Insights Scientific publications

Scientific publications

  • 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.
    Download POSTER_NACLC2023_v5CG3-1.pdf
  • 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.
    Download IASLC-2023-NACLC_Poster_MedianTechnologies_final.pdf
  • 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.
    Read more Download Can-we-predict-discordant-RECIST-1.1-evaluations-in-double-read-clinical-trials.pdf
  • 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
    Read more Download ijms-24-11433.pdf
  • 06/02/2023

    Multicenter Evaluation of AI-Based CT Radiomics for EGFR Mutation Prediction in NSCLC

    This abstract discusses using CT image-based radiomics model as a non-invasive solution to predict EGFR mutation status in NSCLC. The study collected CT images from multiple centers and open-source databases to investigate the performance of the model. The model achieved promising results with an AUC of 0.83 on cross-validation and an AUC of 0.76 on the test set. The authors conclude that AI-powered medical image analysis has the potential to serve as predictive biomarkers for guiding targeted therapies in the future.

    Y. Liu [1], F. Zerka [1], S. Bodard [2], M. Felfli [1], C. Voyton [1], A. Thinnes [1], S. Jacques [1], A. Iannessi [1], – Affiliations: [1] Median Technologies, Valbonne, France. [2] Hôpital Universitaire Necker, Paris, France
    Read more Download Multicenter-evaluation-of-AI-based-CT-radiomics-for-EGFR-mutation-prediction-in-NSCLC.pdf