Introduction: STS are mostly prognosticated through nomograms relying on age, size, histotype and grade. Radiomics approaches, complemented with deep-learning, deep-radiomics and gene-expression profiling, could help understanding the bridge between STS radiophenotypes and molecular features and provide more efficient prognostic tools. Our goals were to investigate correlations between imaging and transcriptomics patterns, and to develop supervised prognostic models for STS patients.

Methods: We included all consecutive adult patients with newly-diagnosed locally-advanced STS managed at our sarcoma reference center between 2008 and 2020, with contrast-enhanced baseline MRI. After MRI dataset homogenization, we reduced the dimensions of the MRI data space by extracting 138 radiomics features (RFs) and 1024 deep-RFs with computational approach and autoencoder neural networks. Patient RNA was extracted from untreated samples. Following transcriptomic sequence analysis, gene expression levels for each patient were calculated. Complexity Index in Sarcoma (CINSARC) signature was extracted. Unsupervised classifications of patients based on radiomics, deep-radiomics and transcriptomics datasets were built using consensus hierarchical clustering. Differential Gene Expression and oncogenetic pathways analyses were performed. Associations between the 3 classifications, CINSARC, grade, histotypes and SARCULATOR were explored, as well as their prognostic value. The main outcome was the metastatic-relapse free survival (MFS). The SARCULATOR nomogram and prognostic semantic-radiological features were extracted for benchmarking and understanding models outputs.

Results: 220 patients were included (111 men, median age: 62 years); 60 patients developed metastases after completing curative treatments (data are being updated with 2 additional follow-up years). Transcriptomic analysis was achieved in 54 patients and is being updated with 56 additional samples.

So far, no significant associations were found between the radiomics-based classifications and the transcriptomics-based (including CINSARC).

Nevertheless, the computational radiomics, deep-radiomics, and transcriptomics classifications were associated with MFS, though transcriptomic significance was dampened by the small sample size (P=0.008 [N=220], 0.006 [N=220] and 0.070 [N=54], respectively), suggesting complementary prognostic information.

Supervised models using data-splitting, cross-validated algorithms training, and various combinations of input data are being elaborated to improve the MFS prediction.

Conclusion: Integrating complementary multiomics datasets with computational and deep radiomics should pave the way for better performing and personalized prognostications in STS patients.

Citation Format: Amandine Crombe, Carlo Lucchesi, Frédéric Bertolo, Michèle Kind, Raul Perret, Francois Le Loarer, Mariella Spalato-Ceruso, Maud Toulmonde, Audrey Laroche, Vanessa Chaire, Aurelien Bourdon, Antoine Italiano. Correlating and combining computational radiomics, deep radiomics and transcriptomics data in soft-tissue sarcomas (STS) patients highlight complementary prognostic information. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5435.