Department of Radiation Oncology, Graduate School of Biomedical Health Sciences, Hiroshima University, Hiroshima, Japan.
School of Medicine, Hiroshima University, Hiroshima, Japan.
Br J Radiol. 2022 Jul 1;95(1135):20210934. doi: 10.1259/bjr.20210934. Epub 2022 May 23.
To propose deep-learning (DL)-based predictive model for pathological complete response rate for resectable locally advanced esophageal squamous cell carcinoma (SCC) after neoadjuvant chemoradiotherapy (NCRT) with endoscopic images.
This retrospective study analyzed 98 patients with locally advanced esophagus cancer treated by preoperative chemoradiotherapy followed by surgery from 2004 to 2016. The patient data were split into two sets: 72 patients for the training of models and 26 patients for testing of the model. Patients was classified into two groups with the LC (Group I: responder and Group II: non-responder). The scanned images were converted into joint photographic experts group (JPEG) format and resized to 150 × 150 pixels. The input image without imaging filter (w/o filter) and with Laplacian, Sobel, and wavelet imaging filters deep-learning model to predict the pathological CR with a convolution neural network (CNN). The accuracy, sensitivity, and specificity, the area under the curve (AUC) of the receiver operating characteristic were evaluated.
The average of accuracy for the cross-validation was 0.64 for w/o filter, 0.69 for Laplacian filter, 0.71 for Sobel filter, and 0.81 for wavelet filter, respectively. The average of sensitivity for the cross-validation was 0.80 for w/o filter, 0.81 for Laplacian filter, 0.67 for Sobel filter, and 0.80 for wavelet filter, respectively. The average of specificity for the cross-validation was 0.37 for w/o filter, 0.55 for Laplacian filter, 0.68 for Sobel filter, and 0.81 for wavelet filter, respectively. From the ROC curve, the average AUC for the cross-validation was 0.58 for w/o filter, 0.67 for Laplacian filter, 0.73 for Sobel filter, and 0.83 for wavelet filter, respectively.
The current study proposed the improvement the accuracy of the DL-based prediction model with the imaging filters. With the imaging filters, the accuracy was significantly improved. The model can be supported to assist clinical oncologists to have a more accurate expectations of the treatment outcome.
The accuracy of the prediction for the local control after radiotherapy can improve with the input image with the imaging filter for deep learning.
提出一种基于深度学习（DL）的预测模型，用于预测接受新辅助放化疗（NCRT）后的可切除局部晚期食管鳞状细胞癌（SCC）的病理完全缓解率（pCRR），其预测模型的输入为内镜图像。
本回顾性研究纳入了 2004 年至 2016 年期间接受术前放化疗联合手术治疗的 98 例局部晚期食管癌患者。将患者数据分为两组：72 例用于模型训练，26 例用于模型测试。将患者分为两组：一组为有反应组（LC 组 I），另一组为无反应组（LC 组 II）。扫描图像转换为联合摄影专家组（JPEG）格式，并调整为 150×150 像素大小。将无成像滤波器（无滤波器）和具有拉普拉斯、索贝尔和小波滤波器的输入图像输入到卷积神经网络（CNN）中，以预测病理 CR。评估准确性、敏感性和特异性、受试者工作特征曲线（ROC）下面积（AUC）。
在交叉验证中，无滤波器的平均准确率为 0.64，拉普拉斯滤波器为 0.69，索贝尔滤波器为 0.71，小波滤波器为 0.81。在交叉验证中，无滤波器的平均敏感性为 0.80，拉普拉斯滤波器为 0.81，索贝尔滤波器为 0.67，小波滤波器为 0.80。在交叉验证中，无滤波器的平均特异性为 0.37，拉普拉斯滤波器为 0.55，索贝尔滤波器为 0.68，小波滤波器为 0.81。从 ROC 曲线来看，在交叉验证中，无滤波器的平均 AUC 为 0.58，拉普拉斯滤波器为 0.67，索贝尔滤波器为 0.73，小波滤波器为 0.83。
本研究提出了一种利用成像滤波器提高基于深度学习的预测模型准确性的方法。通过使用成像滤波器，准确性得到了显著提高。该模型可以支持临床肿瘤学家更准确地预测治疗结果。
通过为深度学习输入带有成像滤波器的图像，可以提高预测放疗后局部控制的准确性。
