Deep Learning Approach for Tumor Segmentation in Breast Cancer
Keywords:
Image segmentation, Deep learning, CNN, VGGnet, Mobilenet.Abstract
In today's world, breast cancer presents a major health challenge, especially for women, necessitating advanced diagnostic methods to enhance patient outcomes. The disease is marked by the uncontrolled growth of breast cells, forming tumors that can spread if not detected early. To prevent complications from breast cancer, it is crucial to accurately detect and diagnose the condition, followed by providing timely and appropriate treatment. This research explores the use of deep learning to develop a more accurate and efficient system for breast cancer detection. Our methodology starts with the segmentation of ultrasound images using the U-Net algorithm to precisely identify and locate tumors. Post-segmentation, these images are classified using three different models: CNN, VGG19, and MobileNet, to determine if the tumors are benign, malignant, or normal. The findings from our research reveal that the CNN model attained an accuracy of 82%, followed by the MobileNet model reaching 88%, and the VGG19 model outperformed both with an accuracy of 91%. A comparative analysis of algorithms is presented, showcasing the VGG19 model's efficiency in detecting tumors from BUS ultrasound images, in this research paper. This comparison highlights that the VGG19 model delivers the highest accuracy in breast cancer diagnosis among the models evaluated.
Downloads
References
I. Maniecka-Bryła, M. Bryła, P. Bryła, M. Pikala, ‘‘The burden of premature mortality in Poland analysed with the use of standard expected years of life lost, BMC Public Health 15 (1) (2015) 101. [4] R.A. Hubbard, K
Jose´ Baselga, Mario Campone, Martine Piccart, Howard A Burris III, Hope S Rugo, Tarek Sahmoud, Shinzaburo Noguchi, Michael Gnant, Kathleen I Pritchard, Fabienne Lebrun, et al. Everolimus in postmenopausal hormone-receptor–positive advanced breast cancer. New England Journal of Medicine, 366(6):520–529, 2012.
Qinghua Huang, Yonghao Huang, Yaozhong Luo, Feiniu Yuan, and Xuelong Li. Segmentation of breast ultrasound image with semantic classification of superpixels. Medical Image Analysis, 61:101657, 2020.
Tsochatzidis, Lazaros, Lena Costaridou, and Ioannis Pratikakis. "Deep learning for breast cancer diagnosis from mammograms—a comparative study." Journal of Imaging 5, no. 3 (2019): 37.
Salama, Wessam M., and Moustafa H. Aly. "Deep learning in mammography images segmentation and classification: Automated CNN approach." Alexandria Engineering Journal 60, no. 5 (2021): 4701-4709.
Arevalo, John, Fabio A. González, Raúl Ramos-Pollán, Jose L. Oliveira, and Miguel Angel Guevara Lopez. "Representation learning for mammography mass lesion classification with convolutional neural networks." Computer methods and programs in biomedicine 127 (2016): 248-257.
Ilesanmi, Ademola Enitan, Utairat Chaumrattanakul, and Stanislav S. Makhanov. "A method for segmentation of tumors in breast ultrasound images using the variant enhanced deep learning." Biocybernetics and Biomedical Engineering 41, no. 2 (2021): 802-818.
Moon, Woo Kyung, Yan-Wei Lee, Hao-Hsiang Ke, Su Hyun Lee, Chiun-Sheng Huang, and Ruey-Feng Chang. "Computer‐aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networks." Computer methods and programs in biomedicine 190 (2020): 105361.
Caballo, Marco, Domenico R. Pangallo, Ritse M. Mann, and Ioannis Sechopoulos. "Deep learning-based segmentation of breast masses in dedicated breast CT imaging: Radiomic feature stability between radiologists and artificial intelligence." Computers in biology and medicine 118 (2020): 103629.
Kakileti, Siva Teja, Aman Dalmia, and Geetha Manjunath. "Exploring deep learning networks for tumour segmentation in infrared images." Quantitative InfraRed Thermography Journal 17, no. 3 (2020): 153-168.
Tsochatzidis, Lazaros, Panagiota Koutla, Lena Costaridou, and Ioannis Pratikakis. "Integrating segmentation information into CNN for breast cancer diagnosis of mammographic masses." Computer Methods and Programs in Biomedicine 200 (2021): 105913.
Huang, Qinghua, Yonghao Huang, Yaozhong Luo, Feiniu Yuan, and Xuelong Li. "Segmentation of breast ultrasound image with semantic classification of superpixels." Medical Image Analysis 61 (2020): 101657.
Sivamurugan, J., and G. Sureshkumar. "Applying dual models on optimized LSTM with U-net segmentation for breast cancer diagnosis using mammogram images." Artificial Intelligence in Medicine 143 (2023): 102626.
Civilibal, Soner, Kerim Kursat Cevik, and Ahmet Bozkurt. "A deep learning approach for automatic detection, segmentation and classification of breast lesions from thermal images." Expert Systems with Applications 212 (2023): 118774.
Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A. Dataset of breast ultrasound images. Data in Brief. 2020 Feb;28:104863. DOI: 10.1016/j.dib.2019.104863.
Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
Rocha,J., Cunha, A., Mendonça, A.M.:Conventional filtering ver sus U-NET based models for pulmonary nodule segmentation in CT images. J. Med. Syst. 44, 81 (2020). https://doi.org/10.1007/ s10916-020-1541-9.
Shahriar, N. (2023, March 17). What is Convolutional Neural Network (CNN) - Deep Learning. Medium. https://nafizshahriar.medium.com/what-is-convolutional-neural-network-cnn-deep-learning-b3921bdd82d5
Bhandare, S. (2023, May 23). VGG Net architecture explained. Medium. https://medium.com/@siddheshb008/vgg-net-architecture-explained-71179310050f
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.
