RESUMO
A new model-based vision (MBV) algorithm is developed to find regions of interest (ROI's) corresponding to masses in digitized mammograms and to classify the masses as malignant/benign. The MBV algorithm is comprised of five modules to structurally identify suspicious ROI's, eliminate false positives, and classify the remaining as malignant or benign. The focus of attention module uses a difference of Gaussians (DoG) filter to highlight suspicious regions in the mammogram. The index module uses tests to reduce the number of nonmalignant regions from 8.39 to 2.36 per full breast image. Size, shape, contrast, and Laws texture features are used to develop the prediction module's mass models. Derivative-based feature saliency techniques are used to determine the best features for classification. Nine features are chosen to define the malignant/benign models. The feature extraction module obtains these features from all suspicious ROI's. The matching module classifies the regions using a multilayer perceptron neural network architecture to obtain an overall classification accuracy of 100% for the segmented malignant masses with a false-positive rate of 1.8 per full breast image. This system has a sensitivity of 92% for locating malignant ROI's. The database contains 272 images (12 b, 100 microm) with 36 malignant and 53 benign mass images. The results demonstrate that the MBV approach provides a structured order of integrating complex stages into a system for radiologists.
Assuntos
Neoplasias da Mama/diagnóstico por imagem , Mamografia , Intensificação de Imagem Radiográfica , Interpretação de Imagem Radiográfica Assistida por Computador , Algoritmos , Feminino , HumanosRESUMO
A general purpose two-dimensional (2-D) image processing software system was used to produce high quality three-dimensional (3-D) surface reconstructions from serial sections such as CT scan slices. Depth-encoded 3-D surface images, gradient-shaded 3-D surface images, and weighted sums of these two images were computed. Images that simulate transmission radiographs ("volumetric" views) were created from the same slice data. Hidden surfaces were displayed by reconstructing in 3-D only subvolumes of the original data set. The 2-D image processing functions used were limited to: planar subimage selection and merge, arithmetic and boolean operations, piecewise linear gray scale transform, convolution (1-D), and format conversion (byte-integer-float). Using these methods any user with a general purpose 2-D image processing system can analyze and view multi-slice data as 3-D volume and surface projections.