Comparative Analysis of High Accuracy Hybrid Models for Mammography Image Classification with and without Segmentation
Keywords:
CAD, Hybrid model, Mini DDSM, MultiResUNet, UNetAbstract
Mammography is an essential diagnostic tool for early detection of breast cancer. Advances in deep learning, including transfer learning models and hybrid Convolutional Neural Network (CNN) classifiers, have shown promise in improving diagnostic accuracy. This study compares the classification performance of transfer learning models and a hybrid CNN classifier without segmentation to a dedicated computer-aided diagnosis (CAD) system with segmentation on mammographic images. The objective is to evaluate the effectiveness of standalone models versus integrated CAD systems in detecting breast cancer. The contribution of this paper can be summarised as follows: the initial phase involved preprocessing, which included image contrast improvement technique CLAHE (Contrast Limited Adaptive Histogram Equalization), resizing, normalisation, and image augmentation. The second step is classifying pre-processed images without segmentation using VGG16, MobileNet, ResNet152V2, ResNet50V2, and four hybrid models H1, H2, H3, and H4 as benign and malignant. The suggested hybrid methods exhibit improved performance in comparison to the corresponding transfer learning models, capitalising on the combined benefits of both networks. Furthermore, the incorporation of a probability-based weight factor (????) and threshold value (????) is essential for achieving optimal hybridisation. The empirically discovered optimal threshold value (????) improves the speed and accuracy of the system. Significantly, in contrast to conventional deep learning techniques, the suggested framework demonstrates exceptional performance. Finally, the images are segmented using the MultiResUNet++ model, and the obtained segmented masses are classified using the four hybrid models. In this paper, the classification of the mammography images was compared with and without segmentation. The experimental results demonstrate the superiority of the proposed VGG16- ResNet50V2 scheme over the current state-of-the-art methods, with a precision of 98.94%, accuracy of 98.42%, Recall of 97.89%, F1 Score of 98.41% and ROC score of 98.54%.
Downloads
References
X. Xiao, L. Xu, B.Y. Liu, Three-dimensional simulation for early breast cancer detection by ultra-wideband, Acta Phys. Sin. 62 (4) (2013) 221–229;(b) J. Ferlay, H.R. Shin, F. Bray, et al., Estimates of worldwide burden of cancerin 2008: globocan 2008, Int. J. Cancer 127 (12) (2010) 2893–2917.
L. Guang-Dong, Three-dimensional microwave-induced thermos acoustic imaging for breast cancer detection, Acta Phys. Sin. 60 (7) (2011)074303–074913.
J.M. Timmers, H.J. van Doorne-Nagtegaal, H.M. Zonderland, et al., The BreastImaging Reporting and Data System (BI-RADS) in the Dutch breast cancer screening program: its role as an assessment and stratification tool, Int. J.Med. Radiol. 22 (8) (2012) 1717–1723.
N.V.S.S.R. Lakshmi, C. Manoharan, An automated system for classification of micro calcification in mammography based on Jacobi moments, Int. J. Comput.Theory Eng. 3 (3) (2011) 431–434.
Gautam, A. Recent advancements of deep learning in detecting breast cancer: a survey. Multimedia Systems 29, 917–943 (2023).
Wang L (2024) Mammography with deep learning for breast cancer detection, Front. Oncol. 14:1281922
Yoo, S., Lee, S., Kim, S. et al. Integrating deep learning into CAD/CAE system: generative design and evaluation of 3D conceptual wheel. Struct Multidisc Optim 64, 2725–2747 (2021).
Vivek Kumar Singh, Hatem A. Rashwan, Santiago Romani, Farhan Akram, Nidhi Pandey, Md. Mostafa Kamal Sarker, Adel Saleh, Meritxell Arenas, Miguel Arquez, Domenec Puig, Jordina Torrents-Barrena, Breast tumor segmentation and shape classification in mammograms using generative adversarial and convolutional neural network, Expert Systems with Applications, Volume 139, 2020,112855, ISSN 0957-4174.
O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, Lect. Notes Comput. Sci.(Including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). 9351 (2015) 234–241.
Z. Zhou, M.M.R. Siddiquee, N. Tajbakhsh, J. Liang UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation IEEE Trans. Med. Imaging., 39(2020), pp. 1856-1867.L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, Lect. Notes Comput. Sci. (Including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). 11211 LNCS (2018)833–851.
A. Baccouche, B. Garcia-Zapirain, C. Castillo Olea, A.S. Elmaghraby Connected-UNets: a deep learning architecture for breast mass segmentation, Npj Breast Cancer, 7(2021), pp. 1-12.
N.K. Tomar, A. Shergill, B. Rieders, U. Bagci, D. Jha, TransResU-Net: Transformer based ResU Net for Real-Time Colonoscopy PolypSegmentation, ArXiv. (2022) 1–4.
Garrucho, K. Kushibar, S. Jouide, O. Diaz, L. Igual, K. Lekadir Domain generalization in deep learning based mass detection in mammography: large-scale multi-center study Artif. Intell. Med., 132(2022), Article 102386.
Nabil Ibtehaz, M. Sohel Rahman. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation. Networks Volume 121, Pages 74-87, January 2020.
A. Shrestha, A. Mahmood, Review of deep learning algorithms and architectures, IEEE Access 7 (2019) 53040–53065.
J. Arevalo, F.A. Gonza´ lez, R. Ramos-Polla´ n, J.L. Oliveira, M. A.G. Lopez, Representation learning for mammography mass lesion classification with convolutional neural networks, Comput. Methods Programs Biomed. 127 (15) (2016) 248–257.
D. Abdelhafiz, C. Yang, R. Ammar, S. Nabavi, Deep convolutional neural networks for mammography: Advances, challenges and applications, BMC Bioinf. 20 (11) (2019) 1–20.
L. Tsochatzidis, L. Costaridou, I. Pratikakis, Deep learning for breast cancer diagnosis from mammograms—a comparative study, J. Imaging 5 (3) (2019) 37.
N. Alam, A. Oliver, E.R. Denton, R. Zwiggelaar, Automatic segmentation of microcalcification clusters, Annual Conference on Medical Image Understanding and Analysis, 894, Springer, Cham, 2018, pp. 251–261
S. Duraisamy, S. Emperumal, Computer-aided mammogram diagnosis system using deep learning convolutional fully complex-valued relaxation neural network classifier, IET Comput. Vis., 11 (8) (2017) 656–662.
E. Deniz, A. S_engu¨r, Z. Kadirog˘ lu, Y. Guo, V. Bajaj, U¨. Budak, Transfer learning based histopathologic image classification for breast cancer detection, Health Inform. Sci. Syst. (1) (2018) 1–7.
S. Kwok, Multiclass classification of breast cancer in whole-slide images, International conference image analysis and recognition, 10882, Springer, Cham, 2018, pp. 931–940.
Li, Chen, Dan Xue, Hu. Zhijie, Hao Chen, Yao. Yudong, Yong Zhang, Mo Li, Qian Wang, Xu. Ning, A Survey for breast histopathology image analysis using classical and deep neural networks, in International Conference on Information Technologies in Biomedicine. Springer, Cham, vol. 1011, 2019, pp. 222–233.
D.A. Ragab, M. Sharkas, S. Marshall, J. Ren, Breast cancer detection using deep convolutional neural networks and support vector machines, PeerJ 7 (4) (2019) e6201.
C. Liang, M. Li, Z. Bian, W. Lv, D. Zeng, J. Ma, Establishment of a deep feature-based classification model for distinguishing benign and malignant breast tumors on full-filed digital mammography, J. Southern Med. Univ. 39 (1) (2019) 88–92.
S.C. Wong, A. Gatt, V. Stamatescu, and M.D. McDonnell, Understanding data augmentation for classification: when to warp, in 2016 International Conference on Digital Image Computing: IEEE Techniques and Applications (DICTA), Gold Coast, QLD, Australia, pp. 1–6, 2016.
Y. Chen, T. Zheming, Z. Yang, S. Holly, L. Norford, Transfer learning with deep neural networks for model predictive control of HVAC and natural ventilation in smart buildings, J. Cleaner Prod. 254 (119866) (2020) 1–10.
M. S. Akter, H. Shahriar, S. Sneha and A. Cuzzocrea, "Multi-class Skin Cancer Classification Architecture Based on Deep Convolutional Neural Network," 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan, 2022, pp. 5404-5413, doi: 10.1109/BigData55660.2022.10020302.
Maity, S., Saha, D., Singh, P.K. et al. JUIVCDv1: development of a still-image-based dataset for Indian vehicle classification. Multimed Tools Appl (2024).
K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, 2014, arXiv preprint arXiv:1409.1556.
C.D. Lekamlage, F. Afzal, E. Westerberg, A. Cheddad, Mini-DDSM: Mammography-based automatic age estimation, 2020, arXiv preprint arXiv:2010.00494.
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.
Ange Lou, Shuyue Guan, and Murray Loew "DC-UNet: rethinking the U-Net architecture with dual channel efficient CNN for medical image segmentation", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115962T (15 February 2021)
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818-2826, 2016.
S. Targ, D. Almeida, K. Lyman, Resnet in Resnet: Generalizing residual architectures, In International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2-4 May, pp. 1–4, 2016.
X. Zhang, J. Zou, K. He, J. Sun, Accelerating very deep convolutional networks for classification and detection, IEEE Trans. Pattern Anal. Mach. Intell. 38 (10) (2015) 1943–1955.
H. Shin, H.R. Chang, G. Roth, L. Lu, X. Mingchen, I. Ziyue, Y. Nogues, D. Jianhua, Mollura, R.M. Summers, Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning, IEEE Trans. Med. Imaging, 35 (5) (2016) 1285–1298.
S. Sasikala, M. Bharathi, M. Ezhilarasi, M. Ramasubba Reddy, S. Arunkumar, Fusion of MLO and CC view binary patterns to improve the performance of breast cancer diagnosis, Curr. Med. Imaging 14 (4) (2018) 651–658.
Chapala, H., &Sujatha, B. (2020, July). ResNet: Detection of Invasive Ductal Carcinomain Breast Histopathology Images Using Deep Learning. In2020 International Conference on Electronics and Sustainable Communication Systems (ICESC)(pp. 60-67).IEEE.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.-C. Chen, Mobilenetv2: Inverted residuals and linear bottlenecks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510–4520.
K. Balaji. "Image Augmentation based on Variational Autoencoder for Breast Tumor Segmentation", Academic Radiology, 2023.
Heath, M.; Bowyer, K.; Kopans, D.; Kegelmeyer, P.; Moore, R.; Chang, K.; Munishkumaran, S. Current status of the digital database for screening mammography. In Digital Mammography; Springer: Cham, Switzerland, 1998; pp. 457–460.
Ozkaraca O, Bağrıacık Oİ, Guruler H, Khan F, Hussain J, Khan J, Ue Laila (2023) Multiple brain tumor classification with dense cnn architecture using brain mri images. Life 13(2):349.
Asad R, Rehman SU, Imran A, Li J, Almuhaimeed A, Alzahrani A (2023) Computer-aided early melanoma brain-tumor detection using deep-learning approach. Biomedicines 11(1):184.
Altheneyan A, Alhadlaq A (2023) Big data ml-based fake news detection using distributed learning. IEEE Access 11:29447–29463.
Alkaissy M, Arashpour M, Golafshani EM, Hosseini MR, Khan mohammadi S, Bai Y, Feng H (2023) Enhancing construction safety: machine learning-based classification of injury types. Safety Sci 162:106102.
Sahu A, Das P, Meher S High accuracy hybrid CNN classifiers for breast cancer detection using mammogram and ultrasound datasets Signal Processing and Control, (2023), 80.
K. Dong, C. Zhou, Y. Ruan and Y. Li, "MobileNetV2 Model for Image Classification," 2020 2nd International Conference on Information Technology and Computer Application (ITCA), Guangzhou, China, 2020, pp. 476-480, doi: 10.1109/ITCA52113.2020.00106.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
