کاربردهای یادگیری عمیق در تصویربرداری سرطان پستان: دستاوردهای گذشته و چالش های آینده
محورهای موضوعی : مهندسی پزشکی
زهرا مقصودزاده سروستانی
1
*
,
سلما شیردل
2
1 - گروه مهندسی برق، واحد شیراز، دانشگاه آزاد اسلامی، شیراز، ایران
2 - دانشجو، دانشگاه صدا و سیما، دانشکده فنی و مهندسی رسانه
کلید واژه: ماموگرافی, سونوگرافی, تصویربرداری تشدید مغناطیسی, یادگیری عمیق ,
چکیده مقاله :
از سال ۲۰۲۰، سرطان سینه به شایع ترین بدخیمی تشخیص داده شده در سراسر جهان تبدیل شده است. نقش تصویربرداری پستان در تشخیص زودهنگام و مداخله برای بهبود نتایج بیمار بسیار مهم است. در دهه گذشته، یادگیری عمیق انقلابی در تجزیه و تحلیل تصویربرداری سرطان پستان ایجاد کرده است و پیشرفت های قابل توجهی در تفسیر داده های پیچیده از روش های مختلف تصویربرداری ارائه می دهد. با تکامل سریع فناوری یادگیری عمیق و افزایش بروز سرطان سینه، مرور دستاوردهای گذشته و شناسایی چالش های آینده ضروری است. این مقاله بررسی گسترده ای از تحقیقات تصویربرداری سرطان پستان مبتنی بر یادگیری عمیق را ارائه می دهد که بر مطالعات مربوط به ماموگرافی، سونوگرافی، تصویربرداری تشدید مغناطیسی و تصاویر آسیب شناسی دیجیتال در ده سال گذشته تمرکز دارد. روش های یادگیری عمیق اولیه و کاربردهای آنها در غربالگری، تشخیص، پیش بینی پاسخ درمان و پیش آگهی مبتنی بر تصویربرداری را برجسته می کند. بر اساس یافته های تحقیق، چالش ها مورد بحث قرار می گیرد و جهت های تحقیقاتی بالقوه آینده در تصویربرداری سرطان پستان مبتنی بر یادگیری عمیق پیشنهاد می شود.
Since 2020, breast cancer has become the most frequently diagnosed malignancy worldwide. The role of breast imaging in early detection and intervention is critical for improving patient outcomes. In the past decade, deep learning has revolutionized the analysis of breast cancer imaging, providing significant advancements in interpreting the complex data from various imaging modalities. With the rapid evolution of deep learning technology and the increasing incidence of breast cancer, it is essential to review past achievements and identify future challenges. This paper offers an extensive review of deep learning-based breast cancer imaging research, focusing on studies involving mammograms, ultrasound, magnetic resonance imaging, and digital pathology images over the last ten years. It highlights the primary deep learning methods and their applications in imaging-based screening, diagnosis, treatment response prediction, and prognosis. Based on the research findings, we discuss the challenges and propose potential future research directions in deep learning-based breast cancer imaging.
[1] J. Wang and S.-G. Wu, “Breast Cancer: An Overview of Current Therapeutic Strategies, Challenge, and Perspectives,” Breast Cancer: Targets and Therapy, vol. 15, pp. 721–730, Oct. 2023, doi: https://doi.org/10.2147/bctt.s432526.
[2] A. N. Giaquinto et al., “Breast Cancer Statistics, 2022,” CA: A Cancer Journal for Clinicians, vol. 72, no. 6, Oct. 2022, doi: https://doi.org/10.3322/caac.21754.
[3] H. Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries,” CA: a Cancer Journal for Clinicians, vol. 71, no. 3, pp. 209–249, Feb. 2021, doi: https://doi.org/10.3322/caac.21660.
[4] M. B. Amin et al., “The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more ‘personalized’ approach to cancer staging,” CA: A Cancer Journal for Clinicians, vol. 67, no. 2, pp. 93–99, Jan. 2017, doi: https://doi.org/10.3322/caac.21388.
[5] L. Nyström, I. Andersson, N. Bjurstam, J. Frisell, B. Nordenskjöld, and L. E. Rutqvist, “Long-term effects of mammography screening: updated overview of the Swedish randomised trials,” The Lancet, vol. 359, no. 9310, pp. 909–919, Mar. 2002, doi: https://doi.org/10.1016/s0140-6736(02)08020-0.
[6] J. Didkowska and Urszula Wojciechowska, “WHO position paper on mammography screening,” vol. 11, no. 1, pp. 16–19, Jan. 2015.
[7] M. G. Marmot, D. G. Altman, D. A. Cameron, J. A. Dewar, S. G. Thompson, and M. Wilcox, “The benefits and harms of breast cancer screening: an independent review,” British Journal of Cancer, vol. 108, no. 11, pp. 2205–2240, Jun. 2013, doi: https://doi.org/10.1038/bjc.2013.177.
[8] A. Chong, S. P. Weinstein, E. S. McDonald, and E. F. Conant, “Digital Breast Tomosynthesis: Concepts and Clinical Practice,” Radiology, vol. 292, no. 1, pp. 1–14, Jul. 2019, doi: https://doi.org/10.1148/radiol.2019180760.
[9] J. J. Wild and D. Neal, “Use of high-frequency ultrasonic waves for detecting changes of texture in living tissues.,” The Lancet, vol. 257, no. 6656, pp. 655–657, Mar. 1951, doi: 10.1016/S0140-6736(51)92403-8.
[10] C. M. Sehgal, S. P. Weinstein, P. H. Arger, and E. F. Conant, “A Review of Breast Ultrasound,” Journal of Mammary Gland Biology and Neoplasia, vol. 11, no. 2, pp. 113–123, Nov. 2006, doi: https://doi.org/10.1007/s10911-006-9018-0.
[11] R. J. Hooley, L. M. Scoutt, and L. E. Philpotts, “Breast Ultrasonography: State of the Art,” Radiology, vol. 268, no. 3, pp. 642–659, Sep. 2013, doi: https://doi.org/10.1148/radiol.13121606.
[12] A. Kapur et al., “Combination of Digital Mammography with Semi-automated 3D Breast Ultrasound,” vol. 3, no. 4, pp. 325–334, Aug. 2004, doi: https://doi.org/10.1177/153303460400300402.
[13] W. A. Berg, “Combined Screening With Ultrasound and Mammography vs Mammography Alone in Women at Elevated Risk of Breast Cancer,” JAMA, vol. 299, no. 18, p. 2151, May 2008, doi: https://doi.org/10.1001/jama.299.18.2151.
[14] L. C. H. Leong, A. Gogna, R. Pant, Fook Cheong Ng, and L. S. J. Sim, “Supplementary Breast Ultrasound Screening in Asian Women with Negative But Dense Mammograms—A Pilot Study,” Annals, Academy of Medicine, Singapore/Annals of the Academy of Medicine, Singapore, vol. 41, no. 10, pp. 432–439, Oct. 2012, doi: https://doi.org/10.47102/annals-acadmedsg.v41n10p432.
[15] C. M. Sehgal, P. H. Arger, S. E. Rowling, E. F. Conant, C. Reynolds, and J. A. Patton, “Quantitative vascularity of breast masses by Doppler imaging: regional variations and diagnostic implications.,” Journal of Ultrasound in Medicine, vol. 19, no. 7, pp. 427–440, Jul. 2000, doi: https://doi.org/10.7863/jum.2000.19.7.427.
[16] W. A. Berg, “Combined Screening With Ultrasound and Mammography vs Mammography Alone in Women at Elevated Risk of Breast Cancer,” JAMA, vol. 299, no. 18, p. 2151, May 2008, doi: https://doi.org/10.1001/jama.299.18.2151.
[17] A. Kalovidouri et al., “Fat suppression techniques for breast MRI: Dixon versus spectral fat saturation for 3D T1-weighted at 3 T,” La radiologia medica, vol. 122, no. 10, pp. 731–742, Jun. 2017, doi: https://doi.org/10.1007/s11547-017-0782-2.
[18] M. A. Bernstein and K. F. King, “Handbook of MRI Pulse Sequences by Matt A. Bernstein, Kevin F. King & Xiaohong Joe Zhou Engineering,” Sep. 2004.
[19] M.-Y. Su et al., “Correlation of dynamic contrast enhancement MRI parameters with microvessel density and VEGF for assessment of angiogenesis in breast cancer,” vol. 18, no. 4, pp. 467–477, Oct. 2003, doi: https://doi.org/10.1002/jmri.10380.
[20] Y. Gao and S. L. Heller, “Abbreviated and Ultrafast Breast MRI in Clinical Practice,” RadioGraphics, vol. 40, no. 6, pp. 1507–1527, Oct. 2020, doi: https://doi.org/10.1148/rg.2020200006.
[21] E. Duregon et al., “Comparative diagnostic and prognostic performances of the hematoxylin-eosin and phospho-histone H3 mitotic count and Ki-67 index in adrenocortical carcinoma,” Modern Pathology, vol. 27, no. 9, pp. 1246–1254, Jan. 2014, doi: https://doi.org/10.1038/modpathol.2013.230.
[22] Enabling histopathological annotations on immunofluorescent images through virtualization of hematoxylin and eosin
[23] W. M. Hanna et al., “HER2 in situ hybridization in breast cancer: clinical implications of polysomy 17 and genetic heterogeneity,” Modern Pathology, vol. 27, no. 1, pp. 4–18, Jun. 2014, doi: https://doi.org/10.1038/modpathol.2014.103.
[24] A. S. Coates et al., “Tailoring therapies—improving the management of early breast cancer: St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2015,” Annals of Oncology, vol. 26, no. 8, pp. 1533–1546, Aug. 2015, doi: https://doi.org/10.1093/annonc/mdv221.
[25] S. J. Magny, R. Shikhman, and A. L. Keppke, “Breast Imaging Reporting and Data System,” PubMed, 2022. https://www.ncbi.nlm.nih.gov/books/NBK459169/
[26] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: https://doi.org/10.1038/nature14539.
[27] G. Litjens et al., “A Survey on Deep Learning in Medical Image Analysis,” Medical Image Analysis, vol. 42, no. 1, pp. 60–88, Dec. 2017, doi: https://doi.org/10.1016/j.media.2017.07.005.
[28] E. J. Topol, “High-performance medicine: the Convergence of Human and Artificial Intelligence,” Nature Medicine, vol. 25, no. 1, pp. 44–56, Jan. 2019.
[29] J. Bai, R. Posner, T. Wang, C. Yang, and S. Nabavi, “Applying deep learning in digital breast tomosynthesis for automatic breast cancer detection: A review,” Medical Image Analysis, vol. 71, p. 102049, Jul. 2021, doi: https://doi.org/10.1016/j.media.2021.102049.
[30] A. Duggento, A. Conti, A. Mauriello, M. Guerrisi, and N. Toschi, “Deep computational pathology in breast cancer,” Seminars in Cancer Biology, vol. 72, pp. 226–237, Jul. 2021, doi: https://doi.org/10.1016/j.semcancer.2020.08.006.