Medizinische Universität Graz - Research portal
Selected Publication:
SHR Neuro Cancer Cardio Lipid Metab Microb
Steiner, J; Bloice, M; Igrec, J; Liegl-Atzwanger, B; Leithner, A; Fuchsjäger, M; Urschler, M.
MRI-based deep learning and radiomics pipeline for myxoid liposarcoma: a feasibility study in a rare sarcoma.
Sci Rep. 2025; 15(1): 44104
Doi: 10.1038/s41598-025-27217-0
[OPEN ACCESS]
Web of Science
PubMed
FullText
FullText_MUG
- Leading authors Med Uni Graz
- Bloice Marcus
- Igrec Jasminka
- Steiner Jakob
- Co-authors Med Uni Graz
- Fuchsjäger Michael
- Leithner Andreas
- Liegl-Atzwanger Bernadette
- Urschler Martin
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- Myxoid liposarcoma (MLPS) is a rare soft tissue sarcoma characterized by histopathological variability, which poses challenges for accurate grading and treatment planning. This study evaluated the feasibility of an automated MRI-based pipeline that combines deep learning and radiomics for non-invasive tumor assessment. In a retrospective multicenter cohort of 48 patients with histologically confirmed MLPS, a 3D U-Net convolutional neural network was trained to perform automatic tumor segmentation on axial T2-weighted MR images. Radiomics features were subsequently extracted from the segmented volumes and used to train a Random Forest classifier for predicting tumor grade, defined by centralized histopathological review according to WHO criteria. The segmentation model achieved a median Dice similarity coefficient of 0.892. The radiomics-based grading classifier reached a mean area under the curve of 0.745, with an F1-score of 0.729 and a balanced accuracy of 0.723 in distinguishing high-grade from low-grade tumors. Most classification errors occurred in borderline or histologically heterogeneous cases. These findings suggest that automated segmentation and radiomics analysis may offer valuable support for MLPS grading and complement histopathology, particularly in diagnostically complex cases. Further prospective validation in larger cohorts is warranted.
- Find related publications in this database (using NLM MeSH Indexing)
- Humans - administration & dosage
- Liposarcoma, Myxoid - diagnostic imaging, pathology
- Deep Learning - administration & dosage
- Magnetic Resonance Imaging - methods
- Feasibility Studies - administration & dosage
- Male - administration & dosage
- Female - administration & dosage
- Middle Aged - administration & dosage
- Retrospective Studies - administration & dosage
- Aged - administration & dosage
- Adult - administration & dosage
- Neoplasm Grading - administration & dosage
- Radiomics - administration & dosage
- Find related publications in this database (Keywords)
- Liposarcoma, myxoid
- Sarcoma
- Neoplasm grading
- Magnetic resonance imaging
- Deep learning