计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230600043-7.doi: 10.11896/jsjkx.230600043
李鑫蕊1, 张艳芳2, 康晓东1, 李博3, 韩俊玲1,4
LI Xinrui1, ZHANG Yanfang2, KANG Xiaodong1, LI Bo3, HAN Junling1,4
摘要： 脑肿瘤是由于颅脑内部组织出现癌变而导致的高危害疾病,及时诊断脑肿瘤对其治疗及预后至关重要。现阶段不同的网络模型有不同的分类效果,单一的网络模型很难在多个评价指标上有突出的表现。文中基于集成学习提出了一种分类功能强大的Treer-Net模型,它是以TransFG,ResNet50,EfficientNet B4,EfficientNet B7和ResNeXt101为基础模型,通过集成学习的加权平均的结合策略得到的模型。文中将其在脑肿瘤MRI二分类、三分类和四分类的公开数据集上训练完成分类任务。实验数据和结果表明,Treer-Net模型在脑肿瘤三分类数据集上的准确率、精确率、召回率和AUC分别高达99.15%,99.16%,99.15%和99.87%,通过对比分析,充分验证了所提的集成学习方法具有精准、快捷的优越性,更适用于临床辅助诊断脑肿瘤。
中图分类号:
| [1]LIU M H,ZHANG G.Research progress in brain tumor ima-ging based on deep learning[J].Imaging Technology,2021,33(5):50-55. [2]SUN F Q,CUI Z Q,ZOU P,et al.Brain tumor segmentation algorithm based on multi-scale features[J].Computer Science,2022,49(S1):12-16,73. [3]BUCHLAK Q D,ESMAILI N,LEVEQUE J C,et al.Machine learning applications to neuroimaging for glioma detection and classification:An artificial intelligence augmented systematic review[J].J Clin Neurosci,2021,89:177-198. [4]ZHENG L Y.Research and Implementation of Brain Tumor Image Classification Based on Deep Learning[D].Chengdu:University of Electronic Science and Technology of China,2021. [5]CHEN J H J N,LIU S,KORTYLEWSKI A,et al.TransFG:A Transformer Architecture for Fine-grained Recognition[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:852-860. [6]AYADI W,ELHAMZI W,CHARFI I,et al.Deep CNN forBrain Tumor Classification[J].Neural Processing Letters,2021,53(1):671-700. [7]ALI K,SHAIKH Z A,KHAN A A,et al.Multiclass skin cancer classification using EfficientNets-a first step towards preventing skin cancer[J].Neuroscience Informatics,2022,2(4):100034. [8]JIANG L Q,NING C Y,LI J Y.Glioma classification framework based on SE-ResNeXt network and its optimization[J].IET Image Processing,2022,16(2):596-605. [9]WANG X,YI J,LI Y.Application of Fusion Model of 3D-ResNeXt and Bi-LSTM Network in Alzheimer’s Disease Classification[C]//2022 6th International Conference on Communication and Information Systems(ICCIS).2022:136-140. [10]GONG A,YAO X J,DU B,et al.Dermatoscope image classification method based on Ensemble learning and Generative adversarial network[J].Science,Technology and Engineering,2021,21(3):1071-1076. [11]JU C,BIBAUT A,VAN DER LAAN M.The relative performance of ensemble methods with deep convolutional neural networks for image classification[J].Journal of Applied Statistics,2018,45(15):2800-2818. [12]MÜLLER D,SOTO-REY I,KRAMER F. Multi-disease detection in retinal imaging based on ensembling heterogeneous deep learning models[M]//German Medical Data Sciences 2021:Digital Medicine:Recognize-Understand-Heal.IOS Press,2021:23-31. [13]GANAIE M A,HU M,MALIK A,et al.Ensemble deep learning:A review[J].Engineering Applications of Artificial Intelligence,2022,115:105151. [14]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [15]GU R F,LI X,REN W M.Research on Image ClassificationBased on ResNet50 Improved Model[J].Modern Electronic Technology,2023,46(4):107-112. [16]TAN M,LE Q.Efficientnet:Rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning.2019:6105-6114. [17]XIE S,GIRSHICK R,DOLLÁR P,et al.Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1492-1500. [18]JIANG L Q.Research on Brain Tumor Image ClassificationTechnology Based on Deep Learning[D].Changchun:Changchun University of Science and Technology,2022. [19]SAHAAI M B,JOTHILAKSHMI G,RAVIKUMAR D,et al.ResNet-50 based deep neural network using transfer learning for brain tumor classification[C]//AIP Conference Proceedings.2022. [20]LATIF G,BEN BRAHIM G,ISKANDAR D A,et al.GliomaTumors’ classification using deep-neural-network-based features with SVM classifier[J].Diagnostics,2022,12(4):1018. [21]KHAN A R,KHAN S,HAROUNI M,et al.Brain tumor segmentation using K-means clustering and deep learning with synthetic data augmentation for classification[J].Microscopy Research and Technique,2021,84(7):1389-1399. [22]YAHYAOUI H,GHAZOUANI F,FARAH I R.Deep learning guided by an ontology for medical images classification using a multi modal fusion[C]//2021 International Congress of Advanced Technology and Engineering(ICOTEN).2021:1-6. [23]BHATELE K R,BHADAURIA S S.Machine learning application in Glioma classification:review and comparison analysis[J].Archives of Computational Methods in Engineering,2022,29(1):247-274. [24]MURTHY M Y B,KOTESWARARAO A,BABU M S.Adaptive fuzzy deformable fusion and optimized CNN with ensemble classification for automated brain tumor diagnosis[J].Biomedical Engineering Letters,2022,12(1):37-58. [25]DEEPAK S,AMEER P.Brain tumor classification using deep CNN features via transfer learning[J].Computers in Biology and Medicine,2022,12(1):37-58. [26]GHASSEMI N,SHOEIBI A,ROUHANI M.Deep neural network with generative adversarial networks pre-training for brain tumor classification based on MR images[J].Biomedical Signal Processing and Control,2020,57:101678. [27]ÖZKARACA O,BAǴRIAÇIK O,GÜRÜLER H,et al.Multiple Brain Tumor Classification with Dense CNN Architecture Using Brain MRI Images[J].Life,2023,13(2):349. [28]ALI R,AL-JUMAILI S,DURU A D,et al.Classification ofBrain Tumors using MRI images based on Convolutional Neural Network and Supervised Machine Learning Algorithms[C]//2022 International Symposium on Multidisciplinary Studies and Innovative Technologies(ISMSIT).2022:822-827. |
|
||
首页