Automated differentiation of calcifications and their clusters on the mammography image: the outcomes of the computer aided diagnosis system module

INTRODUCTION: Previously we developed the computer aided detection system (CAD) for mammography MammCheck II that increased the detection rate of small and difficult to detect breast carcinomas (BC). However this system was not specifically designed for calcification detection and discrimination. On the other hand, the calcifications had no influence on the CAD capability to detect BCs that appeared as a focal lesions.

OBJECTIVE: To develop the approach for automated differentiation of benign and suspicious calcifications on the mammography images and assess its clinical value.

MATERIALS AND METHODS: For the developed software testing we used a set of 390 mammography images with calcifications of all possible types (278 images with benign and 112 images with suspicious calcifications). For classification we used linear support vector machine (SVM) model, that was trained on the set of 126 images (70 — benign and 56 — suspicious). We developed two SVM models: with no vascular calcification analysis and with it. Statistics: for comparison between the normally distributed samples we used the Student’s T-test, for non-normally distributed — Wilcoxon signed-rank or Chi-square tests. For correlation testing of normally distributed samples the Paerson coefficient was calculated, for non-normally distributed samples — the Spearman or Kendall correlation coefficients. The statistical significance corresponded to Р-values <0,05.

RESULTS: During the testing of the first model version with no vascular calcification analysis we discovered the similarity of small early vascular calcifications and the suspicious ones. As a result this model falsely classified 14 of 23 (60.87%) vascular calcification clusters as suspicious. Therefore the model was improved. The final discrimination results for all calcification types (both benign and suspicious) obtained with the help of improved model were the following: true positive conclusions — 375/390 (96.15%), false positive conclusions — 15/390 (3.84%). In both cases when suspicious calcifications were classified as benign the wrong results were een only on one mammography view. At the same time, on another view the suspicious calcifications were correctly classified.

DISCUSSION: During the CAD development it seems important not only mark the suspicious areas but also suppress false positive markings corresponding to the obviously benign lesions. However it is important during this operation not to suppress the true positive markings. Therefore such systems are inevitably characterized by a certain shift to decreased prognostic value of suspicious markings at the expense of the highest possible prognostic value of benign markings. In our viewpoint, the developed approach meets this requirement. Moreover, its integration into the CAD allows to suppress the markings of soft tissue lesions associated with typical benign calcifications, appeared on the previous processing steps. This capability may decrease the false positive rate of the main CAD module.

CONCLUSION: The developed approach to benign and suspicious calcification discrimination (version with vascular calcification analysis) on the mammography image provided the sensitivity — 98.21%, specificity — 95.32%, negative predictive value (benign marking) — 99.25%, positive predictive value (suspicious marking) — 89.43%.

1. Sung H., Ferlay J., Siegel R.L. et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries // CA Cancer J. Clin. 2021. Vol. 71, No. 3. Р. 209–249. doi: 10.3322/caac.21660.

2. Shakhzadovaya A.O., Starinskiy V.V., Lisichnikova I.V. Oncology care to the population of Russia in 2022. Siberian Journal of Oncology, 2023, Vol. 22, No. 5, pp. 5–13 (In Russ.). doi: 10.21294/1814-4861-2023-22-5-5-13.

3. Lauby-Secretan B., Scoccianti C., Loomis D., Benbrahim-Tallaa L., Bouvard V., Bianchini F., Straif K. Breast-cancer screening — viewpoint of the IARC Working Group // The New England Journal of Medicine. 2015. Vol. 372, No. 24. Р. 2353–2358. doi: 10.1056/NEJMsr1504363.

4. Ali M.A., Czene K., Hall P., Humphreys K. Association of Microcalcification Clusters with Short-term Invasive Breast Cancer Risk and Breast Cancer Risk Factors // Sci. Rep. 2019. Vol. 9, No. 1. Р. 1–8. doi: 10.1038/s41598-019-51186-w.

5. Gromov A.I., Komin Yu.A., Mozerov S.A., Krasnitskaya S.K. Twinkling artifact in differential diagnosis of mammary calcinates. Medical Visualization, 2021, Vol. 25, No. 3, pp. 157–166 (In Russ.). doi: 10.24835/1607-0763-1025.

6. Bennani-Baiti B., Baltzer P.A. MR Imaging for Diagnosis of Malignancy in Mammographic Microcalcifications: A Systematic Review and Meta-Analysis // Radiology. 2017. Vol. 283, No. 3. Р. 692–701. doi: 10.1148/radiol.2016161106.

7. Masud R., Al-Rei M., Lokker C. Computer-Aided Detection for Breast Cancer Screening in Clinical Settings: Scoping Review // JMIR Med Inform. 2019. Vol. 7, No. 3. e12660. doi: 10.2196/12660.

8. Rao A.A., Feneis J., Lalonde C., Ojeda-Fournier H. A Pictorial Review of Changes in the BI-RADS. Fifth Edition // Home Radio Graphics. 2016. Vol. 36, No 3. Р. 623–639. URL: https://doi.org/10.1148/rg.2016150178.

9. Egoshin I., Pasynkov D., Kolchev A., Kliouchkin I., Pasynkova O. A segmentation approach for mammographic images and its clinical value // IEEE International Conference on Microwaves, Antennas, Communications and Electronic Systems (COMCAS) (Tel-Aviv, Israel, November 13–15, 2017). Tel-Aviv, Israel, 2017. P. 1–6. doi: 10.1109/COMCAS.2017.8244764.

10. Pasynkov D.V., Egoshin I.A., Kolchev A.A., Klyushkin I.V., Pasynkova O.O. The value of computer aided detection system in breast cancer difficult to detect at screening mammography. Russian Electronic Journal of Radiology, 2019, Vol. 9, No. 2, pp. 107–118 (In Russ.). doi: 10.21569/2222-7415-2019-9-2-107-118.

11. Khasanov R.Sh., Tukhbatullin M.G., Pasynkov D.V. The value of computer aided detection system for mammography in the breast cancer screening: single-center, prospective, randomized clinical trial. Questions of Oncology, 2021, Vol. 67, No. 6, pp. 777–784 (In Russ.). doi: 10.37469/0507-3758-2021-67-6-777-784.

12. Pasynkov D.V., Egoshin I.A., Kolchev A.A., Romanycheva E.A., Klyushkin I.V., Pasynkova O.O. Detection and classification of microcalcification clusters on mammographic images. Medical Engineering, 2024, No. 1, pp. 29–32 (In Russ.).

13. Chaudhury S., Rakhra M., Memon N., Sau K., Ayana M.T. Breast Cancer Calcifications: Identification Using a Novel Segmentation Approach // Comput. Math Methods Med. 2021. Vol. 2021, P. 9905808. doi: 10.1155/2021/9905808.

14. Guirguis M.S., Adrada B., Santiago L., Candelaria R., Arribas E. Mimickers of breast malignancy: imaging findings, pathologic concordance and clinical management // Insights Imaging. 2021. Vol. 12, No. 1, p. 53. doi: 10.1186/s13244-021-00991-x.

15. Oliveira E.L., Freitas-Junior R., Afiune-Neto A., Murta E.F., Ferro J.E., Melo A.F. Vascular calcifications seen on mammography: an independent factor indicating coronary artery disease // Clinics (Sao Paulo). 2009. Vol. 64, No. 8. Р. 763–767. doi: 10.1590/S1807-59322009000800009.

16. Loizidou K., Skouroumouni G., Nikolaou C., Pitris C. An Automated Breast Micro-Calcification Detection and Classification Technique Using Temporal Subtraction of Mammograms // IEEE Access. 2020. Vol. 8. Р. 52785–52795. doi: 10.1109/ACCESS.2020.2980616.

17. Gowri V., Valluvan K.R., Chamundeeswari V.V. Automated Detection and Classification of Microcalcification Clusters with Enhanced Preprocessing and Fractal Analysis // Asian Pac. J. Cancer Prev. 2018. Vol. 19, No. 11. Р. 3093–3098. doi: 10.31557/APJCP.2018.19.11.3093.

18. Brahimetaj R., Willekens I., Massart A., Forsyth R., Cornelis J., De Mey J., Jansen B. Improved automated early detection of breast cancer based on high resolution 3D micro-CT microcalcification images // BMC Cancer. 2022. Vol. 22, No. 1. Р. 162. doi: 10.1186/s12885-021-09133-4.

19. Veldkamp W.J.H., Karssemeijer N., Otten J.D.M., Hendriks J.H.C.L. Automated classification of clustered microcalcifications into malignant and benign types // Med. Phys. 2000. Vol. 27, No. 11. Р. 2600–2608. doi: 10.1118/1.1318221.

20. Kuznetsov A.A., Klimova N.V. Possibilities of the program for searching for clusters of microcalcifications on digital mammograms to increase the efficiency of diagnosing breast cancer. Bulletin of Surgut State University Medicine, 2022, Vol. 53, No 3, pp. 46–50 (In Russ.). doi: 10.34822/2304-9448-2022-3-46-50.