Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association · 2025
Clinical-radiomic prognostic model integrating staging before and after neoadjuvant chemotherapy in gastric cancer: a multicenter retrospective study.
СтатьяМногоцентровое исследованиеПоддержка исследования: вне правительства СШАНазвание 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.
Wei Yizhou, Pan Siwei, Tong Yahan, Zheng Guoliang, Cao Mengxuan, Zhang Yanqiang, Zhang Ruolan, Zhu Weiwei, Yang Qing, Shen Ke, Zhou Mengya, Xu Ruixin, He Jintao, Sun Jiancheng, Xu Zhiyuan, Cheng Xiangdong, Hu Can
Аннотация
BACKGROUND: Tumor regression grade (TRG) and ypTNM are primarily employed to evaluate the efficacy of Neoadjuvant chemotherapy (NAC) in gastric cancer (GC) patients, however, have limited prognostic value. In this study, we established a clinical-radiomic fusion model, without TRG information, for better prognosis assessment of patients following NAC.
METHODS: A retrospective multicenter study comprising 875 GC patients from three centers was conducted. Cox hazard regression model was used for variable screening and risk weight assignment. Lasso regression was applied for dimensionality reduction and screening of radiomic features. Models were constructed for better prognosis assessment, and were verified in external cohorts.
RESULTS: Survival analysis showed that dynamic T/N staging changes after NAC could effectively distinguish patients based on prognosis. Moreover, the Clinical SCORE model based on the dynamic T/N staging changes and other clinicopathological data had also been found in internal and external validations to be capable of effectively stratifying patients' risks. For CT images, the identified radiomics features were employed to establish the CT SCORE model, which was subsequently integrated with the Clinical SCORE model to construct the Final SCORE model for prognostic evaluation. In the training and validation cohorts, the prognostic discrimination performance of the Final SCORE model exceeded that of TRG and ypTNM. Furthermore, the final model might also be helpful for the screening of the population benefiting from postoperative adjuvant therapy.
CONCLUSION: The developed clinical-radiomic Final SCORE model showed superior prognostic assessment performance than TRG and ypTNM for prognostic assessment of GC patients following NAC.
METHODS: A retrospective multicenter study comprising 875 GC patients from three centers was conducted. Cox hazard regression model was used for variable screening and risk weight assignment. Lasso regression was applied for dimensionality reduction and screening of radiomic features. Models were constructed for better prognosis assessment, and were verified in external cohorts.
RESULTS: Survival analysis showed that dynamic T/N staging changes after NAC could effectively distinguish patients based on prognosis. Moreover, the Clinical SCORE model based on the dynamic T/N staging changes and other clinicopathological data had also been found in internal and external validations to be capable of effectively stratifying patients' risks. For CT images, the identified radiomics features were employed to establish the CT SCORE model, which was subsequently integrated with the Clinical SCORE model to construct the Final SCORE model for prognostic evaluation. In the training and validation cohorts, the prognostic discrimination performance of the Final SCORE model exceeded that of TRG and ypTNM. Furthermore, the final model might also be helpful for the screening of the population benefiting from postoperative adjuvant therapy.
CONCLUSION: The developed clinical-radiomic Final SCORE model showed superior prognostic assessment performance than TRG and ypTNM for prognostic assessment of GC patients following NAC.