Combining Super Resolution and Efficient Net Models to Reduce False Positives and False Negatives in Breast Cancer Detection
Combining Super Resolution and Efficient Net Models to Reduce False Positives and False Negatives in Breast Cancer Detection |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-5 |
||
| Year of Publication : 2023 | ||
| Author : Vandana Lingampally, Radhika Kavuri |
||
| DOI : 10.14445/22315381/IJETT-V71I5P239 | ||
How to Cite?
Vandana Lingampally, Radhika Kavuri, "Combining Super Resolution and Efficient Net Models to Reduce False Positives and False Negatives in Breast Cancer Detection," International Journal of Engineering Trends and Technology, vol. 71, no. 5, pp. 386-401, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I5P239
Abstract
The accurate detection of breast cancer is imperative for optimal therapeutic outcomes, and minimizing false positive and false negative rates is a vital element in this process. Super-resolution images are particularly used in health research due to their ability to provide higher spatial resolution and more detailed information about the appearance of tissues and structures in medical images. These images can enable the model to learn to identify subtle abnormalities and distinguish them from normal tissue, and they are also more resistant to image degradation, such as noise or blur. To obtain high-resolution mammograms, a generator network (SRGAN) was trained and obtained SR images were applied on EfficientNet models, which are highly effective deep learning architectures that exhibit superior performance on a wide range of tasks with a reduced number of parameters and lower computational complexity compared to other models. A combination of three datasets (CBIS-DDSM, Mini-MIAS, and INbreast) with data augmentation was used to train and evaluate the model. The proposed model achieved a false positive and false negative rate of 0.0029, indicating a high level of accuracy in detecting breast cancer. This low rate highlights the efficacy of the approach in minimizing false positive and false negative rates, which is crucial for optimal treatment outcomes.
Keywords
Breast cancer, Deep learning, Efficientnet, SRGAN, Super-resolution.
References
[1] Alexey Lukin, Andrey S. Krylov, and Andrey Nasonov “Image Interpolation By Super-Resolution,” In Proceedings of Graphicon, vol. 2006, pp. 239-242, 2006.
[Google Scholar] [Publisher Link]
[2] R. Key, “Cubic Convolution Interpolation for Digital Image Processing,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 29, no. 6, pp. 1153-60, 1981.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Chao Dong et al., “Image Super-Resolution Using Deep Convolutional Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 295-307, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Chao Dong, Chen Change Loy, and Xiaoou Tang, “Accelerating the Super-Resolution Convolutional Neural Network,” In: European Conference on Computer Vision, vol. 9906, pp. 391–407, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Wenzhe Shi et al., “Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874- 1883, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee, “Accurate Image Super-Resolution Using Very Deep Convolutional Networks,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646- 1654, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Bee Lim et al., “Enhanced Deep Residual Networks for Single Image Super- Resolution,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 136-144, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Christian Ledig et al., “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4681-4690, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Xintao Wang et al., “Esrgan: Enhanced Super-Resolution Generative Adversarial Networks,” Inproceedings of the European Conference on Computer Vision (ECCV) Workshops, pp. 1-16, 2018.
[Google Scholar] [Publisher Link]
[10] Alec Radford, Luke Metz, and Soumith Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” Arxiv Preprint Arxiv:1511.06434, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Mehdi Mirza, and Simon Osindero, “Conditional Generative Adversarial Nets,” Arxiv Preprint Arxiv:1411.1784. 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Martin Arjovsky, Soumith Chintala, and Léon Bottoul, “Wasserstein Generative Adversarial Networks,” International Conference on Machine Learning, vol. 70, pp. 214-223, 2017.
[Google Scholar] [Publisher Link]
[13] Jun Zheng, Olac Fuentes, and Ming-Ying Leung, “Super-Resolution of Mammograms,” In 2010 IEEE Symposium on Computational Intelligence In Bioinformatics and Computational Biology, pp. 1-7, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Kensuke Umeharaorcid, Junko Ota, and Takayuki Ishida, “Super-Resolution Imaging of Mammograms Based on the Super-Resolution Convolutional Neural Network,” Open Journal of Medical Imaging, vol. 7, no. 4, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Faezehsadat Shahidi, “Breast Cancer Histopathology Image Super-Resolution Using Wide-Attention Gan With Improved Wasserstein Gradient Penalty and Perceptual Loss,” IEEE Access, vol. 9, pp. 32795-809, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Dimitrios Korkinof et al., “High-Resolution Mammogram Synthesis Using Progressive Generative Adversarial Networks,” Arxiv Preprint Arxiv:1807.03401, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Zhongyuan Wang et al., “Ultra-Dense GAN for Satellite Imagery Super-Resolution,” Neurocomputing, vol. 398, pp. 328-37, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Menglei Zhang, and Qiang Ling, “Supervised Pixel-Wise GAN for Face Super-Resolution,” IEEE Transactions on Multimedia, 2020 vol. 23, 1938-50, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Agapi Davradou et al., “Diabetic Foot Ulcers Monitoring by Employing Super Resolution and Noise Reduction Deep Learning Techniques,” In proceedings of the 15th International Conference on Pervasive Technologies Related to Assistive Environments 2022, pp. 83-88, 2022.
[CrossRef] [Publisher Link]
[20] M. Langarizadeh et al., “Improvement of Digital Mammogram Images Using Histogram Equalization, Histogram Stretching and Median Filter,” Journal of Medical Engineering & Technology, vol. 35, no. 2, pp. 103-108.
[CrossRef] [Google Scholar] [Publisher Link]
[21] M. C. Shanker, and M. Vadivel, "Hybrid Transfer Learning of Mammogram Images for Screening of Micro-Calcifications," SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 8, pp. 40-47, 2022.
[CrossRef] [Publisher Link]
[22] Fatemeh Pak, Hamidreza Rashidy Kanan, and Afsaneh Alikhassi, “Breast Cancer Detection and Classification in Digital Mammography Based on Non-Subsampled Contourlet Transform (NSCT) and Super Resolution,” Computer Methods and Programs in Biomedicine, vol. 122, no. 22, pp. 89-107, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Nabin Kharel et al., “Early Diagnosis of Breast Cancer Using Contrast Limited Adaptive Histogram Equalization (CLAHE) and Morphology Methods,” In 2017 8th International Conference on Information and Communication Systems (ICICS), pp. 120-124, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Sheeba Jenifer, S. Parasuraman, and Amudha Kadirvelu, “Contrast Enhancement and Brightness Preserving of Digital Mammograms Using Fuzzy Clipped Contrast-Limited Adaptive Histogram Equalization Algorithm,” Applied Soft Computing, vol. 42, pp. 167-77, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Chaitanya Singla et al., “Deep Learning Enhancement on Mammogram Images for Breast Cancer Detection,” Materials Today: Proceedings, vol. 49, pp. 3098-104, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Dina A. Ragab, “Breast Cancer Detection Using Deep Convolutional Neural Networks and Support Vector Machines,” PeerJ, p. E6201, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Mugahed A. Al-antari et al., “A Fully Integrated Computer-Aided Diagnosis System For Digital X-Ray Mammograms Via Deep Learning Detection, Segmentation, and Classification,” International Journal of Medical Informatics, vol. 117, pp. 44-54, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Felipe André Zeiser et al., “Segmentation of Masses on Mammograms Using Data Augmentation and Deep Learning,” Journal of Digital Imaging, vol. 33, pp. 858-68, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Ian Goodfellow et al., “Generative Adversarial Networks,” Communication of the ACM, vol. 63, no. 11, pp. 139-144, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Mingxing Tan, and Quoc Le, “Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks,” International Conference on Machine Learningm, pp. 6105-6114, 2019.
[Google Scholar] [Publisher Link]
[31] 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. 76-92, 2022.
[CrossRef] [Publisher Link]
[32] Ridhi Arora, Prateek Kumar Rai, and Balasubramanian Raman, “Deep Feature–Based Automatic Classification of Mammograms,” Medical and Biological Engineering and Computing, vol. 58, no. 6, pp. 1199-211.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Lenin G. Falconi et al., “Transfer Learning and Fine Tuning in Breast Mammogram Abnormalities Classification on CBIS-DDSM Database,” Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 2, pp. 154-65, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[34] J Dafni Rose, “Computer-Aided Diagnosis for Breast Cancer Detection and Classification Using Optimal Region Growing Segmentation with Mobilenet Model,” Concurrent Engineering, vol. 30, no. 2, pp. 181-9, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Shelda Mohan, and M. Ravishankar, “Modified Contrast Limited Adaptive Histogram Equalization Based on Local Contrast Enhancement for Mammogram Images,” International Conference on Advances In Information Technology and Mobile Communication, pp. 397-403, 2012.
[CrossRef] [Google Scholar] [Publisher Link]