European journal of radiology · 2026
Ultrasound-, CT-, and MRI-based logistic regression models for the diagnosis of supraclavicular lymph node metastasis in esophageal squamous cell carcinoma.
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.
Du Jingsai, Huang Yue, Han Binbin, Li Ling, Zhang Ruirui, Zhou Yang, Wang Zhaoqi, Zhao Keke, Chu Funing, Bai Bingmei, Zhang Hongkai, Wang Zihan, Li Wenshi, Li Jing, Wang Mengzhu, Li Qian, Qu Jinrong
Аннотация
OBJECTIVES: Accurate diagnosis of supraclavicular lymph node metastasis (SCLNM) in esophageal squamous cell carcinoma (ESCC) is critical for staging and treatment planning. We aimed to develop and validate ultrasound-, computed tomography (CT)- and magnetic resonance imaging (MRI)-based logistic regression models for diagnosing SCLNM in ESCC and to compare their diagnostic performance.
METHODS: This retrospective study with prospective validation included patients with ESCC from two centers. Ultrasound-guided core needle biopsy (ultrasound-CNB) of supraclavicular lymph nodes served as the reference standard. Univariate and multivariate logistic regression analyses were used to develop the models. All models were externally and prospectively validated. The area under the receiver operating characteristic curve (AUROC) was compared among the models and against the traditional size-based criterion. Calibration curves and decision curve analysis were used to evaluate clinical utility.
RESULTS: A total of 143, 66, and 52 participants were included in the training, external validation, and prospective validation cohorts, respectively. The AUROCs of the ultrasound, CT, conventional MRI, functional MRI, and integrated MRI models in the training, external validation, and prospective validation cohorts were 0.846, 0.830, and 0.815; 0.887, 0.837, and 0.825; 0.899, 0.869 and 0.843; 0.912, 0.861, and 0.841; 0.918, 0.879, and 0.867, respectively. Calibration curves showed good agreement and decision curve analysis demonstrated favorable clinical utility. TheCT- and MRI-basedmodels showed significantly higher AUROCs than the traditional size-based criterion.
CONCLUSIONS: Ultrasound-, CT-, and MRI-based logistic regression models demonstrate robust diagnostic performance for SCLNM in ESCC. The CT- and MRI-based models significantly outperforme the traditional size-based criterion and may serve as valuable noninvasive diagnostic tools.
METHODS: This retrospective study with prospective validation included patients with ESCC from two centers. Ultrasound-guided core needle biopsy (ultrasound-CNB) of supraclavicular lymph nodes served as the reference standard. Univariate and multivariate logistic regression analyses were used to develop the models. All models were externally and prospectively validated. The area under the receiver operating characteristic curve (AUROC) was compared among the models and against the traditional size-based criterion. Calibration curves and decision curve analysis were used to evaluate clinical utility.
RESULTS: A total of 143, 66, and 52 participants were included in the training, external validation, and prospective validation cohorts, respectively. The AUROCs of the ultrasound, CT, conventional MRI, functional MRI, and integrated MRI models in the training, external validation, and prospective validation cohorts were 0.846, 0.830, and 0.815; 0.887, 0.837, and 0.825; 0.899, 0.869 and 0.843; 0.912, 0.861, and 0.841; 0.918, 0.879, and 0.867, respectively. Calibration curves showed good agreement and decision curve analysis demonstrated favorable clinical utility. TheCT- and MRI-basedmodels showed significantly higher AUROCs than the traditional size-based criterion.
CONCLUSIONS: Ultrasound-, CT-, and MRI-based logistic regression models demonstrate robust diagnostic performance for SCLNM in ESCC. The CT- and MRI-based models significantly outperforme the traditional size-based criterion and may serve as valuable noninvasive diagnostic tools.