Spectral CT-based habitat analysis for predicting pathologic response to neoadjuvant therapy in gastric cancer.

objectivesTo investigate the predictive value of habitat imaging based on spectral CT-derived iodine maps (IMs) for pathologic response to neoadjuvant therapy (NAT) in gastric cancer (GC). MATERIALS AND

methodsThis retrospective, two-center study included 151 patients with pathologically confirmed GC who underwent NAT followed by gastrectomy between July 2022 and June 2025. All patients underwent dual-phase, contrast-enhanced, dual-layer spectral CT scans before NAT. Based on tumor regression grade, patients were categorized as responders or non-responders. In venous-phase IMs, tumor voxels in the entire lesion were clustered into distinct habitats using the k-means algorithm. The volume fraction of each habitat and an intratumoral heterogeneity score (ITHscore) were calculated. Univariate analysis and logistic regression analyses determined predictive parameters among clinicopathologic and IM-based variables. A weighted logistic regression model for responders was developed and validated using fivefold cross-validation and an external test set.

resultsAmong the 151 patients, 54 (35.8%) were responders. Three distinct perfusion habitats (high, middle, and low) were identified. Responders exhibited a higher volume fraction of the low-perfusion habitat and a lower ITHscore (both p < 0.05). By integrating these two metrics, patients were stratified into four perfusion subtypes, with response rates ranging from 75.0% to 17.4% (p < 0.001). The predictive model combining perfusion subtype and Lauren classification achieved an average area under the curve (AUC) of 0.794 (0.751-0.836) in internal cross-validation and 0.782 (0.605-0.909) in the external test set.

conclusionIM-derived habitat imaging can distinguish distinct perfusion subtypes, suggesting a promising approach for predicting pathologic response to NAT in GC. KEY POINTS: Question Accurately predicting the efficacy of neoadjuvant therapy prior to treatment in gastric cancer remains challenging due to the lack of reliable biomarkers. Findings Perfusion subtypes identified through iodine map-based habitat imaging effectively predict tumor regression in gastric cancer following neoadjuvant therapy. Clinical relevance Iodine map-based habitat imaging is a promising biomarker for noninvasively predicting pathologic response to neoadjuvant therapy in patients with gastric cancer, thereby enabling more personalized treatment strategies for this population.