Resource library

Scientific publications

Scientific publications

Fully-Learned Features for Lung Cancer Overall Survival Prediction

Danny Francis [1], Vladimir Groza [1], Benoit Huet [1], Nozha Boujemaa [1] – Affiliations: [1] Median Technologies, Valbonne, France.

This work presents an end-to-end trained method and its preliminary results demonstrating the possibility to predict Overall Survival (OS) time for patients with lung cancer.

Preliminary Study to Identify the Severity of Hepatic Fibrosis in Patients with Non-Alcoholic Steatohepatitis (NASH) Using iBiopsy®

Jean-Christophe Brisset [1], Benoit Huet [1], Nozha Boujemaa [1] – Affiliations: [1] Median Technologies, Valbonne, France.

The objective of this study was to quantify the ability of iBiopsy®’s algorithms to discriminate between early and advanced fibrosis grade in NASH patients using clinically available tests and images.

RECIST 1.1 and lesion selection: How to deal with ambiguity at baseline?

Antoine Iannessi [1], Hubert Beaumont [1], Yan Liu [1], Anne-Sophie Bertrand [2] – Affiliations: [1] Median Technologies, Valbonne, France. [2] Centre Hospitalier Princesse Grâce, Monaco

The goal of this paper is to provide insights for radiologists faced with equivocal baseline abnormalities and to raise awareness of the potential risks arising from such situations regarding the outcome of clinical trials using the RECIST evaluation technique.

See publication

Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging

Hubert Beaumont [1], Antoine Iannessi [2], Anne-Sophie Bertrand [3], Jean Michel Cucchi [3], Olivier Lucidarme [4] - Affiliations: [1] Median Technologies, Valbonne , France. [2] Centre Antoine Lacassagne, Nice, France. [3] Centre Hospitalier Princesse Grâce, Monaco. [4] Hopital La Pitié Salpêtrière, Paris, France.

This scientific paper published in European Radiology addresses the generalizability of classification models performances in improving the reliability of radiomic features using harmonized data. The work was conducted on diseased/non-diseased liver images and evaluated two different harmonization approaches. This paper is a result of a collaboration between Centre Hospitalier Princesse Grâce, Monaco, AP-HP La Pitié Salpêtrière, Paris and Median Technologies.

See publication

High risk fibrosis score prediction using computed tomography imaging

Elton Rexhepaj [1], Corinne Ramos [1], Yan Liu [1], Benoit Huet [1], Olivier Lucidarme [2], Nozha Boujemaa [1] – Affiliations: [1] Median Technologies, Valbonne, France - [2] Hôpital Universitaire Pitié-Salpêtrière-APHP, Paris, France

Poster presented at the Digital International Liver Congress – EASL – August 27-29, 2020

Hepatic fibrosis diagnosis is important for risk stratification, prognosis evaluation and monitoring of treatment response. Using computer tomography (CT) perfusion imaging and splenic radiomics, the objective of this study is to validate the use this non-invasive fibrosis scoring method to identify patients whose tumors are at high risk of recurrence after hepatic resection.

Resource library