Frontiers in oncology · 2026
Application value of high-resolution CT imaging features combined with texture analysis in patients with solitary pulmonary nodules.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
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.
Zong Jie, Li Haiyan, Li Zhiling
Аннотация
INTRODUCTION: This retrospective study evaluated whether high-resolution CT (HRCT) texture analysis adds diagnostic value to conventional morphological assessment for differentiating benign from malignant solitary pulmonary nodules (SPNs).
METHODS: We analyzed 200 patients with pathologically confirmed SPNs (43 benign, 157 malignant) examined between September 2022 and October 2023, using the most recent preoperative HRCT obtained within one month of confirmation. Conventional CT features and texture parameters (entropy, difference in entropy, sum of entropy) were compared between groups. All continuous predictors were Z-score standardized, and three multivariable logistic-regression models-conventional morphological, texture-only, and combined-were constructed; diagnostic performance was assessed by ROC analysis with optimism-corrected bootstrap internal validation.
RESULTS: The three entropy-related parameters were significantly higher in malignant nodules (P < 0.001). The combined model achieved the highest discrimination (AUC = 0.958; 95% CI, 0.931-0.986; sensitivity 96.8%, specificity 81.4%), significantly outperforming the morphological model alone (DeLong P < 0.001). Multicollinearity was negligible (all predictor variance inflation factors < 1.25), and the optimism-corrected AUC remained high (0.946), supporting favorable internal discrimination after optimism correction.
DISCUSSION: HRCT-based entropy parameters provided incremental information beyond morphology within this cohort; independent external validation is required before clinical application.
METHODS: We analyzed 200 patients with pathologically confirmed SPNs (43 benign, 157 malignant) examined between September 2022 and October 2023, using the most recent preoperative HRCT obtained within one month of confirmation. Conventional CT features and texture parameters (entropy, difference in entropy, sum of entropy) were compared between groups. All continuous predictors were Z-score standardized, and three multivariable logistic-regression models-conventional morphological, texture-only, and combined-were constructed; diagnostic performance was assessed by ROC analysis with optimism-corrected bootstrap internal validation.
RESULTS: The three entropy-related parameters were significantly higher in malignant nodules (P < 0.001). The combined model achieved the highest discrimination (AUC = 0.958; 95% CI, 0.931-0.986; sensitivity 96.8%, specificity 81.4%), significantly outperforming the morphological model alone (DeLong P < 0.001). Multicollinearity was negligible (all predictor variance inflation factors < 1.25), and the optimism-corrected AUC remained high (0.946), supporting favorable internal discrimination after optimism correction.
DISCUSSION: HRCT-based entropy parameters provided incremental information beyond morphology within this cohort; independent external validation is required before clinical application.