Detection of microcalcification in digitized mammograms with multistable cellular neural networks using a new image enhancement method: automated lesion intensity enhancer (ALIE)

Microcalcification detection is a very important issue in early diagnosis of breast cancer. Generally physicians use mammogram images for this task; however, sometimes analyzing these images become a hard task because of problems in images such as high brightness values, dense tissues, noise, and insufficient contrast level. In this paper, we present a novel technique for the task of microcalcification detection. This technique consists of three steps. The first step is focused on removing pectoral muscle and unnecessary parts from the mammogram images by using cellular neural networks (CNNs), which makes this a novel process. In the second step, we present a novel image enhancement technique focused on enhancing lesion intensities called the automated lesion intensity enhancer (ALIE). In the third step, we use a special CNN structure, named multistable CNNs. After applying the combination of these methods on the MIAS database, we achieve 82.0% accuracy, 90.9% sensitivity, and 52.2% specificity values.

Detection of microcalcification in digitized mammograms with multistable cellular neural networks using a new image enhancement method: automated lesion intensity enhancer (ALIE)

Microcalcification detection is a very important issue in early diagnosis of breast cancer. Generally physicians use mammogram images for this task; however, sometimes analyzing these images become a hard task because of problems in images such as high brightness values, dense tissues, noise, and insufficient contrast level. In this paper, we present a novel technique for the task of microcalcification detection. This technique consists of three steps. The first step is focused on removing pectoral muscle and unnecessary parts from the mammogram images by using cellular neural networks (CNNs), which makes this a novel process. In the second step, we present a novel image enhancement technique focused on enhancing lesion intensities called the automated lesion intensity enhancer (ALIE). In the third step, we use a special CNN structure, named multistable CNNs. After applying the combination of these methods on the MIAS database, we achieve 82.0% accuracy, 90.9% sensitivity, and 52.2% specificity values.

___

  • th
  • Annual International Conference of the IEEE Engineering in Medicine
  • and Biology Society; 1992. New York, NY, USA: IEEE. pp. 1938–1939.
  • Jiang J, Yao B, Wason AM. A genetic algorithm design for microcalcification detection and classification in digital
  • mammograms. Comput Med Imag Grap 2007; 31: 49–61.
  • Wang TC, Karayiannis NB. Detection of microcalcifications in digital mammograms. IEEE T Med Imaging 1998; 17: 498–509.
  • Sajda P, Spence C, Pearson J. Learning contextual relationships in mammograms using a hierarchical pyramid
  • neural network. IEEE T Med Imaging 2002; 21: 239–250.
  • Bazzani A, Bevilacqua A, Bollini D, Brancaccio R, Campanini R, Lanconelli N, Riccardi A, Romani D. A SVM
  • classifier to separate false signals from microcalcifications in digital mammograms. Phys Med Biol 2001; 46: 1651– 1663. Szir´anyi T, Csapodi M. Texture classification and segmentation by cellular neural networks using genetic learning. Comput Vis Image Und 1998; 71: 255–270. Chua LO, Yang L. Cellular neural networks: theory. IEEE T Circuits Syst 1988; 35: 1257–1272.
  • Chua LO, Yang L. Cellular neural networks: application. IEEE T Circuits Syst 1988; 35: 1273–1290.
  • Dogaru R, Murgan AT, Ortmann S, Glesner M. Getting order in chaotic cellular neural networks by self-organization
  • with Hebbian adaptation rules. In: Proceedings of the 1996 Fourth IEEE International Workshop on Cellular Neural Networks and Their Applications; 1996. New York, NY, USA: IEEE. pp. 115–120.
  • Paasio A, Dawidziuk A, Halonen K, Porra V. About the robustness of CNN linear templates with bipolar images.
  • In: 1996 IEEE International Symposium on Circuits and Systems; 1996. New York, NY, USA: IEEE. pp. 555–557.
  • Zarandy A, Roska T, Liszka G, Hegyesi J, Kek L, Rekeczky C. Design of analogic CNN algorithms for mammogram
  • analysis. In: Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and Their Applications; 1994. New York, NY, USA: IEEE. pp. 255–260.
  • Venetianter PL, Roska T. Image compression by cellular neural networks. IEEE T Circuits-I 1998; 45: 205–215.
  • Zanjun L, Derong L. A new synthesis procedure for a class of cellular neural networks with space-invariant cloning template. IEEE T Circuits-II 1998; 45: 1601–1605.
  • Suckling J, Parker J, Dance DR, Astley SM, Hutt I, Boggis CRM, Ricketts I, Stamatakis E, Cerneaz N, Kok SL et al. The mammographic image analysis society digital mammogram database. In: Proceedings of the International Workshop on Digital Mammography; 1994. pp. 211–221.
  • Kawahara M, Inoue T, Nishio Y. Cellular neural network with dynamic template and its output characteristics. In:
  • Proceedings of International Joint Conference on Neural Networks; Atlanta, GA, USA; 2009. pp. 155–1558.
  • Perfetti R, Ricci E, Casali D, Costantini G. Cellular neural networks with virtual template expansion for retinal vessel segmentation. IEEE T Circuits Syst 2007; 54: 141–145.
  • Kozek T, Roska T, Chua LO. Genetic algorithm for CNN template learning. IEEE T Circuits-I 1993; 40: 392–402.
  • Roska T, Chua LO. CNN: Cellular Analog Programmable Multidimensional Processing Array with Distributed Logic and Memory. Rep. DNS-2-1992. Budapest, Hungary: Computer and Automation Institute of the Hungarian Academy of Sciences, 1992.
  • Yokosawa K, Nakaguchi T, Tanji Y, Tanaka M. Cellular neural networks with output function having multiple
  • constant regions. IEEE T Circuits-I 2003; 50: 847–857.
  • Medina Hernandez JA, Castaeda FG, Moreno Cadenas JA. Multistable cellular neural networks and their application to image decomposition. In: 52nd IEEE International Midwest Symposium on Circuits and Systems; 2009. New York, NY, USA: IEEE. pp. 873–876.
  • Quintanilla-Dominguez J, Cortina-Januchs MG, Ojeda-Magana B, Jevtic A, Vega-Corona A, Andina D. Microcal- cification detection applying artificial neural networks and mathematical morphology in digital mammograms. In: Spain World Automation Congress (WAC); 2010. pp. 1–6.
  • Morrow WM, Paranjape RB, Rangayyan RM, Desautels JEL. Region-based contrast enhancement of mammograms.
  • IEEE T Med Imaging 1992; 11: 392–406. Chen ZY, Abidi BR, David L, Abidi MA. Gray-level grouping (GLG): an automatic method for optimized image contrast enhancement - Part II: The variations. IEEE T Image Process 2006; 15: 2303–2314. Panetta KA, Wharton EJ, Agaian SS. Human visual system-based image enhancement and logarithmic contrast measure. IEEE T Syst Man Cy B 2008; 38: 174–188.
  • Smathers RL, Bush E, Drace J, Stevens M, Sommer FG, Brown BW, Kanas B. Mammographic microcalcifications:
  • detection with xerography, screen-film and digitized film display. Radiology 1986; 159: 673–677.
  • Kosheleva O, Arenas J, Aguirre M, Mendoza C, Cabrera SD. Compression degradation metrics for analysis of
  • consistency in microcalcification detection. In: IEEE Southwest Symposium on Image Analysis and Interpretation; 1998. New York, NY, USA: IEEE. pp. 35–40.
  • Thangavel K, Karnan M. Computer aided diagnosis in digital mammograms: detection of microcalcifications by meta-heuristic algorithms. GVIP Journal 2005; 5: 41–55.
  • Masek M, Chandrasekhar R, deSilva CJS, Attikiouzel Y. Spatially based application of the minimum cross-entropy
  • thresholding algorithm to segment the pectoral muscle in mammograms. In: The Seventh Australian and New Zealand Intelligent Information Systems Conference; 2001. pp. 101–106. Kwok SM, Chandrasekhar R, Attikiouzel Y, Rickard MT. Automatic pectoral muscle segmentation on mediolateral oblique view mammograms. IEEE T Med Imaging 2004; 23: 1129–1140.
  • Guzelis C, Karamahmut S. Algorithm for completely stable cellular neural networks. In: Proceedings of the Third IEEE International Workshop on Cellular Neural Network and Applications; Rome, Italy; 1994. pp. 177–182. Vilari˜no DL, Cabello D, Pardo XM, Brea VM. Cellular neural networks and active contours: a tool for image segmentation. Image Vision Comput 2003; 21: 189–204.
  • Grgic S, Grgic M, Mrak M. Reliability of objective picture quality measures. J Electr Eng 2004; 55: 3–10. Sundaram M, Ramar K, Arumugam N, Prabin G. Histogram modified local contrast enhancement for mammogram images. Appl Soft Comput 2011; 11: 5809–5816.
  • Wang Z, Bovik AC. A universal image quality index. IEEE Signal Proc Lett 2002; 9: 81–84.
  • Agaian SS, Lentz KP, Grigoryan AM. A new measure of image enhancement. In: IASTED International Conference on Signal Processing & Communication; 2000.
Turkish Journal of Electrical Engineering and Computer Science-Cover
  • ISSN: 1300-0632
  • Yayın Aralığı: Yılda 6 Sayı
  • Yayıncı: TÜBİTAK
Sayıdaki Diğer Makaleler

Approximations of higher-order fractional differentiators and integrators using indirect discretization

RICHA YADAV, MANEESHA GUPTA

A novel adaptive filter design using Lyapunov stability theory

ENGİN CEMAL MENGÜÇ, NURETTİN ACIR

An OFDM throughput analysis for cognitive radio application in contiguous or noncontiguous TV white spaces

Cebrail ÇİFLİKLİ, Ahmet Turgut TUNCER, Yusuf ÖZTÜRK

A new hysteresis band current control technique for a shunt active filter

MURAT KALE, ENGİN ÖZDEMİR

Model-based test case prioritization using cluster analysis: a soft-computing approach

NİDA GÖKÇE, FEVZİ BELLİ, MÜBARİZ EMİNLİ, BEKİR TANER DİNÇER

Using the finite element method to calculate parameters for a detailed model of transformer winding for partial discharge research

SEYED MOHAMMAD HASSAN HOSSEINI, SEYED MOHSEN ENJAVI MADAR, MEHDI VAKILIAN

EMG classification in obstructive sleep apnea syndrome and periodic limb movement syndrome patients by using wavelet packet transform and extreme learning machine

Necmettin SEZGİN, Necmettin SEZGİN

Detection of microcalcification in digitized mammograms with multistable cellular neural networks using a new image enhancement method: automated lesion intensity enhancer (ALIE)

Levent CİVCİK, Burak YILMAZ, Yüksel ÖZBAY, Ganime Dilek EMLİK

Estimating facial angles using Radon transform

Mohamad Amin BAKHSHALI, Mousa SHAMSI

Conceptual design of a low-cost real-time hardware-in-the-loop simulator for satellite attitude control system

Farhad BAYAT