Digital Subtraction Angiography (DSA) is a well-established powerful modality for the visualization of stenosis and blood vessels in general. This paper presents two novel approaches which address image quality. In the first approach we combine anisotropic diffusion with nonlinear normalization. The second approach consists of an introduction of a regularization strategy followed by a classification procedure to improve the enhancement. The performances of two strategies are evaluated based on a database of 73 subjects using SNR, CNR and Tenengrad's metric. Compared with conventional DSA, Eigen's diffusion embedded nonlinear enhancement strategies can improve image quality 95.25% in terms of SNR. The regularization embedded linear enhancement strategy can also improve SNR 51.46% compared with conventional DSA. Similar results are obtained by CNR and Tenengrad's metric measurements. Our system runs on a PC-based workstation using C++ in Windows environment.
Prostate volume is an indirect indicator for several prostate diseases. Volume estimation is a desired requirement during
prostate biopsy, therapy and clinical follow up. Image segmentation is thus necessary. Previously, discrete dynamic contour (DDC) was implemented in orthogonal unidirectional on the slice-by-slice basis
for prostate boundary estimation. This suffered from the glitch that it needed stopping criteria during the propagation of
segmentation procedure from slice-to-slice. To overcome this glitch, axial DDC was implemented and this suffered from the fact that central axis never remains fixed and wobbles during propagation of segmentation from slice-to-slice. The effect of this was a multi-fold reconstructed surface. This paper presents a bidirectional DDC approach, thereby removing the two glitches. Our bidirectional DDC protocol was tested on a clinical dataset on 28 3-D ultrasound image volumes acquired using side fire Philips transrectal ultrasound. We demonstrate the orthogonal bidirectional DDC strategy achieved the most accurate volume estimation compared with previously published orthogonal unidirectional DDC and axial DDC methods. Compared to the ground truth, we show that the mean volume estimation errors were: 18.48%, 9.21% and 7.82% for unidirectional, axial and bidirectional DDC methods, respectively. The segmentation architecture is implemented in Visual C++ in Windows environment.
DSA images suffer from challenges like system X-ray noise and artifacts due to patient movement. In this paper, we present a two-step strategy to improve DSA image quality. First, a hierarchical deformable registration algorithm is used to register the mask frame and the bolus frame before subtraction. Second, the resulted DSA image is further enhanced by background diffusion and nonlinear normalization for better visualization. Two major changes are made in the hierarchical deformable registration algorithm for DSA images: 1) B-Spline is used to represent the deformation field in order to produce the smooth deformation field; 2) two features are defined as the attribute vector for each point in the image, i.e., original image intensity and gradient. Also, for speeding up the 2D
image registration, the hierarchical motion compensation algorithm is implemented by a multi-resolution framework. The proposed method has been evaluated on a database of 73 subjects by quantitatively measuring signal-to-noise (SNR) ratio. DSA embedded with proposed strategies demonstrates an improvement of 74.1% over conventional DSA in terms of SNR. Our system runs on Eigen's DSA workstation using C++ in Windows environment.
The human user is an often ignored component of the imaging chain. In medical diagnostic tasks, the human observer plays the role of the decision-maker, forming opinions based on visual assessment of images. In content-based image retrieval, the human user is the ultimate judge of the relevance of images recalled from a database. We argue that data collected from human observers should be used in conjunction with machine-learning algorithms to model and optimize
performance in tasks that involve humans. In essence, we treat the human observer as a nonlinear system to be identified. In this paper, we review our work in two applications of this general idea. In the first, a learning machine is trained to predict the accuracy of human observers in a lesion detection task for purposes of assessing image quality. In the second, a learning machine is trained to predict human users' perception of the similarity of two images for purposes
of content-based image retrieval from a database. In both examples, it is shown that a nonlinear learning machine can accurately identify the nonlinear human system that maps images into numerical values, such as detection performance or image similarity.
In this paper we investigate several state-of-the-art machine-learning methods for automated classification of clustered microcalcifications (MCs), aimed to assisting radiologists for more accurate diagnosis of breast cancer in a computer-aided diagnosis (CADx) scheme. The methods we consider include: support vector machine (SVM), kernel Fisher discriminant (KFD), and committee machines (ensemble averaging and AdaBoost), most of which have been developed recently in statistical learning theory. We formulate differentiation of malignant from benign MCs as a supervised learning problem, and apply these learning methods to develop the classification algorithms. As input, these methods use image features automatically extracted from clustered MCs. We test these methods using a database of 697 clinical mammograms from 386 cases, which include a wide spectrum of difficult-to-classify cases. We use receiver operating characteristic (ROC) analysis to evaluate and compare the classification performance by the different methods. In addition, we also investigate how to combine information from multiple-view mammograms of the same case so that the best decision can be made by a classifier. In our experiments, the kernel-based methods (i.e., SVM, KFD) yield the best performance, significantly outperforming a well-established CADx approach based on neural network learning.
Microcalcification (MC) clusters in mammograms can be important early signs of breast cancer in women. Accurate detection of MC clusters is an important but challenging problem. In this paper, we propose the use of a recently developed machine learning technique -- relevance vector machine (RVM) -- for automatic detection of MCs in digitized mammograms. RVM is based on Bayesian estimation theory, and as a feature it can yield a decision function that depends on only a very small number of so-called relevance vectors. We formulate MC detection as a supervised-learning problem, and use RVM to classify if an MC object is present or not at each location in a mammogram image. MC clusters are then identified by grouping the detected MC objects. The proposed method is tested using a database of 141 clinical mammograms, and compared with a support vector machine (SVM) classifier which we developed previously. The detection performance is evaluated using the free-response receiver operating characteristic (FROC) curves. It is demonstrated that the RVM classifier matches closely with the SVM classifier in detection performance, and does so with a much sparser kernel representation than the SVM classifier. Consequently, the RVM classifier greatly reduces the computational complexity, making it more suitable for real-time processing of MC clusters in mammograms.
We are comparing two different methods for obtaining the radiologists’ subjective impression of similarity, for application in distinguishing benign from malignant lesions. Thirty pairs of mammographic clustered calcifications were used in this study. These 30 pairs were rated on a 5-point scale as to their similarity, where 1 was nearly identical and 5 was not at all similar. After this, all possible combinations of pairs of pairs were shown to the reader (n=435) and the reader selected which pair was most similar. This experiment was repeated by the observers with at least a week between reading sessions. Using analysis of variance, intra-class correlation coefficients (ICC) were calculated for both absolute scoring method and paired comparison method. In addition, for the paired comparison method, the coefficient of consistency within each reader was calculated. The average coefficient of consistence for the 4 readers was 0.88 (range 0.49-0.97). These results were statistically significant different from guessing at p << 0.0001. The ICC for intra-reader agreement was 0.51 (0.37-0.66 95% CI) for the absolute method and 0.82 (0.73-0.91 95% CI) for the paired comparison method. This difference was statistically significant (p=0.001). For the inter-reader agreement, the ICC for the absolute method was 0.39 (0.21-0.57 95% CI) and 0.37 (0.18-0.56 95% CI) for the paired comparison method. We conclude that humans are able to judge similarity of clustered calcifications in a meaningful way. Further, radiologists had greater intra-reader agreement when using the paired comparison method than when using an absolute rating scale. Differences in the criteria used by different observers to judge similarity and differences in interpreting which calcifications comprise the cluster can lead to low ICC values for inter-reader agreement for both methods.