医学影像人工智能辅助诊断的样本增广方法

doi:10.11772/j.issn.1001-9081.2019030450

计算机应用 ›› 2019, Vol. 39 ›› Issue (9): 2558-2567.DOI: 10.11772/j.issn.1001-9081.2019030450

医学影像人工智能辅助诊断的样本增广方法

魏小娜¹, 李英豪², 王振宇¹, 李皓尊², 汪红志^1,2

1. 上海市磁共振重点实验室(华东师范大学), 上海 200062;
2. 华东师范大学物理与材料科学学院, 上海 200062

收稿日期:2019-03-19 修回日期:2019-05-15 出版日期:2019-09-10 发布日期:2019-05-28
通讯作者: 汪红志
作者简介:魏小娜(1986-),女,安徽宿州人,硕士研究生,主要研究方向:深度学习、医学图像处理;李英豪(1999-),男,重庆人,主要研究方向:机器学习、图像重建;王振宇(1996-),男,江西抚州人,硕士研究生,主要研究方向:深度学习、医学图像处理;李皓尊(1996-),男,上海人,主要研究方向:机器学习、图像重建;汪红志(1975-),男,湖北黄冈人,副教授,博士,主要研究方向:磁共振(成像)技术、医学影像分析。
基金资助:
上海浦江人才计划项目（17PJ1432500）。

Methods of training data augmentation for medical image artificial intelligence aided diagnosis

WEI Xiaona1, LI Yinghao2, WANG Zhenyu1, LI Haozun2, WANG Hongzhi1,2

1. Shanghai Key Laboratory of Magnetic Resonance(East China Normal University), Shanghai 200062, China;
2. School of Physics and Material Science, East China Normal University, Shanghai 200062, China

Received:2019-03-19 Revised:2019-05-15 Online:2019-09-10 Published:2019-05-28
Supported by:
This work is partially supported by the Shanghai Pujiang Talent Plan (17PJ1432500).

摘要/Abstract

摘要：

针对不同领域人工智能（AI）应用研究所面临的采用常规手段获取大量样本时耗时耗力耗财的问题，许多AI研究领域提出了各种各样的样本增广方法。首先，对样本增广的研究背景与意义进行介绍；其次，归纳了几种公知领域（包括自然图像识别、字符识别、语义分析）的样本增广方法，并在此基础上详细论述了医学影像辅助诊断方面的样本获取或增广方法，包括X光片、计算机断层成像（CT）图像、磁共振成像（MRI）图像的样本增广方法；最后，对AI应用领域数据增广方法存在的关键问题进行总结，并对未来的发展趋势进行展望。经归纳总结可知，获取足够数量且具有广泛代表性的训练样本是所有领域AI研发的关键环节。无论是公知领域还是专业领域都进行样本增广，且不同领域甚至同一领域的不同研究方向，其样本获取或增广方法均不相同。此外，样本增广并不是简单地增加样本数量，而是尽可能再现小样本量无法完全覆盖的真实样本存在，进而提高样本多样性，增强AI系统性能。

关键词: 人工智能, 医学影像, 辅助诊断, 样本增广

Abstract:

For the problem of time, effort and money consuming to obtain a large number of samples by conventional means faced by Artificial Intelligence (AI) application research in different fields, a variety of sample augmentation methods have been proposed in many AI research fields. Firstly, the research background and significance of data augmentation were introduced. Then, the methods of data augmentation in several common fields (including natural image recognition, character recognition and discourse parsing) were summarized, and on this basis, a detailed overview of sample acquisition or augmentation methods in the field of medical image assisted diagnosis was provided, including X-ray, Computed Tomography (CT), Magnetic Resonance Imaging (MRI) images. Finally, the key issues of data augmentation methods in AI application fields were summarized and the future development trends were prospected. It can be concluded that obtaining a sufficient number of broadly representative training samples is the key to the research and development of all AI fields. Both the common fields and the professional fields have conducted sample augmentation, and different fields or even different research directions in the same field have different sample acquisition or augmentation methods. In addition, sample augmentation is not simply to increase the number of samples, but to reproduce the existence of real samples that cannot be completely covered by small sample size as far as possible, so as to improve sample diversity and enhance AI system performance.

Key words: Artificial Intelligence (AI), medical image, aided diagnosis, sample augmentation

中图分类号:

TP391.41

魏小娜, 李英豪, 王振宇, 李皓尊, 汪红志. 医学影像人工智能辅助诊断的样本增广方法[J]. 计算机应用, 2019, 39(9): 2558-2567.

WEI Xiaona, LI Yinghao, WANG Zhenyu, LI Haozun, WANG Hongzhi. Methods of training data augmentation for medical image artificial intelligence aided diagnosis[J]. Journal of Computer Applications, 2019, 39(9): 2558-2567.

参考文献

[1] HACKER NOON. Big challenge in deep learning[EB/OL].[2018-11-04]. https://hackernoon.com/%EF%B8%8F-big-challenge-in-deep-learning-training-data-31a88b97b282.
[2] ELIZEBETH G. AI firms lure academics[J]. Nature, 2016, 532(4):422-423.
[3] ALEXIS C. MADRIGAL. Inside Waymo's secret world for training self-driving cars[EB/OL].[2019-01-04]. https://www.yahoo.com/news/inside-waymo-apos-secret-world-152456397.html.
[4] SILVER D, SCHRITTWIESER J, SIMONYAN K, et al. Mastering the game of Go without human knowledge[J]. Nature, 2017, 550(7676):354-359.
[5] SILVER D, HUBERT T, SCHRITTWIESER J, et al. A general reinforcement learning algorithm that masters chess, shogi and Go through self-play[J]. Science, 2018, 362(6419):1140-1144.
[6] TING D S W, LIU Y, BURLINA P, et al. AI for medical imaging goes deep[J]. Nature Medicine, 2018,24(5):539-540.
[7] 李纲,徐鼎梁.AI+医疗:如何做好一只被风吹上天的猪[EB/OL].[2019-01-04]. www.sohu.com/a/222070262_487521. (LI G, XU D L. AI+ medicine:how to be a pig that is blown to the sky[EB/OL].[2019-01-04]. www.sohu.com/a/222070262_487521.)
[8] GREENSPAN H, van GINNEKEN B, SUMMERS R M. Guest editorial deep learning in medical imaging:overview and future promise of an exciting new technique[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1153-1159.
[9] MAXMEN A. AI researchers embrace bitcoin technology to share medical data[J]. Nature, 2018,555(7696):293-294.
[10] 汪红志,赵地,杨丽琴,等.基于AI+MRI的影像诊断的样本增广与批量标注方法[J].波谱学杂志,2018,35(4):447-456.(WANG H Z, ZHAO D, YANG L Q, et al. An approach for training data enrichment and batch labeling in AI+MRI aided diagnosis[J]. Chinese Journal of Magnetic Resonance, 2018, 35(4):447-456.)
[11] 王晓刚.深度学习在图像识别中的研究进展与展望[EB/OL].[2019-01-10]. http://www.360doc.com/content/15/0604/11/20625606_475573792.shtml. (WANG X G. Research progress and prospect of deep learning in image recognition[EB/OL].[2019-01-10]. http://www.360doc.com/content/15/0604/11/20625606_475573792.shtml.)
[12] DENG J, DONG W, SOCHER R, et al. ImageNet:a large-scale hierarchical image database[C]//Proceedings of the 2009 Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2009:248-255.
[13] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet largescale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3):211-252.
[14] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 2012 International Conference on Neural Information Processing Systems. North Miami Beach, FL, USA:Curran Associates, 2012:1097-1105.
[15] CHATFIELD K, SIMONYAN K, VEDALDI A, et al. Return of the devil in the details:delving deep into convolutional nets[EB/OL].[2019-01-10]. https://arxiv.org/pdf/1405.3531.pdf.
[16] RAITOHARJU J, RIABCHENKO E, MEISSNER K, et al. Data enrichment in fine-grained classification of aquatic macroinvertebrates[C]//Proceedings of the ICPR 2nd Workshop on Computer Vision for Analysis of Underwater Imagery. Washington, DC:IEEE Computer Society, 2016:43-48.
[17] ZHANG H Y, CISSSE M, DAUPHIN Y N, et al. Mixup:beyond empirical risk minimization[EB/OL].[2019-01-10]. https://arxiv.org/pdf/1710.09412.pdf.
[18] GATYS L A, ECKER A S, BETHGE M. Image style transfer using convolutional neural networks[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:2414-2423.
[19] JOHNSON J, ALAHI A, LI F. Perceptual losses for real-time style transfer and super-resolution[C]//Proceedings of the 2016 European Conference on Computer Vision, LNCS 9906. Berlin:Springer, 2016:694-711.
[20] GATYS L A, ECKER A S, BETHGE M. A neural algorithm of artistic style[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1508.06576.pdf.
[21] JACKSON P T, TAPOUR-ABARGHOUEI A, BONNER S, et al. Style augmentation:data augmentation via style randomization[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1809.05375v1.pdf.
[22] RAJ B. Data augmentation:how to use deep learning when you have limited data[EB/OL].[2019-01-04]. https://www.kdnuggets.com/2018/05/data-augmentation-deep-learning-limited-data.html.
[23] ZHU J, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2017:2242-2251.
[24] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2014:2672-2680.
[25] 林懿伦,戴星原,李力,等.人工智能研究的新前线:生成式对抗网络[J].自动化学报,2018,44(5):775-792.(LIN Y L, DAI X Y, LI L, et al. The new frontier of AI research:generative adversarial networks[J]. Acta Automatica Sinica, 2018, 44(5):775-792.)
[26] ANTONIOU A, STORKEY A, EDWARDS H. Data augmentation generative adversarial networks[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1711.04340.pdf.
[27] ZHONG Z, ZHENG L, KANG G, et al. Random erasing data augmentation[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1708.04896.pdf.
[28] CUBUK E D, ZOPH B, MANE D, et al. AutoAugment:learning augmentation policies from data[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1805.09501.pdf.
[29] Sebastian Ruder. Transfer learning-machine learning's next frontier[EB/OL].[2019-01-04]. http://ruder.io/transfer-learning/.
[30] PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Transaction on Knowledge and Data Engineering, 2010, 22(10):1345-1359.
[31] YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks?[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1411.1792.pdf.
[32] TAN C, SUN F, KONG T, et al. A survey on deep transfer learning[C]//Proceedings of the 2018 International Conference on Artificial Neural Networks, LNCS 11141. Berlin:Springer:270-279.
[33] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1409.1556.pdf.
[34] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:770-778.
[35] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1512.00567.pdf.
[36] RIABCHENKO E, MEISSNER K, AHMAD I, et al. Learned vs. engineered features for fine-grained classification of aquatic macroinvertebrates[C]//Proceedings of the 23rd International Conference on Pattern Recognition. Piscataway, NJ:IEEE, 2016:2276-2281.
[37] 金连文,钟卓耀,杨钊,等.深度学习在手写汉字识别中的应用综述[J].自动化学报,2016,42(8):1125-1141.(JIN L W, ZHONG Z Y, YANG Z, et al. Applications of deep learning for handwritten Chinese character recognition:a review[J]. Acta Automatica Sinica, 2016, 42(8):1125-1141.)
[38] LeCUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[39] SIMARD P Y, STEINKRAUS D, PLATT J C. Best practices for convolutional neural networks applied to visual document analysis[C]//Proceedings of the 7th International Conference on Document Analysis and Recognition. Washington, DC:IEEE Computer Society, 2003:958-962.
[40] YAEGER L, LYON R, WEBB B. Effective training of a neural network character classifier for word recognition[C]//Proceedings of the 9th International Conference on Neural Information Processing Systems. Denver, Colorado:[s.n.], 1997:807-816.
[41] BASTIEN F, BENGIO Y, BERGERON A, et al. Deep self-taught learning for handwritten character recognition[EB/OL].[2019-01-10]. https://arxiv.org/pdf/1009.3589v1.pdf.
[42] VARGA T, BUNKE H. Generation of synthetic training data for an HMM-based handwriting recognition system[C]//Proceedings of the 7th International Conference on Document Analysis and Recognition. Piscataway, NJ:IEEE, 2003:618-622.
[43] JADERBERG M, SIMONYAN K, VEDALDI A, et al. Synthetic data and artificial neural networks for natural scene text recognition[EB/OL].[2019-01-10]. https://arxiv.org/pdf/1406.2227.pdf.
[44] 毕佳晶,李敏,郑蕊蕊,等. 面向满文字符识别的训练数据增广方法研究[J].大连民族大学学报,2018,20(1):73-78.(BI J J,LI M, ZHENG R R, et al. Research on training data augmentation methods for Manchu character recognition[J]. Journal of Dalian Minzu University, 2018, 20(1):73-78.)
[45] JIN L, HUANG J, YIN J, et al. Deformation transformation for handwritten Chinese character shape correction[C]//Proceedings of the 3rd International Conference on Multimodal Interfaces, LNCS 1948. Berlin:Springer, 2000:450-457.
[46] CHEN G, ZHANG H, GUO J. Learning pattern generation for handwritten Chinese character using pattern transform method with cosine function[C]//Proceedings of the 2006 International Conference on Machine Learning and Cybernetics. Piscataway, NJ:IEEE, 2006:3329-3333.
[47] WONG S C, GATT A, STAMATESCU V, et al. Understanding data augmentation for classification:when to warp?[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1609.08764.pdf.
[48] BAIRD H S. Document image defect models[M]//BAIRD H S, BUNKE H, YAMAMOTO K. Structured Document Image Analysis. Berlin:Springer, 1992:546-556.
[49] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE:synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16(1):321-356.
[50] DEVRIES T, TAYLOR G W. Dateset augmentation in feature space[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1702.05538.pdf.
[51] GURUMURTHY S, SARVADEVABHATLA R K, BABU R V. DeLiGAN:generative adversarial networks for diverse and limited data[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2017:4941-4949.
[52] 杨明,刘强,尹忠科,等.基于轮廓追踪的字符识别特征提取[J].计算机工程与应用2007,43(20):207-209.(YANG M, LIU Q, YIN Z K, et al. Feature extraction in character recognition based on contour pursuit[J]. Computer Engineering and Applications, 2007, 43(20):207-209.)
[53] MIYAO H, MARUYAMA M. Virtual example synthesis based on PCA for off-line handwritten character recognition[C]//Proceedings of the 7th International Workshop on Document Analysis Systems, LNCS 3872. Berlin:Springer, 2006:96-105.
[54] LEUNG K C, LEUNG C H. Recognition of handwritten Chinese characters by combining regularization, Fisher's discriminant and distorted sample generation[C]//Proceedings of the 10th International Conference on Document Analysis and Recognition. Piscataway, NJ:IEEE, 2009:1026-1030.
[55] 赵元庆,吴华.多尺度特征和神经网络相融合的手写体数字识别[J].计算机科学,2013,40(8):316-318.(ZHAO Y Q, WU H. Hand written numeral recognition based on multi-scale features and neural network[J]. Computer Science, 2013, 40(8):316-318.)
[56] 张敏,韩先培,张家俊,等.中文信息处理发展报告(2016)[R].北京:中国中文信息学会,2016.(ZHANG M, HAN X P, ZHANG J J, et al. Chinese information processing development report (2016)[R]. Beijing:Chinese Information Society, 2016.)
[57] JIA R, LIANG P. Data recombination for neural semantic parsing[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics, 2016:12-22.
[58] XU Y, JIA R, MOU L, et al. Improved relation classification by deep recurrent neural networks with data augmentation[EB/OL].[2019-01-04]. https:arxiv.org/pdf/1601.03651.pdf.
[59] JIANG K, CARENINI G, NG R T. Training data enrichment for infrequent discourse relations[EB/OL].[2019-01-04]. https://www.aclweb.org/anthology/C16-1245.
[60] FADAEE M, BISAZZA A, MONZ C. Data augmentation for low-resource neural machine translation[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics, 2017:567-573.
[61] KOBAYASHI S. Contextual augmentation:data augmentation by words with paradigmatic relations[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1805.06201.pdf.
[62] HOU Y, LIU Y, CHE W, et al. Sequence-to-sequence data augmentation for dialogue language understanding[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1807.01554.pdf.
[63] JAEGER S, CANDEMIR S, ANTANI S, et al. Two public chest X-ray datasets for computer-aided screening of pulmonary diseases[J]. Quantitative Imaging in Medicine and Surgery, 2014, 4(6):475-477.
[64] JAEGER S, KARARGYRIS A, CANDEMIR S, et al. Automatic tuberculosis screening using chest radiographs[J]. IEEE Transactions on Medical Imaging, 2014, 33(2):233-245.
[65] CANDEMIR S, JAEGER S, PALANIAPPAN K, et al. Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration[J]. IEEE Transactions on Medical Imaging, 2014, 33(2):577-590.
[66] DEMNER-FUSHMAN D, KOHLI M D, ROSENMAN M B, et al. Preparing a collection of radiology examinations for distribution and retrieval[J]. Journal of the American Medical Informatics Association, 2016, 23(2):304-310.
[67] Open-i. Open access biomedical image search engine[DB/OL].[2019-01-04]. https://openi.nlm.nih.gov.
[68] WANG X, PENG Y, LU L, et al. Chest X-ray8:hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2017:3462-3471.
[69] RAJPURKAR P, IRVIN J, ZHU K, et al. CheXNet:radiologist-level pneumonia detection on chest X-rays with deep learning[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1711.05225.pdf.
[70] RAJPURKAR P, IRVIN J, BAGUL A, et al. MURA dataset:towards radiologist-level abnormality detection in musculoskeletal radiographs[EB/OL].[2019-01-04].https://stanfordmlgroup.github.io/competitions/mura/.
[71] 程国华,陈波,季红丽. 基于3D全连接卷积神经网络的CT图像肺结节检测系统:CN201710173432.6[P/OL].2017-07-11[2019-01-04]. http://www2.drugfuture.com/cnpat/search.aspx.(CHENG G H, CHEN B, JI H L. CT image pulmonary nodule detection system based on 3D fully connected convolutional neural network:CN201710173432.6[P/OL]. 2017-07-11[2019-01-04]. http://www2.drugfuture.com/cnpat/search.aspx.)
[72] 机器之心.天池大数据竞赛第一名,上海交通大学人工智能实验室如何用AI定位肺结节[EB/OL].[2019-01-04].https://www.jiqizhixin.com/articles/2017-10-24.(Heart of Machine. How to locate pulmonary nodules with AI in artificial intelligence laboratory of Shanghai Jiaotong University which is Tianchi Big Data Competition No. 1[EB/OL].[2019-01-04]. https://www.jiqizhixin.com/articles/2017-10-24.)
[73] FRID-ADAR M, KLANG E, AMITAI M, et al. Synthetic data augmentation using GAN for improved liver lesion classification[C]//Proceedings of the IEEE 15th International Symposium on Biomedical Imaging. Piscataway, NJ:IEEE, 2018:289-293.
[74] NIE D, TRULLO R, LIANG J, et al. Medical image synthesis with context-aware generative adversarial networks[C]//Proceedings of the 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 10435. Berlin:Springer, 2017:417-425.
[75] 林伟铭,高钦泉,杜民.卷积神经网络诊断阿尔兹海默症的方法[J].计算机应用,2017, 32(12):3504-3508.(LIN W M, GAO Q Q, DU M. Convolutional neural network based method for diagnosis of Alzheimer's disease[J]. Journal of Computer Applications, 2017, 32(12):3504-3508.)
[76] THYREAU B, SATO K, FUKUDA H, et al. Segmentation of the hippocampus by transferring algorithmic knowledge for large cohort processing[J]. Medical Image Analysis, 2018,43:214-228.
[77] DONG H, YANG G, LIU F, et al. Automatic brain tumor detection and segmentation using U-net based fully convolutional networks[C]//Proceedings of the 2017 Annual Conference on Medical Image Understanding and Analysis, CCIS 723. Berlin:Springer, 2017:506-517.
[78] RONNEBERGER O, FISCHER P, BROX T. U-net:convolutional networks for biomedical image segmentation[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Berlin:Springer, 2015:234-241.
[79] MENZE B H, JAKAB A, BAUER S, et al. The multimodal brain tumor image segmentation benchmark (BRATS)[J]. IEEE Transactions on Medical Imaging, 2015, 34(10):1993-2024.
[80] SHIN H, TENEHOLTZ N A, ROGERS J K, et al. Medical image synthesis for data augmentation and anonymization using generative adversarial networks[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1807.10225.pdf.
[81] VASCONCELOS C N, VASCONCELOS B N. Increasing deep learning melanoma classification by classical and expert knowledge based image transforms[EB/OL].[2019-01-04]. https://arxiv.org/pdf/1702.07025v1.pdf.
[82] CIRESAN D C, GIUSTI A, GAMBARDELLA L M, et al. Mitosis detection in breast cancer histology images with deep neural networks[C]//Proceedings of the 2013 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 8150. Berlin:Springer, 2013:411-418.

医学影像人工智能辅助诊断的样本增广方法

Methods of training data augmentation for medical image artificial intelligence aided diagnosis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘子辰, 李小娟, 韦伟. 基于循环神经网络的专利价格自动评估[J]. 计算机应用, 2021, 41(9): 2532-2538.
[2]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[3]	徐少伟, 秦品乐, 曾建朝, 赵致楷, 高媛. 基于注意力机制的两阶段纵膈淋巴结自动分割算法[J]. 计算机应用, 2021, 41(2): 556-562.
[4]	孙中杰, 万涛, 陈东, 汪昊, 赵艳丽, 秦曾昌. 深度学习在主动脉中膜变性病理图像分类中的应用[J]. 计算机应用, 2021, 41(1): 280-285.
[5]	肖禾, 刘志勤, 王庆凤, 黄俊, 周莹, 刘启榆, 徐卫云. 基于迁移学习的多视角乳腺肿块和钙化簇分类方法[J]. 计算机应用, 2020, 40(5): 1460-1464.
[6]	李恬, 张树美, 赵俊莉. 即时战略游戏的智能流场寻路算法设计与实现[J]. 计算机应用, 2020, 40(2): 602-607.
[7]	张俊杰, 孙光民, 郑鲲. 视线跟踪及其在智能教育中的应用研究综述[J]. 计算机应用, 2020, 40(11): 3346-3356.
[8]	戚永军, 顾军华, 张亚娟, 王锋, 田泽培. 基于深度混合卷积模型的肺结节检测方法[J]. 计算机应用, 2020, 40(10): 2904-2909.
[9]	张强, 杨剑, 富丽贞. 双输入流深度反卷积的插值神经网络[J]. 计算机应用, 2019, 39(8): 2271-2275.
[10]	秦品乐, 李鹏波, 张瑞平, 曾建潮, 刘仕杰, 徐少伟. 基于自适应感受野机制的颈部淋巴结自动识别算法[J]. 计算机应用, 2019, 39(12): 3535-3540.
[11]	秦品乐, 李鹏波, 曾建潮, 朱辉, 徐少伟. 基于级联全卷积神经网络的颈部淋巴结自动识别算法[J]. 计算机应用, 2019, 39(10): 2915-2922.
[12]	林伟铭, 高钦泉, 杜民. 卷积神经网络诊断阿尔兹海默症的方法[J]. 计算机应用, 2017, 37(12): 3504-3508.
[13]	董林佳, 强彦, 赵涓涓, 原杰, 赵文婷. 基于三维形状指数的肺结节自动检测方法[J]. 计算机应用, 2017, 37(11): 3182-3187.
[14]	陆惠玲, 周涛, 王惠群, 王文文. 基于特征级融合神经网络的磁共振成像前列腺肿瘤CAD模型[J]. 计算机应用, 2015, 35(10): 2813-2818.
[15]	邢谦谦刘哲星林炳权钱俊曹蕾. CT图像肺结节的毛刺检测与量化评估[J]. 计算机应用, 2014, 34(12): 3599-3604.