Few-shot cervical cell classification combining weighted prototype and adaptive tensor subspace

doi:10.11772/j.issn.1001-9081.2023101416

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3200-3208.DOI: 10.11772/j.issn.1001-9081.2023101416

• Multimedia computing and computer simulation • Previous Articles Next Articles

Few-shot cervical cell classification combining weighted prototype and adaptive tensor subspace

Li XIE¹(), Weiping SHU¹, Junjie GENG¹, Qiong WANG², Hailin YANG³

^1.School of Internet of Things Engineering，Jiangnan University，Wuxi Jiangsu 214122，China
^2.Department of Medical Laboratory，Wuxi People’s Hospital Affiliated to Nanjing Medical University，Wuxi Jiangsu 214023，China
^3.School of Biological Engineering，Jiangnan University，Wuxi Jiangsu 214122，China

Received:2023-10-19 Revised:2023-12-21 Accepted:2023-12-22 Online:2024-10-15 Published:2024-10-10
Contact: Li XIE
About author:SHU Weiping， born in 1998， M. S. candidate. His research interests include deep learning， image processing.
GENG Junjie， born in 2000， M. S. candidate. His research interests include deep learning， image processing.
WANG Qiong， born in 1981， Ph. D.， associate chief physician. Her research interests include cell image recognition， pathogenesis and diagnostic markers of hematological diseases.
YANG Hailin， born in 1971， Ph. D.， professor. His research interests include biological image processing， optimization and control of fermentation process.
Supported by:
National Key Research and Development Program of China(2022YFC3401302)

结合加权原型和自适应张量子空间的小样本宫颈细胞分类

谢莉¹(), 舒卫平¹, 耿俊杰¹, 王琼², 杨海麟³

^1.江南大学物联网工程学院，江苏无锡 214122
^2.南京医科大学附属无锡人民医院医学检验科，江苏无锡 214023
^3.江南大学生物工程学院，江苏无锡 214122

通讯作者: 谢莉
作者简介:谢莉（1985—），女，重庆人，副教授，博士，主要研究方向：图像处理、软测量建模、系统辨识 xieli@jiangnan.edu.cn
舒卫平（1998—），男，安徽黄山人，硕士研究生，主要研究方向：深度学习、图像处理
耿俊杰（2000—），男，江苏南通人，硕士研究生，主要研究方向：深度学习、图像处理
王琼（1981—），女，湖北咸宁人，副主任医师，博士，主要研究方向：细胞图像识别、血液系统疾病发病机制与诊断标志物
杨海麟（1971—），男，江苏无锡人，教授，博士，主要研究方向：生物细胞图像处理、发酵过程优化与控制。
基金资助:
国家重点研发计划项目(2022YFC3401302)

Abstract

Abstract:

Deep learning image classification algorithms rely on a large amount of training data typically. However， for cervical cell classification tasks in the medical field， collecting large amount of image data is difficult. To accurately classify cervical cells with a limited number of image samples， a few-shot classification algorithm Combining Weighted Prototype and Adaptive Tensor Subspace （CWP-ATS） was proposed. Firstly， the pre-training technique was combined with meta-learning to ensure that the feature extraction network learned more priori knowledge from the meta-training set. Subsequently， the maximum mean discrepancy algorithm was adopted in the prototype computation procedure to assign appropriate weight to each support set sample， and the transductive learning algorithm was further employed for making corrections and obtaining more accurate prototypes. Finally， the multilinear principal component analysis algorithm was utilized to project each class of samples into their respective low-dimensional tensor subspaces， enabling efficient adaptive subspace classifiers in the low-dimensional space to be learned without compromising the natural structures of the original tensor features. In the 2-way 10-shot and 3-way 10-shot classification tasks of few-shot Herlev cervical cell images， compared with the DeepBDC （Deep Brownian Distance Covariance） algorithm， CWP-ATS improved classification accuracy by 2.43 and 3.23 percentage points， respectively； when 30% samples of the meta-test set were interfered by noise， in comparison with the prototype network， the classification accuracy of CWP-ATS was improved by more than 20 percentage points. The experimental results demonstrate that the proposed algorithm can effectively improve the classification accuracy and robustness of few-shot cervical cells.

Key words: image classification, cervical cell, few-shot learning, weighted prototype, adaptive tensor subspace

摘要：

基于深度学习的图像分类算法通常依赖大量训练数据，然而对于医学领域中的宫颈细胞分类任务，难以实现收集大量的图像数据。为了在少量图像样本的条件下正确分类宫颈细胞，提出一种结合加权原型和自适应张量子空间的小样本分类算法（CWP-ATS）。首先，结合预训练技术和元学习，保证特征提取网络从元训练集中学习更多的先验知识；其次，在原型计算过程中采用最大均值差异算法为每个支持集样本赋予合适的权重，并采用转导学习算法修正，以获得更准确的原型；最后，利用多线性主成分分析算法将每类样本投影至各自的低维张量子空间，从而在不破坏原始张量特征自然结构的前提下，在低维空间中学习高效的自适应子空间分类器。在小样本Herlev宫颈细胞图像的2-way 10-shot和3-way 10-shot分类任务中，与DeepBDC（Deep Brownian Distance Covariance）算法相比，CWP-ATS的分类准确度分别提高了2.43和3.23个百分点；当元测试集中30%的样本受噪声干扰时，与原型网络相比，CWP-ATS的分类准确度有超过20个百分点的提升。实验结果表明，CWP-ATS有效提高了对小样本宫颈细胞的分类准确度和鲁棒性。

关键词: 图像分类, 宫颈细胞, 小样本学习, 加权原型, 自适应张量子空间

CLC Number:

TP391.4

Li XIE, Weiping SHU, Junjie GENG, Qiong WANG, Hailin YANG. Few-shot cervical cell classification combining weighted prototype and adaptive tensor subspace[J]. Journal of Computer Applications, 2024, 44(10): 3200-3208.

谢莉, 舒卫平, 耿俊杰, 王琼, 杨海麟. 结合加权原型和自适应张量子空间的小样本宫颈细胞分类[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3200-3208.

Figures/Tables 12

References 38

1	中国抗癌协会妇科肿瘤专业委员会. 宫颈癌诊断与治疗指南（第四版）［J］. 中国实用妇科与产科杂志， 2018， 34（6）： 613-622.
	Gynecological Oncology Professional Committee of China Anti-Cancer Association. Guidelines for the diagnosis and treatment of cervical cancer （fourth edition）［J］. Chinese Journal of Practical Gynecology and Obstetrics， 2018， 34（6）： 613-622.
2	SIEGEL R L， MILLER K D， JEMAL A. Cancer statistics， 2017［J］. CA： A Cancer Journal for Clinicians， 2017， 67（1）： 7-30.
3	韩颖，赵萌，陈胜勇，等. 基于最大截面特征的病变宫颈细胞核的自动筛查［J］. 计算机应用， 2019， 39（4）： 1189-1195.
	HAN Y， ZHAO M， CHEN S Y， et al. Automatic screening of abnormal cervical nucleus based on maximum section feature［J］. Journal of Computer Applications， 2019， 39（4）： 1189-1195.
4	WANG P， WANG L， LI Y， et al. Automatic cell nuclei segmentation and classification of cervical Pap smear images［J］. Biomedical Signal Processing and Control， 2019， 48： 93-103.
5	赵越，曾立波，吴琼水. 卷积神经网络的宫颈细胞图像分类［J］. 计算机辅助设计与图形学学报， 2018， 30（11）： 2049-2054.
	ZHAO Y， ZENG L B， WU Q S. Classification of cervical cells based on convolution neural network［J］. Journal of Computer-Aided Design & Computer Graphics， 2018， 30（11）： 2049-2054.
6	杨洪刚，陈洁洁，徐梦飞. 双线性内卷神经网络用于眼底疾病图像分类［J］. 计算机应用， 2023， 43（1）： 259-264.
	YANG H G， CHEN J J， XU M F. Bilinear involution neural network for image classification of fundus diseases［J］. Journal of Computer Applications， 2023， 43（1）： 259-264.
7	周迪，张自力，陈佳，等. 基于EfficientNetV2和物体上下文表示的胃癌图像分割方法［J］. 计算机应用， 2023， 43（9）： 2955-2962.
	ZHOU D， ZHANG Z L， CHEN J， et al. Stomach cancer image segmentation method based on EfficientNetV2 and object-contextual representation［J］. Journal of Computer Applications， 2023， 43（9）： 2955-2962.
8	胡卉，蔡金清. 基于深度卷积神经网络的宫颈细胞涂片的病变细胞分类［J］. 软件工程， 2018， 21（8）： 19-22.
	HU H， CAI J Q. Lesion cell classification of cervical smear based on deep convolution neural network［J］. Software Engineering， 2018， 21（8）： 19-22.
9	SHI J， WANG R， ZHENG Y， et al. Cervical cell classification with graph convolutional network［J］. Computer Methods and Programs in Biomedicine， 2021， 198： 105807.
10	JIA A D， LI B Z， ZHANG C C. Detection of cervical cancer cells based on strong feature CNN-SVM network［J］. Neurocomputing， 2020， 411： 112-127.
11	董阳，潘海为，崔倩娜，等. 面向多模态磁共振脑瘤图像的小样本分割方法［J］. 计算机应用， 2021， 41（4）： 1049-1054.
	DONG Y， PAN H W， CUI Q N， et al. Few-shot segmentation method for multi-modal magnetic resonance images of brain tumor［J］. Journal of Computer Applications， 2021， 41（4）： 1049-1054.
12	JIANG W， HUANG K， GENG J， et al. Multi-scale metric learning for few-shot learning［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2020， 31（3）： 1091-1102.
13	JIANG H， GAO M， LI H， et al. Multi-learner based deep meta-learning for few-shot medical image classification［J］. IEEE Journal of Biomedical and Health Informatics， 2023， 27（1）： 17-28.
14	SINGH R， BHARTI V， PUROHIT V， et al. MetaMed： few-shot medical image classification using gradient-based meta-learning［J］. Pattern Recognition， 2021， 120： 108111.
15	DAI Z， YI J， YAN L， et al. PFEMed： few-shot medical image classification using prior guided feature enhancement［J］. Pattern Recognition， 2023， 134： 109108.
16	安胜彪，郭昱岐，白宇，等. 小样本图像分类研究综述［J］. 计算机科学与探索， 2023， 17（3）： 511-532.
	AN S B， GUO Y Q， BAI Y， et al. Survey of few-shot image classification research［J］. Journal of Frontiers of Computer Science and Technology， 2023， 17（3）： 511-532.
17	ZHANG R， CHE T， GHAHRAMANI Z， et al. MetaGAN： an adversarial approach to few-shot learning［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates， 2018： 2371-2380.
18	FINN C， ABBEEL P， LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks ［C］// Proceedings of the 34th International Conference on Machine Learning. New York： JMLR.org， 2017： 1126-1135.
19	RUSU A A， RAO D， SYGNOWSKI J， et al. Meta-learning with latent embedding optimization ［EB/OL］. ［2023-12-16］. .
20	VINYALS O， BLUNDELL C， LILLICRAP T， et al. Matching networks for one shot learning［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates， 2016： 3637-3645.
21	SNELL J， SWERSKY K， ZEMEL R. Prototypical networks for few-shot learning［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates， 2017： 4080-4090.
22	ORESHKIN B， RODRÍGUEZ LÓPEZ P， LACOSTE A. TADAM： task dependent adaptive metric for improved few-shot learning［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates， 2018： 719-729.
23	JI Z， CHAI X， YU Y， et al. Improved prototypical networks for few-shot learning［J］. Pattern Recognition Letters， 2020， 140： 81-87.
24	YANG L， LI L， ZHANG Z， et al. DPGN： distribution propagation graph network for few-shot learning［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 13387-13396.
25	HOU R， CHANG H， MA B， et al. Cross attention network for few-shot classification［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates， 2019： 4003-4014.
26	SIMON C， KONIUSZ P， NOCK R， et al. Adaptive subspaces for few-shot learning［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 4135-4144.
27	TIAN Y， WANG Y， KRISHNAN D， et al. Rethinking few-shot image classification： a good embedding is all you need？［C］// Proceedings of the 16th European Conference on Computer Vision. Cham： Springer， 2020： 266-282.
28	LAENEN S， BERTINETTO L. On episodes， prototypical networks， and few-shot learning［J］. Advances in Neural Information Processing Systems， 2021， 34： 24581-24592.
29	GRETTON A， BORGWARDT K M， RASCH M J， et al. A kernel two-sample test［J］. The Journal of Machine Learning Research， 2012， 13： 723-773.
30	KIM B， KHANNA R， KOYEJO O. Examples are not enough， learn to criticize！ Criticism for interpretability［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates， 2016： 2288-2296.
31	LU H， PLATANIOTIS K N， VENETSANOPOULOS A N. MPCA： multilinear principal component analysis of tensor objects［J］. IEEE Transactions on Neural Networks， 2008， 19（1）： 18-39.
32	JANTZEN J， NORUP J， DOUNIAS G， et al. Pap-smear benchmark data for pattern classification［C］// Proceedings of the 2015 Nature Inspired Smart Information System： EU Co-ordination Action. Albufeira， Portugal： NiSIS， 2005： 1-9.
33	SUNG F， YANG Y， ZHANG L， et al. Learning to compare： relation network for few-shot learning［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 1199-1208.
34	DEVOS A， GROSSGLAUSER M. Regression networks for meta-learning few-shot classification ［EB/OL］. ［2023-12-16］. .
35	CHEN H， LI H， LI Y， et al. Multi-level metric learning for few-shot image recognition［C］// Proceedings of the 31st International Conference on Artificial Neural Networks. Cham： Springer， 2022： 243-254.
36	XING L， SHAO S， LIU W， et al. Learning task-specific discriminative embeddings for few-shot image classification［J］. Neurocomputing， 2022， 488： 1-13.
37	XIE J， LONG F， LV J， et al. Joint distribution matters： deep Brownian distance covariance for few-shot classification［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 7962-7971.
38	MA R， FANG P， DRUMMOND T， et al. Adaptive poincaré point to set distance for few-shot classification［C］// Proceedings of the 2022 AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2022， 36（2）： 1926-1934.

数据属性	类别	图像数
元训练集	轻度非典型增生	182
	中度非典型增生	146
	重度非典型增生	197
	原位癌	150
元测试集	浅表鳞状上皮	74
	中层鳞状上皮	70
	柱状上皮	98

数据属性	类别	图像数
元训练集	轻度非典型增生	182
	中度非典型增生	146
	重度非典型增生	197
	原位癌	150
元测试集	浅表鳞状上皮	74
	中层鳞状上皮	70
	柱状上皮	98

特征提取网络	参数量/10⁶	分类准确度/%
特征提取网络	参数量/10⁶	2-way 3-shot	2-way 5-shot	2-way 10-shot	3-way 3-shot	3-way 5-shot	3-way 10-shot
Conv_64F	0.113	94.56±0.77	95.43±0.69	96.10±0.54	88.14±0.62	90.12±0.45	91.58±0.38
ResNet-7	1.219	93.94±0.90	94.88±0.79	95.75±0.54	86.26±0.73	89.24±0.55	90.68±0.48
ResNet-12	8.008	89.13±1.20	90.65±1.17	91.16±1.04	78.23±0.84	80.59±0.75	82.67±0.61

特征提取网络	参数量/10⁶	分类准确度/%
特征提取网络	参数量/10⁶	2-way 3-shot	2-way 5-shot	2-way 10-shot	3-way 3-shot	3-way 5-shot	3-way 10-shot
Conv_64F	0.113	94.56±0.77	95.43±0.69	96.10±0.54	88.14±0.62	90.12±0.45	91.58±0.38
ResNet-7	1.219	93.94±0.90	94.88±0.79	95.75±0.54	86.26±0.73	89.24±0.55	90.68±0.48
ResNet-12	8.008	89.13±1.20	90.65±1.17	91.16±1.04	78.23±0.84	80.59±0.75	82.67±0.61

算法	分类准确度
算法	2-way 3-shot	2-way 5-shot	2-way 10-shot	3-way 3-shot	3-way 5-shot	3-way 10-shot
ProtoNet^［21］	87.10±0.94	90.06±0.72	92.25±0.65	78.62±0.65	81.54±0.60	87.08±0.49
DSN^［26］	89.27±0.88	91.34±0.77	93.26±0.79	79.92±0.77	83.44±0.58	87.31±0.47
RelationNet^［33］	85.22±1.04	88.20±0.65	89.69±0.56	68.76±0.74	73.35±0.58	77.34±0.49
RegressionNet^［34］	89.68±0.96	91.15±0.83	93.16±0.71	79.53±0.82	83.65±0.64	87.72±0.46
MML^［35］	90.46±0.76	92.01±0.62	93.52±0.53	80.99±0.52	84.02±0.41	87.98±0.33
TDE-FSL^［36］	88.16±0.88	91.21±0.67	92.88±0.61	80.11±0.61	83.26±0.55	88.16±0.46
DeepBDC^［37］	90.61±0.92	92.35±0.69	93.67±0.56	80.81±0.69	84.25±0.61	88.35±0.55
APP2S^［38］	90.16±0.71	91.91±0.65	93.01±0.49	80.92±0.54	84.36±0.43	88.42±0.37
本文算法	94.56±0.77	95.43±0.69	96.10±0.54	88.14±0.62	90.12±0.45	91.58±0.38

Few-shot cervical cell classification combining weighted prototype and adaptive tensor subspace

结合加权原型和自适应张量子空间的小样本宫颈细胞分类

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 38

Related Articles 15

Recommended Articles

Metrics

算法	主干网络	分类准确度
算法	主干网络	2-way 3-shot	2-way 5-shot	2-way 10-shot	3-way 3-shot	3-way 5-shot	3-way 10-shot
MetaMed^［14］	Conv_32F	90.12	91.21	93.37	75.08	80.00	84.08
PFEMed^［15］	双路WRN-28-10	94.21±0.81	95.05±0.71	95.46±0.58	87.62±0.67	90.03±0.51	92.11±0.44
本文算法	Conv_64F	94.56±0.77	95.43±0.69	96.10±0.54	88.14±0.62	90.12±0.45	91.58±0.38

模型	预训练	加权原型	张量子空间	原型修正	分类准确度
模型	预训练	加权原型	张量子空间	原型修正	2-way 3-shot	2-way 5-shot	2-way 10-shot	3-way 3-shot	3-way 5-shot	3-way 10-shot
Ⅰ					87.10±0.94	90.06±0.72	92.25±0.65	78.62±0.65	81.54±0.60	87.08±0.49
Ⅱ	√				89.41±1.10	91.76±0.89	93.68±0.60	83.13±0.69	87.97±0.49	88.26±0.43
Ⅲ	√	√			89.61±0.96	92.46±0.65	94.42±0.54	83.51±0.66	88.20±0.47	88.89±0.50
Ⅳ	√	√	√		91.99±0.84	94.46±0.68	95.63±0.50	85.26±0.62	88.90±0.46	91.21±0.39
Ⅴ	√	√	√	√	94.56±0.77	95.43±0.69	96.10±0.54	88.14±0.62	90.12±0.45	91.58±0.38

[1]	Dongwei WANG, Baichen LIU, Zhi HAN, Yanmei WANG, Yandong TANG. Deep network compression method based on low-rank decomposition and vector quantization [J]. Journal of Computer Applications, 2024, 44(7): 1987-1994.
[2]	Xinyan YU, Cheng ZENG, Qian WANG, Peng HE, Xiaoyu DING. Few-shot news topic classification method based on knowledge enhancement and prompt learning [J]. Journal of Computer Applications, 2024, 44(6): 1767-1774.
[3]	Feiyu ZHAI, Handa MA. Hybrid classical-quantum classification model based on DenseNet [J]. Journal of Computer Applications, 2024, 44(6): 1905-1910.
[4]	Bin XIAO, Mo YANG, Min WANG, Guangyuan QIN, Huan LI. Domain generalization method of phase-frequency fusion from independent perspective [J]. Journal of Computer Applications, 2024, 44(4): 1002-1009.
[5]	Xue LI, Guangle YAO, Honghui WANG, Jun LI, Haoran ZHOU, Shaoze YE. Remote sensing image classification based on sample incremental learning [J]. Journal of Computer Applications, 2024, 44(3): 732-736.
[6]	Wen ZHOU, Yuzhang CHEN, Zhiyuan WEN, Shiqi WANG. Fish image classification based on positional overlapping patch embedding and multi-scale channel interactive attention [J]. Journal of Computer Applications, 2024, 44(10): 3209-3216.
[7]	Tong CHEN, Jiwei WEI, Shiyuan HE, Jingkuan SONG, Yang YANG. Adversarial training method with adaptive attack strength [J]. Journal of Computer Applications, 2024, 44(1): 94-100.
[8]	Bihui YU, Xingye CAI, Jingxuan WEI. Few-shot text classification method based on prompt learning [J]. Journal of Computer Applications, 2023, 43(9): 2735-2740.
[9]	Xiaomin ZHOU, Fei TENG, Yi ZHANG. Automatic international classification of diseases coding model based on meta-network [J]. Journal of Computer Applications, 2023, 43(9): 2721-2726.
[10]	Junjian JIANG, Dawei LIU, Yifan LIU, Yougui REN, Zhibin ZHAO. Few-shot object detection algorithm based on Siamese network [J]. Journal of Computer Applications, 2023, 43(8): 2325-2329.
[11]	Bin WANG, Tian XIANG, Yidong LYU, Xiaofan WANG. Adaptive multi-scale feature channel grouping optimization algorithm based on NSGA‑Ⅱ [J]. Journal of Computer Applications, 2023, 43(5): 1401-1408.
[12]	Zhenliang LI, Bo LI. Improved method of convolution neural network based on matrix decomposition [J]. Journal of Computer Applications, 2023, 43(3): 685-691.
[13]	Kai WEN, Xiao XUE, Juan JI. Shared transformation matrix capsule network for complex image classification [J]. Journal of Computer Applications, 2023, 43(11): 3411-3417.
[14]	Jiaxuan WEI, Shikang DU, Zhixuan YU, Ruisheng ZHANG. Review of white-box adversarial attack technologies in image classification [J]. Journal of Computer Applications, 2022, 42(9): 2732-2741.
[15]	Wei REN, Hexiang BAI. Multi-label image classification method based on global and local label relationship [J]. Journal of Computer Applications, 2022, 42(5): 1383-1390.