JLE

Hépato-Gastro & Oncologie Digestive

MENU

Radiomics, a promising new discipline : example of hepatocellular carcinoma Volume 29, issue 10, December 2022

Figures


  • Figure 1

  • Figure 2

  • Figure 3

Tables

Authors
1 CHU de Nice, Hôpital de l’Archet 2, Unité d’hépatologie, pôle DIGi-TUNED, Nice
2 CHU de Nice, Hôpital de l’Archet 2, Service d’imagerie médicale, Nice
3 CHU de Nice, Hôpital de l’Archet 1, Département de médecine nucléaire, Nice
4 Université Côte d’Azur, CN3S, I3S, Nice
5 Hôpital Saint Joseph, Marseille
6 Centre Antoine-Lacassagne, Département de médecine nucléaire, Université Côte d’Azur, Nice
7 Université Côte d’Azur, TIRO-UMR E 4320, Nice
8 Université Côte d’Azur, INSERM, U1065, C3M, Nice
* Correspondant : T. Lévi-Strauss

Radiomics is the discipline that studies medical images through their digital data. Using "artificial intelligence" algorithms, it performs a quantitative and high-throughput analysis of the image’s textural richness to obtain relevant information for the clinician, from diagnostic assistance to therapeutic guidance. Exploitation of these data could allow a more detailed characterization of each phenotype, for each patient, making radiomics a new biomarker of interest, highly promising in the era of precision medicine. Moreover, radiomics is non-invasive, cost-effective, and easily reproducible in time. In the field of oncology, it performs an analysis of the entire tumor, impossible with a single biopsy, to understand its heterogeneity, which is known to be closely related to prognosis. However, current results are sometimes less accurate than expected and often require the addition of non-radiomic data to create a performing model. To highlight the strengths and weaknesses of this new technology, we take the example of hepatocellular carcinoma and show how radiomics could facilitate its diagnosis in difficult cases, predict certain histological features and estimate treatment response, whether medical or surgical.