基于CVT-RegNet构建MRI下胶质瘤P53基因状态预测模型  

Prediction model of glioma P53 gene status under MRI based on CVT⁃RegNet

作　　者：赵钰琳 梁峰宁 曹亚茹 赵藤 王淋 丁世飞[2] 朱红 Zhao Yulin;Liang Fengning;Cao Yaru;Zhao Teng;Wang Lin;Ding Shifei;Zhu Hong(School of Medical Information and Engineering,Xuzhou Medical University,Xuzhou,221004,China;School of Computer Technology and Science,China University of Mining and Technology,Xuzhou,221116,China)

机构地区：[1]徐州医科大学医学信息与工程学院,徐州221004 [2]中国矿业大学计算机科学与技术学院,徐州221116

出　　处：《南京大学学报（自然科学版）》2024年第4期542-551,共10页Journal of Nanjing University（Natural Science）

基　　金：国家自然科学基金(62102345);江苏省卫生健康委医学科研项目(Z2020032);徐州市重点研发计划(KC22117)。

摘　　要：P53基因状态是胶质瘤精准诊疗的重要依据.针对目前基于MRI(Magnetic Resonance Imaging)的P53基因状态预测的深度学习模型中存在的异质性特征提取不全面、模型存在固有的多种不确定性等问题,提出脑胶质瘤P53基因状态精准预测模型CVT-RegNet(Improved RegNet Integrating CNN,Vision Transfomer and Truth Discovery).首先,采用RegNet网络作为P53基因突变状态预测模型的基础架构,自适应设计搜索P53基因的异质性特征;其次,在模型中将ViT(Vision Transfomer)模块与卷积神经网络(Convolutional Neural Networks,CNN)模块进行融合以改进RegNet网络,进一步优化模型的特征提取性能与计算效率;最后,融入真值发现算法进行迭代寻优以改善模型输出的不确定性,提高预测结果的准确度.实验结果表明,CVT-RegNet模型对P53突变状态的预测准确率达到95.06%,AUC(Area under Curve)得分为0.9492,优于现有的P53基因状态预测模型.CVT-RegNet实现了胶质瘤P53基因状态的无创预测,减轻了患者的经济负担及身心伤害,为胶质瘤的临床精准诊断治疗提供了重要价值.P53 gene status is an important basis for precise diagnosis and treatment of glioma.To solve the problems of incomplete heterogeneous feature extraction and multiple uncertainties inherent in the current deep learning model for MRI(Magnetic Resonance Imaging)⁃based P53 gene status prediction,we propose the precise prediction model of P53 gene status for glioma,CVT⁃RegNet(Improved RegNet integrating CNN,Vision Transfomer,and Truth Discovery).First,the RegNet network is adopted as the infrastructure of the P53 gene mutation status prediction model,which is adaptively designed to search for the heterogeneous features of the P53 gene.Second,the ViT(Vision Transfomer)module and the CNN(Convolutional Neural Networks)module are fused in the model to improve the RegNet network and further optimize the feature extraction performance and computational efficiency of the model.Finally,the Truth Discovery algorithm is incorporated for iterative optimization to improve the uncertainty of the model output,thus improving the accuracy of the prediction results.The experimental results show that the CVT⁃RegNet model predicts the P53 mutation status with an accuracy of 95.06%and an AUC score of 0.9492,which is better than the existing P53 gene status prediction models.CVT⁃RegNet realizes the non⁃invasive prediction of glioma P53 gene status,and reduces the economic burden and physical and psychological harm to patients,which provides a significant value for the precise clinical diagnosis and treatment of glioma.

关 键 词：脑胶质瘤 P53 深度学习 真值发现 不确定性校准 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]