PDF(Pubmed)
Abstract：
BACKGROUND: The aim of this study was to establish a deep learning prediction model for neoadjuvant FLOT chemotherapy response. The neural network utilized clinical data and visual information from whole-slide images (WSIs) of therapy-naïve gastroesophageal cancer biopsies.
METHODS: This study included 78 patients from the University Hospital of Cologne and 59 patients from the University Hospital of Heidelberg used as external validation.
RESULTS: After surgical resection, 33 patients from Cologne (42.3%) were ypN0 and 45 patients (57.7%) were ypN+, while 23 patients from Heidelberg (39.0%) were ypN0 and 36 patients (61.0%) were ypN+ (p = 0.695). The neural network had an accuracy of 92.1% to predict lymph node metastasis and the area under the curve (AUC) was 0.726. A total of 43 patients from Cologne (55.1%) had less than 50% residual vital tumor (RVT) compared to 34 patients from Heidelberg (57.6%, p = 0.955). The model was able to predict tumor regression with an error of ±14.1% and an AUC of 0.648.
CONCLUSIONS: This study demonstrates that visual features extracted by deep learning from therapy-naïve biopsies of gastroesophageal adenocarcinomas correlate with positive lymph nodes and tumor regression. The results will be confirmed in prospective studies to achieve early allocation of patients to the most promising treatment.
METHODS: This study included 78 patients from the University Hospital of Cologne and 59 patients from the University Hospital of Heidelberg used as external validation.
RESULTS: After surgical resection, 33 patients from Cologne (42.3%) were ypN0 and 45 patients (57.7%) were ypN+, while 23 patients from Heidelberg (39.0%) were ypN0 and 36 patients (61.0%) were ypN+ (p = 0.695). The neural network had an accuracy of 92.1% to predict lymph node metastasis and the area under the curve (AUC) was 0.726. A total of 43 patients from Cologne (55.1%) had less than 50% residual vital tumor (RVT) compared to 34 patients from Heidelberg (57.6%, p = 0.955). The model was able to predict tumor regression with an error of ±14.1% and an AUC of 0.648.
CONCLUSIONS: This study demonstrates that visual features extracted by deep learning from therapy-naïve biopsies of gastroesophageal adenocarcinomas correlate with positive lymph nodes and tumor regression. The results will be confirmed in prospective studies to achieve early allocation of patients to the most promising treatment.
摘要：
背景：本研究的目的是建立新辅助FLOT化疗反应的深度学习预测模型。神经网络利用来自治疗初胃食管癌活检的全载玻片图像(WSI)的临床数据和视觉信息。
方法：该研究包括来自科隆大学医院的78名患者和来自海德堡大学医院的59名患者，用作外部验证。
结果：手术切除后，来自科隆的33例患者(42.3%)为ypN0,45例患者(57.7%)为ypN+,海德堡23例(39.0%)为ypN0,ypN+36例(61.0%)(p=0.695)。神经网络预测淋巴结转移的准确率为92.1％，曲线下面积（AUC）为0.726。来自科隆的43例患者（55.1％）的残余重要肿瘤（RVT）少于50％，而来自海德堡的34例患者（57.6％，p=0.955)。该模型能够预测肿瘤消退，误差为±14.1%，AUC为0.648。
结论：这项研究表明，通过深度学习从胃食管腺癌的初始治疗活检中提取的视觉特征与阳性淋巴结和肿瘤消退相关。结果将在前瞻性研究中得到证实，以实现患者早期分配给最有希望的治疗。
方法：该研究包括来自科隆大学医院的78名患者和来自海德堡大学医院的59名患者，用作外部验证。
结果：手术切除后，来自科隆的33例患者(42.3%)为ypN0,45例患者(57.7%)为ypN+,海德堡23例(39.0%)为ypN0,ypN+36例(61.0%)(p=0.695)。神经网络预测淋巴结转移的准确率为92.1％，曲线下面积（AUC）为0.726。来自科隆的43例患者（55.1％）的残余重要肿瘤（RVT）少于50％，而来自海德堡的34例患者（57.6％，p=0.955)。该模型能够预测肿瘤消退，误差为±14.1%，AUC为0.648。
结论：这项研究表明，通过深度学习从胃食管腺癌的初始治疗活检中提取的视觉特征与阳性淋巴结和肿瘤消退相关。结果将在前瞻性研究中得到证实，以实现患者早期分配给最有希望的治疗。
