Classification of the presence of malignant lesions on mammogram using deep learning
- 作者: Ibragimov A.A.1, Senotrusova S.A.1, Litvinov A.A.1, Beliaeva A.A.1, Ushakov E.N.1, Markin Y.V.1
-
隶属关系:
- Institute for System Programming
- 期: 卷 5, 编号 1S (2024)
- 页面: 137-139
- 栏目: 青年科学家的文章
- ##submission.dateSubmitted##: 16.02.2024
- ##submission.dateAccepted##: 05.03.2024
- ##submission.datePublished##: 03.07.2024
- URL: https://jdigitaldiagnostics.com/DD/article/view/627019
- DOI: https://doi.org/10.17816/DD627019
- ID: 627019
如何引用文章
全文:
详细
BACKGROUND: Breast cancer is one of the leading causes of cancer-related mortality in women [1]. Regular mass screening with mammography plays a critical role in the early detection of changes in breast tissue. However, the early stages of pathology often go undetected and are difficult to diagnose [2].
Despite the effectiveness of mammography in reducing breast cancer mortality, manual image analysis can be time consuming and labor intensive. Therefore, attempts to automate this process, for example using computer-aided diagnosis systems, are relevant [3]. In recent years, however, solutions based on neural networks have gained increasing interest, especially in biology and medicine [4-6]. Technological advances using artificial intelligence have already demonstrated their effectiveness in pathology detection [7, 8].
AIM: The study aimed to develop an automated solution to detect breast cancer on mammograms.
MATERIALS AND METHODS: The solution is implemented as follows: a deep neural network-based tool has been developed to obtain the probability of malignancy from the input image. A combined dataset from public datasets such as MIAS, CBIS-DDSM, INbreast, CMMD, KAU-BCMD, and VinDr-Mammo [9–14] was used to train the model.
RESULTS: The classification model, based on the EfficientNet-B3 architecture, achieved an area under the ROC curve of 0.95, a sensitivity of 0.88, and a specificity of 0.9 when tested on a sample from the combined dataset. The model’s high generalization ability, which is another advantage, was demonstrated by its ability to perform well on images from different datasets with varying data quality and acquisition regions. Furthermore, techniques such as image pre-cropping and augmentations during training were used to enhance the model's performance.
CONCLUSIONS: The experimental results demonstrated that the model is capable of accurately detecting malignancies with a high degree of confidence. The obtained high-quality metrics offer a significant potential for implementing this method in automated diagnostics, for instance, as an additional opinion for medical specialists.
全文:
BACKGROUND: Breast cancer is one of the leading causes of cancer-related mortality in women [1]. Regular mass screening with mammography plays a critical role in the early detection of changes in breast tissue. However, the early stages of pathology often go undetected and are difficult to diagnose [2].
Despite the effectiveness of mammography in reducing breast cancer mortality, manual image analysis can be time consuming and labor intensive. Therefore, attempts to automate this process, for example using computer-aided diagnosis systems, are relevant [3]. In recent years, however, solutions based on neural networks have gained increasing interest, especially in biology and medicine [4-6]. Technological advances using artificial intelligence have already demonstrated their effectiveness in pathology detection [7, 8].
AIM: The study aimed to develop an automated solution to detect breast cancer on mammograms.
MATERIALS AND METHODS: The solution is implemented as follows: a deep neural network-based tool has been developed to obtain the probability of malignancy from the input image. A combined dataset from public datasets such as MIAS, CBIS-DDSM, INbreast, CMMD, KAU-BCMD, and VinDr-Mammo [9–14] was used to train the model.
RESULTS: The classification model, based on the EfficientNet-B3 architecture, achieved an area under the ROC curve of 0.95, a sensitivity of 0.88, and a specificity of 0.9 when tested on a sample from the combined dataset. The model’s high generalization ability, which is another advantage, was demonstrated by its ability to perform well on images from different datasets with varying data quality and acquisition regions. Furthermore, techniques such as image pre-cropping and augmentations during training were used to enhance the model's performance.
CONCLUSIONS: The experimental results demonstrated that the model is capable of accurately detecting malignancies with a high degree of confidence. The obtained high-quality metrics offer a significant potential for implementing this method in automated diagnostics, for instance, as an additional opinion for medical specialists.
作者简介
Alisher Ibragimov
Institute for System Programming
编辑信件的主要联系方式.
Email: ibragimov@ispras.ru
ORCID iD: 0000-0002-4406-4562
SPIN 代码: 3540-3992
俄罗斯联邦, Moscow
Sofya Senotrusova
Institute for System Programming
Email: senotrusova@ispras.ru
ORCID iD: 0000-0003-0960-8920
SPIN 代码: 4872-3388
俄罗斯联邦, Moscow
Arsenii Litvinov
Institute for System Programming
Email: filashkov@ispras.ru
ORCID iD: 0009-0000-3561-3817
俄罗斯联邦, Moscow
Aleksandra Beliaeva
Institute for System Programming
Email: belyaeva.a@ispras.ru
俄罗斯联邦, Moscow
Egor Ushakov
Institute for System Programming
Email: ushakov@ispras.ru
ORCID iD: 0000-0001-8370-6911
俄罗斯联邦, Moscow
Yury Markin
Institute for System Programming
Email: ustas@ispras.ru
ORCID iD: 0000-0003-1145-5118
SPIN 代码: 8440-9532
俄罗斯联邦, Moscow
参考
- Milroy MJ. Cancer statistics: Global and national. In: Quality Cancer Care: Survivorship Before, During and After Treatment. Hopewood P, Milroy MJ, editors. Springer; 2018.
- Mainiero MB, Moy L, Baron P, et al. ACR appropriateness criteria breast cancer screening. Journal of the American College of Radiology. 2017;14(11S):S383–S390. doi: 10.1016/j.jacr.2017.08.044
- Elter M, Horsch A. CADx of mammographic masses and clustered microcalcifications: a review. Medical physics. 2009;36(6):2052–2068. doi: 10.1118/1.3121511
- Kegeles E, Naumov A, Karpulevich EA, Volchkov P, Baranov P. Convolutional neural networks can predict retinal differentiation in retinal organoids. Front. Cell. Neurosci. 2020;14:171. doi: 10.3389/fncel.2020.00171
- Ibragimov A, Senotrusova S, Markova K, et al. Deep semantic segmentation of angiogenesis images. Int. J. Mol. Sci. 2023;24(2). doi: 10.3390/ijms24021102
- Naumov A, Ushakov E, Ivanov A, et al. EndoNuke: Nuclei detection dataset for estrogen and progesterone stained IHC endometrium scans. Data (Basel). 2022;7(6). doi: 10.3390/data7060075
- Dembrower K, Wåhlin E, Liu Y, et al. Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study. The Lancet Digital Health. 2020;2(9):e468–e474. doi: 10.1016/S2589-7500(20)30185-0
- Jiang Y, Edwards AV, Newstead GM. Artificial intelligence applied to breast MRI for improved diagnosis. Radiology. 2021;298(1):38–46. doi: 10.1148/radiol.2020200292
- Suckling J. The mammographic image analysis society digital mammogram database. Exerpta Medica International Congress. 1994;1069:375–378.
- Lee RS, Gimenez F, Hoogi A, et al. A curated mammography data set for use in computer-aided detection and diagnosis research. Sci. Data. 2017;4:170177. doi: 10.1038/sdata.2017.177
- Moreira IC, Amaral I, Domingues I, et al. INbreast: toward a full-field digital mammographic database. Acad. Radiol. 2012;19(2):236–248. doi: 10.1016/j.acra.2011.09.014
- Cui C, Li L, Cai H, et al. The Chinese mammography database (CMMD): An online mammography database with biopsy confirmed types for machine diagnosis of breast. Data Cancer Imaging Arch. 2021. doi: 10.7937/tcia.eqde-4b16
- Alsolami AS, Shalash W, Alsaggaf W, et al. King abdulaziz university breast cancer mammogram dataset (KAU-BCMD). Data Basel. 2021;6(11):111. doi: 10.3390/data6110111
- Nguyen HT, Nguyen HQ, Pham HH, et al. VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography. Sci. Data. 2023;10(1):277. doi: 10.1038/s41597-023-02100-7
补充文件
![](/img/style/loading.gif)