Insights Scientific publications

Scientific publications

Keyword
  • 02/23/2026

    What are RECIST 1.1 progressions made of? Variability in double-read oncology trials

    The study offers an in‑depth look at how RECIST 1.1 progression events are defined and where variability between independent readers can emerge. By shedding light on the mechanisms that influence PD assessments, this work provides valuable insights for strengthening the reliability and consistency of imaging endpoints in oncology trials.

    These insights bring tangible value to both sponsors and CROs, helping teams better anticipate imaging‑related risks, design stronger study frameworks, and reinforce the consistency of interpretation across global programs. Strengthening these foundations ultimately supports more confident decision‑making throughout oncology development.


    H. Beaumont [1], L. Cantini[2], K. Saini [2], N. Faye [1], R. Gill [3], A. Iannessi [1], – Affiliations: [1] Median Technologies, Valbonne, France, [2]Fortrea Inc., [3] Durham, NC, USA Columbia University Vagelos College of Physicians and Surgeons University Medical Center, New York, NY, USA
    Read more Download what_are_PD_ER_2026.pdf
  • 02/23/2026

    Rethinking lung cancer screening: longitudinal AI/ML diagnostics beyond nodule size growth

    Oral Scientific presentation at RSNA 2025 conference


    Bodard S, Baudot P, Renoust B, Voyton C, De Bie G, Geremia E, Le V, FrancisD, Siot P, Haddou Y, Bourdès V, Huet B
    Download RSNA2025BodardRethinkingLCS.pdf
  • 02/23/2026

    Radiologists’ perception on AI/ML software as a medical device (SaMD) unveiled via post-study usability survey: key assets to redefine lung cancer screening

    Poster presented at ESMO AI conference


    Grossi F, Seijo L, Osarogiagbon R, Gotera C, Ostrin E, Vachani A, Haddag S, Baraghini S, Boy Machefer L, Voyton C, Bourdes V.
    Download ESMO-AI-2025-Poster_Median_eyonis_ESMO2025-PDF-160X90.pdf
  • 05/24/2025

    Technical performance of the L3 Skeletal Muscle Index in CT

    Our comprehensive evaluation of L3-SMI’s bias, repeatability, reproducibility, and linearity establishes the basis for associating confidence intervals with its measurements. This enables the detection of significant patient changes, laying a strong foundation for L3-SMI’s clinical qualification as a reliable biomarker in health assessments.

    Abstract #e24073 published by ASCO 2025


    H. Beaumont [1], E. Khayat, A. Thinnes [1], A. Iannessi [1], – Affiliations: [1] Median Technologies, Valbonne, France.
    Read more Download ASCO2025-e-abstract-Technical-performance-of-the-L3-Skeletal-Muscle-Index-in-CT.pdf
  • 05/24/2025

    Using tumor growth modeling and informed neural networks as early predictive clinical endpoints

    This study evaluates the utility of TGM within formed neural networks in predicting response and durability. Our findings suggest that early tumor growth parameters, may serve as predictive clinical endpoints for response and long-term outcomes.

    Abstract #e13590 published by ASCO 2025


    M. Felfli [1], S. Jacques [1], A. Thinnes [1], A. Iannessi [1], – Affiliations: [1] Median Technologies, Valbonne, France.
    Read more Download ASCO2025-e-abstract_Using-tumor-growth-modeling-and-informed-neural-networks-as-early-predictive-clinical-endpoints.pdf
    • 1 … 14