Automatic Pectoral Muscle Removal and Microcalcification Localization in Digital Mammograms
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: Breast cancer is the most common cancer diagnosed in women, and microcalcification (MCC) clusters act as an early indicator. Thus, the detection of MCCs plays an important role in diagnosing breast cancer. Methods: This paper presents a methodology for mammogram preprocessing and MCC detection. The preprocessing method employs automatic artefact deletion and pectoral muscle removal based on region-growing segmentation and polynomial contour fitting. The MCC detection method uses a convolutional neural network for region-of-interest (ROI) classification, along with morphological operations and wavelet reconstruction to reduce false positives (FPs). Results: The methodology was evaluated using the mini-MIAS and UTP datasets in terms of segmentation accuracy in the preprocessing phase, as well as sensitivity and the mean FP rate per image in the MCC detection phase. With the mini-MIAS dataset, the proposed methods achieved accuracy scores of 99% for breast segmentation and 95% for pectoral segmentation, a sensitivity score of 82% for MCC detection, and an FP rate per image of 3.27. With the UTP dataset, the methods achieved accuracy scores of 97% for breast segmentation and 91% for pectoral segmentation, a sensitivity score of 78% for MCC detection, and an FP rate per image of 0.74. Conclusions: The proposed preprocessing method outperformed the state-of-the-art methods for breast segmentation and achieved relatively good results for pectoral muscle removal. Furthermore, the MCC detection module achieved the highest test accuracy in identifying potential ROIs with MCCs compared to other methods.
Abstract
Objectives: Breast cancer is the most common cancer diagnosed in women, and microcalcification (MCC) clusters act as an early indicator. Thus, the detection of MCCs plays an important role in diagnosing breast cancer. Methods: This paper presents a methodology for mammogram preprocessing and MCC detection. The preprocessing method employs automatic artefact deletion and pectoral muscle removal based on region-growing segmentation and polynomial contour fitting. The MCC detection method uses a convolutional neural network for region-of-interest (ROI) classification, along with morphological operations and wavelet reconstruction to reduce false positives (FPs). Results: The methodology was evaluated using the mini-MIAS and UTP datasets in terms of segmentation accuracy in the preprocessing phase, as well as sensitivity and the mean FP rate per image in the MCC detection phase. With the mini-MIAS dataset, the proposed methods achieved accuracy scores of 99% for breast segmentation and 95% for pectoral segmentation, a sensitivity score of 82% for MCC detection, and an FP rate per image of 3.27. With the UTP dataset, the methods achieved accuracy scores of 97% for breast segmentation and 91% for pectoral segmentation, a sensitivity score of 78% for MCC detection, and an FP rate per image of 0.74. Conclusions: The proposed preprocessing method outperformed the state-of-the-art methods for breast segmentation and achieved relatively good results for pectoral muscle removal. Furthermore, the MCC detection module achieved the highest test accuracy in identifying potential ROIs with MCCs compared to other methods.
참고문헌 (29)
- Kwan ML, "Epidemiology of breast cancer subtypes in two prospective cohort studies of breast cancer survivors", Breast Cancer Res, 11(3), pp.R31~ (2009)
- Raba D, "Iberian conference on pattern recognition and image analysis", pp.471~478 (2005), Springer
- Linguraru MG, "A biologically inspired algorithm for microcalcification cluster detection", Med Image Anal, 10(6), pp.850~862 (2006)
- Elshinawy MY, "Pre-CAD system for normal mammogram detection using local binary pattern features", Proceedings of 2010 IEEE 23rd international Symposium on Computer-Based Medical Systems(CBMS), pp.352~357 (2010)
- Karale VA, "A screening CAD tool for the detection of microcalcification clusters in mammograms", J Digit Imaging, 32(5), pp.728~745 (2019)
- Giger ML, "Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer", Annu Rev Biomed Eng, 15, pp.327~357 (2013)
- Moghbel M, "A review of breast boundary and pectoral muscle segmentation methods in computer-aided detection", diagnosis of breast mammography, 2020, pp.53(3), 1873~1918
- Ancy CA, "Intelligent engineering informatics", pp.197~208 (2018), Springer
- Rahimeto S, "Automatic pectoral muscle removal in mammograms", Evol Syst, 12, pp.519~526 (2019)
- Karale VA, "Reduction of false positives in the screening CAD tool for microcalcification detection", Sadhana, 45, pp.44~ (2020)
- Chan HP, "Computerized analysis of mam mographic microcalcifications in morphological and texture feature spaces", Med Phys, 25(10), pp.2007~2019 (1998)
- Leichter I, "Optimizing parameters for computeraided diagnosis of microcalcifications at mammography", Acad Radiol, 7(6), pp.406~412 (2000)
- Tsujii O, "Classification of microcalcifications in digital mammograms using trendoriented radial basis function neural network", Pattern Recognit, 32(5), pp.891~903 (1999)
- Betal D, "Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology", Br J Radiol, 70(837), pp.903~917 (1997)
- Paquerault S, "Radial gradient-based segmentation of mammographic microcalcifications : observer evaluation and effect on CAD performance", Med Phys, 31(9), pp.2648~2657 (2004)
- Kim JK, "Statistical textural features for detection of microcalcifications in digitized mammograms", IEEE Trans Med Imaging, 18(3), pp.231~238 (1999)
- Soltanian-Zadeh H, "Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms", Pattern Recognit, 37(10), pp.1973~1986 (2004)
- Qayyum A, "Automatic breast segmentation and cancer detection via SVM in mammograms", Proceedings of 2016 International Conference on Emerging Technologies (ICET), pp.1~6 (2016)
- Slavkovic-Ilic M, "Breast region segmentation and pectoral muscle removal in mammograms", Telfor J, 8(1), pp.50~55 (2016)
- Yoon WB, "Automatic detection of pectoral muscle region for computer-aided diagnosis using MIAS mammograms", Biomed Res Int, 2016, pp.5967580~ (2016)
- Camilus KS, "Computeraided identification of the pectoral muscle in digitized mammograms", J Digit Imaging, 23(5), pp.562~580 (2010)
- Abdellatif H, "K2. Automatic pectoral muscle boundary detection in mammograms using eigenvectors segmentation", Proceedings of 2012 29th National Radio Science Conference (NRSC), pp.633~640 (2012)
- Shinde V, "Cognitive informatics and soft computing", pp.227~237 (2019), Springer
- El-Naqa I, "A support vector machine approach for detection of microcalcifications", IEEE Trans Med Imaging, 21(12), pp.1552~1563 (2002)
- Liu X, "Microcalcification detection in full-field digital mammograms with PFCM clustering and weighted SVM-based method", EURASIP J Adv Signal Process, 2015, pp.73~ (2015)
- Wang J, "Global detection approach for clustered microcalcifications in mammograms using a deep learning network", J Med Imaging(Bellingham), 4(2), pp.024501~ (2017)
- Wang J, "A context-sensitive deep learning approach for microcalcification detection in mammograms", Pattern Recognit, 78, pp.12~22 (2018)
- Alam N, "Medical image understanding and analysis", pp.251~261 (2018), Springer
- McCann J, "Impact of false-positive mammography on subsequent screening attendance and risk of cancer", Breast Cancer Res, 4(5), pp.R11~ (2002)