Classification of the presence of malignant lesions on mammogram using deep learning

Capa


Citar

Texto integral

Resumo

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.

Texto integral

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.

×

Sobre autores

Alisher Ibragimov

Institute for System Programming

Autor responsável pela correspondência
Email: ibragimov@ispras.ru
ORCID ID: 0000-0002-4406-4562
Código SPIN: 3540-3992
Rússia, Moscow

Sofya Senotrusova

Institute for System Programming

Email: senotrusova@ispras.ru
ORCID ID: 0000-0003-0960-8920
Código SPIN: 4872-3388
Rússia, Moscow

Arsenii Litvinov

Institute for System Programming

Email: filashkov@ispras.ru
ORCID ID: 0009-0000-3561-3817
Rússia, Moscow

Aleksandra Beliaeva

Institute for System Programming

Email: belyaeva.a@ispras.ru
Rússia, Moscow

Egor Ushakov

Institute for System Programming

Email: ushakov@ispras.ru
ORCID ID: 0000-0001-8370-6911
Rússia, Moscow

Yury Markin

Institute for System Programming

Email: ustas@ispras.ru
ORCID ID: 0000-0003-1145-5118
Código SPIN: 8440-9532
Rússia, Moscow

Bibliografia

  1. Milroy MJ. Cancer statistics: Global and national. In: Quality Cancer Care: Survivorship Before, During and After Treatment. Hopewood P, Milroy MJ, editors. Springer; 2018.
  2. 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
  3. 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
  4. 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
  5. 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
  6. 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
  7. 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
  8. 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
  9. Suckling J. The mammographic image analysis society digital mammogram database. Exerpta Medica International Congress. 1994;1069:375–378.
  10. 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
  11. 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
  12. 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
  13. 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
  14. 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

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML
Baixar

Declaração de direitos autorais © Eco-Vector, 2024

Creative Commons License
Este artigo é disponível sob a Licença Creative Commons Atribuição–NãoComercial–SemDerivações 4.0 Internacional.
СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № ФС 77 - 79539 от 09 ноября 2020 г.


Este site utiliza cookies

Ao continuar usando nosso site, você concorda com o procedimento de cookies que mantêm o site funcionando normalmente.

Informação sobre cookies