Hidefumi Kobatake

Computerized detection of malignant tumors on digital mammograms

This paper presents a tumor detection system for fully digital mammography. The processing scheme adopted in the proposed system focuses on the solution of two problems. One is how to detect tumors as suspicious regions with a very weak contrast to their background and another is how to extract features which characterize malignant tumors. For the first problem, a unique adaptive filter called the iris filter is proposed. It is very effective in enhancing approximately rounded opacities no matter what their contrasts might be. Clues for differentiation between malignant tumors and other tumors are believed to be mostly in their border areas. This paper proposes typical parameters which reflect boundary characteristics. To confirm the system performance for unknown samples, large scale experiments using 1212 CR images were performed. The results showed that the sensitivity of the proposed system was 90.5% and the average number of false positives per image was found to be only 1.3. These results show the effectiveness of the proposed system.

Convergence index filter for vector fields

This paper proposes a unique fitter called an iris filter, which evaluates the degree of convergence of the gradient vectors within its region of support toward a pixel of interest. The degree of convergence is related to the distribution of the directions of the gradient vectors and not to their magnitudes. The convergence index of a gradient vector at a given pixel is defined as the cosine of its orientation with respect to the line connecting the pixel and the pixel of interest. The output of the iris filter is the average of the convergence indices within its region of support and lies within the range [-1,1]. The region of support of the iris filter changes so that the degree of convergence of the gradient vectors in it becomes a maximum, i.e., the size and shape of the region of support at each pixel of interest changes adaptively according to the distribution pattern of the gradient vectors around it. Theoretical analysis using models of a rounded convex region and a semi-cylindrical one is given. These show that rounded convex regions are generally enhanced, even if the contrast to their background is weak and also that elongated objects are suppressed. The filter output is 1/pi at the boundaries of rounded convex regions and semi-cylindrical ones. This value does not depend on the contrast to their background. This indicates that boundaries of rounded or slender objects, with weak contrast to their background, are enhanced by the iris filter and that the absolute value of 1/pi can be used to detect the boundaries of these objects. These theoretical characteristics are confirmed by experiments using X-ray images.

Segmentation of multiple organs in non-contrast 3D abdominal CT images

ObjectiveWe propose a simultaneous extraction method for 12 organs from non-contrast three-dimensional abdominal CT images.Materials and methodsThe proposed method uses an abdominal cavity standardization process and atlas guided segmentation incorporating parameter estimation with the EM algorithm to deal with the large fluctuations in the feature distribution parameters between subjects. Segmentation is then performed using multiple level sets, which minimize the energy function that considers the hierarchy and exclusiveness between organs as well as uniformity of grey values in organs. To assess the performance of the proposed method, ten non-contrast 3D CT volumes were used.ResultsThe accuracy of the feature distribution parameter estimation was slightly improved using the proposed EM method, resulting in better performance of the segmentation process. Nine organs out of twelve were statistically improved compared with the results without the proposed parameter estimation process. The proposed multiple level sets also boosted the performance of the segmentation by 7.2 points on average compared with the atlas guided segmentation. Nine out of twelve organs were confirmed to be statistically improved compared with the atlas guided method.ConclusionThe proposed method was statistically proved to have better performance in the segmentation of 3D CT volumes.

Detection of spicules on mammogram based on skeleton analysis

Existence of spicules is one of important clues of malignant tumors. This paper presents a new image processing method for the detection of spicules on mammogram. Spicules can be recognized as line patterns radiating from the center of tumor. To detect such characteristic patterns, line skeletons and a modified Hough transform are proposed. Line skeleton processing is effective in enhancing spinal axes of spicules and in reducing the other skeletons. The modified Hough transform is applied to line skeletons and radiating line structures are obtained. Experiments were made to test the performance of the proposed method. The system was designed using 19 training images, for which one normal case was recognized to be star-shaped. The other case were recognized correctly. Another experiments using 34 test images were also performed. The correct classification rate was 74%. These results shows the effectiveness of the proposed method.

Medical image analysis of 3D CT images based on extension of Haralick texture features

PURPOSE A new approach to the segmentation of 3D CT images is proposed in an attempt to provide texture-based segmentation of organs or disease diagnosis. 3D extension of Haralick texture features was studied calculating co-occurrences of all voxels in a small cubic region around the voxel. RESULTS For verification, the proposed method was tested on a set of abdominal 3D volumes of patients. Statistically, the improvement in segmentation was significant for most of the organs considered herein. CONCLUSIONS The proposed method has potential application in medical image segmentation, including diagnosis of diseases.

Automated pancreas segmentation from three-dimensional contrast-enhanced computed tomography

PurposeWe propose an automated pancreas segmentation algorithm from contrast-enhanced multiphase computed tomography (CT) and verify its effectiveness in segmentation.MethodsThe algorithm is characterized by three unique ideas. First, a two-stage segmentation strategy with spatial standardization of pancreas was employed to reduce variations in the pancreas shape and location. Second, patient- specific probabilistic atlas guided segmentation was developed to cope with the remaining variability in shape and location. Finally, a classifier ensemble was incorporated to refine the rough segmentation results.ResultsThe effectiveness of the proposed algorithm was validated with 20 unknown CT volumes, as well as three on-site CT volumes distributed in a competition of pancreas segmentation algorithms. The experimental results indicated that the segmentation performance was enhanced by the proposed algorithm, and the Jaccard index between an extracted pancreas and a true one was 57.9%.ConclusionsThis study verified the effectiveness of two-stage segmentation with spatial standardization of pancreas in delineating the pancreas region, patient-specific probabilistic atlas guided segmentation in reducing false negatives, and a classifier ensemble in boosting segmentation performance.

Robust face detection using Gabor filter features

In this paper, we present a classification-based face detection method using Gabor filter features. Taking advantage of the desirable characteristics of spatial locality and orientation selectivity of Gabor filters, we design four filters corresponding to four orientations for extracting facial features from local images in sliding windows. The feature vector based on Gabor filters is used as the input of the face/non-face classifier, which is a polynomial neural network (PNN) on a reduced feature subspace learned by principal component analysis (PCA). The effectiveness of the proposed method is demonstrated by experiments on a large number of images. We show that using both of the magnitude and phase of Gabor filter response as features, the detection performance is better than that using magnitude only, and using the real part only also performs fairly well. Our detection performance is competitive with those reported in the literature.

Face detection from cluttered images using a polynomial neural network

Abstract Automatic detection of human faces from cluttered images is important for face recognition and security applications. This problem is challenging due to the multitude of variations and the confusion between face and background regions. This paper proposes a new face detection method using a polynomial neural network (PNN). To locate the human faces in an image, the local regions in multiscale sliding windows are classified by the PNN to two classes, namely, face and non-face. The PNN takes as inputs the binomials of the projection of the local image onto a feature subspace learned by principal component analysis (PCA). We investigated the influence of PCA on either the face samples or the pooled face and non-face samples. In addition, we integrate the distance from the feature subspace into the PNN to improve the detection performance. In experiments on images with complex backgrounds, the proposed method has produced promising results in terms of high detection rate and low false positive rate.

Multi-shape graph cuts with neighbor prior constraints and its application to lung segmentation from a chest CT volume

This paper presents a novel graph cut algorithm that can take into account multi-shape constraints with neighbor prior constraints, and reports on a lung segmentation process from a three-dimensional computed tomography (CT) image based on this algorithm. The major contribution of this paper is the proposal of a novel segmentation algorithm that improves lung segmentation for cases in which the lung has a unique shape and pathologies such as pleural effusion by incorporating multiple shapes and prior information on neighbor structures in a graph cut framework. We demonstrate the efficacy of the proposed algorithm by comparing it to conventional one using a synthetic image and clinical thoracic CT volumes.

Computer-aided diagnosis in full digital mammography

RATIONALE AND OBJECTIVES The authors clarify the detection rates for breast cancerous tumors and clustered microcalcifications with computer-aided diagnosis (CAD) based on Fuji Computed Radiography. The authors also determine whether mammographic reading with CAD contributes to the discovery of breast cancer. METHODS Data acquired by Fuji Computed Radiography 9000, which consisted of 4148 digital mammograms including 267 cases of breast cancer, was transferred directly to an analysis workstation where an original software program determined extraction rates for breast tumors and clustered microcalcifications. Furthermore, using another 344 mammograms from 86 women, observer performance studies were conducted on five doctors for receiver operating characteristic (ROC) analysis. RESULTS Sensitivity to breast cancerous tumors and clustered microcalcifications were 89.9% and 92.8%, respectively false-positive rates were 1.35 and 0.40 per image, respectively. The observer performance studies indicate that an average Az value for the five doctors was greater with the CAD system than with a film-only reading without CAD, and that a reading with CAD was significantly superior at P < 0.022. CONCLUSIONS It has been shown that CAD based on Fuji Computed Radiography offers good detection rates for both breast cancerous tumors and clustered microcalcifications, and that the reading of mammograms with this CAD system would provide potential improvement in diagnostic accuracy for breast cancer.