Skip to main content
NCBI home page
Journal of Digital Imaging logoLink to Journal of Digital Imaging
. 1998 Aug;11(3):101–115. doi: 10.1007/BF03168733

A breast density index for digital mammograms based on radiologists’ randing

John M Boone 1,✉, Karen K Lindfors 1, Carol S Beatty 1, J Anthony Seibert 1
PMCID: PMC3453202  PMID: 9718500

Abstract

The purpose of this study was to develop and evaluate a computerized method of calculating a breast density index (BDI) from digitized mammograms that was designed specifically to model radiologists’ perception of breast density. A set of 153 pairs of digitized mammograms (cranio-caudal, CC, and mediolateral oblique, MLO, views) were acquired and preprocessed to reduce detector biases. The sets of mammograms were ordered on an ordinal scale (a scale based only on relative rank-ordering) by two radiologists, and a cardinal (an absolute numerical score) BDI value was calculated from the oridinal ranks. The images were also assigned cardinal BDI values by the radiologists in a subsequent session. Six. mathematical features (including fractal dimension and others) were calculated from the digital mammograms, and were used in conjunction with single value decomposition and multiple linear regression to calculate a computerized BDI. The linear correlation coefficient between different ordinal ranking sessions were as follows: intraradiologist intraprojection (CC/CC):r=0.978; intraradiologist interprojection (CC/MLO):r=0.960; and interradiologist intraprojection (CC/CC):r=0.968. A separate breast density index was derived from three separate ordinal rankings by one radiologist (two with CC views, one with the MLO view). The computer derivedBDI had a correlation coefficient (r) of 0.907 with the radiologists’ ordinalBDI. A comparison between radiologists using a cardinal scoring system (which is closest to how radiologists actually evaluate breast density) showedr=0.914. A breast density index calculated by a computer but modeled after radiologist perception of breast density may be valuable in objectively measuring breast density. Such a metric may prove valuable in numerous areas, including breast cancer risk assessment and in evaluating screening techniques specifically designed to improve imaging of the dense breast.

Key words: breast cancer, mammography, breast density, digital mammography, computer aided diagnosis

Full Text

The Full Text of this article is available as a PDF (2.3 MB).

Footnotes

Research funded in part by the Breast Cancer Research Program for the United States Army (Grant DAMDI 17-94-J-4424) and the California Breast Cancer Research Program (Grant 1RB-0192).

References

  • 1.Wolfe JN. Breast patterns as an index of risk for developing breast cancer. AJR Am J Roentgenol. 1976;126:1130–1137. doi: 10.2214/ajr.126.6.1130. [DOI] [PubMed] [Google Scholar]
  • 2.Wolfe JN. Risk for breast cancer development determined by mammographic parenchymal pattern. Cancer. 1976;37:2486–2492. doi: 10.1002/1097-0142(197605)37:5<2486::AID-CNCR2820370542>3.0.CO;2-8. [DOI] [PubMed] [Google Scholar]
  • 3.Boyd NF, Byng JW, Jong RA, et al. Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening Study. J Natl Cancer Inst. 1995;87:670–675. doi: 10.1093/jnci/87.9.670. [DOI] [PubMed] [Google Scholar]
  • 4.Feig SA, Yaffe MJ. Digital mammography, computeraided diagnosis, and telemammography. Radiol Clin North Am. 1995;33:1205–1230. [PubMed] [Google Scholar]
  • 5.Yaffe MJ. Direct digital mammography using a scanned-slot CCD imaging system. Med Prog Technol. 1993;19:13–21. [PubMed] [Google Scholar]
  • 6.Feig SA. The role of ultrasound in a breast imaging center. Semin Ultrasound CT MR. 1989;10:90–105. [PubMed] [Google Scholar]
  • 7.Guyer PB, Dewbury KC. Ultrasound of the breast in the symptomatic and X-ray dense breast. Clin Radiol. 1985;36:69–76. doi: 10.1016/S0009-9260(85)80028-3. [DOI] [PubMed] [Google Scholar]
  • 8.Graham SJ, Bronskill MJ, Byng JW, et al. Quantitative correlation of breast tissue parameters using magnetic resonance and X-ray mammography. Br J Cancer. 1996;73:162–168. doi: 10.1038/bjc.1996.30. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 9.Dash N, Lupetin AR, Daffner RH, et al. Magnetic resonance imaging in the diagnosis of breast disease. AJR Am J Roentgenol. 1986;146:119–125. doi: 10.2214/ajr.146.1.119. [DOI] [PubMed] [Google Scholar]
  • 10.Turner DA, Alcorn FS, Adler YT. Nuclear magnetic resonance in the diagnosis of breast cancer. Radiol Clin North Am. 1988;26:673–687. [PubMed] [Google Scholar]
  • 11.Jansson T, Westlin JE, Ahlstrom H, et al. Positron emission tomography studies in patients with locally advanced and/or metastatic breast cancer: A method for early therapy evaluation? J Clin Oncol. 1995;13:1470–1477. doi: 10.1200/JCO.1995.13.6.1470. [DOI] [PubMed] [Google Scholar]
  • 12.Wahl RL, Zasadny K, Helvie M, et al. Metabolic monitoring of breast cancer chemohormonotherapy using positron emission tomography: Initial evaluation. J Clin Oncol. 1993;11:2101–2111. doi: 10.1200/JCO.1993.11.11.2101. [DOI] [PubMed] [Google Scholar]
  • 13.Rambaldi PF, Mansi L, Procaccini E, et al. Breast cancer detection with Tc-99m tetrofosmin. Clin Nucl Med. 1995;20:703–705. doi: 10.1097/00003072-199508000-00009. [DOI] [PubMed] [Google Scholar]
  • 14.Takahashi T, Moriya E, Miyamoto Y, et al. The usefulness of 201T1C1 scintigraphy for the diagnosis of breast tumor. Nippon Igaku Hoshasen Gakkai Zasshi. 1994;54:644–649. [PubMed] [Google Scholar]
  • 15.Wolfe JN. Developments in mammography. Am J Obstet Gynecol. 1976;124:312–323. doi: 10.1016/0002-9378(76)90164-2. [DOI] [PubMed] [Google Scholar]
  • 16.Wolfe JN, Albert S, Belle S, et al. Breast parenchymal patterns: Analysis of 332 incident breast carcinomas. AJR Am J Roentgenol. 1982;138:113–118. doi: 10.2214/ajr.138.1.113. [DOI] [PubMed] [Google Scholar]
  • 17.Wolfe JN, Albert S, Belle S, et al. Breast parenchymal patterns and their relationship to risk for having or developing carcinoma. Radiol Clin North Am. 1983;21:127–136. [PubMed] [Google Scholar]
  • 18.Wolfe JN, Saftlas AF, Salane M. Mammographic parenchymal patterns and quantitative evaluation of mammographic densities: a case-control study. AJR Am J Roentgenol. 1987;148:1087–1092. doi: 10.2214/ajr.148.6.1087. [DOI] [PubMed] [Google Scholar]
  • 19.Rockette HE, Gur D, Metz CE. The use of continuous and discrete confidence judgments in receiver operating characteristic studies of diagnostic imaging techniques. Invest Radiol. 1992;27:169–172. doi: 10.1097/00004424-199202000-00016. [DOI] [PubMed] [Google Scholar]
  • 20.Press WH, Fannery BP, Teukolsky SA, et al. Numerical Recipes in C: The Art of Scientific Computing. Cambridge: Cambridge University Press; 1988. [Google Scholar]
  • 21.Astion ML, Wilding P. The application of backpropagation neural networks to problems in pathology and laboratory medicine. Arch. Pathol Lab Med. 1992;116:995–1001. [PubMed] [Google Scholar]
  • 22.Gurney JW. Neural networks at the crossroads: Caution ahead. Radiology. 1994;193:27–28. doi: 10.1148/radiology.193.1.8090906. [DOI] [PubMed] [Google Scholar]
  • 23.Wu Y, Giger ML, Doi K, et al. Artificial neural networks in mammography: Application to decision making in the diagnosis of breast cancer. Radiology. 1993;187:81–87. doi: 10.1148/radiology.187.1.8451441. [DOI] [PubMed] [Google Scholar]
  • 24.Floyd CE, Tourassi GD. An artificial neural network for lesion detection on single-photon emission computed tomographic images. Invest Radiol. 1992;27:667–672. doi: 10.1097/00004424-199209000-00001. [DOI] [PubMed] [Google Scholar]
  • 25.Asada N, Doi K, MacMahon H, et al. Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung diseases: Pilot study. Radiology. 1990;177:857–860. doi: 10.1148/radiology.177.3.2244001. [DOI] [PubMed] [Google Scholar]
  • 26.Tourassi GD, Floyd CE, Sostman HD, et al. Artificial neural network for diagnosis of acute pulmonary embolism: Effect of case and observer selection. Radiology. 1995;194:889–893. doi: 10.1148/radiology.194.3.7862997. [DOI] [PubMed] [Google Scholar]
  • 27.Morin RL. Monte Carlo Simulation in the Radiological Sciences. Boca Raton, FL: CRC Press; 1988. [Google Scholar]
  • 28.Caldwell CB, Stapleton SJ, Holdsworth DW, et al. Characterisation of mammographic parenchymal pattern by fractal dimension. Phys Med Biol. 1990;35:235–247. doi: 10.1088/0031-9155/35/2/004. [DOI] [PubMed] [Google Scholar]
  • 29.Dorfman DD, Berbaum KS, Metz CE. Receiver operating characteristic rating analysis. Generalization to the population of readers and patients with the jackknife method. Invest Radiol. 1992;27:723–731. doi: 10.1097/00004424-199209000-00015. [DOI] [PubMed] [Google Scholar]
  • 30.Boone JM. Neural networks at the crossroad. Radiology. 1993;189:357–359. doi: 10.1148/radiology.189.2.8210359. [DOI] [PubMed] [Google Scholar]
  • 31.Boone JM. Sidetracked at the crossroads. Radiology. 1994;193:28–30. doi: 10.1148/radiology.193.1.8090909. [DOI] [PubMed] [Google Scholar]
  • 32.Glantz SA. Primer of Biostatistics. 3rd ed. New York, NY: McGraw Hill; 1992. [Google Scholar]
  • 33.Lee-Han H, Cooke G, Boyd NF. Quantitative evaluation of mammographic densities: A comparison of methods of assessment. Eur J Cancer Prev. 1995;4:285–292. doi: 10.1097/00008469-199508000-00003. [DOI] [PubMed] [Google Scholar]
  • 34.Saftlas AF, Hoover RN, Brinton LA, et al. Mammographic densities and risk of breast cancer. Cancer. 1991;67:2833–2838. doi: 10.1002/1097-0142(19910601)67:11<2833::AID-CNCR2820671121>3.0.CO;2-U. [DOI] [PubMed] [Google Scholar]
  • 35.Taylor P, Hajnal S, Dilhuydy MH, et al. Measuring image texture to separate “difficult” from “easy” mammograms. Br J Radiol. 1994;67:456–463. doi: 10.1259/0007-1285-67-797-456. [DOI] [PubMed] [Google Scholar]
  • 36.Greulich WW, Pyle SI. Radiographic atlas of the skeletal development of the hand and wrist. 2nd ed. Stanford, CA: Stanford University Press; 1959. [Google Scholar]
  • 37.Wolfe JN. Risk of develping breast cancer determined by mammography. Prog Clin Biol Res. 1977;12:223–238. [PubMed] [Google Scholar]
  • 38.Boyd NF, Jensen HM, Cooke G, et al. Relationship between mammographic and histological risk factors for breast cancer. J Natl Cancer Inst. 1992;84:1170–1179. doi: 10.1093/jnci/84.15.1170. [DOI] [PubMed] [Google Scholar]
  • 39.Byrne C, Schairer C, Wolfe J, et al. Mammographic features and breast cancer risk: Effects with time, age, and menopause status. J Natl Cancer Inst. 1995;87:1622–1629. doi: 10.1093/jnci/87.21.1622. [DOI] [PubMed] [Google Scholar]
  • 40.Ciatto S, Zappa M. A prospective study of the value of mammographic patterns as indicators of breast cancer risk in a screening experience. Eur J Radiol. 1993;17:122–125. doi: 10.1016/0720-048X(93)90048-R. [DOI] [PubMed] [Google Scholar]
  • 41.Beisang AA, Geise RA, Ersek RA. Radiolucent prosthetic gel. Plast Reconstr Surg. 1991;87:885–892. doi: 10.1097/00006534-199105000-00013. [DOI] [PubMed] [Google Scholar]
  • 42.Kato I, Beinart C, Bleich A., et al. A nested case-control study of mammographic patterns, breast volume. Cancer Causes and Control. 1995;6:431–438. doi: 10.1007/BF00052183. [DOI] [PubMed] [Google Scholar]
  • 43.Brisson J, Morrison AS, Khalid N. Mammographic parenchymal features and breast cancer in the breast cancer detection demonstration project. J Natl Cancer Inst. 1988;80:1534–1540. doi: 10.1093/jnci/80.19.1534. [DOI] [PubMed] [Google Scholar]
  • 44.Saftlas AF, Wolfe JN, Hoover RN, et al. Mammographic parenchymal patterns as indicators of breast cancer risk. Am J Epidemiol. 1989;129:518–526. doi: 10.1093/oxfordjournals.aje.a115163. [DOI] [PubMed] [Google Scholar]
  • 45.Vogel VG. High-risk populations as targets for breast cancer prevention trials. Prev Med. 1991;20:86–100. doi: 10.1016/0091-7435(91)90009-S. [DOI] [PubMed] [Google Scholar]
  • 46.Feig SA. Breast masses. Mammographic and sonographic evaluation. Radiol Clin North Am. 1992;30:67–92. [PubMed] [Google Scholar]
  • 47.Fornage BD, Toubas O, Morel M. Clinical, mammographic, and sonographic determination of preoperative breast cancer size. Cancer. 1987;60:765–771. doi: 10.1002/1097-0142(19870815)60:4<765::AID-CNCR2820600410>3.0.CO;2-5. [DOI] [PubMed] [Google Scholar]
  • 48.Liem SJ. Target ultrasonic mammography. An additional diagnostic tool for the detection of breast cancer. Diagn Imaging Clin Med. 1985;54:192–201. [PubMed] [Google Scholar]
  • 49.Stomper PC, Voorhis BJ, Ravnikar VA, et al. Mammographic changes associated with postmenopausal hormone replacement therapy: A longitudinal study. Radiology. 1990;174:487–490. doi: 10.1148/radiology.174.2.2136958. [DOI] [PubMed] [Google Scholar]
  • 50.Gils CH, Otten JD, Verbeek AL, et al. Short communication: breast parenchymal patterns and their changes with age. Br J Radiol. 1995;68:1133–1135. doi: 10.1259/0007-1285-68-814-1133. [DOI] [PubMed] [Google Scholar]
  • 51.Feig SA. Hormonal reduction of mammographic densities: Potential effects on breast cancer risk and performance of diagnostic and screening mammography. J Natl Cancer Inst. 1994;86:408–409. doi: 10.1093/jnci/86.6.408. [DOI] [PubMed] [Google Scholar]
  • 52.Flook D, Gilhome RW, Harman J, et al. Changes in Wolfe mammographic patterns with aging. Br J Radiol. 1987;60:455–456. doi: 10.1259/0007-1285-60-713-455. [DOI] [PubMed] [Google Scholar]

Articles from Journal of Digital Imaging are provided here courtesy of Springer

RESOURCES