A Combined MobileNetV2 and CBAM Model to Improve Classifying the Breast Cancer Ultrasound Images
DOI:
https://doi.org/10.37385/jaets.v6i1.4836Keywords:
MobileNetV2, CBAM, Image Classification, Breast Cancer, UltrasoundAbstract
Breast cancer is the main cause of death in women throughout the world. Early detection using ultrasound is very necessary to reduce cases of breast cancer. However, the ultrasound analysis process requires a lot of time and medical personnel because classification is difficult due to noise, complex texture, and subjective assessment. Previous studies were successful in ultrasound classification of breast cancer but required large computations and complex models. This research aims to overcome these shortcomings by using a lighter but more accurate model. We integrated the CBAM attention module into the MobileNetV2 model to improve breast cancer detection accuracy, speed up diagnosis, and reduce computational requirements. Gradient Weighted Class Activation Mapping (Grad-CAM) is used to improve classification explanations. Ultrasound images from two databases were combined to train, validate, and test this model. The test results show that MobileNetV2-CBAM achieves a test accuracy of 93%, higher than the complex models VGG-16 (80%), VGG-19 (82%), InceptionV3 (80%), and ResNet-50 (84%). CBAM is proven to improve MobileNetV2 performance with an 11% increase in accuracy. Grad-CAM visualization shows that MobileNetV2-CBAM can better focus on localizing important regions in breast cancer images, providing clearer explanations and assisting medical personnel in diagnosis.
Downloads
References
A Samah, A., Nasien, D., Hashim, H., Sahar, J., Majid, H., Yusoff, Y., & Ali Shah, Z. (2020). Application of Deep Learning Method in Facilitating the Detection of Breast Cancer. IOP Conference Series: Materials Science and Engineering, 864, 12079. https://doi.org/10.1088/1757-899X/864/1/012079
Al-Dhabyani, W., Gomaa, M., Khaled, H., & Fahmy, A. (2020). Dataset of breast ultrasound images. Data in Brief, 28, 104863. https://doi.org/https://doi.org/10.1016/j.dib.2019.104863
Arleo EK, Hendrick RE, Helvie MA, S. E. (n.d.). Comparison of recommendations for screening mammography using CISNET models. https://doi.org/doi: 10.1002/cncr.30842.
Bal-Ghaoui, M., El Yousfi Alaoui, M. H., Jilbab, A., & Bourouhou, A. (2023). Optimizing Ultrasound Image Classification Through Transfer Learning: Fine-Tuning Strategies and Classifier Impact on Pre-Trained Inner-Layers. In Informatyka Automatyka Pomiary W Gospodarce I Ochronie ?rodowiska. https://doi.org/10.35784/iapgos.4464
Disha, E., Manxhuka-Kerliu, S., Ymeri, H., & Kutllovci, A. (2009). Comparative Accuracy of Mammography and Ultrasound in Women with Breast Symptoms According to Age and Breast Density. Bosnian Journal of Basic Medical Sciences / Udruženje Basi?nih Mediciniskih Znanosti = Association of Basic Medical Sciences, 9, 131–136. https://doi.org/10.17305/bjbms.2009.2832
Fenu, G. (2021). Using Multioutput Learning to Diagnose Plant Disease and Stress Severity. In Complexity. https://doi.org/10.1155/2021/6663442
Fujioka, T., Mori, M., Kubota, K., Oyama, J., Yamaga, E., Yashima, Y., Katsuta, L., Nomura, K., Nara, M., Oda, G., Nakagawa, T., Kitazume, Y., & Tateishi, U. (2020). The utility of deep learning in breast ultrasonic imaging: A review. Diagnostics, 10(12). https://doi.org/10.3390/diagnostics10121055
Gao, W., Wang, D., & Huang, Y. (2023). Designing a Deep Learning-Driven Resource-Efficient Diagnostic System for Metastatic Breast Cancer: Reducing Long Delays of Clinical Diagnosis and Improving Patient Survival in Developing Countries. In Cancer Informatics. https://doi.org/10.1177/11769351231214446
Hadiyoso, S., Fahrozi, F., Hariyani, Y. S., & Sulistyo, M. D. (2022). Image Based ECG Signal Classification Using Convolutional Neural Network. International Journal of Online and Biomedical Engineering (IJOE), 18(04), 64–78. https://doi.org/10.3991/ijoe.v18i04.27923
Hossain, A. B. M. A., Nisha, J. K., & Johora, F. (2023). Breast Cancer Classification from Ultrasound Images using VGG16 Model based Transfer Learning. International Journal of Image, Graphics and Signal Processing, 15(1), 12 – 22. https://doi.org/10.5815/ijigsp.2023.01.02
Hossinq, M. M., Molla, S., Javed Mehedi Shamrat, F. M., Samia, M. M., Saha, R. M., & Khater, A. (2022). Comparative Study On Breast Cancer Classification Using Multiple Convolution Neural Network Architectures. 2022 3rd International Conference on Smart Electronics and Communication (ICOSEC), 1081–1088. https://doi.org/10.1109/ICOSEC54921.2022.9951881
Ijaz, A., Raza, B., Kiran, I., Waheed, A., Raza, A., Shah, H., & Aftan, S. (2023). Modality Specific CBAM-VGGNet Model for the Classification of Breast Histopathology Images via Transfer Learning. IEEE Access, 11, 15750–15762. https://doi.org/10.1109/ACCESS.2023.3245023
Khairnar, S., Gite, S., & Thepade, S. D. (2024). Empirical Performance Analysis of Deep Convolutional Neural Networks Architectures for Face Liveness Detection. https://doi.org/10.21203/rs.3.rs-3824202/v1
Kurniawan, B., Sulistiyo, M. D., Hadiyoso, S., & Zarifie Bin Hashim, N. M. (2023). Semantic Segmentation of Anatomical Structures in Posterior-Anterior Chest X-Ray Image Using U-Net. 2023 11th International Conference on Information and Communication Technology (ICoICT), 142–147. https://doi.org/10.1109/ICoICT58202.2023.10262815
Liu, X., Yang, D., & Gamal, A. El. (2017). Deep neural network architectures for modulation classification. 2017 51st Asilomar Conference on Signals, Systems, and Computers, 915–919. https://doi.org/10.1109/ACSSC.2017.8335483
Ma, R., Wang, J., Zhao, W., Guo, H., Dai, D., Yun, Y., Li, L., Hao, F., Bai, J., & Ma, D. (2022). Identification of Maize Seed Varieties Using MobileNetV2 with Improved Attention Mechanism CBAM. Agriculture, 13, 11. https://doi.org/10.3390/agriculture13010011
Mukhlif, A. A., Al-Khateeb, B., & Mohammed, M. A. (2022). An extensive review of state-of-the-art transfer learning techniques used in medical imaging: Open issues and challenges. Journal of Intelligent Systems, 31(1), 1085–1111. https://doi.org/doi:10.1515/jisys-2022-0198
Nasien, D., Enjeslina, V., Adiya, M. H., & Baharum, Z. (2022). Breast Cancer Prediction Using Artificial Neural Networks Back Propagation Method. Journal of Physics: Conference Series, 2319(1), 12025. https://doi.org/10.1088/1742-6596/2319/1/012025
Niu, J., Li, H., Zhang, C., & Li, D. (2021). Multi-scale attention-based convolutional neural network for classification of breast masses in mammograms. Medical Physics, 48(7), 3878–3892. https://doi.org/https://doi.org/10.1002/mp.14942
Nugraha, D. B., Rachmawati, E., & Sulistiyo, M. D. (2022). Semantic Segmentation of Whole-Body Bone Scan Image Using Btrfly-Net. 2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE), 264–269. https://doi.org/10.1109/ICITEE56407.2022.9954073
Organization, W. H. (2021). Breast Cancer. https://www.who.int/news-room/fact-sheets/detail/breast-cancer
Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. https://doi.org/10.1109/TKDE.2009.191
Plass, M., Kargl, M., Kiehl, T. R., Regitnig, P., Geißler, C., Evans, T., Zerbe, N., Carvalho, R., Holzinger, A., & Müller, H. (2023). Explainability and causability in digital pathology. Journal of Pathology and Clinical Research, 9(4), 251–260. https://doi.org/10.1002/cjp2.322
Rachburee, N., & Punlumjeak, W. (2022). Lotus species classification using transfer learning based on VGG16, ResNet152V2, and MobileNetV2. IAES International Journal of Artificial Intelligence (IJ-AI), 11(4), 1344. https://doi.org/10.11591/ijai.v11.i4.pp1344-1352
Rafi, W., Sulistiyo, M. D., Hadiyoso, S., & Wisesty, U. (2023). Polyp Identification from a Colonoscopy Image Using Semantic Segmentation Approach. Building of Informatics, Technology and Science (BITS), 5(2), 423?431. https://doi.org/10.47065/bits.v5i2.4083
Rajinikanth, V., Raj, A. N. J., Krishnan, P. T., & Naik, G. R. (2020). A Customized VGG19 Network With Concatenation of Deep and Handcrafted Features for Brain Tumor Detection. In Applied Sciences. https://doi.org/10.3390/app10103429
Rodrigues, P. S. (2018). Breast Ultrasound Image. Mendeley Data, 1. https://doi.org/oi: 10.17632/wmy84gzngw.1
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., & Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge.
Sahiner, B., Chan, H.-P., Roubidoux, M., Hadjiiski, L., Helvie, M., Paramagul, C., Bailey, J., Nees, A., & Blane, C. (2007). Malignant and Benign Breast Masses on 3D US Volumetric Images: Effect of Computer-aided Diagnosis on Radiologist Accuracy 1. Radiology, 242, 716–724. https://doi.org/10.1148/radiol.2423051464
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
Sebastian, A. M., & Peter, D. (2022). Artificial Intelligence in Cancer Research: Trends, Challenges and Future Directions. Life, 12(12). https://doi.org/10.3390/life12121991
Shahi, T. B., Sitaula, C., Neupane, A., & Guo, W. (2022). Fruit classification using attention-based MobileNetV2 for industrial applications. PLOS ONE, 17(2), 1–21. https://doi.org/10.1371/journal.pone.0264586
Shehab, M., Abualigah, L., Shambour, Q., Abu-Hashem, M. A., Shambour, M. K. Y., Alsalibi, A. I., & Gandomi, A. H. (2022). Machine learning in medical applications: A review of state-of-the-art methods. Computers in Biology and Medicine, 145, 105458. https://doi.org/https://doi.org/10.1016/j.compbiomed.2022.105458
Silva, L., Araújo, L. dos S., Souza, V. F., Neto, R. M. B., & Santos, A. (2021). Comparative Analysis of Convolutional Neural Networks Applied in the Detection of Pneumonia Through X-Ray Images of Children. In Learning and Nonlinear Models. https://doi.org/10.21528/lnlm-vol18-no2-art1
Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition.
Sitaba, A. Y., Rachmawati, E., & Sulistiyo, M. D. (2023). Investigating Convolution-Attention Model for Bone Scan Image Segmentation. 2023 10th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), 344–349. https://doi.org/10.1109/ICITACEE58587.2023.10276939
Starke, G., & Poppe, C. (2022). Karl Jaspers and artificial neural nets: on the relation of explaining and understanding artificial intelligence in medicine. Ethics and Information Technology, 24(3), 26. https://doi.org/10.1007/s10676-022-09650-1
Syam, R. F. K., Rachmawati, E., & Sulistiyo, M. D. (2023). Whole-Body Bone Scan Segmentation Using SegFormer. 2023 10th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), 419–424. https://doi.org/10.1109/ICITACEE58587.2023.10277219
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2015). Rethinking the Inception Architecture for Computer Vision.
Tasnim, J., & Hasan, M. K. (2023). CAM-QUS guided self-tuning modular CNNs with multi-loss functions for fully automated breast lesion classification in ultrasound images. Physics in Medicine & Biology, 69(1), 15018. https://doi.org/10.1088/1361-6560/ad1319
Tharwat, A. (2021). Classification assessment methods. Applied Computing and Informatics, 17(1), 168–192. https://doi.org/10.1016/j.aci.2018.08.003
Uysal, F., & Köse, M. M. (2023). Classification of Breast Cancer Ultrasound Images with Deep Learning-Based Models. Engineering Proceedings, 31(1). https://doi.org/10.3390/ASEC2022-13791
Woo, S., Park, J., Lee, J.-Y., & Kweon, I.-S. (2018). CBAM: Convolutional Block Attention Module. European Conference on Computer Vision.
Wu, J.-M., Chen, L., Chen, S.-P., Lee, C.-C., Huang, T.-K., Tseng, N.-C., Tsai, W. S., Lin, Y., Wu, Y.-C., Cheng, B., & Yu, J.-T. (2023). Classification of Catheters and Tubes on Chest Radiographs Using Light-Weight Deep Convolutional Neural Networks. https://doi.org/10.21203/rs.3.rs-2463844/v1
Xiao, T., Liu, L., Li, K., Qin, W., Yu, S., & Li, Z.-C. (2018). Comparison of Transferred Deep Neural Networks in Ultrasonic Breast Masses Discrimination. BioMed Research International, 2018, 1–9. https://doi.org/10.1155/2018/4605191
Yu, L., Li, B., & Jiao, B. (2019). Research and Implementation of CNN Based on TensorFlow. IOP Conference Series: Materials Science and Engineering, 490(4), 42022. https://doi.org/10.1088/1757-899X/490/4/042022
Zagoruyko, S., & Komodakis, N. (2017). Wide Residual Networks.