Evaluation of Breast Cancer Size Measurement by Computer-Aided Diagnosis (CAD) and a Radiologist on Breast MRI

Overview

Journal J Clin Med

Specialty General Medicine

Date 2022 Mar 10

PMID 35268263

Authors

Ji Yeon Park

Affiliations

Soon will be listed here.

Abstract

Purpose: This study aimed to evaluate cancer size measurement by computer-aided diagnosis (CAD) and radiologist on breast magnetic resonance imaging (MRI) relative to histopathology and to determine clinicopathologic and MRI factors that may affect measurements. Methods: Preoperative MRI of 208 breast cancers taken between January 2017 and March 2021 were included. We evaluated correlation between CAD-generated size and pathologic size as well as that between radiologist-measured size and pathologic size. We classified size discrepancies into accurate and inaccurate groups. For both CAD and radiologist, clinicopathologic and imaging factors were compared between accurate and inaccurate groups. Results: The mean sizes as predicted by CAD, radiologist and pathology were 2.66 ± 1.68 cm, 2.54 ± 1.68 cm, and 2.30 ± 1.61 cm, with significant difference (p < 0.001). Correlation coefficients of cancer size measurement by radiologist and CAD in reference to pathology were 0.898 and 0.823. Radiologist’s measurement was more accurate than CAD, with statistical significance (p < 0.001). CAD-generated measurement was significantly more inaccurate for cancers of larger pathologic size (>2 cm), in the presence of an extensive intraductal component (EIC), with positive progesterone receptor (PR), and of non-mass enhancement (p = 0.045, 0.045, 0.03 and 0.002). Radiologist-measured size was significantly more inaccurate for cancers in presence of an in situ component, EIC, positive human epidermal growth factor receptor 2 (HER2), and non-mass enhancement (p = 0.017, 0.008, 0.003 and <0.001). Conclusion: Breast cancer size measurement showed a very strong correlation between CAD and pathology and radiologist and pathology. Radiologist-measured size was significantly more accurate than CAD size. Cancer size measurement by CAD and radiologist can both be inaccurate for cancers with EIC or non-mass enhancement.

Citing Articles

Deep learning-based automatic segmentation for size and volumetric measurement of breast cancer on magnetic resonance imaging.

Yue W, Zhang H, Zhou J, Li G, Tang Z, Sun Z Front Oncol. 2022; 12:984626.

PMID: 36033453 PMC: 9404224. DOI: 10.3389/fonc.2022.984626.

References

DeMartini W, Liu F, Peacock S, Eby P, Gutierrez R, Lehman C . Background parenchymal enhancement on breast MRI: impact on diagnostic performance. AJR Am J Roentgenol. 2012; 198(4):W373-80. DOI: 10.2214/AJR.10.6272. View

Lai H, Chen D, Wu Y, Chen C, Lee C, Kuo S . Comparison of the Diagnostic Accuracy of Magnetic Resonance Imaging with Sonography in the Prediction of Breast Cancer Tumor Size: A Concordance Analysis with Histopathologically Determined Tumor Size. Ann Surg Oncol. 2015; 22(12):3816-23. DOI: 10.1245/s10434-015-4424-4. View

Rastelli F, Crispino S . Factors predictive of response to hormone therapy in breast cancer. Tumori. 2008; 94(3):370-83. DOI: 10.1177/030089160809400314. View

Meeuwis C, van de Ven S, Stapper G, Fernandez Gallardo A, van den Bosch M, Mali W . Computer-aided detection (CAD) for breast MRI: evaluation of efficacy at 3.0 T. Eur Radiol. 2009; 20(3):522-8. PMC: 2822230. DOI: 10.1007/s00330-009-1573-5. View

Leddy R, Irshad A, Metcalfe A, Mabalam P, Abid A, Ackerman S . Comparative accuracy of preoperative tumor size assessment on mammography, sonography, and MRI: Is the accuracy affected by breast density or cancer subtype?. J Clin Ultrasound. 2015; 44(1):17-25. DOI: 10.1002/jcu.22290. View

Fisher B, Anderson S, Bryant J, Margolese R, Deutsch M, Fisher E . Twenty-year follow-up of a randomized trial comparing total mastectomy, lumpectomy, and lumpectomy plus irradiation for the treatment of invasive breast cancer. N Engl J Med. 2002; 347(16):1233-41. DOI: 10.1056/NEJMoa022152. View

Blackwell K, Dewhirst M, Liotcheva V, Snyder S, Broadwater G, Bentley R . HER-2 gene amplification correlates with higher levels of angiogenesis and lower levels of hypoxia in primary breast tumors. Clin Cancer Res. 2004; 10(12 Pt 1):4083-8. DOI: 10.1158/1078-0432.CCR-03-0695. View

Goldhirsch A, Wood W, Coates A, Gelber R, Thurlimann B, Senn H . Strategies for subtypes--dealing with the diversity of breast cancer: highlights of the St. Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2011. Ann Oncol. 2011; 22(8):1736-47. PMC: 3144634. DOI: 10.1093/annonc/mdr304. View

Sanderink W, Caballo M, Strobbe L, Bult P, Vreuls W, Venderink D . Reliability of MRI tumor size measurements for minimal invasive treatment selection in small breast cancers. Eur J Surg Oncol. 2020; 46(8):1463-1470. DOI: 10.1016/j.ejso.2020.04.038. View

10.

Kumar A, Chen D, Au A, Chen Y, Leung J, Garwood E . Biologic significance of false-positive magnetic resonance imaging enhancement in the setting of ductal carcinoma in situ. Am J Surg. 2006; 192(4):520-4. PMC: 4087109. DOI: 10.1016/j.amjsurg.2006.07.003. View

11.

Allen L, Lago-Toro C, Hughes J, Careaga E, Brown A, Chernick M . Is there a role for MRI in the preoperative assessment of patients with DCIS?. Ann Surg Oncol. 2010; 17(9):2395-400. DOI: 10.1245/s10434-010-1000-9. View

12.

Kim D, Moon W, Cho N, Ko E, Yang S, Park J . MRI of the breast for the detection and assessment of the size of ductal carcinoma in situ. Korean J Radiol. 2007; 8(1):32-9. PMC: 2626696. DOI: 10.3348/kjr.2007.8.1.32. View

13.

Gilles R, Zafrani B, Guinebretiere J, Meunier M, Lucidarme O, Tardivon A . Ductal carcinoma in situ: MR imaging-histopathologic correlation. Radiology. 1995; 196(2):415-9. DOI: 10.1148/radiology.196.2.7617854. View

14.

Marcotte-Bloch C, Balu-Maestro C, Chamorey E, Ettore F, Raoust I, Flipo B . MRI for the size assessment of pure ductal carcinoma in situ (DCIS): a prospective study of 33 patients. Eur J Radiol. 2009; 77(3):462-7. DOI: 10.1016/j.ejrad.2009.09.003. View

15.

Beresford M, Padhani A, Taylor N, Ah-See M, Stirling J, Makris A . Inter- and intraobserver variability in the evaluation of dynamic breast cancer MRI. J Magn Reson Imaging. 2006; 24(6):1316-25. DOI: 10.1002/jmri.20768. View

16.

Yoo E, Nam S, Choi H, Hong M . Agreement between MRI and pathologic analyses for determination of tumor size and correlation with immunohistochemical factors of invasive breast carcinoma. Acta Radiol. 2017; 59(1):50-57. DOI: 10.1177/0284185117705010. View

17.

Fernandez-Morales L, Segui M, Andreu X, Dalmau E, Saez A, Pericay C . Analysis of the pathologic response to primary chemotherapy in patients with locally advanced breast cancer grouped according to estrogen receptor, progesterone receptor, and HER2 status. Clin Breast Cancer. 2007; 7(7):559-64. DOI: 10.3816/CBC.2007.n.012. View

18.

Kyndi M, Sorensen F, Knudsen H, Overgaard M, Nielsen H, Overgaard J . Estrogen receptor, progesterone receptor, HER-2, and response to postmastectomy radiotherapy in high-risk breast cancer: the Danish Breast Cancer Cooperative Group. J Clin Oncol. 2008; 26(9):1419-26. DOI: 10.1200/JCO.2007.14.5565. View

19.

Schouten van der Velden A, Boetes C, Bult P, Wobbes T . Magnetic resonance imaging in size assessment of invasive breast carcinoma with an extensive intraductal component. BMC Med Imaging. 2009; 9:5. PMC: 2674416. DOI: 10.1186/1471-2342-9-5. View

20.

Ikeda O, Nishimura R, Miyayama H, Yasunaga T, Ozaki Y, Tsuji A . Magnetic resonance evaluation of the presence of an extensive intraductal component in breast cancer. Acta Radiol. 2004; 45(7):721-5. DOI: 10.1080/02841850410001349. View