Computer aided automatic detection of malignant lesions in diffuse optical mammography.

PURPOSE Computer aided detection (CAD) data analysis procedures are introduced and applied to derive composite diffuse optical tomography (DOT) signatures of malignancy in human breast tissue. In contrast to previous optical mammography analysis schemes, the new statistical approach utilizes optical property distributions across multiple subjects and across the many voxels of each subject. The methodology is tested in a population of 35 biopsy-confirmed malignant lesions. METHODS DOT CAD employs multiparameter, multivoxel, multisubject measurements to derive a simple function that transforms DOT images of tissue chromophores and scattering into a probability of malignancy tomogram. The formalism incorporates both intrasubject spatial heterogeneity and intersubject distributions of physiological properties derived from a population of cancercontaining breasts (the training set). A weighted combination of physiological parameters from the training set define a malignancy parameter (M), with the weighting factors optimized by logistic regression to separate training-set cancer voxels from training-set healthy voxels. The utility of M is examined, employing 3D DOT images from an additional subjects (the test set). RESULTS Initial results confirm that the automated technique can produce tomograms that distinguish healthy from malignant tissue. When compared to a gold standard tissue segmentation, this protocol produced an average true positive rate (sensitivity) of 89% and a true negative rate (specificity) of 94% using an empirically chosen probability threshold. CONCLUSIONS This study suggests that the automated multisubject, multivoxel, multiparameter statistical analysis of diffuse optical data is potentially quite useful, producing tomograms that distinguish healthy from malignant tissue. This type of data analysis may also prove useful for suppression of image artifacts.

[1]  I. Fidler,et al.  Tumor heterogeneity and the biology of cancer invasion and metastasis. , 1978, Cancer research.

[2]  S R Arridge,et al.  Optical imaging in medicine: I. Experimental techniques , 1997, Physics in medicine and biology.

[3]  John C Schotland,et al.  Scanning paraxial optical tomography. , 2002, Optics letters.

[4]  Alessandro Torricelli,et al.  Seven-wavelength time-resolved optical mammography extending beyond 1000 nm for breast collagen quantification. , 2009, Optics express.

[5]  Regine Choe,et al.  Comparison of diffuse optical tomography of human breast with whole-body and breast-only positron emission tomography. , 2008, Medical physics.

[6]  B. Tromberg,et al.  In vivo absorption, scattering, and physiologic properties of 58 malignant breast tumors determined by broadband diffuse optical spectroscopy. , 2006, Journal of biomedical optics.

[7]  Soren D. Konecky,et al.  Differentiation of benign and malignant breast tumors by in-vivo three-dimensional parallel-plate diffuse optical tomography. , 2009, Journal of biomedical optics.

[8]  Nirmala Ramanujam,et al.  Model based and empirical spectral analysis for the diagnosis of breast cancer. , 2008, Optics express.

[9]  I. Weissman,et al.  Stem cells, cancer, and cancer stem cells , 2001, Nature.

[10]  B. Pogue,et al.  Tutorial on diffuse light transport. , 2008, Journal of biomedical optics.

[11]  B. Pogue,et al.  Automated region detection based on the contrast-to-noise ratio in near-infrared tomography. , 2004, Applied optics.

[12]  M. Pepe The Statistical Evaluation of Medical Tests for Classification and Prediction , 2003 .

[13]  B. Pogue,et al.  Near-Infrared Characterization of Breast Tumors In Vivo using Spectrally-Constrained Reconstruction , 2005, Technology in cancer research & treatment.

[14]  Lothar Lilge,et al.  Classification of breast tissue density by optical transillumination spectroscopy: optical and physiological effects governing predictive value , 2003, Other Conferences.

[15]  G Gulsen,et al.  In vivo water state measurements in breast cancer using broadband diffuse optical spectroscopy , 2008, Physics in medicine and biology.

[16]  D. Ruppert The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[17]  Huabei Jiang,et al.  Noninvasive in vivo tomographic optical imaging of cellular morphology in the breast: possible convergence of microscopic pathology and macroscopic radiology. , 2008, Medical physics.

[18]  A. Darzi,et al.  Diffuse optical imaging of the healthy and diseased breast: A systematic review , 2008, Breast Cancer Research and Treatment.

[19]  E. Conant,et al.  Breast cancer detection based on incremental biochemical and physiological properties of breast cancers: a six-year, two-site study. , 2005, Academic radiology.

[20]  E. Conant,et al.  Breast Cancer Detection Based on Incremental Biochemical and Physiological Properties of Breast Cancers , 2005 .

[21]  J P Culver,et al.  Optimization of optode arrangements for diffuse optical tomography: A singular-value analysis. , 2001, Optics letters.

[22]  Qizhi Zhang,et al.  Automated breast cancer classification using near-infrared optical tomographic images. , 2008, Journal of biomedical optics.

[23]  S. Arridge,et al.  Optical tomography: forward and inverse problems , 2009, 0907.2586.

[24]  B Chance,et al.  Metabolism-enhanced tumor localization by fluorescence imaging: in vivo animal studies. , 2003, Optics letters.

[25]  Vadim A. Markel,et al.  Imaging complex structures with diffuse light. , 2008, Optics express.

[26]  Alexander D Klose,et al.  Multiparameter classifications of optical tomographic images. , 2008, Journal of biomedical optics.

[27]  Woo Kyung Moon,et al.  Computer-aided detection in full-field digital mammography: sensitivity and reproducibility in serial examinations. , 2008, Radiology.

[28]  F. Winsberg,et al.  Detection of Radiographic Abnormalities in Mammograms by Means of Optical Scanning and Computer Analysis , 1967 .

[29]  Lothar Lilge,et al.  Non-ionizing near-infrared radiation transillumination spectroscopy for breast tissue density and assessment of breast cancer risk. , 2004, Journal of biomedical optics.

[30]  B. Tromberg,et al.  Spatial variations in optical and physiological properties of healthy breast tissue. , 2002, Journal of biomedical optics.

[31]  R. Jong,et al.  Assessing breast tissue density by transillumination breast spectroscopy (TIBS): an intermediate indicator of cancer risk. , 2007, The British journal of radiology.

[32]  E. Somers International Agency for Research on Cancer. , 1985, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[33]  M. Giger,et al.  Computer-aided detection and diagnosis of breast cancer. , 2000, Radiologic clinics of North America.

[34]  Hamid Dehghani,et al.  Image analysis methods for diffuse optical tomography. , 2006, Journal of biomedical optics.

[35]  B. Tromberg,et al.  Imaging in breast cancer: Diffuse optics in breast cancer: detecting tumors in pre-menopausal women and monitoring neoadjuvant chemotherapy , 2005, Breast Cancer Research.