IJBTT

Local Attention-Based Descriptor Definition using Vision Transformer for Breast Cancer Identification

Local Attention-Based Descriptor Definition using Vision Transformer for Breast Cancer Identification
	© 2022 by IJETT Journal
	Volume-70 Issue-12
	Year of Publication : 2022
	Author : Anish Anurag, Aniket Das, Jaya H. Dewan, Rik Das, Govind Kumar Jha, Sudeep D. Thepade
	DOI : 10.14445/22315381/IJETT-V70I12P230

How to Cite?

Anish Anurag, Aniket Das, Jaya H. Dewan, Rik Das, Govind Kumar Jha, Sudeep D. Thepade, "Local Attention-Based Descriptor Definition using Vision Transformer for Breast Cancer Identification," International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 317-327, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P230

Abstract
Assorted morphological characteristics of breast cancer have categorized it as a heterogeneous life-threatening ailment for females. Researchers have proposed automated approaches for detecting malignant breast cancer from patient images for faster diagnosis with higher precision. Descriptor definition with local attention by dividing a given image into patches can result in a robust representation of the breast cancer histopathological images for identification of malignancy. This work has experimented with feature extraction with local attention-based vision transformers and has evaluated the classification results under multiple classification environments. The research paper has also compared the resilience of classical descriptors generated using handcrafted methods and automated pre-trained convolutional neural network (CNN)- based feature extraction. Three separate handcrafted feature extraction methods, namely Color Histogram, Local Binary Pattern (LBP), and Oriented FAST and Rotated BRIEF(ORB), are used in the process, along with pre-trained CNN-based feature extraction methods (InceptionNet-v1, EfficientNet-B7, and ResNet-50). The experimentation is performed using the BreakHis dataset, and the results have revealed the superior performance of vision transformer-based features as compared to all other individual features considered. Furthermore, early fusion-based descriptors with different combinations of handcrafted and deep-learning features are created to investigate any improvement in the generalization of descriptors. The results have indicated that the feature extracted with local attention-based vision transformer overfits with early fusion has the best performance when evaluated individually in three different classification environments

Keywords
Breast cancer, Local attention, Vision transformer, Color histogram, Local Binary Pattern, Convolutional Neural Networks.

References
[1] Juan Carlos Martín-Sánchez et al., “Projections in Breast and Lung Cancer Mortality among Women: A Bayesian Analysis of 52 Countries Worldwide,” Cancer Research, vol. 78, no. 15, pp. 4436–4442, 2018. Crossref, http://doi.org/10.1158/0008-5472.CAN-18- 0187
[2] Ophira Ginsburg et al., “Breast Cancer Early Detection: A Phased Approach to Implementation,” Cancer, vol. 126, no. S10, pp. 2379– 2393, 2020. Crossref, http://doi.org/10.1002/cncr.32887
[3] Shweta Saxena, and Manasi Gyanchandani, “Machine Learning Methods for Computer-Aided Breast Cancer Diagnosis Using Histopathology: A Narrative Review,” Journal of Medical Imaging Radiation Sciences, vol. 51, no. 1, pp. 182–193, 2020. Crossref, http://doi.org/10.1016/j.jmir.2019.11.001
[4] Mark C.Lloyd et al., “Using Image Analysis as a Tool for Assessment of Prognostic and Predictive Biomarkers for Breast Cancer: How Reliable is it?,” Journal of Pathology Informatics, vol. 1, no. 1, p. 29, 2010. Crossref, http://doi.org/10.4103/2153-3539.74186
[5] Christian A. Falk Dahl StudPsychol et al., “A Study of Body Image in Long-Term Breast Cancer Survivors,” Cancer, vol. 116, no. 15, pp. 3549–3557, 2010. Crossref, http://doi.org/10.1002/cncr.25251
[6] Icro Meattini et al., “Radiation Therapy for Young Women with Early Breast Cancer: Current State of the Art,” Critical Reviews in Oncology/Hematology, vol. 137, pp. 143–153, 2019. Crossref, http://doi.org/10.1016/j.critrevonc.2019.02.014
[7] Farah J Nassar, Rihab Nasr, and Rabih Talhouk, “MicroRNAs as Biomarkers for Early Breast Cancer Diagnosis, Prognosis and Therapy Prediction,” Pharmacology & Therapeutics, vol. 172, pp. 34–49, 2017. Crossref, http://doi.org/10.1016/j.pharmthera.2016.11.012
[8] Liaqat Ali et al., “A Novel Sample and Feature Dependent Ensemble Approach for Parkinson’s Disease Detection,” Neural Computing and Applications, 2022. Crossref, http://doi.org/10.1007/s00521-022-07046-2
[9] Marek Kowal et al., “Computer-Aided Diagnosis of Breast Cancer Based on Fine Needle Biopsy Microscopic Images,” Computers in Biology and Medicine, vol. 43, no. 10, pp. 1563–1572, 2013. Crossref, http://doi.org/10.1016/j.compbiomed.2013.08.003
[10] Paweł Filipczuk et al., “Computer-Aided Breast Cancer Diagnosis Based on the Analysis of Cytological Images of Fine Needle Biopsies,” IEEE Transactions on Medical Imaging, vol. 32, no. 12, pp. 2169–2178, 2013. Crossref, http://doi.org/10.1109/TMI.2013.2275151
[11] Yasmeen Mourice George et al., “Remote Computer-Aided Breast Cancer Detection and Diagnosis System Based on Cytological Images,” IEEE Systems Journal, vol. 8, no. 3, pp. 949–964, 2014. Crossref, http://doi.org/10.1109/JSYST.2013.2279415
[12] Bailing Zhang, “Breast Cancer Diagnosis from Biopsy Images by Serial Fusion of Random Subspace Ensembles,” in 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI), pp. 180–186, 2011. Crossref, http://doi.org/10.1109/BMEI.2011.6098229
[13] Fabio A. Spanhol et al., “A Dataset for Breast Cancer Histopathological Image Classification,” IEEE Transactions on Biomedical Engineering, vol. 63, no. 7, pp. 1455–1462, 2016. Crossref, http://doi.org/10.1109/TBME.2015.2496264
[14] Yann Le Cun, Yoshua Bengio, and Geoffrey Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. Crossref, http://doi.org/10.1038/nature14539
[15] B. Suryakanth, and S A. Hari Prasad, “3D CNN-Residual Neural Network Based Multimodal Medical Image Classification,” International Journal of Engineering Trends and Technology, vol. 70, no. 10, pp. 371–380, 2022. Crossref, http://doi.org/10.14445/22315381/IJETT-V70I10P236
[16] D. M. Bongulwar, V. P. Singh, and T. S N, “Evaluation of CNN based on Hyperparameters to Detect the Quality of Apples,” International Journal of Engineering Trends and Technology, vol. 70, no. 10, pp. 232–246, 2022. Crossref, http://doi.org/10.14445/22315381/IJETT-V70I10P222
[17] Afsaneh Jalalian et al., “Computer-Aided Detection/Diagnosis of Breast Cancer in Mammography and Ultrasound: A Review,” Clinical Imaging, vol. 37, no. 3, pp. 420–426, 2013. Crossref, http://doi.org/10.1016/j.clinimag.2012.09.024
[18] Sudha Prathyusha Jakkaladiki, and Filip Maly, “Potential Role of Artificial Intelligence in Breast Cancer Detection- A Review,” International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 130–139, 2022. Crossref, http://doi.org/10.14445/22315381/IJETT-V70I7P214
[19] Pratheep Kumar P, and V. Mary Amala Bai, “Breast Cancer Detection on Mammographic Images using Hyper Parameter Tuning & Optimization: A Convolutional Neural Network & Transfer Learning Approach,” International Journal of Engineering Trends and Technology, vol. 70, no. 9, pp. 79–92, 2022. Crossref, http://doi.org/10.14445/22315381/IJETT-V70I9P208
[20] B. Stenkvist et al., “Computerized Nuclear Morphometry as an Objective Method for Characterizing Human Cancer Cell Populations,” Cancer Research, vol. 38, no. 12, pp. 4688–4697, 1978.
[21] Andrew J.Evans et al., “2014 American Telemedicine Association Clinical Guidelines for Telepathology: Another Important Step in Support of Increased Adoption of Telepathology for Patient Care,” Journal of Pathology Informatics, vol. 6, no. 1, p. 13, 2015. Crossref, http://doi.org/10.4103/2153-3539.153906
[22] Rik Das, Kanwalpreet Kaur, and Ekta Walia, “Feature Generalization for Breast Cancer Detection in Histopathological Images,” Interdisciplinary Sciences: Computational Life Sciences, vol. 14, no. 2, pp. 566–581, 2022. Crossref, http://doi.org/10.1007/s12539-022-00515-1
[23] Emmanuel Maggiori et al., “Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 55, no. 2, pp. 645–657, 2017. Crossref, http://doi.org/10.1109/TGRS.2016.2612821
[24] Mohammad Rastegari et al., “XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks,” European Conference on Computer Vision, pp. 525-542, 2016. Crossref, http://doi.org/10.1007/978-3-319-46493-0_32
[25] Fabio Alexandre Spanhol et al., “Breast Cancer Histopathological Image Classification using Convolutional Neural Networks,” 2016 International Joint Conference on Neural Networks (IJCNN), pp. 2560–2567, 2016. Crossref, http://doi.org/10.1109/IJCNN.2016.7727519
[26] Smita Khairnar, Sudeep D.Thepade, and Shilpa Gite, “Effect of Image Binarization Thresholds on Breast Cancer Identification in Mammography Images using OTSU, Niblack, Burnsen, Thepade’s SBTC,” Intelligent Systems with Applications, vol. 10–11, p. 200046, 2021. Crossref, http://doi.org/10.1016/j.iswa.2021.200046
[27] Xiaobo Zhou, Xiaodong Wang, and Edward R Dougherty, “Binarization of Microarray Data on the Basis of a Mixture Model,” Molecular Cancer Therapeutics, vol. 2, no. 7, pp. 679–84, 2003.
[28] Youssef Masmoudi, Metin Türkay, and Habib Chabchoub, “A Binarization Strategy for Modelling Mixed Data in Multigroup Classification,” 2013 International Conference on Advanced Logistics and Transport, pp. 347–353, 2013. Crossref, http://doi.org/10.1109/ICAdLT.2013.6568483
[29] Huiling Gong et al., “Ultrasound Image Texture Feature Learning-Based Breast Cancer Benign and Malignant Classification,” Computational and Mathematical Methods in Medicine, vol. 2021, pp. 1–8, 2021. Crossref, http://doi.org/10.1155/2021/6261032
[30] R. Karthiga, and K. Narasimhan, “Medical Imaging Technique Using Curvelet Transform and Machine Learning for the Automated Diagnosis of Breast Cancer From Thermal Image,” Pattern Analysis and Application, vol. 24, no. 3, pp. 981–991, 2021. Crossref, http://doi.org/10.1007/s10044-021-00963-3
[31] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017. Crossref, http://doi.org/10.1145/3065386
[32] Andre Esteva et al., “Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks,” Nature, vol. 542, pp. 115–118, 2017. Crossref, http://doi.org/10.1038/nature21056
[33] Syeda Sara Samreen, and Hakeem Aejaz Aslam, "Hyperspectral Image Classification using Deep Learning Techniques: A Review," SSRG International Journal of Electronics and Communication Engineering, vol. 9, no. 6, pp. 1-4, 2022. Crossref, https://doi.org/10.14445/23488549/IJECE-V9I6P101
[34] Yangqin Feng, Lei Zhang, and Juan Mo, “Deep Manifold Preserving Autoencoder for Classifying Breast Cancer Histopathological Images,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 17, no. 1, pp. 91–101, 2020. Crossref, https://doi.org/10.1109/TCBB.2018.2858763
[35] Nima Tajbakhsh et al., “Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?,” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1299–1312, 2016. Crossref, https://doi.org/10.1109/TMI.2016.2535302
[36] Le Hou et al., “Patch-Based Convolutional Neural Network for Whole Slide Tissue Image Classification,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2424-2433, 2016. Crossref, https://doi.org/10.1109/CVPR.2016.266
[37] Jeff Donahue et al., “DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition,” Proceedings of the 31st International Conference on Machine Learning, 2013.
[38] Artem Babenko et al., “Neural Codes for Image Retrieval,” European Conference on Computer Vision, pp. 584-599, 2014. Crossref, https://doi.org/10.1007/978-3-319-10590-1_38
[39] Mircea Cimpoi, Subhransu Maji, and Andrea Vedaldi, “Deep Filter Banks for Texture Recognition and Segmentation,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3828–3836, 2015. Crossref, https://doi.org/10.1109/CVPR.2015.7299007
[40] Ali Sharif Razavian et al., “CNN Features Off-the-Shelf: An Astounding Baseline for Recognition,” in 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 512–519, 2014. Crossref, https://doi.org/10.1109/CVPRW.2014.131
[41] Behnaz Gheflati, and Hassan Rivaz, “Vision Transformer for Classification of Breast Ultrasound Images,” 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 480-483, 2021. Crossref, https://doi.org/10.1109/EMBC48229.2022.9871809
[42] Zhu He et al., “Deconv-Transformer (Dect): A Histopathological Image Classification Model for Breast Cancer Based on Color Deconvolution and Transformer Architecture,” Information Sciences, vol. 608, pp. 1093–1112, 2022. Crossref, https://doi.org/10.1016/j.ins.2022.06.091
[43] Xiyue Wang et al., “TransPath: Transformer-Based Self-supervised Learning for Histopathological Image Classification,” International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 186–195, 2021. Crossref, https://doi.org/10.1007/978-3-030-87237-3_18
[44] Xuxin Chen et al., “Transformers Improve Breast Cancer Diagnosis from Unregistered Multi-View Mammograms,” Diagnostics, vol. 12, no. 7, p. 1549, 2022. Crossref, https://doi.org/10.3390/diagnostics12071549
[45] Nidhi Mongoriya, and Vinod Patel, "Review The Breast Cancer Detection Technique Using Hybrid Machine Learning," SSRG International Journal of Computer Science and Engineering, vol. 8, no. 6, pp. 5-8, 2021. Crossref, https://doi.org/10.14445/23488387/IJCSE-V8I6P102
[46] P. V. Rukmangadha, and R. Das, “Representation-Learning-Based Fusion Model for Scene Classification Using Convolutional Neural Network (CNN) and Pre-trained CNNs as Feature Extractors,” Computational Intelligence in Pattern Recognition, pp. 631–643, 2022. Crossref, https://doi.org/10.1007/978-981-16-2543-5_54
[47] T. Ojala, M. Pietikäinen, and D. Harwood, “A Comparative Study of Texture Measures with Classification Based on Featured Distributions,” Pattern Recognition, vol. 29, no. 1, pp. 51–59, 1996. Crossref, https://doi.org/10.1016/0031-3203(95)00067-4
[48] Keerti Maithil, and Tasneem Bano Rehman, "Urban Remote Sensing Image Segmentation using Dense U-Net+," SSRG International Journal of Computer Science and Engineering, vol. 9, no. 3, pp. 21-28, 2022. Crossref, https://doi.org/10.14445/23488387/IJCSE-V9I3P103
[49] Bhagwati Charan Patel, and G.R.Sinha, “An Adaptive K-Means Clustering Algorithm for Breast Image Segmentation,” International Journal of Computer Applications, vol. 10, no. 4, pp. 35–38, 2010. Crossref, https://doi.org/10.5120/1467-1982
[50] Pavel Král, and Ladislav Lenc, “LBP Features for Breast Cancer Detection,” 2016 IEEE International Conference on Image Processing (ICIP), pp. 2643–2647, 2016. Crossref, https://doi.org/10.1109/ICIP.2016.7532838
[51] Soumya Deep Roy et al., “Computer Aided Breast Cancer Detection Using Ensembling of Texture and Statistical Image Features,” Sensors, vol. 21, no. 11, p. 3628, 2021. Crossref, https://doi.org/10.3390/s21113628
[52] Maheshvar Chandrasekar et al., “Breast Cancer Histopathological Image Classification using EfficientNet Architecture,” in 2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET), pp. 1–5, 2020. Crossref, https://doi.org/10.1109/TEMSMET51618.2020.9557441
[53] Mohammed Abdulla Salim Al Husaini et al., “Thermal-Based Early Breast Cancer Detection Using Inception V3, Inception V4 and Modified Inception MV4,” Neural Computing and Applications, vol. 34, no. 1, pp. 333–348, 2022. Crossref, https://doi.org/10.1007/s00521-021-06372-1
[54] Arijit Das, and Srinibas Rana, “Exploring Residual Networks for Breast Cancer Detection from Ultrasound Images,” in 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 1–6, 2021. Crossref, https://doi.org/10.1109/ICCCNT51525.2021.9580160
[55] Xiaoyu Yue et al., “Vision Transformer with Progressive Sampling,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 377-386, 2021. Crossref, https://doi.org/10.1109/ICCV48922.2021.00044
[56] Zhongyi Han et al., “Breast Cancer Multi-Classification from Histopathological Images with Structured Deep Learning Model,” Scientific Reports, vol. 7, no. 1, p. 4172, 2017. Crossref, https://doi.org/10.1038/s41598-017-04075-z
[57] Payal Chhabra, Naresh Kumar Garg, and Munish Kumar, “Content-based Image Retrieval System using ORB and SIFT Features,” Neural Computing and Applications, vol. 32, no. 7, pp. 2725–2733, 2020. Crossref, https://doi.org/10.1007/s00521-018-3677-9