Deep learning model based on multi-lesion and time series CT images for predicting the benefits from anti-HER2 targeted therapy in stage IV gastric cancer.

OBJECTIVE: To develop and validate a deep learning model based on multi-lesion and time series CT images in predicting overall survival (OS) in patients with stage IV gastric cancer (GC) receiving anti-HER2 targeted therapy. METHODS: A total of 207 patients were enrolled in this multicenter study, with 137 patients for retrospective training and internal validation, 33 patients for prospective validation, and 37 patients for external validation. All patients received anti-HER2 targeted therapy and underwent pre- and post-treatment CT scans (baseline and at least one follow-up). The proposed deep learning model evaluated the multiple lesions in time series CT images to predict risk probabilities. We further evaluated and validated the risk score of the nomogram combining a two-follow-up lesion-based deep learning model (LDLM-2F), tumor markers, and clinical information for predicting the benefits from treatment (Nomo-LDLM-2F). RESULTS: In the internal validation and prospective cohorts, the one-year AUCs for Nomo-LDLM-2F using the time series medical images and tumor markers were 0.894 (0.728-1.000) and 0.809 (0.561-1.000), respectively. In the external validation cohort, the one-year AUC of Nomo-LDLM-2F without tumor markers was 0.771 (0.510-1.000). Patients with a low Nomo-LDLM-2F score derived survival benefits from anti-HER2 targeted therapy significantly compared to those with a high Nomo-LDLM-2F score (all p < 0.05). CONCLUSION: The Nomo-LDLM-2F score derived from multi-lesion and time series CT images holds promise for the effective readout of OS probability in patients with HER2-positive stage IV GC receiving anti-HER2 therapy. CRITICAL RELEVANCE STATEMENT: The deep learning model using baseline and early follow-up CT images aims to predict OS in patients with stage IV gastric cancer receiving anti-HER2 targeted therapy. This model highlights the spatiotemporal heterogeneity of stage IV GC, assisting clinicians in the early evaluation of the efficacy of anti-HER2 therapy. KEY POINTS: • Multi-lesion and time series model revealed the spatiotemporal heterogeneity in anti-HER2 therapy. • The Nomo-LDLM-2F score was a valuable prognostic marker for anti-HER2 therapy. • CT-based deep learning model incorporating time-series tumor markers improved performance.

Associations of subcutaneous fat area and Systemic Immune-inflammation Index with survival in patients with advanced gastric cancer receiving dual PD-1 and HER2 blockade.

BACKGROUND: Systemic Immune-inflammation Index (SII) and body composition parameters are easily assessed, and can predict overall survival (OS) in various cancers, allowing early intervention. This study aimed to assess the correlation between CT-derived body composition parameters and SII and OS in patients with advanced gastric cancer receiving dual programmed death-1 (PD-1) and human epidermal growth factor receptor 2 (HER2) blockade. MATERIALS AND METHODS: This retrospective study enrolled patients with advanced gastric cancer treated with dual PD-1 and HER2 blockade from March 2019 to June 2022. We developed a deep learning model based on nnU-Net to automatically segment skeletal muscle, subcutaneous fat and visceral fat at the third lumbar level, and calculated the corresponding Skeletal Muscle Index, skeletal muscle density, subcutaneous fat area (SFA) and visceral fat area. SII was computed using the formula that total peripheral platelet count×neutrophil/lymphocyte ratio. Univariate and multivariate Cox regression analysis were used to determine the associations between SII, body composition parameters and OS. RESULTS: The automatic segmentation deep learning model was developed to efficiently segment body composition in 158 patients (0.23 s/image). Multivariate Cox analysis revealed that high SII (HR=2.49 (95% CI 1.54 to 4.01), p<0.001) and high SFA (HR=0.42 (95% CI 0.24 to 0.73), p=0.002) were independently associated with OS, whereas sarcopenia was not an independent prognostic factor for OS (HR=1.41 (95% CI 0.86 to 2.31), p=0.173). In further analysis, patients with high SII and low SFA had worse long-term prognosis compared with those with low SII and high SFA (HR=8.19 (95% CI 3.91 to 17.16), p<0.001). CONCLUSION: Pretreatment SFA and SII were significantly associated with OS in patients with advanced gastric cancer. A comprehensive analysis of SII and SFA may improve the prognostic stratification of patients with gastric cancer receiving dual PD-1 and HER2 blockade.