Deep learning radiomics and mediastinal adipose tissue-based nomogram for preoperative prediction of postoperative brain metastasis risk in non-small cell lung cancer
Niu Y., Jia HB., Li XM., Huang WJ., Liu PP., Liu L.
Retrospective Study, published in BMC Cancer (2025) — summary generated from the PubMed abstract.
Early human evidence such as case series or small samples is exploring possible benefits.
- Level A · Stronger Clinical Evidence
- Level B · Emerging clinical evidence with positive signals
- Level C · Early human research exploring benefits
- Level D · Scientific groundwork from lab and animal studies
- Emerging · Emerging topic under active research
This page is generated from the PubMed record. The Thai description is an automated summary of bibliographic fields and the abstract, not a full translation, and is not medical advice.
- Study type
- Retrospective Study
- Journal
- BMC Cancer (2025)
- Reported sample size
- —
- Source database
- Europe PMC
- PMID
- 40597925
- PMCID
- PMC12219950
- DOI
- 10.1186/s12885-025-14466-5
Abstract (original English)
BACKGROUND AND OBJECTIVES: Brain metastasis (BM) significantly affects the prognosis of non-small cell lung cancer (NSCLC) patients. Increasing evidence suggests that adipose tissue influences cancer progression and metastasis. This study aimed to develop a predictive nomogram integrating mediastinal fat area (MFA) and deep learning (DL)-derived tumor characteristics to stratify postoperative BM risk in NSCLC patients. MATERIALS AND METHODS: A retrospective cohort of 585 surgically resected NSCLC patients was analyzed. Preoperative computed tomography (CT) scans were utilized to quantify MFA using ImageJ software (radiologist-validated measurements). Concurrently, a DL algorithm extracted tumor radiomic features, generating a deep learning brain metastasis score (DLBMS). Multivariate logistic regression identified independent BM predictors, which were incorporated into a nomogram. Model performance was assessed via area under the receiver operating characteristic curve (AUC), calibration plots, integrated discrimination improvement (IDI), net reclassification improvement (NRI), and decision curve analysis (DCA). RESULTS: Multivariate analysis identified N stage, EGFR mutation status, MFA, and DLBMS as independent predictors of BM. The nomogram achieved superior discriminative capacity (AUC: 0.947 in the test set), significantly outperforming conventional models. MFA contribute
What this study does not prove
- • This study does not prove SVF is an approved treatment or a replacement for standard care.
- • Without an adequate control group, treatment effects cannot be separated from other factors.
Evidence level
Early human evidence such as case series or small samples is exploring possible benefits.
How we grade evidenceBrowse all related research
Filter the research library by this study's title keywords, author, or publication year.