Learning and Foundation Model Adaptation.
