EU-NET: Deep Reinforcement Learning Aided Breast Tumor Segmentation and Attention based Severity Classification using Fused Ultrasound and Mammography Images
Article Sidebar
Main Article Content
Abstract
Breast cancer is increased gradually during the past few years, which is the second leading disease diagnosed in women. Hence, early detection of breast cancer is one the way to reduce mortality. Ultrasound and mammography are an excellent diagnosing technique for breast tumors, but their identification and classification have many challenges. Hence, it limits with less accuracy, true positive rate, and high false positive rate. To overcome these issues, we proposed EU-Net model which includes three major processes such as three stage preprocessing, dual agent-based segmentation, and breast tumor severity classification. Initially, noise removal is performed by hybrid filters (wiener and fuzzy filters) which provides noiseless image. After that, contrast enhancement is performed by Advanced Contrast Limited Adaptive Histogram Equalization (A-CLAHE) which enhances the image contrast by adaptively change the clip limit and histogram. The preprocessed ultrasound and mammography images are fused by Undecimated Discrete Wavelet Transform (UDWT) and Independent Component Analysis (ICA) which utilizes both the information of ultrasound and mammography which also increases segmentation and classification accuracy. In second, Dual Agent-Deep Q Network (DA-DQN) algorithm is proposed for segmenting the tumor region by considering various features. Finally, Enhanced U-Net (EU-Net) is proposed for severity classification based on segmented region which classifies the images into three classes such as normal, moderate, and severe. The simulation of this research is conducted by Matlab simulation tool and the performance of this research is evaluated by various performance metrics by considering two public datasets namely Breast UltraSound image (BUS) dataset and Digital Database for Screening Mammography (DDSM) dataset.
Article Details
References
Nagpure, R., Chandak, S., & Pathak, N. (2020). Breast Cancer Detection using Neural Network Mammogram. 2020 International Conference on Convergence to Digital World - Quo Vadis (ICCDW), 1-6.
Zheng, J., Lin, D., Gao, Z., Wang, S., He, M., & Fan, J. (2020). Deep Learning Assisted Efficient AdaBoost Algorithm for Breast Cancer Detection and Early Diagnosis. IEEE Access, 8, 96946-96954.
Wu, H., Gole, R., Ghosh, S., & Basu, A. (2020). Alternative Techniques for Breast Tumour Detection using Ultrasound. 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2047-2050.
Rahman, M., Hussain, M.G., Hasan, M.R., Sultana, B., & Akter, S. (2020). Detection and Segmentation of Breast Tumor from MRI Images Using Image Processing Techniques. 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), 720-724.
Tang, X.L., An, Y., & Li, C. (2021). Intelligent Segmentation and Recognition Method of Breast Cancer Based on Digital Image Processing Technology. Wireless Communications and Mobile Computing.
Nguyen, T., Nguyen, T., Ngo, B., & Vo, D. (2020). Breast Image Segmentation for evaluation of Cancer Disease. 2020 5th International Conference on Green Technology and Sustainable Development (GTSD), 344-348.
Huang, Q., Lee, S., Liu, L., Lu, M., Jin, L., & Li, A. (2012). A robust graph-based segmentation method for breast tumors in ultrasound images. Ultrasonics, 52 2, 266-75 .
Singh, V.K., Abdel-Nasser, M., Akram, F., Rashwan, H.A., Sarker, M.M., Pandey, N., Romaní, S., & Puig, D. (2020). Breast tumor segmentation in ultrasound images using contextual-information-aware deep adversarial learning framework. Expert Syst. Appl., 162, 113870.
Shen, T., Gou, C., Wang, J., & Wang, F. (2020). Simultaneous Segmentation and Classification of Mass Region From Mammograms Using a Mixed-Supervision Guided Deep Model. IEEE Signal Processing Letters, 27, 196-200.
Song, R., Li, T., & Wang, Y. (2020). Mammographic Classification Based on XGBoost and DCNN With Multi Features. IEEE Access, 8, 75011-75021.
Zeimarani, B., Costa, M.G., Nurani, N.Z., Bianco, S.R., de Albuquerque Pereira, W.C., & Filho, C.F. (2020). Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network. IEEE Access, 8, 133349-133359.
Lu, H., Loh, E., & Huang, S. (2019). The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection. 2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD), 9-12.
Jebarani, P.E., Umadevi, N., Dang, H., & Pomplun, M. (2021). A Novel Hybrid K-Means and GMM Machine Learning Model for Breast Cancer Detection. IEEE Access, 9, 146153-146162.
Shia, W., & Chen, D. (2021). Classification of malignant tumors in breast ultrasound using a pretrained deep residual network model and support vector machine. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 87, 101829 .
Liao, W., He, P., Hao, J., Wang, X., Yang, R., An, D., & Cui, L. (2020). Automatic Identification of Breast Ultrasound Image Based on Supervised Block-Based Region Segmentation Algorithm and Features Combination Migration Deep Learning Model. IEEE Journal of Biomedical and Health Informatics, 24, 984-993.
Tang, X.L., An, Y., & Li, C. (2021). Intelligent Segmentation and Recognition Method of Breast Cancer Based on Digital Image Processing Technology. Wireless Communications and Mobile Computing.
Jebarani, P.E., Umadevi, N., Dang, H., & Pomplun, M. (2021). A Novel Hybrid K-Means and GMM Machine Learning Model for Breast Cancer Detection. IEEE Access, 9, 146153-146162.
Dewangan, K.K., Dewangan, D.K., Sahu, S.P., & Janghel, R.R. (2022). Breast cancer diagnosis in an early stage using novel deep learning with hybrid optimization technique. Multimedia Tools and Applications, 1 - 26.
Ibrahim, A., Mohammed, S., Ali, H.A., & Hussein, S.E. (2020). Breast Cancer Segmentation From Thermal Images Based on Chaotic Salp Swarm Algorithm. IEEE Access, 8, 122121-122134.
Pavithra, S.K., Vanithamani, R., & Justin, J. (2020). Computer aided breast cancer detection using ultrasound images. Materials Today: Proceedings.
Baccouche, A., Garcia-Zapirain, B., Castillo Olea, C., & Elmaghraby, A.S. (2021). Connected-UNets: a deep learning architecture for breast mass segmentation. NPJ Breast Cancer, 7.
Demir, F. (2021). DeepBreastNet: A novel and robust approach for automated breast cancer detection from histopathological images. Biocybernetics and Biomedical Engineering.
Zhuang, Z., Yang, Z., Raj, A.N., Wei, C., Jin, P., & Zhuang, S. (2021). Breast ultrasound tumor image classification using image decomposition and fusion based on adaptive multi-model spatial feature fusion. Computer methods and programs in biomedicine, 208, 106221
Loizidou, K., Skouroumouni, G., Nikolaou, C., & Pitris, C. (2020). An Automated Breast Micro-Calcification Detection and Classification Technique Using Temporal Subtraction of Mammograms. IEEE Access, 8, 52785-52795.
Houby, E.M., & Yassin, N.I. (2021). Malignant and nonmalignant classification of breast lesions in mammograms using convolutional neural networks. Biomed. Signal Process. Control., 70, 102954
Rehman, K.U., Li, J., Pei, Y., Yasin, A., Ali, S., & Saeed, Y. (2021). Architectural Distortion-Based Digital Mammograms Classification Using Depth Wise Convolutional Neural Network. Biology, 11.
Kaur, P., Singh, G., & Kaur, P. (2019). Intellectual detection and validation of automated mammogram breast cancer images by multi-class SVM using deep learning classification. Informatics in Medicine Unlocked.
Li, J., Cheng, L., Xia, T., Ni, H., & Li, J. (2021). Multi-Scale Fusion U-Net for the Segmentation of Breast Lesions. IEEE Access, 9, 137125-137139.
Li, Y., Liu, Y., Huang, L., Wang, Z., & Luo, J. (2022). Deep weakly-supervised breast tumor segmentation in ultrasound images with explicit anatomical constraints. Medical image analysis, 76, 102315.
Dilovan., Ahmed Ibrahim., Diyar., (2021).Breast Cancer Detection Using Mammogram Images with Improved Multi-Fractal Dimension Approach and Feature Fusion. Sensors
Mohiyuddin, A., Basharat, A., Ghani, U., Peter, V., Abbas, S., Naeem, O.B., & Rizwan, M. (2022). Breast Tumor Detection and Classification in Mammogram Images Using Modified YOLOv5 Network. Computational and Mathematical Methods in Medicine, 2022.