The diagnosis, classification, and treatment of sarcoma in this era of artificial intelligence and immunotherapy

Abstract

Soft-tissue sarcomas (STS) represent a group of rare and heterogeneous tumors associated with several challenges, including incorrect or late diagnosis, the lack of clinical expertise, and limited therapeutic options. Digital pathology and radiomics represent transformative technologies that appear promising for improving the accuracy of cancer diagnosis, characterization and monitoring. Herein, we review the potential role of the application of digital pathology and radiomics in managing patients with STS. We have particularly described the main results and the limits of the studies using radiomics to refine diagnosis or predict the outcome of patients with soft-tissue sarcomas. We also discussed the current limitation of implementing radiomics in routine settings. Standard management approaches for STS have not improved since the early 1970s. Immunotherapy has revolutionized cancer treatment; nonetheless, immuno-oncology agents have not yet been approved for patients with STS. However, several lines of evidence indicate that immunotherapy may represent an efficient therapeutic strategy for this group of diseases. Thus, we emphasized the remarkable potential of immunotherapy in sarcoma treatment by focusing on recent data regarding the immune landscape of these tumors. We have particularly emphasized the fact that the development of immunotherapy for sarcomas is not an aspect of histology (except for alveolar soft-part sarcoma) but rather that of the tumor microenvironment. Future studies investigating immunotherapy strategies in sarcomas should incorporate at least the presence of tertiary lymphoid structures as a stratification factor in their design, besides including a strong translational program that will allow for a better understanding of the determinants involved in sensitivity and treatment resistance to immune-oncology agents.

Keywords: artificial intelligence; digital pathology; immunotherapy; radiomics; sarcoma.

FIGURE 1

The radiomics workflow and potentialities adapted to baseline multi‐parametric multimodal imaging of a patient with soft‐tissue sarcoma. A schematic illustration of the patient's journey, including image acquisition, analysis utilizing radiomics, and other clinical and biological variables to derive a predictive signature of the patient's outcome. High‐level statistical modeling involving machine learning is applied for disease classification, patient clustering, and individual risk stratification. Abbreviations: ADC: apparent diffusion coefficient, CE T1: contrast‐enhanced T1, CINSARC: complexity index in sarcoma signature, K^trans: transfer constant, mTLS: mature tertiary lymphoid structure, PD‐L1: program death ligand 1, PET: (18F‐fluorodeoxyglucose) positron emission tomography, RF: radiomics features, and TILs: tumor infiltrative lymphocytes.

FIGURE 2

Radiomics to distinguish between immune low (A) and high UPS (B) according to Toulmonde et al. [106]. On contrast‐enhanced MRI, immune high UPS (black arrows) is characterized by a more heterogeneous aspect than immune low UPS (white arrows), captured through a combination of nine radiomics features, all related to heterogeneity. *The local texture map corresponds to the GLCM homogeneity (homo.) calculated on a small tile (or kernel) of 3 × 3 voxels. Higher values correspond to greater local homogeneity. Abbreviations: CE: contrast‐enhanced; MRI: magnetic resonance imaging; No.: number; SI: signal intensity; UPS: undifferentiated pleomorphic sarcomas; GLCM: gray‐level co‐occurrence matrix. This figure is original.