Separation of malignant and benign masses using image and segmentation features

The purpose of this study is to investigate the efficacy of image features versus likelihood features of tumor boundaries for differentiating benign and malignant tumors and to compare the effectiveness of two neural networks in the classification study: (1) circular processing-based neural network and (2) conventional Multilayer Perceptron (MLP). The segmentation method used is an adaptive region growing technique coupled with a fuzzy shadow approach and maximum likelihood analyzer. Intensity, shape, texture, and likelihood features were calculated for the extracted Region of Interest (ROI). We performed these studies: experiment number 1 utilized image features used as inputs and the MLP for classification, experiment number 2 utilized image features used as inputs and the neural net with circular processing for classification, and experiment number 3 used likelihood values as inputs and the MLP for classification. The experiments were validated using an ROC methodology. We have tested these methods on 51 mammograms using a leave-one-case-out experiment (i.e., Jackknife procedure). The Az values for the four experiments were as follows: 0.66 in experiment number 1, 0.71 in experiment number 2, and 0.84 in experiment number 3.

[1]  Shelton D Caruthers,et al.  Targeted nanoparticles for quantitative imaging of sparse molecular epitopes with MRI , 2004, Magnetic resonance in medicine.

[2]  B Sahiner,et al.  False-positive reduction technique for detection of masses on digital mammograms: global and local multiresolution texture analysis. , 1997, Medical physics.

[3]  M. Gottesman,et al.  Reduced endocytosis and altered lysosome function in cisplatin-resistant cell lines , 2003, British Journal of Cancer.

[4]  Lennart Larsson,et al.  Lunar dust: A negative control for biomarker analyses of extraterrestrial samples? , 2001 .

[5]  S. Feig,et al.  Clinically occult breast lesions: localization and significance. , 1987, Radiology.

[6]  D. Kopans,et al.  Occult breast abnormalities: percutaneous preoperative needle localization. , 1984, Radiology.

[7]  N. Boyd,et al.  Automated analysis of mammographic densities. , 1996, Physics in medicine and biology.

[8]  M. Gottesman,et al.  Depolymerization of microtubules increases the motional freedom of molecular probes in cellular plasma membranes , 1985, The Journal of cell biology.

[9]  L. Brinton,et al.  Recent trends in breast cancer incidence and mortality , 2002, Environmental and molecular mutagenesis.

[10]  Forst E. Brown.  Atlas of Mammography: Histologic and Mammographic Correlations. Second Edition , 1990 .

[11]  D L Foxall,et al.  Continuous perfusion of mammalian cells embedded in agarose gel threads. , 1984, Experimental cell research.

[12]  L. Fajardo,et al.  Previous mammograms in patients with impalpable breast carcinoma: retrospective vs blinded interpretation. 1993 ARRS President's Award. , 1993, AJR. American journal of roentgenology.

[13]  Youguo Huang,et al.  Physical state changes of membrane lipids in human lung adenocarcinoma A(549) cells and their resistance to cisplatin. , 2002, The international journal of biochemistry & cell biology.

[14]  R A Clark,et al.  False-positive reduction in CAD mass detection using a competitive classification strategy. , 2001, Medical physics.

[15]  R. Epand,et al.  Increased accumulation of drugs in a multidrug resistant cell line by alteration of membrane biophysical properties. , 1993, Biochimica et biophysica acta.

[16]  I. Pastan,et al.  Characterisation of high-level cisplatin-resistant cell lines established from a human hepatoma cell line and human KB adenocarcinoma cells: cross-resistance and protein changes. , 1995, British Journal of Cancer.

[17]  E T BELL,et al.  The Diseases of the Breast , 1925, Nature.

[18]  Maryellen L. Giger,et al.  Automated seeded lesion segmentation on digital mammograms , 1998, IEEE Transactions on Medical Imaging.

[19]  Edward J. Delp,et al.  The EM/MPM algorithm for segmentation of textured images: analysis and further experimental results , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[20]  R. Liddington,et al.  Crystal structure of the I domain from integrin alpha2beta1. , 1997, The Journal of biological chemistry.

[21]  H P Chan,et al.  Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue. , 1996, Medical physics.

[22]  P. Csermely,et al.  Protein kinase C is involved in the early signals of interferon-alpha but not of interferon-gamma in U937 cells. , 1990, Journal of interferon research.

[23]  Sheng Liu,et al.  Statistical Segmentation of Mammograms , 1996 .

[24]  Shelton D Caruthers,et al.  Molecular imaging of angiogenesis in early-stage atherosclerosis with alpha(v)beta3-integrin-targeted nanoparticles. , 2003, Circulation.

[25]  K. Maheswari,et al.  Interaction of cisplatin with planar model membranes - dose dependent change in electrical characteristics. , 2000, Biochimica et biophysica acta.

[26]  P. Williamson,et al.  Altered lipid packing identifies apoptotic thymocytes. , 1993, Immunology letters.

[27]  Huai Li,et al.  A multiple circular path convolution neural network system for detection of mammographic masses , 2002, IEEE Transactions on Medical Imaging.

[28]  Richard H. Moore,et al.  Current Status of the Digital Database for Screening Mammography , 1998, Digital Mammography / IWDM.

[29]  N. Karssemeijer,et al.  Segmentation of suspicious densities in digital mammograms. , 2001, Medical physics.

[30]  D R Dance,et al.  Segmentation of mammograms using multiple linked self-organizing neural networks. , 1995, Medical physics.

[31]  C. W. Browning,et al.  Use of merocyanine (MC540) in quantifying lipid domains and packing in phospholipid vesicles and tumor cells. , 1993, Biochimica et biophysica acta.

[32]  E. Hol,et al.  Cisplatin neuropathy. , 1995, Neurology.

[33]  Berkman Sahiner,et al.  An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection , 1996, IEEE Trans. Medical Imaging.

[34]  J. S. Cohen,et al.  NMR Studies of Metabolism of Cells and Perfused Organs , 1992 .

[35]  J. S. Cohen,et al.  NMR studies of perfused cells , 1983 .

[36]  R. Scott,et al.  Plasma membrane fluidity gradients of human peripheral blood leukocytes , 1990, Journal of cellular physiology.

[37]  Matthew T. Freedman,et al.  Automatic segmentation of mammographic masses using fuzzy shadow and maximum-likelihood analysis , 2002, Proceedings IEEE International Symposium on Biomedical Imaging.

[38]  M. Moskowitz,et al.  Breast cancer missed by mammography. , 1979, AJR. American journal of roentgenology.

[39]  M. Gottesman,et al.  The multidrug resistance phenotype: 31P nuclear magnetic resonance characterization and 2-deoxyglucose toxicity. , 1991, Cancer research.

[40]  B. de Kruijff,et al.  Interaction of the anti-cancer drug cisplatin with phosphatidylserine in intact and semi-intact cells. , 1999, Biochimica et biophysica acta.

[41]  Lubomir M. Hadjiiski,et al.  Improvement of mammographic mass characterization using spiculation meausures and morphological features. , 2001, Medical physics.