Journal of computer assisted tomography · 2024
Invasion in Advanced Gastric Cancer Based on Enhanced Computer Tomography Radiomics Nomogram.
СтатьяНазвание и аннотация: Перевод в очереди
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.
Wang Fan, Hou Qiang, Jiao Junxia, Cheng Huacai, Cui Qiang
Аннотация
OBJECTIVE: To evaluate the efficacy of an enhanced computed tomography (CT) radiomics nomogram in predicting preoperative lymphovascular invasion (LVI) or perineural invasion (PNI) in patients with advanced gastric cancer (GC).
MATERIALS AND METHODS: Data from 149 patients with GC from our hospital (January 2019 to December 2022) were analyzed. High throughput radiomics features were extracted from manually delineated volumes of interest on enhanced CT venous phase images. Optimal features were identified using intraclass correlation coefficient analysis and least absolute shrinkage and selection operator. Models were constructed using the radiomics score (Rad-score), the above features, and independent risk factors. Performance was assessed via the receiver operating characteristic, decision curve analysis and calibration curves.
RESULTS: Eight radiomics features were deemed essential. Factors including history of alcohol consumption ( P = 0.029), peritumor fatty infiltration ( P = 0.046), degree of enhancement ( P = 0.012), and Rad-score ( P < 0.001) were significant predictors of LVI/PNI. The radiomics nomogram, which integrated these factors, showed superior prediction (the training group: area under the curve [AUC] = 0.917; the validation group: AUC = 0.925) compared with other models.
CONCLUSION: The enhanced CT radiomics nomogram offers robust preoperative prediction for LVI/PNI in patients with GC.
MATERIALS AND METHODS: Data from 149 patients with GC from our hospital (January 2019 to December 2022) were analyzed. High throughput radiomics features were extracted from manually delineated volumes of interest on enhanced CT venous phase images. Optimal features were identified using intraclass correlation coefficient analysis and least absolute shrinkage and selection operator. Models were constructed using the radiomics score (Rad-score), the above features, and independent risk factors. Performance was assessed via the receiver operating characteristic, decision curve analysis and calibration curves.
RESULTS: Eight radiomics features were deemed essential. Factors including history of alcohol consumption ( P = 0.029), peritumor fatty infiltration ( P = 0.046), degree of enhancement ( P = 0.012), and Rad-score ( P < 0.001) were significant predictors of LVI/PNI. The radiomics nomogram, which integrated these factors, showed superior prediction (the training group: area under the curve [AUC] = 0.917; the validation group: AUC = 0.925) compared with other models.
CONCLUSION: The enhanced CT radiomics nomogram offers robust preoperative prediction for LVI/PNI in patients with GC.