A novel artificial intelligence-based hybrid system to improve breast cancer detection using DCE-MRI

• Autorzy: Akgül İsmail , Kaya Volkan , Karavaş Erdal , Aydin Sonay , Baran Ahmet

Identyfikatory

DOI

10.24425/bpasts.2024.149172

• Języki publikacji: EN

Abstrakty

EN

The interpretation of breast magnetic resonance imaging (MRI) in the healthcare field depends on the good knowledge and experience of radiologists. Recent developments in artificial intelligence (AI) have shown advances in the field of radiology. However, the desired levels have not been reached in the field of radiology yet. In this study, a novel model structure is proposed to characterize the diagnostic performance of AI technology for individual breast dynamic contrast material–enhanced (DCE) MRI sequences. In the proposed model structure, Inception-v3, EfficientNet-B3, and DenseNet-201 models were used as hybrids together with the Yolo-v3 algorithm to detect breast and cancer regions. In the proposed model, DCE-MRI sequences (T2, ADC, Diffusion, Non-Contrast Fat Non-Suppressed T1, Non-Contrast Fat Suppressed T1, Contrast Fat Suppressed T1, and Subtraction T1) were evaluated separately and validation was made, thus providing a unique perspective. According to the validation results, the model structure with the best performance was determined as Yolo-v3 + DenseNet-201. With this model structure, 92.41% accuracy, 0.5936 loss, 92.44% sensitivity, and 92.44% specificity rates were obtained. In addition, it was determined that the results obtained without using contrast material in the best model were 91.53% accuracy, 0.9646 loss, 92.19% sensitivity, and 92.19% specificity. Therefore, it is predicted that the need for contrast material use can be reduced with the help of this model structure.

Słowa kluczowe

EN

artificial intelligence; artificial neural network; deep learning; DCE-MRI; breast cancer detection; breast cancer classification; dynamic contrast enhanced magnetic resonance imaging

PL

sztuczna inteligencja; sztuczna sieć neuronowa; uczenie głębokie; DCE-MRI; rezonans magnetyczny ze wzmocnionym kontrastem dynamicznym; rak piersi wykrywanie; rak piersi klasyfikacja

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2024
• Tom: Vol. 72, nr 3
• Strony: art. no. e149172
• Opis fizyczny: Bibliogr. 27 poz., rys., tab.

Twórcy

autor

Akgül İsmail

• Department of Computer Engineering, Faculty of Engineering and Architecture, Erzincan Binali Yıldırım University, Türkiye

• https://orcid.org/0000-0003-2689-8675

autor

Kaya Volkan

• Department of Computer Engineering, Faculty of Engineering and Architecture, Erzincan Binali Yıldırım University, Türkiye

• https://orcid.org/0000-0001-6940-3260

autor

Karavaş Erdal

• Department of Radiology, Faculty of Medicine, Bandırma Onyedi Eylül University, Balıkesir, Türkiye

• https://orcid.org/0000-0001-6649-3256

autor

Aydin Sonay

• Department of Radiology, Faculty of Medicine, Erzincan Binali Yıldırım University, Erzincan, Türkiye

• https://orcid.org/0000-0002-3812-6333

autor

Baran Ahmet

• Department of Computer Engineering, Faculty of Engineering and Architecture, Erzincan Binali Yıldırım University, Türkiye

• https://orcid.org/0000-0003-2017-799X

Bibliografia

• [1] F. Pesapane, C. Volonté, M. Codari, and F. Sardanelli, “Artificial intelligence as a medical device in radiology: ethical and regulatory issues in Europe and the United States,” Insights Imaging, vol. 9, no. 5, pp. 745–753, 2018, doi: 10.1007/s13244-018-0645-y.
• [2] M. Codari, S. Schiaffino, F. Sardanelli, and R.M. Trimboli, “Artificial intelligence for breast MRI in 2008–2018: a systematic mapping review,” Am. J. Roentgenol., vol. 212, no. 2, pp. 280–292, 2019, doi: 10.2214/AJR.18.20389.
• [3] D. Özdemir, and N.N. Arslan, “Analysis of Deep Transfer Learning Methods for Early Diagnosis of the Covid-19 Disease with Chest X-ray Images,” Düzce Üniversitesi Bilim ve Teknoloji Dergisi, vol. 10, no. 2, 628–640, 2022, doi: 10.29130/dubited.976118.
• [4] R.M. Warren et al., “Reading protocol for dynamic contrast-enhanced MR images of the breast: sensitivity and specificity analysis,” Radiology, vol. 236, no. 3, pp. 779–788, 2005, doi: 10.1148/radiol.2363040735.
• [5] Y. Jiang, A.V. Edwards, and G.M. Newstead, “Artificial intelligence applied to breast MRI for improved diagnosis,” Radiology, vol. 298, no. 1, pp. 38–46, 2021, doi: 10.1148/radiol.2020200292.
• [6] R.M. Mann, C.K. Kuhl, and L. Moy, “Contrast-enhanced MRI for breast cancer screening,” J. Magn. Reson. Imaging, vol. 50, no. 2, pp. 377–390, 2019, doi: 10.1002/jmri.26654.
• [7] B. Reig, L. Heacock, K.J. Geras, and L. Moy, “Machine learning in breast MRI,” J. Magn. Reson. Imaging, vol. 52, no. 4, pp. 998–1018, 2020, doi: 10.1002/jmri.26852.
• [8] M. Adachi et al., “Detection and diagnosis of breast cancer using artificial intelligence based assessment of maximum intensity projection dynamic contrast-enhanced magnetic resonance images,” Diagnostics, vol. 10, no. 5, p. 330, 2020, doi: 10.3390/diagnostics10050330.
• [9] F. Ayatollahi, S.B. Shokouhi, R.M. Mann, and J. Teuwen, “Automatic breast lesion detection in ultrafast DCE-MRI using deep learning,” Med. Phys., vol. 48, no. 10, pp. 5897–5907, 2021, doi: 10.1002/mp.15156.
• [10] J. Zhou et al., “Diagnosis of benign and malignant breast lesions on DCE-MRI by using radiomics and deep learning with consideration of peritumor tissue,” J. Magn. Reson. Imaging, vol. 51, no. 3, pp. 798–809, 2020, doi: 10.1002/jmri.26981.
• [11] B. Reig, “Radiomics and deep learning methods in expanding the use of screening breast MRI,” Eur. Radiol., vol. 31, no. 8, pp. 5863–5865, 2021, doi: 10.1007/s00330-021-08056-9.
• [12] Colab. Google Colaboratory [Online]. Available: https://colab.research.google.com [Accessed: 10 Sep. 2022]
• [13] J. Redmon, and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint, pp. 1–6, 2018, doi: 10.48550/arXiv.1804.02767.
• [14] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Re-thinking the inception architecture for computer vision,” in Proc. IEEE conference on computer vision and pattern recognition, 2016, pp. 2818–2826.
• [15] M. Tan, and Q. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” in International conference on machine learning, Proceedings of Machine Learning Research (PMLR), 2019, pp. 6105–6114.
• [16] G. Huang, Z. Liu, L. Van Der Maaten, and K.Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE conference on computer vision and pattern recognition, 2017, pp. 4700–4708.
• [17] S. Mirbagheri, and M. Momeni, “A Hybrid Deep Learning Methodology for Breast Cancer Diagnosis using Magnetic Resonance Images,” Res. Square – preprint, pp. 1–16, 2022 doi: 10.21203/rs.3.rs-1604535/v1.
• [18] S. Joo et al., “Multimodal deep learning models for the prediction of pathologic response to neoadjuvant chemotherapy in breast cancer,” Sci. Rep., vol. 11, no. 1, p. 18800, 2021, doi: 10.1038/s41598-021-98408-8.
• [19] Q. Hu, H.M. Whitney, H. Li, Y. Ji, P. Liu, and M.L. Giger, “Improved classification of benign and malignant breast lesions using deep feature maximum intensity projection MRI in breast cancer diagnosis using dynamic contrast-enhanced MRI,” Radiol.-Artif. Intell., vol. 3, no. 3, pp. 1–9, 2021, doi: 10.1148/ryai.2021200159.
• [20] T. Fujioka et al., “Deep-learning approach with convolutional neural network for classification of maximum intensity projections of dynamic contrast-enhanced breast magnetic resonance imaging,” J. Magn. Reson. Imaging, vol. 75, pp. 1–8, 2021, doi: 10.1016/j.mri.2020.10.003.
• [21] L. Wang et al., “An artificial intelligence system using maximum intensity projection MR images facilitates classification of non-mass enhancement breast lesions,” Eur. Radiol., vol. 32, no. 7, pp. 4857–4867, 2022, doi: 10.1007/s00330-022-08553-5.
• [22] Y. Wu, J. Wu, Y. Dou, N. Rubert, Y. Wang, and J. Deng, “A deep learning fusion model with evidence-based confidence level analysis for differentiation of malignant and benign breast tumors using dynamic contrast enhanced MRI,” Biomed. Signal Process. Control, vol. 72, pp. 1–11, 2022, doi: 10.1016/j.bspc.2021.103319.
• [23] G. Ye, S. He, R. Pan, L. Zhu, D. Zhou, and R. Lu, “Research on DCE-MRI Images Based on Deep Transfer Learning in Breast Cancer Adjuvant Curative Effect Prediction,” J. Healthc. Eng., vol. 2022, p. 4477099, 2022, doi: 10.1155/2022/4477099.
• [24] L.A. Kapsner et al., “Automated artifact detection in abbreviated dynamic contrast-enhanced (DCE) MRI-derived maximum intensity projections (MIPs) of the breast,” Eur. Radiol., vol. 32, no. 9, pp. 5997–6007, 2022, doi: 10.1007/s00330-022-08626-5.
• [25] S. Eskreis-Winkler et al., “Using deep learning to improve non-systematic viewing of breast cancer on MRI,” J. Breast Imaging, vol. 3, no. 2, pp. 201–207, 2021, doi: 10.1093/jbi/wbaa102.
• [26] M.Z. Liu et al., “Weakly supervised deep learning approach to breast MRI assessment,” Acad. Radiol., vol. 29, pp. S166-S172, 2022, doi: 10.1016/j.acra.2021.03.032.
• [27] P. Jaglan, R. Dass, and M. Duhan, “An automatic and efficient technique for tumor location identification and classification through breast MR images,” Expert Syst. Appl., vol. 185, p. 115580, 2021, doi: 10.1016/j.eswa.2021.115580.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).