A lightweight spatially-aware classification model for breast cancer pathology images

• Autorzy: Jiang Liang , Zhang Cheng , Zhang Huan , Cao Hui

Identyfikatory

DOI

10.1016/j.bbe.2024.08.011

• Języki publikacji: EN

Abstrakty

EN

Breast cancer is a prevalent malignant tumour with high global incidence. Its diagnosis relies primarily on the analysis of pathological breast images. Owing to the complex organisation of the tumour microenvironment, neural network models are essential as efficient classification tools in the field of pathological image analysis. This study introduced spatially-aware attention swift parallel convolution network (SPA-SPCNet), a lightweight and low-latency model for classifying breast pathologies. A novel module for multi-scale feature extraction was constructed using a depthwise separable convolution method. It focuses on the multi-scale features of pathological images to alleviate recognition problems caused by similar local features in breast cancer tissues. The module concatenates the convolutions of different kernels from three branches. Second, a lightweight dynamic spatially-aware attention module was introduced to integrate the visual graph convolutional architecture in a branch. This allowed the model to capture the spatial structure and relationships in image, enabling better handling of the unique spatial distribution relationship between breast cancer tissue structures. The other branch utilises a self-attention mechanism in the transformer. The module can dynamically adjust the attention of the model to different regions in the image, allowing it to focus on the key features of the complex spatial distribution of breast cancer tissue. This feature fusion method enabled the model to capture both global semantics and local details. Compared with existing lightweight models, the proposed model has advantages in terms of tissue structure classification accuracy, parameter quantity, floating-point operations, and real-time inference speed, providing a powerful tool for computer-aided breast pathological image classification.

Słowa kluczowe

EN

breast cancer classification; multi-scale features; graph convolutional network; feature fusion; lightweight network

PL

klasyfikacja raka piersi; sieć konwolucyjna; fuzja funkcji

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2024
• Tom: Vol. 44, no. 3
• Strony: 586--608
• Opis fizyczny: Bibliogr. 62 poz., rys., tab., wykr.

Twórcy

autor

Jiang Liang

• College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, Shandong 250355, China

autor

Zhang Cheng

• College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, Shandong 250355, China

autor

Zhang Huan

• College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, Shandong 250355, China

autor

Cao Hui

• College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, Shandong 250355, China

Bibliografia

• [1] Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. : GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2020;71(3):209-49. http://dx.doi.org/10.3322/caac.21660.
• [2] Vuong D, Simpson PT, Green B, Cummings MC, Lakhani SR. Molecular classification of breast cancer. Virchows Arch 2014;465:1-14. http://dx.doi.org/10.1007/s00428-014-1593-7.
• [3] Gruber IV, Rueckert M, Kagan KO, Staebler A, Siegmann KC, Hartkopf A, et al. Measurement of tumour size with mammography, sonography and magnetic resonance imaging as compared to histological tumour size in primary breast cancer. BMC Cancer 2013;13:1-8. http://dx.doi.org/10.1186/1471-2407-13-328.
• [4] Hammad M, Bakrey M, Bakhiet A, Tadeusiewicz R, Abd El-Latif AA, Plawiak P. A novel end-to-end deep learning approach for cancer detection based on microscopic medical images. Biocybernet Biomed Eng 2022;42(3):737-48. http: //dx.doi.org/10.1016/j.bbe.2022.05.009.
• [5] Diao JA, Wang JK, Chui WF, Mountain V, Gullapally SC, Srinivasan R, et al. Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes. Nature Commun 2021;12(1):1613. http://dx.doi.org/10.1038/s41467-021-21896-9.
• [6] Huang X, Chen J, Chen M, Wan Y, Chen L. Fre-net: Full-region enhanced network for nuclei segmentation in histopathology images. Biocybernet Biomed Eng 2023;43(1):386-401. http://dx.doi.org/10.1016/j.bbe.2023.02.002.
• [7] Prabhu S, Prasad K, Hoang T, Lu X, Sandhya I. Multi-organ squamous cell carcinoma classification using feature interpretation technique for explainability. Biocybernet Biomed Eng 2024;44(2):312-26. http://dx.doi.org/10.1016/j.bbe.2024.03.001.
• [8] Yousif M, van Diest PJ, Laurinavicius A, Rimm D, van der Laak J, Madabhushi A, et al. Artificial intelligence applied to breast pathology. Virchows Arch 2022;480:191-209. http://dx.doi.org/10.1007/s00428-021-03213-3.
• [9] Wen X, Guo X, Wang S, Lu Z, Zhang Y. Breast cancer diagnosis: A systematic review. Biocybernet Biomed Eng 2024;44(1):119-48. http://dx.doi.org/10.1016/j.bbe.2024.01.002.
• [10] Katayama A, Aoki Y, Watanabe Y, Horiguchi J, Rakha EA, Oyama T. Current status and prospects of artificial intelligence in breast cancer pathology: convolutional neural networks to prospective Vision Transformers. Int J Clin Oncol 2024;1-21. http://dx.doi.org/10.1007/s10147-024-02513-3.
• [11] Khan S, Naseer M, Hayat M, Zamir SW, Khan FS, Shah M. Transformers in vision: A survey. ACM Comput Surv 2022;54(10s):1-41. http://dx.doi.org/10.1145/3505244.
• [12] Addo D, Zhou S, Sarpong K, Nartey OT, Abdullah MA, Ukwuoma CC, et al. A hybrid lightweight breast cancer classification framework using the histopathological images. Biocybernet Biomed Eng 2024;44(1):31-54. http://dx.doi.org/10.1016/j.bbe.2023.12.003.
• [13] Kausar T, Lu Y, Kausar A. Breast cancer diagnosis using lightweight deep convolution neural network model. IEEE Access 2023;11:124869-124886. http: //dx.doi.org/10.1109/ACCESS.2023.3326478.
• [14] Sharma S, Mehra R. Conventional machine learning and deep learning approach for multi-classification of breast cancer histopathology images - a comparative insight. J Dig Imag 2020;33(3):632-54. http://dx.doi.org/10.1007/s10278-019-00307-y.
• [15] Demir F. DeepBreastNet: A novel and robust approach for automated breast cancer detection from histopathological images. Biocybernet Biomed Eng 2021;41(3):1123-39. http://dx.doi.org/10.1016/j.bbe.2021.07.004.
• [16] Nanglia S, Ahmad M, Khan FA, Jhanjhi NZ. An enhanced predictive heterogeneous ensemble model for breast cancer prediction. Biomed Signal Process Control 2022;72:103279. http://dx.doi.org/10.1016/j.bspc.2021.103279.
• [17] Petrillo A, Fusco R, Petrosino T, Vallone P, Granata V, Rubulotta MR, et al. A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer. La Radiol Med 2024;129(6):864-78. http://dx.doi.org/10.1007/s11547-024-01817-8.
• [18] Karthik R, Menaka R, Siddharth MV. Classification of breast cancer from histopathology images using an ensemble of deep multiscale networks. Biocybernet Biomed Eng 2022;42(3):963-76. http://dx.doi.org/10.1016/j.bbe.2022.07.006.
• [19] Chattopadhyay S, Dey A, Singh PK, Oliva D, Cuevas E, Sarkar R. MTRRE-Net: A deep learning model for detection of breast cancer from histopathological images. Comput Biol Med 2022;150:106155. http://dx.doi.org/10.1016/j.compbiomed.2022.106155.
• [20] Amin MS, Ahn H. FabNet: A features agglomeration-based convolutional neural network for multiscale breast cancer histopathology images classification. Cancers 2023;15(4):1013. http://dx.doi.org/10.3390/cancers15041013.
• [21] Li G, Wu G, Xu G, Li C, Zhu Z, Ye Y, et al. Pathological image classification via embedded fusion mutual learning. Biomed Signal Process Control 2023;79:104181. http://dx.doi.org/10.1016/j.bspc.2022.104181.
• [22] Taheri S, Golrizkhatami Z, Basabrain AA, Hazzazi MS. A comprehensive study on classification of breast cancer histopathological images: Binary versus multi-category and magnification-specific versus magnification-independent. IEEE Access 2024;12:50431-43. http://dx.doi.org/10.1109/ACCESS.2024.3386355.
• [23] Yan T, Chen G, Zhang H, Wang G, Yan Z, Li Y, et al. Convolutional neural network with parallel convolution scale attention module and ResCBAM for breast histology image classification. Heliyon 2024;10:e30889. http://dx.doi.org/10.1016/j.heliyon.2024.e30889.
• [24] Li W, Long H, Zhan X, Wu Y. MDAA: multi-scale and dual-adaptive attention network for breast cancer classification. Signal Image Video Process 2024;18:3133-43. http://dx.doi.org/10.1007/s11760-023-02976-3.
• [25] Khan SUR, Zhao M, Asif S, Chen X, Zhu Y. GLNET: global-local CNN’s-based informed model for detection of breast cancer categories from histopathological slides. J Supercomput 2024;80:7316-48. http://dx.doi.org/10.1007/s11227-023-05742-x.
• [26] Maurya R, Pandey NN, Dutta MK, Karnati M. FCCS-net: Breast cancer classification using multi-level fully convolutional-channel and spatial attention-based transfer learning approach. Biomed Signal Process Control 2024;94:106258. http://dx.doi.org/10.1016/j.bspc.2024.106258.
• [27] Hekal AA, Elnakib A, Moustafa HED, Amer HM. Breast cancer segmentation from ultrasound images using deep dual-decoder technology with attention network. IEEE Access 2024;12:10087-101. http://dx.doi.org/10.1109/ACCESS.2024.3351564.
• [28] Rani N, Gupta DK, Singh S. Multi-class classification of breast cancer abnormality using transfer learning. Multimedia Tools Appl 2024;1-16. http://dx.doi.org/10.1007/s11042-023-17832-2.
• [29] Sun K, Zheng Y, Yang X, Chen X, Jia W. Semi-supervised breast cancer pathology image segmentation based on fine-grained classification guidance. Med Biol Eng Comput 2024;62(3):901-12. http://dx.doi.org/10.1007/s11517-023-02970-4.
• [30] Ghuge K, Saravanan D. SRMADNet: Swin ResUnet3+-based mammogram image segmentation and heuristic adopted multi-scale attention based DenseNet for breast cancer detection. Biomed Signal Process Control 2024;88:105515. http: //dx.doi.org/10.1016/j.bspc.2023.105515.
• [31] Springenberg M, Frommholz A, Wenzel M, Weicken E, Ma J, Strodthoff N. From modern CNNs to vision transformers: Assessing the performance, robustness, and classification strategies of deep learning models in histopathology. Med Image Anal 2023;87:102809. http://dx.doi.org/10.1016/j.media.2023.102809.
• [32] Xu H, Xu Q, Cong F, Kang J, Han C, Liu Z, et al. Vision transformers for computational histopathology. IEEE Rev Biomed Eng 2023;17:63-79. http://dx.doi.org/10.1109/RBME.2023.3297604.
• [33] Ding M, Qu A, Zhong H, Lai Z, Xiao S, He P. An enhanced vision transformer with wavelet position embedding for histopathological image classification. Pattern Recognit 2023;140:109532. http://dx.doi.org/10.1016/j.patcog.2023.109532.
• [34] Atabansi CC, Nie J, Liu H, Song Q, Yan L, Zhou X. A survey of transformer applications for histopathological image analysis: New developments and future directions. BioMed Eng OnLine 2023;22:96. http://dx.doi.org/10.1186/s12938-023-01157-0.
• [35] He Z, Lin M, Xu Z, Yao Z, Chen H, Alhudhaif A, et al. Deconv-transformer (DecT): A histopathological image classification model for breast cancer based on color deconvolution and transformer architecture. Inform Sci 2022;608:1093-112. http://dx.doi.org/10.1016/j.ins.2022.06.091.
• [36] Wang L, Liu J, Jiang P, Cao D, Pang B. Local-global vision transformer for breast cancer histopathological image classification. In: Proc. 2023 IEEE international conference on acoustics, speech and signal processing. 2023, http://dx.doi.org/10.1109/ICASSP49357.2023.10096781.
• [37] Stegmüller T, Bozorgtabar B, Spahr A, Thiran JP. Scorenet: Learning non-uniform attention and augmentation for transformer-based histopathological image classification. In: Proc. 2023 proceedings of the IEEE/CVF winter conference on applications of computer vision. 2023, http://dx.doi.org/10.1109/wacv56688.2023.00611.
• [38] Sreelekshmi V, Pavithran K, Nair JJ. SwinCNN: An integrated swin trasformer and CNN for improved breast cancer grade classification. IEEE Access 2024;12:68697-710. http://dx.doi.org/10.1109/ACCESS.2024.3397667.
• [39] Huang SK, Yu YT, Huang CR, Cheng HC. Cross-scale fusion transformer for histopathological image classification. IEEE J Biomed Health Inf 2023;28(1):297-308. http://dx.doi.org/10.1109/JBHI.2023.3322387.
• [40] Zhu C, Chai X, Xiao Y, Liu X, Zhang R, Yang Z, et al. Swin-net: A swin-transformer-based network combing with multi-scale features for segmentation of breast tumor ultrasound images. Diagnostics 2024;14(3):269. http://dx.doi.org/10.3390/diagnostics14030269.
• [41] Pan X, Wang P, Jia S, Wang Y, Liu Y, Zhang Y, et al. Multi-contrast learning-guided lightweight few-shot learning scheme for predicting breast cancer molecular subtypes. Med Biol Eng Comput 2024;62(5):1601-13. http://dx.doi.org/10.1007/s11517-024-03031-0.
• [42] Lin G, Chen M, Tan M, Chen L, Chen J. A dual-stage transformer and MLP-based network for breast ultrasound image segmentation. Biocybernet Biomed Eng 2023;43(4):656-71. http://dx.doi.org/10.1016/j.bbe.2023.09.001.
• [43] Han K, Wang Y, Guo J, Tang Y, Wu E. Vision gnn: An image is worth graph of nodes. In: Proc. 2022 advances in neural information processing systems. 2022, http://dx.doi.org/10.48550/arXiv.2206.00272.
• [44] Liu M, Liu Y, Xu P, et al. Exploiting geometric features via hierarchical graph pyramid transformer for cancer diagnosis using histopathological images. IEEE Trans Med Imaging 2024. http://dx.doi.org/10.1109/TMI.2024.3381994.
• [45] Calderaro S, Bosco GL, Vella F, Rizzo R. Breast cancer histologic grade identification by graph neural network embeddings. In: Proc. 2023 international work-conference on bioinformatics and biomedical engineering. 2023, http://dx.doi.org/10.1007/978-3-031-34960-7_20.
• [46] Patel V, Chaurasia V, Mahadeva R, Patolel SP. GARL-net: Graph based adaptive regularized learning deep network for breast cancer classification. IEEE Access 2023;11:9095-112. http://dx.doi.org/10.1109/ACCESS.2023.3239671.
• [47] Liang M, Chen Q, Li B, Wang L, Wang Y, Zhang Y, et al. Interpretable classification of pathology whole-slide images using attention based context-aware graph convolutional neural network. Comput Methods Programs Biomed 2023;229:107268. http://dx.doi.org/10.1016/j.cmpb.2022.107268.
• [48] Ekta V. Auto-BCS: A hybrid system for real-time breast cancer screening from pathological images. J Imaging Inform Med 2024;1-15. http://dx.doi.org/10.1007/s10278-024-01056-3.
• [49] Liao X, Wu Y, Jiang N, Sun J, Xu W, Gao S, et al. Automated detection of abnormal respiratory sound from electronic stethoscope and mobile phone using MobileNetV2. Biocybernet Biomed Eng 2023;43(4):763-75. http://dx.doi.org/10.1016/j.bbe.2023.11.001.
• [50] Xiao P, Qin Z, Chen D, Zhang N, Ding Y, Deng F, et al. FastNet: A lightweight convolutional neural network for tumors fast identification in mobile computer-assisted devices. IEEE Internet Things J 2023;10(11):9878-91. http://dx.doi.org/10.1109/JIOT.2023.3235651.
• [51] Ma N, Zhang X, Zheng HT, Sun J. Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proc. 2018 proceedings of the European conference on computer vision. http://dx.doi.org/10.1007/978-3-030-01264-9_8.
• [52] Chattopadhyay S, Dey A, Singh PK, Sarkar R. DRDA-Net: Dense residual dual-shuffle attention network for breast cancer classification using histopathological images. Comput Biol Med 2022;145:105437. http://dx.doi.org/10.1016/j.compbiomed.2022.105437.
• [53] Xu C, Yi K, Jiang N, Li X, Zhong M, Zhang Y. MDFF-net: A multi-dimensional feature fusion network for breast histopathology image classification. Comput Biol Med 2023;165:107385. http://dx.doi.org/10.1016/j.compbiomed.2023.107385.
• [54] Liu Y, Liu X, Qi Y. Adaptive threshold learning in frequency domain for classification of breast cancer histopathological images. Int J Intell Syst 2024;2024(1):9199410. http://dx.doi.org/10.1155/2024/9199410.
• [55] Ahmadi M, Karimi N, Samavi S. A lightweight deep learning pipeline with DRDANet and MobileNet for breast cancer classification. 2024, http://dx.doi.org/10.48550/arXiv.2403.11135, arxiv preprint arxiv:2403.11135.
• [56] Ashraf FB, Alam SMM, Sakib SM. Enhancing breast cancer classification via histopathological image analysis: Leveraging self-supervised contrastive learning and transfer learning. Heliyon 2024;10:e24094. http://dx.doi.org/10.1016/j.heliyon.2024.e24094.
• [57] Zhong Y, Piao Y, Tan B, Liu J. A multi-task fusion model based on a residual - Multi-layer perceptron network for mammographic breast cancer screening. Comput Methods Programs Biomed 2024;247:108101. http://dx.doi.org/10.1016/j.cmpb.2024.108101.
• [58] Nissar I, Alam S, Masood S, Kashif M. MOB-CBAM: A dual-channel attention-based deep learning generalizable model for breast cancer molecular subtypes prediction using mammograms. Comput Methods Programs Biomed 2024;248:108121. http://dx.doi.org/10.1016/i.cmpb.2024.108121.
• [59] Ogundokun RO, Misra S, Akinrotimi AO, Ogul H. MobileNet-SVM: A lightweight deep transfer learning model to diagnose BCH scans for IoMT-based imaging sensors. Sensors 2023;23(2):656. http://dx.doi.org/10.3390/s23020656.
• [60] Yu D, Lin J, Cao T, Chen Y, Li M, Zhang X. SECS: An effective CNN joint construction strategy for breast cancer histopathological image classification. J King Saud Univ Comput Inf Sci 2023;35(2):810-20. http://dx.doi.org/10.1016/j.jksuci.2023.01.017.
• [61] Choudhary T, Mishra V, Goswami A, Sarangapani J. A transfer learning with structured filter pruning approach for improved breast cancer classification on point-of-care devices. Comput Biol Med 2021;134:104432. http://dx.doi.org/10.1016/j.compbiomed.2021.104432.
• [62] Maleki A, Raahemi M, Nasiri H. Breast cancer diagnosis from histopathology images using deep neural network and xgboost. Biomed Signal Process Control 2023;86:105152. http://dx.doi.org/10.1016/j.bspc.2023.105152.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).