Transfer Learning-Based Classification of Breast Cancer using Ultrasound Images
Abstract
Objective: One of the most significant cancers impacting the health of women is breast cancer. This study aimed to provide breast cancer classification (benign and malignant) using the transfer learning method on the ultrasound images.
Methods: In the present study, a public imaging dataset was used for the breast cancer classification. Transfer learning technique was implemented for the detection and classification of breast cancer (benign or malignant) based on the ultrasound images. The current research includes data of 150 cases of malignant and 100 normal cases obtained from the Mendeley data. The relevant dataset was partitioned into training (85% of the images) and validation (15% of the images) sets. The present study implemented Teachable Machine (teachablemachine.withgoogle.com) for predicting the benign or malignant of breast cancer tumor based on the ultrasound images.
Results: According to the experimental results, accuracy, sensitivity and specificity with 95% confidence intervals were 0.974 (0.923-1.0), 0.957 (0.781-0.999) and 1 (0.782-1.0), respectively.
Conclusion: The model proposed in this study gave predictions that could be useful to clinicians in classifying breast cancer based on ultrasound images. Thus, this system can be developed in mobile, web, or alternative environments and offered as a computer-aided system for the use of radiologists, pathologists or other healthcare professionals in hospitals.
Methods: In the present study, a public imaging dataset was used for the breast cancer classification. Transfer learning technique was implemented for the detection and classification of breast cancer (benign or malignant) based on the ultrasound images. The current research includes data of 150 cases of malignant and 100 normal cases obtained from the Mendeley data. The relevant dataset was partitioned into training (85% of the images) and validation (15% of the images) sets. The present study implemented Teachable Machine (teachablemachine.withgoogle.com) for predicting the benign or malignant of breast cancer tumor based on the ultrasound images.
Results: According to the experimental results, accuracy, sensitivity and specificity with 95% confidence intervals were 0.974 (0.923-1.0), 0.957 (0.781-0.999) and 1 (0.782-1.0), respectively.
Conclusion: The model proposed in this study gave predictions that could be useful to clinicians in classifying breast cancer based on ultrasound images. Thus, this system can be developed in mobile, web, or alternative environments and offered as a computer-aided system for the use of radiologists, pathologists or other healthcare professionals in hospitals.
Keywords
Breast Cancer , Classification , Ultrasound Images , Transfer Learning
References
- 1. Zhang X, Lin X, Zhang Z, Dong L, Sun X, Sun D, et al. Artificial intelligence medical ultrasound equipment: application of breast lesions detection. Ultrasonic Imaging. 2020;42(4-5):191-202.
- 2. Zhuang Z, Kang Y, Joseph Raj AN, Yuan Y, Ding W, Qiu S. Breast ultrasound lesion classification based on image decomposition and transfer learning. Medical Physics. 2020.
- 3. Hijab A, Rushdi MA, Gomaa MM, Eldeib A, editors. Breast cancer classification in ultrasound images using transfer learning. 2019 Fifth International Conference on Advances in Biomedical Engineering (ICABME); 2019: IEEE.
- 4. Rodrigues PSJMD. Breast ultrasound image. 2017;1.
- 5. Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H, et al. A comprehensive survey on transfer learning. 2020;109(1):43-76. 6. Cai C, Wang S, Xu Y, Zhang W, Tang K, Ouyang Q, et al. Transfer Learning for Drug Discovery. Journal of Medicinal Chemistry. 2020;63(16):8683-94.
- 7. Carney M, Webster B, Alvarado I, Phillips K, Howell N, Griffith J, et al., editors. Teachable machine: Approachable Web-based tool for exploring machine learning classification. Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems; 2020.
- 8. YAŞAR Ş, ARSLAN A, Colak C, Yoloğlu SJMBSJoHS. A Developed Interactive Web Application for Statistical Analysis: Statistical Analysis Software.6(2):227-39.
- 9. Deniz E, Şengür A, Kadiroğlu Z, Guo Y, Bajaj V, Budak ÜJHis, et al. Transfer learning based histopathologic image classification for breast cancer detection. 2018;6(1):1-7.
- 10. Krizhevsky A, Sutskever I, Hinton GEJCotA. ImageNet classification with deep convolutional neural networks. 2017;60(6):84-90.
- 11. Abbasi AA, Hussain L, Awan IA, Abbasi I, Majid A, Nadeem MSA, et al. Detecting prostate cancer using deep learning convolution neural network with transfer learning approach. 2020;14(4):523-33.