Chih-Ying Gwo

Estimation of breast density: An adaptive moment preserving method for segmentation of fibroglandular tissue in breast magnetic resonance images

PURPOSE Breast density has been found to be a potential indicator for breast cancer risk. The estimation of breast density can be seen as a segmentation problem on fibroglandular tissues from a breast magnetic resonance image. The classic moment preserving is a thresholding method, which can be applied to determine an appropriate threshold value for fibroglandular tissue segmentation. METHODS This study proposed an adaptive moment preserving method, which combines the classic moment preserving and a thresholding adjustment method. The breast MR images are firstly performed to extract the fibroglandular tissue from the breast tissue. The next step is to obtain the areas of the fibroglandular tissue and the whole breast tissue. Finally, breast density can be estimated for the given breast. RESULTS The Friedman test shows that the qualities of segmentation are insignificant with p<0.000 and Friedman chi-squared=1116.12. The Friedman test shows that there would be significant differences in the sum of the ranks of at least one segmentation method. Average ranks indicate that the performance of the four methods is ranked as adaptive moment preserving, fuzzy c-means, moment preserving, and Kapurs method in order. Among the four methods, adaptive moment preserving also achieves the minimum values of MAE and RMSE with 9.2 and 12. CONCLUSION This study has verified that the proposed adaptive moment preserving can identify and segment the fibroglandular tissues from the 2D breast MR images and estimate the degrees of breast density.

Plant Identification Through Images: Using Feature Extraction of Key Points on Leaf Contours

Premise of the study: Because plant identification demands extensive knowledge and complex terminologies, even professional botanists require significant time in the field for mastery of the subject. As plant leaves are normally regarded as possessing useful characteristics for species identification, leaf recognition through images can be considered an important research issue for plant recognition. Methods: This study proposes a feature extraction method for leaf contours, which describes the lines between the centroid and each contour point on an image. A length histogram is created to represent the distribution of distances in the leaf contour. Thereafter, a classifier is applied from a statistical model to calculate the matching score of the template and query leaf. Results: The experimental results show that the top value achieves 92.7% and the first two values can achieve 97.3%. In the scale invariance test, those 45 correlation coefficients fall between the minimal value of 0.98611 and the maximal value of 0.99992. Like the scale invariance test, the rotation invariance test performed 45 comparison sets. The correlation coefficients range between 0.98071 and 0.99988. Discussion: This study shows that the extracted features from leaf images are invariant to scale and rotation because those features are close to positive correlation in terms of coefficient correlation. Moreover, the experimental results indicated that the proposed method outperforms two other methods, Zernike moments and curvature scale space.

Stable, fast computation of high-order Zernike moments using a recursive method

Zernike moments and Zernike polynomials have been widely applied in the fields of image processing and pattern recognition. When high-order Zernike moments are computed, both computing speed and numerical accuracy become inferior. The main purpose of this study is to propose a stable, fast method for computing high-order Zernike moments. Based on the recursive formulas for computing Zernike radial polynomials, this study develops stable, fast algorithms to compute Zernike moments. Symmetry under group action and Farey sequence are both applied to shorten the computing time. The experimental results show that the proposed method took 5.292 seconds to compute the top 500-order Zernike moments of an image with 512×512 pixels. The normalized mean square error is 0.00124846 if 450-order moments are used to reconstruct the image. When computing the high-order Zernike moments, the proposed method outperformed other compared methods in terms of speed and accuracy. This study has proposed a recursive method for fast computation of Zernike moments.The idea of Pascals triangle is introduced to pre-calculate the binomial coefficients.Symmetry property and Farey sequence are applied to speed up the computation.The proposed method can yield accurate values of the high-order Zernike moments.The proposed took 5.398 seconds to compute the top 500-order Zernike moments.

Algorithms for Computing Zernike Moments and Image Reconstruction in Parallel Process

Zernike moments can be computed in several ways. This paper proposes several coefficient methods based on the recursive relations among multinomial coefficients to compute the Zernike moments. In addition, it proposes a parallel algorithm based on the q-recursive method for image reconstruction. The experimental results show that it takes only 3.965 seconds to reconstruct an image measuring 512 X 512 from all Zernike moments up to moment order 150.

Identification of breast contour for nipple segmentation in breast magnetic resonance images

PURPOSE The purpose of this study is to develop a method to simulate the breast contour and segment the nipple in breast magnetic resonance images. METHODS This study first identifies the chest wall and removes the chest part from the breast MR images. Subsequently, the cleavage and its motion artifacts are removed, distinguishing the separate breasts, where the edge points are sampled for curve fitting. Next, a region growing method is applied to find the potential nipple region. Finally, the potential nipple region above the simulated curve can be removed in order to retain the original smooth contour. RESULTS The simulation methods can achieve the least root mean square error (RMSE) for certain cases. The proposed YBnd and (Dmin+Dmax)/2 methods are significant due toP = 0.000. The breast contour curve detected by the two proposed methods is closer than that determined by the edge detection method. The (Dmin+Dmax)/2 method can achieve the lowest RMSE of 1.1029 on average, while the edge detection method results in the highest RMSE of 6.5655. This is only slighter better than the comparison methods, which implies that the performance of these methods depends upon the conditions of the cases themselves. Under this method, the maximal Dice coefficient is 0.881, and the centroid difference is 0.36 pixels. CONCLUSIONS The contributions of this study are twofold. First, a method was proposed to identify and segment the nipple in breast MR images. Second, a curve-fitting method was used to simulate the breast contour, allowing the breast to retain its original smooth shape.

The use of scale-invariance feature transform approach to recognize and retrieve incomplete shoeprints.

Shoeprints left at the crime scene provide valuable information in criminal investigation due to the distinctive patterns in the sole. Those shoeprints are often incomplete and noisy. In this study, scale‐invariance feature transform is proposed and evaluated for recognition and retrieval of partial and noisy shoeprint images. The proposed method first constructs different scale spaces to detect local extrema in the underlying shoeprint images. Those local extrema are considered as useful key points in the image. Next, the features of those key points are extracted to represent their local patterns around key points. Then, the system computes the cross‐correlation between the query image and each shoeprint image in the database. Experimental results show that full‐size prints and prints from the toe area perform best among all shoeprints. Furthermore, this system also demonstrates its robustness against noise because there is a very slight difference in comparison between original shoeprints and noisy shoeprints.

Detection and construction of chest wall on breast magnetic resonance images

PURPOSE The purpose of this study is to propose a method for detection and construction of chest wall for breast magnetic resonance images. METHODS A volume of breast MR slices are firstly acquired and utilized to detect initial points of chest wall. To calibrate the chest wall curve, the points along the curve is set with reference to its neighboring points. Through the calibration method, a curve of chest wall can be detected from a volume of breast magnetic resonance (MR) slices. Such a curve can be applied for segmentation of breast region in a volume of MR images. RESULTS The experimental results reveal that the minimal RMSE was measured from the setting two polynomial functions and the points from the vertical position ≤320. If all edge points are used to simulate the curve, two circle functions can reach the minimal RMSE. CONCLUSION The experimental results verify that chest wall for breast density estimation can be better simulated by two circle functions, which simulate right and left chest walls respectively. Furthermore, such a simulation curve is suggested to utilize partial edge points under the given vertical position.

Mammogram Retrieval: Image Selection Strategy of Relevance Feedback for Locating Similar Lesions

Content-based image retrieval CBIR has been proposed by the medical community for inclusion in picture archiving and communication systems PACS. In CBIR, relevance feedback is developed for bridging the semantic gap and improving the effectiveness of image retrieval systems. With relevance feedback, CBIR systems can return refined search results using a learning algorithm and selection strategy. In this study, as the retrieving process proceeds further, the proposed learning algorithm can reduce the influence of the original query point and increase the significance of the centroid of the clusters comprising the features of those relevant images identified in the most recent round of search. The proposed selection strategy is used to find a good starting point and select a set of images at each round to show that search result and ask for the users feedback. In addition, a benchmark is proposed to measure the learning ability to explain the retrieval performance as relevance feedback is incorporated in CBIR systems. The performance evaluation shows that the average precision rate of the proposed scheme was 0.98 and the learning ability reach to 7.17 through the five rounds of relevance feedback.

Identification and segmentation of obscure pectoral muscle in mediolateral oblique mammograms

OBJECTIVE X-ray mammography is a widely used and reliable method for detecting pre-symptomatic breast cancer. One of the difficulties in automatically computerized mammogram analysis is the presence of pectoral muscles in mediolateral oblique mammograms because the pectoral muscle does not belong to the scope of the breast. The objective of this study is to identify the boundary of obscure pectoral muscle in mediolateral oblique mammograms. METHODS Two tentative boundary curves are individually created to be the potential boundaries. To find the first tentative boundary, this study finds local extrema, prunes weak extrema and then determines an appropriate threshold for identifying the brighter tissue, whose edge is considered the first tentative boundary. The second tentative boundary is found by partitioning the breast into several regions, where each local threshold is tuned based on the local intensity. Subsequently, both of these tentative boundaries are used as the reference to create a refined boundary by Hough transform. Then, the refined boundary is partitioned into quadrilateral regions, in which the edge of this boundary is detected. Finally, these reliable edge points are collected to generate the genuine boundary by curve fitting. RESULTS The proposed method achieves the least mean square error 4.88 ± 2.47 (mean ± standard deviation) and the least misclassification error rate (MER) with 0.00466 ± 0.00191 in terms of MER. CONCLUSION The experimental results indicate that this method performs best and stably in boundary identification of the pectoral muscle. ADVANCES IN KNOWLEDGE The proposed method can identify the boundary from obscure pectoral muscle, which has not been solved by the previous studies.

Reconstruction of Banknote Fragments Based on Keypoint Matching Method

Banknotes may be shredded by a scrap machine, ripped up by hand, or damaged in accidents. This study proposes an image registration method for reconstruction of multiple sheets of banknotes. The proposed method first constructs different scale spaces to identify keypoints in the underlying banknote fragments. Next, the features of those keypoints are extracted to represent their local patterns around keypoints. Then, similarity is computed to find the keypoint pairs between the fragment and the reference banknote. The banknote fragments can determine the coordinate and amend the orientation. Finally, an assembly strategy is proposed to piece multiple sheets of banknote fragments together. Experimental results show that the proposed method causes, on average, a deviation of 0.12457 ± 0.12810° for each fragment while the SIFT method deviates 1.16893 ± 2.35254° on average. The proposed method not only reconstructs the banknotes but also decreases the computing cost. Furthermore, the proposed method can estimate relatively precisely the orientation of the banknote fragments to assemble.