Estimating the Accuracy Level Among Individual Detections in Clustered Microcalcifications

Overview

Journal IEEE Trans Med Imaging

Date 2017 Jan 20

PMID 28103550

Citations 2

Authors

Maria V Sainz de Cea

Robert M Nishikawa

Yongyi Yang

Affiliations

Soon will be listed here.

Abstract

Computerized detection of clustered microcalcifications (MCs) in mammograms often suffers from the occurrence of false positives (FPs), which can vary greatly from case to case. We investigate how to apply statistical estimation to determine the number of FPs that are present in a detected MC lesion. First, we describe the number of true positives (TPs) by a Poisson-binomial probability distribution, wherein a logistic regression model is trained to determine the probability for an individual detected MC to be a TP based on its detector output. Afterward, we model the spatial occurrence of FPs in a lesion area by a spatial point process (SPP), of which the distribution parameters are estimated from the detections in the lesion and its surrounding region. Furthermore, to improve the estimation accuracy, we incorporate the Poisson-binomial distribution of the number of TPs into the SPP model using maximum a posteriori estimation. In the experiments, we demonstrated the proposed approach on the detection results from a set of 188 full-field digital mammography (FFDM) images (95 cases) by three existing MC detectors. The results showed that there was a strong consistency between the estimated and the actual number of TPs (or FPs) for these detectors. When the fraction of FPs in detection was varied from 20% to 50%, both the mean and median values of the estimation error were within 11% of the total number of detected MCs in a lesion. In particular, when the number of FPs increased to as high as 11.38 in a cluster on average, the error was 2.51 in the estimated number of FPs. In addition, lesions estimated to be more accurate in detection were shown to have better classification accuracy (for being malignant or benign) than those estimated to be less accurate.

Citing Articles

A context-sensitive deep learning approach for microcalcification detection in mammograms.

Wang J, Yang Y Pattern Recognit. 2018; 78:12-22.

PMID: 30467443 PMC: 6242284. DOI: 10.1016/j.patcog.2018.01.009.

Locally adaptive decision in detection of clustered microcalcifications in mammograms.

Sainz de Cea M, Nishikawa R, Yang Y Phys Med Biol. 2018; 63(4):045014.

PMID: 29364138 PMC: 5987532. DOI: 10.1088/1361-6560/aaaa4c.

References

Wei L, Yang Y, Nishikawa R, Jiang Y . A study on several machine-learning methods for classification of malignant and benign clustered microcalcifications. IEEE Trans Med Imaging. 2005; 24(3):371-80. DOI: 10.1109/tmi.2004.842457. View

Kallergi M . Computer-aided diagnosis of mammographic microcalcification clusters. Med Phys. 2004; 31(2):314-26. DOI: 10.1118/1.1637972. View

Cheng H, Lui Y, Freimanis R . A novel approach to microcalcification detection using fuzzy logic technique. IEEE Trans Med Imaging. 1998; 17(3):442-50. DOI: 10.1109/42.712133. View

Morrow W, Paranjape R, Rangayyan R, Desautels J . Region-based contrast enhancement of mammograms. IEEE Trans Med Imaging. 1992; 11(3):392-406. DOI: 10.1109/42.158944. View

Wang J, Nishikawa R, Yang Y . Improving the accuracy in detection of clustered microcalcifications with a context-sensitive classification model. Med Phys. 2016; 43(1):159. PMC: 4691250. DOI: 10.1118/1.4938059. View

Maslov A, Barone T, Plunkett R, Pruitt S . Neural stem cell detection, characterization, and age-related changes in the subventricular zone of mice. J Neurosci. 2004; 24(7):1726-33. PMC: 6730468. DOI: 10.1523/JNEUROSCI.4608-03.2004. View

Dhawan A, Buelloni G, Gordon R . Enhancement of mammographic features by optimal adaptive neighborhood image processing. IEEE Trans Med Imaging. 1986; 5(1):8-15. DOI: 10.1109/TMI.1986.4307733. View

Fondrinier E, Lorimier G, Mayras C, Dauver N . Breast microcalcifications: multivariate analysis of radiologic and clinical factors for carcinoma. World J Surg. 2002; 26(3):290-6. DOI: 10.1007/s00268-001-0220-3. View

Kettritz U, Morack G, Decker T . Stereotactic vacuum-assisted breast biopsies in 500 women with microcalcifications: radiological and pathological correlations. Eur J Radiol. 2005; 55(2):270-6. DOI: 10.1016/j.ejrad.2004.10.014. View

10.

Shitong W, Min W . A new detection algorithm (NDA) based on fuzzy cellular neural networks for white blood cell detection. IEEE Trans Inf Technol Biomed. 2006; 10(1):5-10. DOI: 10.1109/titb.2005.855545. View

11.

Chan H, Lo S, Sahiner B, Lam K, Helvie M . Computer-aided detection of mammographic microcalcifications: pattern recognition with an artificial neural network. Med Phys. 1995; 22(10):1555-67. DOI: 10.1118/1.597428. View

12.

Nishikawa R, Giger M, Doi K, Vyborny C, Schmidt R . Computer-aided detection of clustered microcalcifications on digital mammograms. Med Biol Eng Comput. 1995; 33(2):174-8. DOI: 10.1007/BF02523037. View

13.

Dengler J, Behrens S, Desaga J . Segmentation of microcalcifications in mammograms. IEEE Trans Med Imaging. 1993; 12(4):634-42. DOI: 10.1109/42.251111. View

14.

El-Naqa I, Yang Y, Wernick M, Galatsanos N, Nishikawa R . A support vector machine approach for detection of microcalcifications. IEEE Trans Med Imaging. 2003; 21(12):1552-63. DOI: 10.1109/TMI.2002.806569. View

15.

Freer T, Ulissey M . Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. Radiology. 2001; 220(3):781-6. DOI: 10.1148/radiol.2203001282. View

16.

DeSantis C, Fedewa S, Sauer A, Kramer J, Smith R, Jemal A . Breast cancer statistics, 2015: Convergence of incidence rates between black and white women. CA Cancer J Clin. 2015; 66(1):31-42. DOI: 10.3322/caac.21320. View

17.

Nakayama R, Uchiyama Y, Watanabe R, Katsuragawa S, Namba K, Doi K . Computer-aided diagnosis scheme for histological classification of clustered microcalcifications on magnification mammograms. Med Phys. 2004; 31(4):789-99. DOI: 10.1118/1.1655711. View

18.

Gur D, Sumkin J, Rockette H, Ganott M, Hakim C, Hardesty L . Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system. J Natl Cancer Inst. 2004; 96(3):185-90. DOI: 10.1093/jnci/djh067. View

19.

Bleyer A, Welch H . Effect of three decades of screening mammography on breast-cancer incidence. N Engl J Med. 2012; 367(21):1998-2005. DOI: 10.1056/NEJMoa1206809. View

20.

Karamouzis M, Likaki-Karatza E, Ravazoula P, Badra F, Koukouras D, Tzorakoleftherakis E . Non-palpable breast carcinomas: correlation of mammographically detected malignant-appearing microcalcifications and molecular prognostic factors. Int J Cancer. 2002; 102(1):86-90. DOI: 10.1002/ijc.10654. View