Authors
Karpov O.E.1, Bronov O.Yu.1, Kapninskiy A.A.2, Pavlovich P.I.1, Abovich Yu.A.1, Subbotin S.A.1, Sokolova S.V.1, Rychagova N.I.1, Milova A.V.1, Nikitin E.D.2
1 Pirogov National Medical and Surgical Center, Moscow
2 Medical Screening Systems LLC, Kaluga
Abstract
The article discusses the possibility of using the AI-based system for the analysis of mammological images Celsus for the detection of malignant neoplasms of the mammary gland during screening mammographic studies. The article presents the results of a retrospective cohort study performed on a group of 49 patients screened at the National Medical and Surgical Center named after N.I. Pirogov and with a verified diagnosis of malignant lesions according to histological examination data.
The quantitative characteristics of the analysis of digital mammograms by the Celsus system were obtained. In particular, malignant neoplasms were detected in 92% of cases, and a complete agreement with a group of radiologists specializing in mammography was made in 90% of cases. The results of a comparative clinical analysis of the most difficult cases for diagnosis are presented. The expediency of using the Celsus system for analytical support of radiologists during screening mammographic studies is shown and use-cases of their use are determined.
Keywords: mammography, artificial intelligence (AI), BI-RADS, Breast Imaging-Reporting and Data System.
References
1. Marmot MG, Altman DG, Cameron DA, Dewar JA, Thompson SG, Wilcox M. The benefits and harms of breast cancer screening: an independent review. Br J Cancer. 2013; 108(11): 2205-2240.
2. Sant M, Allemani C, Berrino F, et al. Breast carcinoma survival in Europe and the United States. Cancer. 2004; 100(4): 715-722.
3. Breast Cancer Screening Market. Global Analysis by Population, Screening Tests [Mammography, MRI, Ultrasound], Countries & Forecast (2018-2024) [URL]. Accessed November 18, 2019.
4. Rawashdeh MA, Lee WB, Bourne RM, et al. Markers of good performance in mammography depend on number of annual readings. Radiology. 2013; 269(1): 61-67.
5. Lehman CD, Wellman RD, Buist DSM, et al. Diagnostic Accuracy of Digital Screening Mammography With and Without Computer-Aided Detection. JAMA Intern Med. 2015; 175(11): 1828-1837.
6. Gilbert FJ, Astley SM, Gillan MGC, et al. Single reading with computer-aided detection for screening mammography. N Engl J Med. 2008; 359(16): 1675-1684.
7. James JJ, Gilbert FJ, Wallis MG, et al. Mammographic features of breast cancers at single reading with computer-aided detection and at double reading in a large multicenter prospective trial of computer-aided detection: CADET II. Radiology. 2010; 256(2): 379-386.
8. Gromet M. Comparison of computer-aided detection to double reading of screening mammograms: review of 231, 221 mammograms. AJR Am J Roentgenol. 2008; 190(4): 854-859.
9. Fenton JJ, Taplin SH, Carney PA, et al. Influence of computer-aided detection on performance of screening mammography. N Engl J Med. 2007; 356(14): 1399-1409.
10. Kooi T, Litjens G, van Ginneken B, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal. 2017; 35: 303-312.
11. Rodríguez-Ruiz A, Krupinski E, Mordang JJ, et al. Detection of Breast Cancer with Mammography: Effect of an Artificial Intelligence Support System. Radiology. 2019; 290(2): 305-314.
12. Shen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W. Deep Learning to Improve Breast Cancer Detection on Screening Mammography. Sci Rep. 2019; 9(1): 12495.
13. Wu N, Phang J, Park J, et al. Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening. arXiv:190308297 [cs, stat]. [preprint] [URL]. Accessed October 3, 2019.
14. Sahran S, Qasem A, Omar K, et al. Machine Learning Methods for Breast Cancer Diagnostic. Breast Cancer and Surgery. Published November 5, 2018. Accessed October 3, 2019.
15. Methodological recommendations on the use of the international system for mammography research, recommended by the decision of the Bureau of the Scientific Medical Council of the Moscow Department of Health dated October 18, 2017. (In Russ).
