SEGMENTATION OF CANCER MASSES ON BREAST ULTRASOUND IMAGES USING MODIFIED U-NET
Ihssane Khallassi
ihssanekhallassi639@gmail.comElectronic Systems Sensors and Nanobiotechnology, National School of Arts and Crafts, Mohammed V University in Rabat, Morocco (Morocco)
https://orcid.org/0009-0006-7965-0269
My Hachem El Yousfi Alaoui
Electronic Systems Sensors and Nanobiotechnology, National School of Arts and Crafts, Mohammed V University in Rabat, Morocco (Morocco)
https://orcid.org/0000-0003-4285-0540
Abdelilah Jilbab
Electronic Systems Sensors and Nanobiotechnology, National School of Arts and Crafts, Mohammed V University in Rabat, Morocco (Morocco)
https://orcid.org/0000-0002-1577-9040
Abstract
Breast cancer causes a huge number of women’s deaths every year. The accurate localization of a breast lesion is a crucial stage. The segmentation of breast ultrasound images participates in the improvement of the process of detection of breast anomalies. An automatic approach of segmentation of breast ultrasound images is presented in this paper, the proposed model is a modified u-net called Attention Residual U-net, designed to help radiologists in their clinical examination to determine adequately the limitation of breast tumors. Attention Residual U-net is a combination of existing models (Convolutional Neural Network U-net, the Attention Gate Mechanism and the Residual Neural Network). Public breast ultrasound images dataset of Baheya hospital in Egypt is used in this work. Dice coefficient, Jaccard index and Accuracy are used to evaluate the performance of the proposed model on the test set. Attention residual u-net can significantly give a dice coefficient = 90%, Jaccard index = 76% and Accuracy = 90%. The proposed model is compared with two other breast segmentation methods on the same dataset. The results show that the modified U-net model was able to achieve accurate segmentation of breast lesions in breast ultrasound images.
Keywords:
convolutional neural network, segmentation, u-net, residual neural networkReferences
AI-Dhabyani W. et al.: Dataset of breast ultrasound images. Data in Brief 28, 2020, 104863.
DOI: https://doi.org/10.1016/j.dib.2019.104863
Google Scholar
Balagalla B et al.: A Review On Ultrasound Image Pre-Processing, Segmentation And Compression For Enhanced Image Storage And Transmission. 11-th International Research Conference General, Sir John Kotelawala Defence University, 2018, 106–111.
Google Scholar
Chollet F.: Kears. https://github.com/fchollet/keras, 2015.
Google Scholar
Dice L. R.: Measures of the Amount of Ecologic Association Between Species. Ecology 26(3), 1945, 297–302.
DOI: https://doi.org/10.2307/1932409
Google Scholar
El Fouhi M. M. et al.: Profil épidémiologique et anatomopathologique du cancer de sein au CHU Ibn Rochd, Casablanca. Pan Afr Med J. 37, 2020, 41.
DOI: https://doi.org/10.11604/pamj.2020.37.41.21336
Google Scholar
Epimack M. et al.: Breast Cancer Segmentation Methods: Current Status and Future Potentials. BioMed Research International 2021, 9962109.
DOI: https://doi.org/10.1155/2021/9962109
Google Scholar
Fondation lalla salma, détection précoce 2022.
Google Scholar
He K. et al.: Deep Residual Learning for Image Recognition. 2016, arXiv:1512.03385.
DOI: https://doi.org/10.1109/CVPR.2016.90
Google Scholar
Jaccard P.: The Distribution of the Flora in the Alpine Zone. The New Phytologist 11(2), 1912, 37–50.
DOI: https://doi.org/10.1111/j.1469-8137.1912.tb05611.x
Google Scholar
Kingma D. P., Ba J. L.: Adam: A Method For Stochastic Optimization. 3rd International Conference for Learning Representations, San Diego, 2015, arXiv:1412.6980.
Google Scholar
Mart´ın A. et al.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. 2016, arXiv:1603.04467.
Google Scholar
Milletari F. et al.: V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. 2016, arXiv:1606.04797.
DOI: https://doi.org/10.1109/3DV.2016.79
Google Scholar
Nations Unies, ONU Info: Le cancer du sein est désormais le plus fréquent au monde, 2021 [https://news.un.org/fr/story/2021/02/1088502].
Google Scholar
Oktay O. et al.: Attention U-Net: Learning Where to Look for the Pancreas, 2018, arXiv:1804.03999.
Google Scholar
Prasad S. N., Houserkova D.: A Comparison Of Mammography And Ultrasonography In The Evaluation Of Breast Masses. Biomed Pap Med Fac Univ Palacky Olomouc Czech Repub. 151(2), 2007, 315–322 [http://doi.org/10.5507/bp.2007.054].
DOI: https://doi.org/10.5507/bp.2007.054
Google Scholar
Ronneberger O. et al.: U-Net: Convolutional Networks for Biomedical Image Segmentation, 2015, arXiv:1505.04597.
DOI: https://doi.org/10.1007/978-3-319-24574-4_28
Google Scholar
Authors
Ihssane Khallassiihssanekhallassi639@gmail.com
Electronic Systems Sensors and Nanobiotechnology, National School of Arts and Crafts, Mohammed V University in Rabat, Morocco Morocco
https://orcid.org/0009-0006-7965-0269
Authors
My Hachem El Yousfi AlaouiElectronic Systems Sensors and Nanobiotechnology, National School of Arts and Crafts, Mohammed V University in Rabat, Morocco Morocco
https://orcid.org/0000-0003-4285-0540
Authors
Abdelilah JilbabElectronic Systems Sensors and Nanobiotechnology, National School of Arts and Crafts, Mohammed V University in Rabat, Morocco Morocco
https://orcid.org/0000-0002-1577-9040
Statistics
Abstract views: 140PDF downloads: 139
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Most read articles by the same author(s)
- Mohamed Bal-Ghaoui, My Hachem El Yousfi Alaoui, Abdelilah Jilbab, Abdennaser Bourouhou, OPTIMIZING ULTRASOUND IMAGE CLASSIFICATION THROUGH TRANSFER LEARNING: FINE-TUNING STRATEGIES AND CLASSIFIER IMPACT ON PRE-TRAINED INNER-LAYERS , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 13 No. 4 (2023)
