Scientific publications
-
03/13/2024 Unraveling Immune Therapy Efficacy Through Growth Kinetics Modeling: A Descriptive Analysis of Imaging Kinetic Biomarkers Using RECIST 1.1 Assessments
Antoine Iannessi [1], – Affiliations: [1] Median Technologies, Valbonne, France. -
12/05/2023 End-to-End AI model for Nodule Detection and Characterization in Lung Cancer Screening: Performances and Subpopulation Analysis
The abstract presents the performances and subpopulation analysis of a computer-aided detection and characterization (CADe/CADx) AI model developed to aid lung cancer screening standard of care. AI 3D-CNN models were used on a test set containing 136 cancer and 2,027 benign patients. Performance at nodule level in terms of AUC-ROC is 0.987, significantly outperforming the NLST Brock model (AUC-ROC 0.971). This result is also consistent across nodules’ key characteristics (size, attenuation, margin) and shows it could aid clinicians in optimizing their clinical routine and the clinical management of patients.
P. BAUDOT [1], C. VOYTON [1], G. DE BIE [1], V. LE1 [1], D. FRANCIS [1], E. GEREMIA [1], B. RENOUST [1], P. SIOT [1], Y. LIU [1], B. HUET [1] – Affiliations: [1] Median Technologies, 1800 Route des Crêtes, 06560 Valbonne, France. -
12/05/2023 A CT Imaging Biomarker for CD8+ Lymphocytes Infiltration Stratification in Patients with Non-Small Cell Lung Cancer
The aim of the study is to investigate the ability of radiomics features to stratify patients based on CD8+ lymphocyte infiltration levels and identify relevant radiomics features associated with these levels. The data used in this study originates from two open-source repositories, TCIA and TCGA. The AI model was trained using TCIA data and tested on TCGA data. The results suggest that four texture features can confidently discriminate CD8+ infiltration levels (high/low). The model achieved a mean area under the curve AUC-ROC of 0.73(±0.08 std) on the training set and an AUC-ROC of 0.67 (95% CI: 53%, 80%) on the test set.
F. Zerka [1], M. Felfli [1], C. Voyton [1], A. Thinnes [1], Jacques [1], Y. Liu [1], A. Iannessi [1,2] – Affiliations: [1] Median Technologies, Valbonne, France. [2] Centre Antoine Lacassagne, Nice, France. -
10/04/2023 Can we predict discordant RECIST 1.1 evaluations in double read clinical trials?
Hubert Beaumont [1], Antoine Iannessi [1], – Affiliations: [1] Median Technologies, Valbonne, France. -
08/22/2023 Systematic Review, Meta-Analysis and Radiomics Quality Score Assessment of CT Radiomics-Based Models Predicting Tumor EGFR Mutation Status in Patients with Non-Small-Cell Lung Cancer
M. Felfli [1], Y. Liu [1], Zerka [1], C. Voyton [1], A. Thinnes [1], S. Jacques [1], A. Iannessi [1], F. S. Bodard [2] – Affiliations: [1] Median Technologies, Valbonne, France. [2] Hôpital Universitaire Necker, Paris, France