DOI 10.1007/s13304-026-02689-5
A radiomics-based nomogram for differentiating minimally invasive adenocarcinoma from stage I invasive non-mucinous adenocarcinoma (CTR < 0.5, GGO-dominant).
Аннотация
The study aimed to develop and validate a radiomics-based predictive model for differentiating minimally invasive adenocarcinoma (MIA) from stage I invasive non-mucinous adenocarcinoma (INMA) in lesions dominated by ground-glass opacity (GGO) with a consolidation-to-tumor ratio (CTR) < 0.5. Patients pathologically diagnosed with MIA or stage I INMA (predominantly presenting as GGO with CTR < 0.5) at the Affiliated Nantong Hospital of Shanghai University between January 2021 and December 2022 were enrolled. All eligible patients were randomly divided into a training cohort and a validation cohort at a ratio of 8:2. Regions of interest (ROIs) were manually delineated using 3D Slicer software. A radiomics signature and a nomogram predictive model were constructed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, univariate, and multivariate logistic regression analyses. The predictive performance of the model was internally validated using the validation cohort. A total of 153 (MIA, 74; INMA, 79) patients were divided into training (n = 122) and validation (n = 31) cohorts. Baseline clinical characteristics were well balanced between the two cohorts (P > 0.05). Fifteen features significantly associated with the study endpoint were selected via LASSO regression. The radiomics signature exhibited favorable discriminative ability, with area under the curve (AUC) values of 0.844 (training cohort) and 0.871 (validation cohort). The nomogram model achieved Harrell's concordance index (C-index) values of 0.864 (95% confidence interval [CI], 0.853-0.876) in the training cohort and 0.896 (95% CI, 0.858-0.934) in the validation cohort. Our radiomics-based nomogram model demonstrates excellent predictive performance for differentiating MIA from stage I INMA in GGO-dominant lesions with CTR < 0.5. This model provides valuable clinical support for personalized and precise diagnosis and treatment, thereby facilitating optimal patient management.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.