Abstract
The rapid growth of the network in deep learning, a subset of artificial intelligence has motivated the researchers to develop the tools for medical imaging analysis. Here we have introduced computer aided diagnosis tools for binary class classification and detection for breast cancer on histopathological images. In this paper, we have proposed a hybrid deep neural network for image level cancer detection in cancerous and non-cancerous category of histopathology images. The hybrid deep neural network comprises of inception and residual block. The network incorporates the advance multilevel feature map for histopathological images and involve the advantages of inception and residual block. The model proposed combines the sturdiness of inception block and residual block and shows the stability in performance against the existing start-of the art algorithms. The proposed method is trained and validated on two publicly available dataset i.e., Breast Histopathology Images (BHI) and BreakHis. The image level classification has been performed at different magnification level in case of BreakHis dataset. The experimental outcome is evaluated on different performance measures and compared with the conventional Inception model and ResNet model as well as state-of-art breast cancer detection techniques. The proposed approach shows the training accuracy of 0.9642 for Breakhis and 0.8017 for BHI dataset. The model proposed outperforms the existing cancer detection algorithms as well as conventional deep neural networks with obtained accuracy of 0.8521 for BHI and 0.8080,0.8276,0.8655and 0.8580 for 40X,100X,200X and 400X respectively for BreakHis dataset.
Research Highlights
With an increase in the availability of huge pixel whole slide image (WSI) of tissues has given bloom to microscopic pathology application of deep learning and the possibility of loading the scanned images onto the machines, it has become easier for the researchers to develop an automated system for analyzing such images. The paper presents the deep learning-based approach for breast cancer for binary class classification. The proposed model has exploited the inception block of Inception V3 and residual block of Resnet. The proposed model is verified experimentally on both the dataset large (BHI) and small (BreakHis). The contribution of the paper can be summarized as-
-
1.
Remarkable classification accuracy is achieved while working on the recent dataset. The two-step feature map extraction model is trained by combining different magnification levels. The dataset is classified into benign and malignant class.
-
2.
The result is discussed on various performance measures for both the benchmark dataset.
-
3.
The experimental outcomes are compared with the result of the conventional model of Inception and Resnet along with the latest work reported in the literature of deep learning for breast cancer.
-
4.
It is concluded from the experimental result that the proposed model works competently with a large dataset as well as the small dataset. And magnification plays an important role.
Similar content being viewed by others
References
Al-Hayani W, YahyaAlgamal Z, AbdulrazaqKahya M (2017) Classification of breast cancer histopathology images based on adaptive sparse support vector machine. J Appl Math Bioinforma 7(1):49–69
Alom MZ et al (2018) The history began from AlexNet: A comprehensive survey on deep learning approaches [Online]. Available: http://arxiv.org/abs/1803.01164
Alom MZ, Yakopcic C, Nasrin MS, Taha TM, Asari VK (2019) Breast cancer classification from histopathological images with inception recurrent residual convolutional neural network. J Digit Imaging 32(4):605–617. https://doi.org/10.1007/s10278-019-00182-7
Alom MZ et al (2019) A state-of-the-art survey on deep learning theory and architectures. Electron 8(3):1–67. https://doi.org/10.3390/electronics8030292
Arau T, Aguiar P, Eloy C (2018) Classification of breast cancer based on histology images using convolutional neural networks. IEEE Access 12(6):1–14. https://doi.org/10.1371/journal.pone.0177544
B. P&D Laboratory – Pathological anatomy and cytopathology, Parana, “Breast Cancer Histopathological Database (BreakHis)”. Kaggle. https://www.kaggle.com/ambarish/breakhis. Accessed 31 Mar 2020
Bidart R. “cnn-fine-tuning.” https://github.com/renebidart/breakHis/blob/master/notebooks/final/cnn-fine-tuning.ipynb. Accessed 20 Mar 2020
Chapala HR, Sujatha B (2020), ResNet: detection of invasive ductal carcinoma in breast histopathology images using deep learning. Proc Int Conf Electron Sustain Commun Syst ICESC 2020, (Icesc): 60–67. https://doi.org/10.1109/ICESC48915.2020.9155805.
Cheng G, Yang C, Yao X, Guo L, Han J (2018) When deep learning meets metric learning : remote sensing image scene classification via learning discriminative CNNs, pp 1–11
Cheng G, Han J, Zhou P, Xu D (2019) Learning rotation-invariant and fisher discriminative convolutional neural networks for object detection. IEEE Trans Image Process 28(1):265–278. https://doi.org/10.1109/TIP.2018.2867198
Chougrad H, Zouaki H, Alheyane O (2018) Deep convolutional neural networks for breast cancer screening. Comput Methods Programs Biomed 157(April):19–30. https://doi.org/10.1016/j.cmpb.2018.01.011
Cruz-Roa A et al (2014) Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks. Med Imaging 2014 Digit Pathol 9041(216):904103. https://doi.org/10.1117/12.2043872
Dara S, Tumma P (2018) Feature extraction by using deep learning: A survey. Proc 2nd Int Conf Electron Commun Aerosp Technol ICECA 2018 (Iceca): 1795–1801. https://doi.org/10.1109/ICECA.2018.8474912
De Matos J, Britto ADS, Oliveira LES, Koerich AL (2019) Double transfer learning for breast cancer histopathologic image classification. Proc Int Jt Conf Neural Netw 2019-July(July):1–8. https://doi.org/10.1109/IJCNN.2019.8852092
Fonseca P et al (2015) Automatic breast density classification using a convolutional neural network architecture search procedure. Med Imaging 2015 Comput Diagn 9414:941428. https://doi.org/10.1117/12.2081576
Geras KJ et al (2017) High-resolution breast cancer screening with multi-view deep convolutional neural networks pp 1–9, [Online]. Available: http://arxiv.org/abs/1703.07047.
Gonzalez R, Woods R (2002) Digital image processing
Han Z, Wei B, Zheng Y, Yin Y, Li K, Li S (2017) Breast cancer multi-classification from histopathological images with structured deep learning model. Sci Rep 7(1):1–10. https://doi.org/10.1038/s41598-017-04075-z
Hargrave M (2019) Deep Learning. Investopedia [Online]. Available: https://www.investopedia.com/terms/d/deep-learning.asp. Accessed 25 May 2020
Haugeland J (1985) Artifical intelligence : The very idea. First MIT Press Paperback Edition, !989
Helvie MA, Samala RK, Wei J, Hadjiiski L, Cha K, Chan H-P (2016) Mass detection in digital breast tomosynthesis: deep convolutional neural network with transfer learning from mammography. Med Phys 43(12):6654–6666. https://doi.org/10.1118/1.4967345
Hirra I et al (2021) Breast cancer classification from histopathological images using patch-based deep learning modeling. IEEE Access 9:24273–24287. https://doi.org/10.1109/ACCESS.2021.3056516
Jaiswal AK, Srivastava R (2019) Copy move forgery detection using shift invariant SWT and block division mean features. In: Recent Trends in Communication, Computing, and Electronics, pp 289–299
Jaiswal AK, Srivastava R (2020) Time-efficient spliced image analysis using higher-order statistics. Mach Vis Appl 31(7–8). https://doi.org/10.1007/s00138-020-01107-z.
Jaiswal AK, Srivastava R (2020) A technique for image splicing detection using hybrid feature set. Multimed Tools Appl 79(17–18):11837–11860. https://doi.org/10.1007/s11042-019-08480-6
Kallenberg M et al (2016) Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring. IEEE Trans Med Imaging 35(5):1322–1331. https://doi.org/10.1109/TMI.2016.2532122
Litjens G et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42(December 2012):60–88. https://doi.org/10.1016/j.media.2017.07.005
Mooney P (2017) Breast Histopathology Images. Kaggle. https://www.kaggle.com/paultimothymooney/breast-histopathology-images. Accessed 02 Apr 2020
Rakhlin A, Shvets A, Iglovikov V, Kalinin AA (2018) Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 10882 LNCS:737–744. https://doi.org/10.1007/978-3-319-93000-8_83
Robert W, Blackburn E, Drucker B, Hartwell L, King C-M (n.d.) Cell biology and cancer. In: Rediscovering biology: molecular to global perspectives, Oregon Pub., Annenberg Learner
Sahoo S (2018) Residual blocks — Building blocks of ResNet. Towards Datascience. https://towardsdatascience.com/residual-blocks-building-blocks-of-resnet-fd90ca15d6ec#:~:text=Essentially%2C residual blocks allows the,other highway network in practice. Accessed 28 Mar 2020
Sheikhpour R, Sarram MA, Sheikhpour R (2016) Particle swarm optimization for bandwidth determination and feature selection of kernel density estimation based classifiers in diagnosis of breast cancer. Appl Soft Comput J 40:113–131. https://doi.org/10.1016/j.asoc.2015.10.005
Spanhol FA, Oliveira LE, Cavalin PR, Petitjean C, Heutte L (2017) Deep features for breast cancer histopathological image classification. 2017 IEEE International Conference on Systems, Man. Cybern, pp 1868–1873
Spanhol FA, Oliveira LS, Petitjean C, Heutte L (2016) A dataset for breast cancer histopathological image classification. IEEE Trans Biomed Eng 63(7):1455–1462. https://doi.org/10.1109/TBME.2015.2496264
Sudharshan PJ, Petitjean C, Spanhol F, Oliveira LE, Heutte L, Honeine P (2019) Multiple instance learning for histopathological breast cancer image classification. Expert Syst Appl 117:103–111. https://doi.org/10.1016/j.eswa.2018.09.049
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-ResNet and the impact of residual connections on learning. 31st AAAI Conf. Artif Intell AAAI 2017, pp 4278–4284
Tajbakhsh N et al (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35(5):1299–1312. https://doi.org/10.1109/TMI.2016.2535302
Truong TD, Pham HTT (2016) Breast cancer histopathological image classification utilizing convolutional neural network. IFMBE Proc 69:531–536. https://doi.org/10.1007/978-981-13-5859-3_92
Vandenberghe ME, Scott MLJ, Scorer PW, Söderberg M, Balcerzak D, Barker C (2017) Relevance of deep learning to facilitate the diagnosis of HER2 status in breast cancer. Sci Rep 7(March):1–11. https://doi.org/10.1038/srep45938
Veta M, Pluim JPW, Van Diest PJ, Viergever MA (2014) Breast cancer histopathology image analysis: A review. IEEE Trans Biomed Eng 61(5):1400–1411. https://doi.org/10.1109/TBME.2014.2303852
Zainudin Z, Shamsuddin SM (2020) Deep layer CNN architecture for breast cancer histopathology image detection. Springer International Publishing
Zhang Q et al (2016) Deep learning based classification of breast tumors with shear-wave elastography. Ultrasonics 72:150–157. https://doi.org/10.1016/j.ultras.2016.08.004
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest statement
Authors declares that they have no conflict of interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, S., Kumar, R. Breast cancer detection from histopathology images with deep inception and residual blocks. Multimed Tools Appl 81, 5849–5865 (2022). https://doi.org/10.1007/s11042-021-11775-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11775-2