Background: Opportunistic computed tomography (CT) screening for the evaluation of sarcopenia and myosteatosis has been gaining emphasis. A fully automated artificial intelligence (AI)–integrated system for body composition assessment on CT scans is a prerequisite for effective opportunistic screening. However, no study has evaluated the implementation of fully automated AI systems for opportunistic screening in real-world clinical practice for routine health check-ups. Objective: The aim of this study is to evaluate the performance and clinical utility of a fully automated AI-integrated system for body composition assessment on opportunistic CT during routine health check-ups. Methods: This prospective multicenter study included 537 patients who underwent routine health check-ups across 3 institutions. Our AI algorithm models are composed of selecting L3 slice and segmenting muscle and fat area in an end-to-end manner. The AI models were integrated into the Picture Archiving and Communication System (PACS) at each institution. Technical success rate, processing time, and segmentation accuracy in Dice similarity coefficient were assessed. Body composition metrics were analyzed across age and sex groups. Results: The fully automated AI-integrated system successfully retrieved anonymized CT images from the PACS, performed L3 selection and segmentation, and provided body composition metrics, including muscle quality maps and muscle age. The technical success rate was 100% without any failed cases requiring manual adjustment. The mean processing time from CT acquisition to report generation was 4.12 seconds. Segmentation accuracy comparing AI results and human expert results was 97.4%. Significant age-related declines in skeletal muscle area and normal-attenuation muscle area were observed, alongside increases in low-attenuation muscle area and intramuscular adipose tissue. Conclusions: Implementation of the fully automated AI-integrated system significantly enhanced opportunistic sarcopenia screening, achieving excellent technical success and high segmentation accuracy without manual intervention. This system has the potential to transform routine health check-ups by providing rapid and accurate assessments of body composition.

Kim KW, et al. J Gastric Cancer. 2023 Jul;23(3):388-399. https://doi.org/10.5230/jgc.2023.23.e30

Background/Objectives: Immune checkpoint inhibitors (ICIs) show durable efficacy in tumors with deficient mismatch repair (dMMR) or high microsatellite instability (MSI-H), yet clinical responses remain heterogeneous. This study aimed to define immune subgroups within dMMR/MSI-H tumors and develop a reproducible transcriptomic signature predictive of ICI response. Methods: Four MSI-H-enriched cancer types (UCEC, COAD, READ, STAD) from The Cancer Genome Atlas were analyzed. Tumors were stratified by immune cell infiltration (MCP-counter immune composite score) and T-cell-inflamed gene expression profiles (GEP score). Integrating these two axes defined four immune subgroups. Differential expression, random forest feature selection, and pathway enrichment were performed to identify immune programs. A 20-gene immune signature representing the most immune-active subgroup was developed and validated across TCGA, GEO (GSE39582), and IMvigor210 cohorts. Results: Among the four subgroups, the most immune-active group showed strong activation of interferon signaling, antigen presentation, and T-cell-mediated pathways. The 20-gene signature—including CD74, STAT1, TAP1, and HLA-class genes—achieved high reproducibility (mean AUC = 0.95 ± 0.02; accuracy ≈ 89%). In the IMvigor210 cohort, this signature identified tumors with higher PD-L1 blockade response (55.6% vs. 32.8%, p = 0.034) and improved survival trends in the TMB-high subset. Conclusions: The proposed 20-gene signature quantitatively captures immune heterogeneity in dMMR/MSI-H tumors and serves as a practical, interpretable biomarker to identify true ICI responders and guide precision immunotherapy.

BACKGROUND Opportunistic CT screening for the evaluation of sarcopenia and myosteatosis has been gaining emphasis. A fully automated AI-integrated system for body composition assessment on CT scans is a prerequisite for effective opportunistic screening. However, no study has evaluated the implementation of fully automated AI systems for opportunistic screening in real-world clinical practice for routine health check-ups. OBJECTIVE To evaluate the performance and clinical utility of a fully automated AI-integrated system for body composition assessment on opportunistic CT during routine health check-ups. METHODS This prospective multicenter study included 537 patients who underwent routine health check-ups across three institutions. Our AI algorithm models are composed of selecting L3 slice and segmenting muscle and fat area in an end-to-end manner. The AI models were integrated into the Picture Archiving and Communication System (PACS) at each institution. Technical success rate, processing time, and segmentation accuracy in Dice similarity coefficient were assessed. Body composition metrics were analyzed across age and sex groups. RESULTS The fully automated AI-integrated system successfully retrieved anonymized CT images from the PACS, performed L3 selection and segmentation, and provided body composition metrics, including muscle quality maps and muscle age. The technical success rate was 100% without any failed cases requiring manual adjustment. The mean processing time from CT acquisition to report generation was 4.12 seconds. Segmentation accuracy comparing AI results and human expert results was 97.4%. Significant age-related declines in skeletal muscle area and normal-attenuation muscle area were observed, alongside increases in low-attenuation muscle area and intramuscular adipose tissue. CONCLUSIONS Implementation of the fully automated AI-integrated system significantly enhanced opportunistic sarcopenia screening, achieving excellent technical success and high segmentation accuracy without manual intervention. This system has the potential to transform routine health check-ups by providing rapid and accurate assessments of body composition.

Yi W, et al. Korean J Radiol. 2026 Oct;27(10):1005-1009. https://doi.org/10.3348/kjr.2026.0865