Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion

Diagnostics - Tập 11 Số 7 - Trang 1212
Rizwana Irfan1, Abdulwahab Ali Almazroi1, Hafiz Tayyab Rauf2, Robertas Damaševičius3, Emad Abouel Nasr4, Abdelaty Edrees Sayed4
1Department of Information Technology, College of Computing and Information Technology at Khulais, University of Jeddah, Jeddah 21959, Saudi Arabia
2Centre for Smart Systems, AI and Cybersecurity, Staffordshire University, Stoke-on-Trent ST4 2DE, UK
3Faculty of Applied Mathematics, Silesian University of Technology, 44-100, Gliwice, Poland
4Industrial Engineering Department, College of Engineering, King Saud University, Riyadh, 11421, Saudi Arabia

Tóm tắt

Breast cancer is becoming more dangerous by the day. The death rate in developing countries is rapidly increasing. As a result, early detection of breast cancer is critical, leading to a lower death rate. Several researchers have worked on breast cancer segmentation and classification using various imaging modalities. The ultrasonic imaging modality is one of the most cost-effective imaging techniques, with a higher sensitivity for diagnosis. The proposed study segments ultrasonic breast lesion images using a Dilated Semantic Segmentation Network (Di-CNN) combined with a morphological erosion operation. For feature extraction, we used the deep neural network DenseNet201 with transfer learning. We propose a 24-layer CNN that uses transfer learning-based feature extraction to further validate and ensure the enriched features with target intensity. To classify the nodules, the feature vectors obtained from DenseNet201 and the 24-layer CNN were fused using parallel fusion. The proposed methods were evaluated using a 10-fold cross-validation on various vector combinations. The accuracy of CNN-activated feature vectors and DenseNet201-activated feature vectors combined with the Support Vector Machine (SVM) classifier was 90.11 percent and 98.45 percent, respectively. With 98.9 percent accuracy, the fused version of the feature vector with SVM outperformed other algorithms. When compared to recent algorithms, the proposed algorithm achieves a better breast cancer diagnosis rate.

Từ khóa


Tài liệu tham khảo

Sung, H., Ferlay, J., Siegel, R.L., Laversanne, M., Soerjomataram, I., Jemal, A., and Bray, F. (2021). Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin.

Gao, J., Wang, H., and Shen, H. (2020, January 18–22). Smartly Handling Renewable Energy Instability in Supporting a Cloud Datacenter. Proceedings of the 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), New Orleans, LA, USA.

Albahli, 2021, Identification of Thoracic Diseases by Exploiting Deep Neural Networks, Neural Netw., 5, 6

Gao, J., Wang, H., and Shen, H. (2020). Task failure prediction in cloud data centers using deep learning. IEEE Trans. Serv. Comput.

Oyewola, 2021, Detecting cassava mosaic disease using a deep residual convolutional neural network with distinct block processing, PeerJ Comput. Sci., 7, 1, 10.7717/peerj-cs.352

Rehman, Z.U., Khan, M.A., Ahmed, F., Damaševičius, R., Naqvi, S.R., Nisar, W., and Javed, K. (2021). Recognizing apple leaf diseases using a novel parallel real-time processing framework based on MASK RCNN and transfer learning: An application for smart agriculture. IET Image Process.

Rauf, 2019, Visual features based automated identification of fish species using deep convolutional neural networks, Comput. Electron. Agric., 167, 105075, 10.1016/j.compag.2019.105075

Hemalatha, J., Roseline, S.A., Geetha, S., Kadry, S., and Damaševičius, R. (2021). An efficient densenet-based deep learning model for malware detection. Entropy, 23.

Rauf, 2020, Adaptive inertia weight Bat algorithm with Sugeno-Function fuzzy search, Appl. Soft Comput., 90, 106159, 10.1016/j.asoc.2020.106159

Pang, 2020, Deep learning radiomics in breast cancer with different modalities: Overview and future, Expert Syst. Appl., 158, 113501, 10.1016/j.eswa.2020.113501

Latif, G., Butt, M.O., Al Anezi, F.Y., and Alghazo, J. (2020, January 14–15). Ultrasound Image Despeckling and Detection of Breast Cancer Using Deep CNN. Proceedings of the 2020 RIVF International Conference on Computing and Communication Technologies (RIVF), Ho Chi Minh City, Vietnam.

Ching, 2018, Opportunities and obstacles for deep learning in biology and medicine, J. R. Soc. Interface, 15, 20170387, 10.1098/rsif.2017.0387

Li, 2020, Radiomics with attribute bagging for breast tumor classification using multimodal ultrasound images, J. Ultrasound Med., 39, 361, 10.1002/jum.15115

Li, 2020, Interpretable mammographic mass classification with fuzzy interpolative reasoning, Knowl.-Based Syst., 191, 105279, 10.1016/j.knosys.2019.105279

Amiri, 2020, Two-stage ultrasound image segmentation using U-Net and test time augmentation, Int. J. Comput. Assist. Radiol. Surg., 15, 981, 10.1007/s11548-020-02158-3

Vakanski, 2020, Attention-enriched deep learning model for breast tumor segmentation in ultrasound images, Ultrasound Med. Biol., 46, 2819, 10.1016/j.ultrasmedbio.2020.06.015

Rakhlin, A., Tiulpin, A., Shvets, A.A., Kalinin, A.A., Iglovikov, V.I., and Nikolenko, S. (2019, January 27–28). Breast Tumor Cellularity Assessment Using Deep Neural Networks. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, Seoul, Korea.

Lahoura, V., Singh, H., Aggarwal, A., Sharma, B., Mohammed, M.A., Damaševičius, R., Kadry, S., and Cengiz, K. (2021). Cloud Computing-Based Framework for Breast Cancer Diagnosis Using Extreme Learning Machine. Diagnostics, 11.

Yap, 2020, Breast ultrasound region of interest detection and lesion localisation, Artif. Intell. Med., 107, 101880, 10.1016/j.artmed.2020.101880

Meraj, T., Rauf, H.T., Zahoor, S., Hassan, A., Lali, M.I., Ali, L., Bukhari, S.A.C., and Shoaib, U. (2019). Lung nodules detection using semantic segmentation and classification with optimal features. Neural Comput. Appl., 1–14.

Pi, 2020, Automated diagnosis of multi-plane breast ultrasonography images using deep neural networks, Neurocomputing, 403, 371, 10.1016/j.neucom.2020.04.123

Hussain, 2020, Contextual Level-Set Method for Breast Tumor Segmentation, IEEE Access, 8, 189343, 10.1109/ACCESS.2020.3029684

Sadad, T., Hussain, A., Munir, A., Habib, M., Ali Khan, S., Hussain, S., Yang, S., and Alawairdhi, M. (2020). Identification of breast malignancy by marker-controlled watershed transformation and hybrid feature set for healthcare. Appl. Sci., 10.

Zhu, L., Chen, R., Fu, H., Xie, C., Wang, L., Wan, L., and Heng, P.A. (2020, January 4–8). A Second-Order Subregion Pooling Network for Breast Lesion Segmentation in Ultrasound. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Lima, Peru.

Shia, 2021, Classification of malignant tumors in breast ultrasound using unsupervised machine learning approaches, Sci. Rep., 11, 1, 10.1038/s41598-021-81008-x

Kim, 2021, Deep learning-based computer-aided diagnosis in screening breast ultrasound to reduce false-positive diagnoses, Sci. Rep., 11, 1

Qian, 2020, A combined ultrasonic B-mode and color Doppler system for the classification of breast masses using neural network, Eur. Radiol., 30, 3023, 10.1007/s00330-019-06610-0

Wang, 2020, Breast cancer classification in automated breast ultrasound using multiview convolutional neural network with transfer learning, Ultrasound Med. Biol., 46, 1119, 10.1016/j.ultrasmedbio.2020.01.001

Yang, 2020, A Temporal Sequence Dual-Branch Network for Classifying Hybrid Ultrasound Data of Breast Cancer, IEEE Access, 8, 82688, 10.1109/ACCESS.2020.2990683

Zhang, 2020, Diagnostic efficiency of the breast ultrasound computer-aided prediction model based on convolutional neural network in breast cancer, J. Digit. Imaging, 33, 1218, 10.1007/s10278-020-00357-7

Liu, 2020, Breast tumors recognition based on edge feature extraction using support vector machine, Biomed. Signal Process. Control, 58, 101825, 10.1016/j.bspc.2019.101825

Rakhlin, A., Shvets, A., Iglovikov, V., and Kalinin, A.A. (2018, January 27–29). Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis. Proceedings of the International Conference Image Analysis and Recognition, Porto, Portugal.

Hossen, 2020, RATE-iPATH: On the design of integrated ultrasonic biomarkers for breast cancer detection, Biomed. Signal Process. Control, 62, 102053, 10.1016/j.bspc.2020.102053

Jarosik, 2020, Breast lesion classification based on ultrasonic radio-frequency signals using convolutional neural networks, Biocybern. Biomed. Eng., 40, 977, 10.1016/j.bbe.2020.04.002

Chang, 2020, Flexible ultrasonic array for breast-cancer diagnosis based on a self-shape–estimation algorithm, Ultrasonics, 108, 106199, 10.1016/j.ultras.2020.106199

Alzubaidi, L., Al-Shamma, O., Fadhel, M.A., Farhan, L., Zhang, J., and Duan, Y. (2020). Optimizing the performance of breast cancer classification by employing the same domain transfer learning from hybrid deep convolutional neural network model. Electronics, 9.

Huang, 2020, Segmentation of breast ultrasound image with semantic classification of superpixels, Med. Image Anal., 61, 101657, 10.1016/j.media.2020.101657

Mojabi, 2020, Tissue-Type Classification With Uncertainty Quantification of Microwave and Ultrasound Breast Imaging: A Deep Learning Approach, IEEE Access, 8, 182092, 10.1109/ACCESS.2020.3027805

Liang, 2020, Application of Contrast-Enhanced Ultrasound in the Differential Diagnosis of Different Molecular Subtypes of Breast Cancer, Ultrason. Imaging, 42, 261, 10.1177/0161734620959780

Luo, Y., Zhao, C., Gao, Y., Xiao, M., Li, W., Zhang, J., Ma, L., Qin, J., Jiang, Y., and Zhu, Q. (2020). Predicting Axillary Lymph Node Status With a Nomogram Based on Breast Lesion Ultrasound Features: Performance in N1 Breast Cancer Patients. Front. Oncol., 10.

Lee, 2020, Real-time burn classification using ultrasound imaging, Sci. Rep., 10, 1

Kore, S.S., and Kadam, A.B. (2020). A novel incomplete sparse least square optimized regression model for abdominal mass detection in ultrasound images. Evol. Intell., 1–16.

Moon, 2020, Computer-aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networks, Comput. Methods Prog. Biomed., 190, 105361, 10.1016/j.cmpb.2020.105361

Byra, 2020, Early prediction of response to neoadjuvant chemotherapy in breast cancer sonography using Siamese convolutional neural networks, IEEE J. Biomed. Health Inform., 25, 797, 10.1109/JBHI.2020.3008040

Gomaa, 2020, Dataset of breast ultrasound images, Data Brief, 28, 104863, 10.1016/j.dib.2019.104863

Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv.

Gonzalez, R.C., Woods, R.E., and Masters, B.R. (2008). Digital Image Processing, Pearson Prentice Hall. [3rd ed.].

Jadon, S. (2020, January 27–29). A Survey of Loss Functions for Semantic Segmentation. Proceedings of the 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Viña del Mar, Chile.

Gomaa, 2019, Deep learning approaches for data augmentation and classification of breast masses using ultrasound images, Int. J. Adv. Comput. Sci. Appl., 10, 1

Byra, 2020, Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network, Biomed. Signal Process. Control, 61, 102027, 10.1016/j.bspc.2020.102027

Lazo, J.F., Moccia, S., Frontoni, E., and De Momi, E. (2020). Comparison of different CNNs for breast tumor classification from ultrasound images. arXiv.