北京生物醫(yī)學(xué)工程

結(jié)合卷積神經(jīng)網(wǎng)絡(luò)與圖卷積網(wǎng)絡(luò)的乳腺癌病理圖像分類(lèi)研究

Research on breast cancer pathological images classification combined with convolution neural network and graph convolution network

作者：汪琳琳施俊韓振奇劉立莊

單位：上海大學(xué)通信與信息工程學(xué)院（上海 200444）中國(guó)科學(xué)院上海高等研究院（上海 201210）

關(guān)鍵詞：乳腺癌；病理圖像分類(lèi)；圖卷積網(wǎng)絡(luò)；卷積神經(jīng)網(wǎng)絡(luò)；空間相關(guān)性

分類(lèi)號(hào)：R318

出版年·卷·期（頁(yè)碼）：2021·40·2（130-138）

摘要：

目的乳腺癌的精確診斷對(duì)于后續(xù)治療具有重要臨床意義，組織病理學(xué)分析是腫瘤診斷的金標(biāo)準(zhǔn)。卷積神經(jīng)網(wǎng)絡(luò)(convolution neural network，CNN)具有良好的局部特征提取能力，但無(wú)法有效捕捉細(xì)胞組織間的空間關(guān)系。為了有效利用這種空間關(guān)系，本文提出一種新的結(jié)合CNN與圖卷積網(wǎng)絡(luò)（graph convolution network，GCN）的病理圖像分類(lèi)框架，應(yīng)用于乳腺癌病理圖像的輔助診斷。方法首先對(duì)病理圖像進(jìn)行卷積及下采樣得到一組特征圖，然后將特征圖上每個(gè)像素位置的特征向量表示為1個(gè)節(jié)點(diǎn)，構(gòu)建具有空間結(jié)構(gòu)的圖，并通過(guò)GCN學(xué)習(xí)圖中蘊(yùn)含的空間結(jié)構(gòu)特征。最后，將基于GCN的空間結(jié)構(gòu)特征與基于CNN的全局特征融合，并同時(shí)對(duì)整個(gè)網(wǎng)絡(luò)進(jìn)行優(yōu)化，實(shí)現(xiàn)基于融合特征的病理圖像分類(lèi)。結(jié)果本文在提出框架下進(jìn)行了3種GCN的比較，其中CNN-sGCN-fusion算法在2015生物成像挑戰(zhàn)賽乳腺組織學(xué)數(shù)據(jù)集上獲得93.53%±1.80%的準(zhǔn)確率，在Databiox乳腺數(shù)據(jù)集上獲得78.47%±5.33%的準(zhǔn)確率。結(jié)論與傳統(tǒng)基于CNN的病理圖像分類(lèi)算法相比，本文提出的結(jié)合CNN與GCN的算法有效融合了病理圖像的全局特征與空間結(jié)構(gòu)特征，從而提升了分類(lèi)性能，具有潛在的應(yīng)用可行性。

Objective The accurate diagnosis of breast cancer is of great clinical significance for subsequent treatment, and histopathological analysis is the gold standard for tumor diagnosis. Convolution neural network (CNN) has good local feature extraction capabilities, but it cannot effectively capture the spatial relationship between cell tissues. In order to effectively utilize this spatial relationship, this paper proposes a new pathological image classification framework combining CNN and graph convolution network (GCN) for the auxiliary diagnosis of breast cancer pathological images. Methods Firstly, the pathological image is convoluted and subsampled to get a group of feature maps. Then, the feature vector of each pixel position on the feature maps is represented as a node to construct the graph with spatial structure, and the spatial structure features contained in the graph are learned by GCN. Finally, the spatial structure features based on GCN are fused with the global features based on CNN, and the whole network is optimized at the same time to achieve pathological image classification based on fusion features. Results This paper compares three types of GCN under the proposed framework. Among them, the CNN-sGCN-fusion algorithm achieved 93.53%±1.80% accuracy on the bioimaging challenge 2015 breast histology dataset, and 78.47%±5.33% accuracy on the Databiox breast dataset. Conclusions Compared with the traditional pathological image classification algorithms based on CNN, the algorithm proposed in this paper combines the global and spatial structure features of pathological images effectively, which improves the classification performance and has potential application feasibility.

參考文獻(xiàn)：

[1]?Wild CP. International agency for research on cancer?[J]. Encyclopedia of Toxicology, 2014, 133(9):?1067-1069.

[2]?Gurcan MN, Boucheron LE, Can A, et al.?Histopathological image analysis: a review?[J]. IEEE Reviews in Biomedical Engineering,?2009, 2: 147-171.

[3]?Yener B. Cell-graphs: image-driven modeling of structure-function relationship [J]. Communications of the ACM, 2016, 60(1):?74-84.

[4]?Baba AI, Catoi C. Tumor cell morphology [M]//Comparative Oncology. Bucharest, RO: The Publishing House of the Romanian Academy, 2007.

[5]?Sharma H, Zerbe N, Lohmann S, et al.?A review of graph-based methods for image analysis in digital histopathology [J].?Diagnostic Pathology, 2015,1(1):1-51.?

[6]?He L, Long LR, Antani S,?et al. Histology image analysis for carcinoma detection and grading [J].?Computer Methods and Programs in Biomedicine,?2012, 107(3):?538-556.

[7]?鄭光遠(yuǎn),劉峽壁,韓光輝.醫(yī)學(xué)影像計(jì)算機(jī)輔助檢測(cè)與診斷系統(tǒng)綜述 [J].軟件學(xué)報(bào),2018, 29(5):1471-1514.

Zheng GY, Liu XB, Han GH. Survey on medical image computer aided detection and diagnosis systems [J]. Journal of Software, 2018, 29(5):1471-1514.

[8]?Lecun Y, Bengio Y, Hinton G. Deep learning [J]. Nature, 2015, 521(7553):436-444.

[9]?Shen DG, Wu GR, Suk HI. Deep learning in medical image analysis [J]. Annual Review of Biomedical Engineering, 2017, 19(1):221-248.

[10]?Litjens G,?Kooi T,?Bejnordi BE,?et al. A survey on deep?learning in medical image analysis [J]. Medical Image?Analysis，2017,?42(9):?60-88.

[11]?Spanhol FA, Oliveira LS, Petitjean C, et al.?Breast cancer histopathological image classification using convolutional neural networks [C] // 2016 International Joint Conference on Neural Networks (IJCNN).?Vancouver, BC：IEEE Press, 2016:?2560-2567.

[12]?Araújo T, Aresta G, Castro E, et al. Classification of breast cancer histology images using convolutional neural networks [J]. PLoS One, 2017, 12(6): e0177544.

[13]?Vesal S, Ravikumar N, Davari AA, et al. Classification of breast cancer histology images using transfer learning [C] // International Conference Image Analysis and Recognition (ICIAR)?2018.?Switzerland:?Springer, Cham, 2018:812-819.

[14]?Yan?R, Ren F, Wang ZH, et al. A hybrid convolutional and recurrent deep neural network for breast cancer pathological image classification [C] //?2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Madrid, Spain: IEEE?Press, 2018: ?957-962.

[15]?Wang CF, Shi J, Zhang Q, et al. Histopathological image classification with bilinear convolutional neural networks [C] //?39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).?Seogwipo: IEEE Press, 2017: 4050-4053.

[16]?Kipf TN, Welling M. Semi-Supervised classification with graph convolutional networks [C] //?International Conference on Learning Representations (ICLR)?2017.??San Juan, Puerto Rico: ICLR, 2017.?

[17]?Wu ZH, Pan SR, Chen FW, et al.?A comprehensive survey on graph neural networks [J]. IEEE Transactions on Neural Networks and Learning System, 2019:1-21.?

[18]?徐冰冰,岑科廷,黃俊杰,等.圖卷積神經(jīng)網(wǎng)絡(luò)綜述[J].計(jì)算機(jī)學(xué)報(bào), 2020,43(5):755-780.

Xu BB, Cen KT, Huang JJ, et al.?A survey of graph convolution neural networks?[J].?Chinese Journal of Computers, 2020,43(5):755-780.

[19]?Hamilton WL, Ying R, Leskovec J. Inductive representation learning on large graphs [C] // 31st Conference on Neural Information Processing Systems (NIPS). Long Beach, CA, USA,?2017:?1024-1034.

[20]?Wang Y, Sun YB, Liu ZW, et al. Dynamic graph cnn for learning on point clouds [J]. ACM Transactions on Graphics, 2019, 38(5):?146-158.

[21]?Bruna J, Zaremba W, Szlam A, et al. Spectral networks and locally connected networks on graphs [C] //?2014?International Conference on Learning Representations (ICLR). Banff, Canada: ICLR, 2014.?

[22]?Zhou YN, Graham S, Koohbanani NA, et al. CGC-Net: cell graph convolutional network for grading of colorectal cancer histology images [C]?//?2019 IEEE International Conference on Computer Vision Workshop (ICCVW).?Seoul, South Korea: IEEE Press, 2019: 388-398.

[23]?Wang JW, Chen RJ, Lu MY, et al.?Weakly supervised prostate TMA classification via graph convolutional network [EB/OL].?[2019-10-29].?https://arxiv.org/pdf/1910.13328v2.pdf.?

[24]?Li RY, Yao JW, Zhu XL,?et al. Graph CNN for survival analysis on whole slide pathological images [M]?//?Medical Image Computing and Computer Assisted Intervention (MICCAI)?2018. Switzerland: Springer,?Cham,?2018, 11071: 174-182.?

[25]?Adnan M, Kalra S, Tizhoosh HR, et al. Representation learning of histopathology images using graph neural networks[C] //?2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).?Seattle, WA, USA: IEEE?Press, 2020: 4254-4261.

[26]?Zhang ML, Zhou ZH. ML-KNN: a lazy learning approach to multi-label learning [J]. Pattern Recognition, 2007, 40(7):?2038-2048.

[27]?Kieffer B, Babaie M, Kalra S, et al. Convolutional neural networks for histopathology image classification: training vs. using pre-trained networks [C]?// 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA). Montreal, QC: IPTA, 2017:1-6.

[28]?He KM, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition [C] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV: IEEE Press, 2016: 770-778.

[29]?Li GH, Müller M, Thabet A, et al. DeepGCNs: Can GCNs go as deep as CNNs? [C] //?IEEE International Conference on Computer Vision (ICCV). Seoul,South Korea: IEEE Press, 2019: 9266-9275.

[30]?Bolhasani H, Amjadi E, Tabatabaeian M, et al. A histopathological image dataset for grading breast invasive ductal carcinomas [J]. Informatics in Medicine Unlocked, 2020, 19:100341.??

[31]?Macenko M, Niethammer M, Marron JS, et al. A method for normalizing histology slides for quantitative analysis [C] //?2009 IEEE International Symposium on Biomedical Imaging (ISBI). Boston, MA, USA?: IEEE Press, 2009:?1107-1110.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频