Traditional pulmonary function tests (PFTs) are indispensable but have well‑known blind spots: reliance on patient cooperation, lack of regional information, and inability to detect early structural changes. A new review in Intelligent Oncology (Volume 2, Issue 2, 2026) discusses how multimodal imaging (X‑ray, CT, MRI, nuclear medicine) combined with radiomics and deep learning can predict pulmonary function. It highlights the shift from traditional PFTs (limited by patient cooperation, lack of regional data, and insensitivity to early lesions) to imaging‑based models that quantify emphysema, airway remodeling, ventilation‑perfusion mismatch, and even lobar‑level functional contribution. The article also introduces the novel concept of “lung biological age” — using imaging features to assess how an individual’s lung function deviates from age‑matched norms.
The authors envision a multimodal integration framework that fuses structural and functional imaging (e.g., CT + hyperpolarized gas MRI) via intermediate fusion and attention mechanisms. Key goals include:
Validating the framework in large‑scale, multicenter prospective cohorts.
Standardizing imaging protocols and data processing to improve generalizability.
Using “lung biological age” for early risk stratification and personalized intervention.
Moving from indirect structure‑function inference to direct, quantitative mapping of functional endpoints (FEV₁, FVC, DLCO, and decline trajectories).
The ultimate aim is not to replace PFTs, but to provide complementary, regional, and more sensitive functional assessment — especially for early disease, surgical planning, and patients unable to perform reliable spirometry.
Full article available on ScienceDirect:
https://doi.org/10.1016/j.intonc.2026.100051
Contact Information for Intelligent Oncology:
LinkedIn: @IntelligentOncology
X: @IntelligentOnco
Facebook: @intelligentoncology
Email Address: editorialoffice@intelligent-oncology.net
Official Website: https://www.sciencedirect.com/journal/intelligent-oncology
Submission Link: https://www2.cloud.editorialmanager.com/intonc/default2.aspx
