Automated 3D Radiomic Body Composition Improves Survival Prediction in Resectable NSCLC

Background and study objective

The PubMed-indexed article titled “Automated three-dimensional radiomic body composition analysis enhances survival prediction in resectable non‑small cell lung cancer” presents a multicenter investigation into whether automated three-dimensional radiomic body composition analysis can improve survival prediction for patients with resectable non-small cell lung cancer (NSCLC). The source text provided here contains bibliographic and authorship metadata but does not include the article abstract or detailed study results.

Study design, setting, and authorship

The entry on PubMed indicates this is a multicenter study published in Eur Radiol Exp on 2026 Sep 18 (volume 10, article 135) with DOI 10.1186/s41747-026-00802-2 and PubMed PMID 42758420. The author list includes investigators affiliated with multiple institutions in China and one institution in The Netherlands. Several authors are indicated to have contributed equally.

Affiliated organizations named in the PubMed record include the Department of Medical Imaging at The First Affiliated Hospital of Kunming Medical University; the Department of Radiology, Guangdong Provincial People’s Hospital (Southern Medical University); Guangdong Provincial Key Laboratories for Artificial Intelligence in Medical Image Analysis and Application and for Medical Image Processing; the School of Biomedical Engineering at Southern Medical University; the First School of Clinical Medicine at Zhejiang Chinese Medical University; Guangzhou First People’s Hospital (School of Medicine, South China University of Technology); and the Department of Radiation Oncology (Maastro) at Maastricht University Medical Centre+.

Automated three-dimensional radiomic body composition: concept and relevance

The study title identifies the central technique as an automated, three-dimensional radiomic analysis of body composition. Radiomic body composition analysis generally refers to extraction of quantitative imaging features from tissues (for example, skeletal muscle, subcutaneous and visceral fat, and other body compartments) on cross-sectional imaging to characterize body habitus, muscle quality, and adiposity in a way that may relate to oncologic outcomes.

The core claim in the title is that this automated 3D radiomic approach enhances survival prediction in patients with resectable NSCLC. The PubMed record supplied does not contain further descriptive text about which body compartments were analyzed, which radiomic features were used, or the image modalities and acquisition parameters employed.

Reported claim and primary outcome statement

Based solely on the article title (the only explicit outcome statement in the provided extract), the authors report that automated 3D radiomic body composition analysis improved the ability to predict survival for resectable NSCLC patients. The PubMed entry does not include numerical performance metrics, effect sizes, p values, or comparative model baselines within the available text.

Available publication metadata and indexing

• Journal: Eur Radiol Exp
• Publication date: 2026 Sep 18;10(1):135
• DOI: 10.1186/s41747-026-00802-2
• PubMed PMID: 42758420
• Study type noted on the PubMed page: Multicenter Study

The PubMed entry provides full author names and institutional affiliations, and indicates that several authors contributed equally. Contact emails for certain corresponding authors are listed in the metadata on the PubMed page.

Missing methodological and result details in the provided source

The supplied PubMed content is largely metadata and does not include the abstract, methods, results, or discussion text. Therefore, the following critical elements were not reported in the provided source extract and cannot be inferred:

• Patient cohort size, inclusion and exclusion criteria, and demographic/clinical characteristics.
• Imaging modality(ies) used (for example, CT vs MRI), imaging protocols, and timing relative to surgery.
• Specific body composition compartments segmented or analyzed (eg, skeletal muscle, visceral adipose tissue, subcutaneous fat).
• Radiomic feature types, feature selection procedures, and whether the analysis used handcrafted features, deep-learning features, or both.
• Details of the automation pipeline (segmentation algorithm, quality control, computational platform).
• Model architecture(s) and statistical or machine-learning methods used for survival prediction, as well as internal or external validation strategies.
• Quantitative performance results (eg, hazard ratios, C-index, AUC, calibration metrics), confidence intervals, and statistical significance testing.
• Follow-up duration, survival endpoints (overall survival, disease-free survival), and subgroup analyses.
• Conclusions beyond the title statement, clinical recommendations, and limitations as reported by the authors.

Because these items are not present in the provided excerpt, they should be sought directly in the full published article for clinical interpretation or operational adoption.

Clinical implications and recommended next steps for readers

The title indicates potential clinical relevance: that automated 3D radiomic body composition assessment may add prognostic value for patients with resectable NSCLC. However, due to the absence of methodological and quantitative results in this PubMed extract, clinicians and researchers should not change practice or adopt specific technical workflows on the basis of the title alone.

Recommended next steps for readers interested in clinical or research implications:

• Consult the full text of the Eur Radiol Exp article via the DOI (10.1186/s41747-026-00802-2) or journal website to review methods, results, validation, and limitations.
• Evaluate reported model performance metrics, internal and external validation procedures, and whether a clinical decision threshold or risk stratification scheme is provided.
• Consider reproducibility and generalizability: check imaging acquisition harmonization, segmentation automation performance, and whether external multicenter validation was performed.

Data availability and where to find the full report

The PubMed record confirms bibliographic indexing and lists author affiliations and contact details but does not include the article abstract or data. For full methodological details, results, and data availability statements, access the article in Eur Radiol Exp using the DOI 10.1186/s41747-026-00802-2 or search PubMed PMID 42758420 for links to the full text. The PubMed page provided here is truncated and did not supply the complete abstract or study data in the supplied extract.