2019 01 v.30;No.93 72-77
基于ResNet50网络的乳腺癌病理图像分类研究
基金项目(Foundation):
国家自然科学基金项目(No.61672476)
邮箱(Email):
DOI:
中文作者单位:
中国计量大学信息工程学院;
摘要(Abstract):
目的:为解决传统机器学习在病理图像诊断方面的性能不足和纯粹人工阅片导致的误诊或者错诊等问题。方法:结合深度学习在图像识别的优势,以ResNet50为基础网络框架,使用迁移学习实现模型功能,设计了一个用于计算机辅助诊断(Computer-Aided Diagnosis, CAD)的乳腺癌病理图像自动分类模型。结果:模型迭代7 000次时在验证集的正确率收敛于98%左右,在测试集上进行测试,正确率达到97.4%。在测试集中的1 083个恶性肿瘤样本中平均有1 061个样本被正确识别出,达到98%的灵敏度。结论:本模型具有泛化性好、深度大、精度高、收敛快的优点,为CAD应用于实际临床诊断提供了可行性论证。
关键词(KeyWords):
计量;;乳腺癌病理图像;;ResNet50网络;;深度学习;;迁移学习
| 3,224 | 66 | 12 |
| 下载次数 | 被引频次 | 阅读次数 |
参考文献
[1] STEWART B, WILD C P. World cancer report 2014[M]//International Agency for Research on Cancer. Switzerland: World Health Organization,2014:16-76.
[2] 陈诗慧,刘维湘,秦璟,等.基于深度学习和医学图像的癌症计算机辅助诊断研究进展[J].生物医学工程学杂志,2017,34(2):314-319.CHEN S H, LIU W X, QIN W, et al. Progress in computer-aided diagnosis of cancer based on deep learning and medical images[J].Biomedical Engineering Journal,2017,34(2):314-319.
[3] JUSTIN K, LIPO W, JAI R. Deep learning applications in medical image analysis[J].IEEE Journals and Magazines,2018,6(3):9375-9389.
[4] WANG P, HU X, LI Y, et al. Automatic cell nuclei segmentation and classification of breast cancer histopathology images[J].Signal Processing,2016,122(5):1-13.
[5] ZHANG Y G, ZHANG B L, COENEN F, et al. One-class kernel sub-space ensemble for medical image classification[J].EURASIP Journal on Advances in Signal Processing,2014,17(1):17-19.
[6] SPANHOL F A, OLIVEIRA L S, PETITJEAN C, et al. A dataset for breast cancer histopathological image classification[J].IEEE Transactions on Biomedical Engineering,2016,63(7):1455-1462.
[7] 郭乔进,李宁,谢俊元.一种基于上下文的医学图像ROI分类方法[J].模式识别与人工智能,2014,12(27):1057-1064.GUO Q J, LI N, XIE J Y. A context based ROI classification method in medical image[J].Pattern Recognition and Artificial Intelligence, 2014,12(27):1057-1064.
[8] LECUN Y, BENGIO Y, HINTON G. Deep learning[J].Nature,2015,521(7553):436-444.
[9] ZHANG X, WANG S, LIU J, et al. Computer-aided diagnosis of four common cutaneous diseases using deep learning algorithm[C]//2017 IEEE International Conference on Bioinformatics and Biomedicine(BIBM). Kansas City, USA: IEEE,2017:1304-1306.
[10] 肖志鹏,王小华,杨冰,等.基于卷积神经网络的绘画图像分类研究[J].中国计量大学学报,2017,28(2):226-233.XIAO Z P, WANG X H, YANG B, et al. Research on painting image classification based on convolution neural network[J].Journal of China University of Metrology,2017,28(2):226-233.
[11] CHEN H, DOU Q, WANG X, et al. Mitosis detection in breast cancer histology images via deep cascaded networks[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Phoenix Arizona, USA: AAAI,2016:1160-1166.
[12] WANG D, KHOSLA A, GARGEYA R, et al. Deep learning for identifying metastatic breast cancer[EB/OL].(2016-06-18)[2018-12-29].https://arxiv.org/pdf/1606.05718.pdf.
[13] SPANHOL F A, OLIVEIRA L S, PETITJEAN C, et al. Breast cancer histopathological image classification using convolutional neural networks[C]//2016 International Joint Conference on Neural Networks. Vancouver, Canada: IJCNN,2016:2560-2567.
[14] BAYRAMOGLU N, KANNALA J, HEIKKILA J. Deep learning for magnification independent breastcancer histopathology image classification[C]//International Conference on Pattern Recognition. Cancun, Mexico: ICPR,2016:2441-2446.
[15] WEI B Z, HAN Z Y, HE X Y, et al. Deep learning model based breast cancer histopathology image classification[C]//International Conference on Pattern Cloud and Big Data Analysis. Chengdu: IEEE,2017:348-353.
[16] IOFFE S, SZEGEDY C .Batch normalization: Accelerating deep network training by reducing internal covariate shift[EB/OL].(2015-03-02)[2018-12-29].https://arxiv.org/abs/1502.03167.
[17] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE,2016:770-778.
[18] SHIN H C, ROTH H R, GAO M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning[J].IEEE Transactions on Medical Imaging,2016,35(5):1285-1298.
[2] 陈诗慧,刘维湘,秦璟,等.基于深度学习和医学图像的癌症计算机辅助诊断研究进展[J].生物医学工程学杂志,2017,34(2):314-319.CHEN S H, LIU W X, QIN W, et al. Progress in computer-aided diagnosis of cancer based on deep learning and medical images[J].Biomedical Engineering Journal,2017,34(2):314-319.
[3] JUSTIN K, LIPO W, JAI R. Deep learning applications in medical image analysis[J].IEEE Journals and Magazines,2018,6(3):9375-9389.
[4] WANG P, HU X, LI Y, et al. Automatic cell nuclei segmentation and classification of breast cancer histopathology images[J].Signal Processing,2016,122(5):1-13.
[5] ZHANG Y G, ZHANG B L, COENEN F, et al. One-class kernel sub-space ensemble for medical image classification[J].EURASIP Journal on Advances in Signal Processing,2014,17(1):17-19.
[6] SPANHOL F A, OLIVEIRA L S, PETITJEAN C, et al. A dataset for breast cancer histopathological image classification[J].IEEE Transactions on Biomedical Engineering,2016,63(7):1455-1462.
[7] 郭乔进,李宁,谢俊元.一种基于上下文的医学图像ROI分类方法[J].模式识别与人工智能,2014,12(27):1057-1064.GUO Q J, LI N, XIE J Y. A context based ROI classification method in medical image[J].Pattern Recognition and Artificial Intelligence, 2014,12(27):1057-1064.
[8] LECUN Y, BENGIO Y, HINTON G. Deep learning[J].Nature,2015,521(7553):436-444.
[9] ZHANG X, WANG S, LIU J, et al. Computer-aided diagnosis of four common cutaneous diseases using deep learning algorithm[C]//2017 IEEE International Conference on Bioinformatics and Biomedicine(BIBM). Kansas City, USA: IEEE,2017:1304-1306.
[10] 肖志鹏,王小华,杨冰,等.基于卷积神经网络的绘画图像分类研究[J].中国计量大学学报,2017,28(2):226-233.XIAO Z P, WANG X H, YANG B, et al. Research on painting image classification based on convolution neural network[J].Journal of China University of Metrology,2017,28(2):226-233.
[11] CHEN H, DOU Q, WANG X, et al. Mitosis detection in breast cancer histology images via deep cascaded networks[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Phoenix Arizona, USA: AAAI,2016:1160-1166.
[12] WANG D, KHOSLA A, GARGEYA R, et al. Deep learning for identifying metastatic breast cancer[EB/OL].(2016-06-18)[2018-12-29].https://arxiv.org/pdf/1606.05718.pdf.
[13] SPANHOL F A, OLIVEIRA L S, PETITJEAN C, et al. Breast cancer histopathological image classification using convolutional neural networks[C]//2016 International Joint Conference on Neural Networks. Vancouver, Canada: IJCNN,2016:2560-2567.
[14] BAYRAMOGLU N, KANNALA J, HEIKKILA J. Deep learning for magnification independent breastcancer histopathology image classification[C]//International Conference on Pattern Recognition. Cancun, Mexico: ICPR,2016:2441-2446.
[15] WEI B Z, HAN Z Y, HE X Y, et al. Deep learning model based breast cancer histopathology image classification[C]//International Conference on Pattern Cloud and Big Data Analysis. Chengdu: IEEE,2017:348-353.
[16] IOFFE S, SZEGEDY C .Batch normalization: Accelerating deep network training by reducing internal covariate shift[EB/OL].(2015-03-02)[2018-12-29].https://arxiv.org/abs/1502.03167.
[17] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE,2016:770-778.
[18] SHIN H C, ROTH H R, GAO M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning[J].IEEE Transactions on Medical Imaging,2016,35(5):1285-1298.
基本信息:
DOI：
中图分类号:R737.9;TP391.41
引用信息:
[1]王恒,李霞,刘晓芳等.基于ResNet50网络的乳腺癌病理图像分类研究[J].中国计量大学学报,2019,30(01):72-77.
基金信息:
国家自然科学基金项目(No.61672476)
暂无数据