{
  "abstract": "Background Predicting ICI benefit relies primarily on PD-L1 expression, which is a poor one-dimensional measure and overlooks resistance mechanisms such as tumor angiogenesis. QVT is a radiomic approach for measuring abnormalities of the tumor-associated vasculature, which have been shown to be associated with poor ICI outcomes. 1 2 Here, we introduce the QVT Score, a continuous index mapping the degree of chaotic vascularity on standard clinical imaging. We validate this biomarker as a survival-associated predictor (from baseline CT) and for early monitoring (from first on-treatment CT) for ICIs. We further assess its biological basis through histopathological correlation.Methods In a discovery cohort of 375 NSCLC patients, an unsupervised clustering model of interpretable QVT features—including vessel curvature, twistedness, and branching—was utilized to create an automated and continuous 0-to-1 Score indicating the degree of high risk elevated vascularity. The QVT Score was computed and validated for association to OS using pre-treatment (n=266) and first on-treatment (n=143) CT from 266 ICI monotherapy recipients. For patients with pre-treatment histopathology samples available (n=31), deep learning models were used to compute the proportions of various cellular subpopulations, which were then correlated with QVT Score.Results Higher QVT Score ( figure 1) was associated with shorter OS at the baseline (HR: 2.07, p = 0.019) and first on-treatment (HR: 4.22, p = 0.00083) scans, as was longitudinal change (HR=2.89, p=0.0056). Stratifying patients by change directionality also stratified OS (HR=1.91, p=0.0017) with median OS of 10 months for Increasing and 22 months for Decreasing. These groups remained independently prognostic when adjusted for RECIST best overall response (p=0.0340) and volume change (p=0.0015). Higher baseline QVT Score was linked to a hypoxic microenvironment, as indicated by a significant association with necrotic cell proportion (r=0.40, p=0.024) on histopathology (table 1).Conclusions QVT Score is a radiomic biomarker predictive of ICI benefit for baseline and on-treatment assessment, which captures the vascular dynamics of therapeutic response independent of traditional imaging endpoints. Unlike post-hoc explainability methods attached to deep learning algorithms, QVT Score is interpretable by design, built from QVT features targeting tumor-immune microenvironment biology. QVT scoring has already been deployed as an exploratory biomarker in ongoing prospective clinical trials for multiple cancer indications. QVT Score offers valuable insight for patient selection and early response assessment in clinical drug development and precision oncology.Abstract 66 Table 1Association of QVT score with cellular composition on histopathology Cell Type Pearson Correlation (r) p-value Necrosis 0.40 0.024 Fibroblasts 0.21 0.25 Lymphocytes 0.23 0.21 Abstract 66 Figure 1QVT score stratifies ICI recipients by OS. Visualized tumor-associated vascular complexity for patients with low (left) and high (right) QVT score. Patients with elevated QVT score, indicating chaotic tumor angiogenesis, have poor ICI outcomes compared to those with normalized vasculature",
  "authors": [
    {
      "affiliations": [
        "Northwestern University, Chicago, IL, USA"
      ],
      "name": "Young Kwang Chae"
    },
    {
      "affiliations": [
        "Picture Health, Cleveland, OH, USA"
      ],
      "name": "Kai Zhang"
    },
    {
      "affiliations": [
        "Northwestern University Feinberg School of Medicine, Chicago, IL, USA"
      ],
      "name": "Liam Il-Young Chung"
    },
    {
      "affiliations": [
        "Picture Health, Cleveland, OH, USA"
      ],
      "name": "Amogh Hiremath"
    },
    {
      "affiliations": [
        "Picture Health, Cleveland, OH, USA"
      ],
      "name": "Haojia Li"
    },
    {
      "affiliations": [
        "Picture Health, Cleveland, OH, USA"
      ],
      "name": "Rhea Chitalia"
    },
    {
      "affiliations": [
        "Northwestern University Feinberg School of Medicine, Chicago, IL, USA"
      ],
      "name": "Julianne Jin"
    },
    {
      "affiliations": [
        "Picture Health, Cleveland, OH, USA"
      ],
      "name": "Omid Haji Maghsoudi"
    },
    {
      "affiliations": [
        "Emory University, Atlanta, GA, USA"
      ],
      "name": "Pushkar Mutha"
    },
    {
      "affiliations": [
        "Picture Health, Cleveland, OH, USA"
      ],
      "name": "Trishan Arul"
    },
    {
      "affiliations": [
        "Laura and Isaac Perlmutter Cancer Center at NYU, Scarsdale, NY, USA"
      ],
      "name": "Vamsidhar Velcheti"
    },
    {
      "affiliations": [
        "Emory University, Atlanta, GA, USA"
      ],
      "name": "Anant Madabhushi"
    },
    {
      "affiliations": [
        "Picture Health, Cleveland, OH, USA"
      ],
      "name": "Nathaniel Braman"
    }
  ],
  "title": "66 QVT Score, a radiomic biomarker of tumor vascularity, enables immune checkpoint inhibitor (ICI) outcome prediction and early survival assessment in NSCLC",
  "uid": "a7f998b0-2142-59a0-90d1-bb60a5236bd0"
}