基于权重分配的直肠癌病理完全反应预测算法  

Prediction Algorithm of Pathological Complete Response of Rectal Cancer Based on Weight Distribution

作　　者：李兰兰 徐斌 李娟[2] 王大彪 LI Lan-lan;XU Bin;LI Juan;WANG Da-biao(Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information,College of Physics and Information Engineering,Fuzhou University,Fuzhou Fujian 350108,China;Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases,The Sixth Affiliated Hospital,Sun Yat-sen University,Guangzhou Guangdong 510655,China;College of Chemical and Engineering,Fuzhou University,Fuzhou Fujian 350108,China)

机构地区：[1]福州大学物理与信息工程学院福建省媒体信息智能处理与无线传输重点实验室,福建福州350108 [2]中山大学附属第六医院广东省结直肠盆底疾病研究重点实验室,广东广州510655 [3]福州大学石油化工学院,福建福州350108

出　　处：《计算机仿真》2024年第4期314-319,共6页Computer Simulation

基　　金：福建省自然科学基金(2020J01453)。

摘　　要：研究的目的是建立一个深度学习模型,用于进行直肠癌患者新辅助放化疗后的病理完全反应的预测。回顾性分析了99例直肠癌患者的MR影像资料,并按照训练组(71例)和测试组(28例)进行划分构成数据集。通过U-Net定位分割出肿瘤大致区域,在预测阶段通过改变神经网络卷积层数和切片大小得到了9个基础预测模型,并且利用权重分配法对预测得分进行修正。在验证组9个模型中,切片大小为256*256时,包含4个卷积层的模型整体性能最好,3折交叉验证中平均准确率、特异性和敏感性分别达到了0.714、0.717和0.708。研究构建的模型可以作为辅助工具对结直肠癌晚期患者对新辅助治疗的病理反应进行预测,预测精度较好,可为临床治疗提供参考。The purpose of this study is to establish a deep learning model for predicting the pathological complete response of rectal cancer patients after neoadjuvant chemoradiotherapy.The MR imaging data of 99 patients with rectal cancer were retrospectively analyzed,and the data set was divided according to the training group(71 cases)and the test group(28 cases).The approximate tumor area was segmented by U-Net positioning.In the prediction stage,nine basic prediction models were obtained by changing the convolution layers and slice size of the neural network,and the prediction score was modified by using the weight distribution method.Among the 9 models in the validation group,when the slice size is 256*256,the model with 4 convolution layers has the best overall performance.The average accuracy,specificity and sensitivity in the 3-fold cross-validation are 0.714,0.717 and 0.708 respectively.The model constructed in this study can be used as an auxiliary tool to predict the pathological response of patients with advanced colorectal cancer to neoadjuvant therapy.The prediction accuracy is good and can provide a reference for clinical treatment.

关 键 词：直肠癌 神经网络 新辅助放化疗 磁共振图像 病理完全反应预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]