The vascular risk score (VRS), a deep learning–based imaging metric that quantifies abnormalities in tumor vasculature on CT scans, is presented and enables noninvasive, objective quantification of tumor vascular abnormality and may serve as a prognostic imaging marker in NSCLC.
Abstract
Morphological abnormality in tumor vasculature, a recently recognized mechanism of resistance to immune checkpoint inhibitors (ICIs), remains difficult to quantify due to its heterogeneity. We present the vascular risk score (VRS), a deep learning–based imaging metric that quantifies abnormalities in tumor vasculature on CT scans. We trained a deep learning model to learn representations of vascular morphology. Abnormality was then quantified using Gaussian mixture modeling as the degree to which each patient’s tumor vasculature deviated from the learned distribution of normal morphology. We validated VRS in a cohort of 321 NSCLC patients treated with ICIs. Patients with low VRS showed significantly longer progression-free and overall survival, and lower VRS was observed in patients with disease control compared with progressive disease. Combining VRS with PD-L1 expression provided modest additional discrimination over either marker alone. VRS enables noninvasive, objective quantification of tumor vascular abnormality and may serve as a prognostic imaging marker in NSCLC.
Lung cancer remains one of the leading causes of cancer-related mortality worldwide, with most patients diagnosed at advanced stages where curative treatment is rarely possible. In advanced non-small cell lung cancer (NSCLC), immune checkpoint inhibitors (ICIs) have significantly improved patient outcomes by enhancing...
Findings demonstrate that the developed model effectively stratifies recurrence risk in thyroid cancer and may serve as an objective, quantitative tool to support individualized postoperative monitoring and prognostic assessment.
Qiu-Yan He, Zi-Lu Lin, Han Wu et al.· Frontiers of Physics· 0 citations
This narrative review critically synthesizes the evidence across solid tumors and compares handcrafted radiomics, classical machine learning, convolutional neural networks, transformer-based approaches, self-supervised learning, and emerging foundation models, and discusses explainable AI, longitudinal imaging, pseudop...
Hang-Yu Wu, Jing Chen· Frontiers in Immunology· 0 citations
Characteristics of the tumor immune microenvironment and PET imaging of PD-1/PD-L1 have potential as biomarkers for immunotherapy in NSCLC are demonstrated and larger studies are required to validate the predictive value of these approaches.
Cancer immunotherapy has revolutionized the treatment landscape, yet its clinical efficacy is limited by modest objective response rates and the emergence of atypical response patterns such as pseudoprogression and hyperprogression. Conventional RECIST criteria relying on anatomical size changes and invasive tissue bio...
Qiao-Ling Zhang, Shu-Fen Xiao, Jing-Xin He et al.· Ultrasound in Medicine and B...· 0 citations