Dataset Information

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics.

ABSTRACT: In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients' risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS). Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS. ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification. T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.

SUBMITTER: Peeken JC

PROVIDER: S-EPMC8073388 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics.

Peeken Jan C JC Neumann Jan J Asadpour Rebecca R Leonhardt Yannik Y Moreira Joao R JR Hippe Daniel S DS Klymenko Olena O Foreman Sarah C SC von Schacky Claudio E CE Spraker Matthew B MB Schaub Stephanie K SK Dapper Hendrik H Knebel Carolin C Mayr Nina A NA Woodruff Henry C HC Lambin Philippe P Nyflot Matthew J MJ Gersing Alexandra S AS Combs Stephanie E SE

Cancers 20210416 8

<h4>Background</h4>In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients' risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS).<h4>Methods</h4>Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FS ...[more]

PMID: 33923697

Similar Datasets

Project description:High-grade soft-tissue sarcoma (STS) is a highly malignant neoplasm with a poor overall prognosis. Numerous prognostic factors determine tumor progression and patient outcomes. Various immune-associated cells identified in the tumor microenvironment have important roles in various tumor types. The present study was performed to evaluate the expression of immune-associated genes and to elucidate the association between these genes and the prognosis in high-grade STS. A total of 12 formalin-fixed, paraffin-embedded tissue samples of high-grade STS were subjected to gene expression analysis using the NanoString nCounter® System and another 35 samples were used for immunohistochemistry. For comparative analysis, the patients were divided into two groups according to overall survival (OS). The expression levels of 770 genes were first analyzed using the nCounter® PanCancer Immune Profiling Panel. Immunohistochemistry was then performed for the most significantly altered genes. Subsequently, the association between gene expression and prognosis of high-grade STS was evaluated. Of the 770 immune-associated genes analyzed, several genes were identified as being differentially expressed between the two groups. Based on gene expression levels and fold change, 13 representative genes were identified; 7 of the 13 candidate genes (C3, CD36, DOCK9, FCER2, FOS, HLA-DRB4 and NCAM1) were significantly overexpressed in the poor prognosis group, while the other 6 immune-associated genes (BIRC5, DUSP4, FOXP3, HLA-DQA1, HLA-DQB1 and LAG3) were increased in the good prognosis group. By immunohistochemistry, the expression of the 13 immune-associated genes was confirmed to be significantly different between the two groups. Expression of HLA-DQA1, HLA-DQB1 and HLA-DRB4 was observed in 74.3, 34.3 and 48.6% of tumors, respectively. HLA-DQA1 and HLA-DQB1 were significantly decreased, whereas HLA-DRB4 was significantly increased in the poor prognosis group. Of note, expression of HLA-DQA1 was associated with a significantly longer OS (P=0.028). In conclusion, HLA-DQA1 expression was significantly associated with long-term survival and may therefore be an immune biomarker for good prognosis in high-grade STS.

Dataset Information

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics.

Publications

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets