Phase portrait analysis for automatic initialization of multiple snakes for segmentation of the ultrasound images of breast cancer

Segmentation of ultrasound (US) images of breast cancer is one of the most challenging problems of modern medical image processing. A number of popular codes for US segmentation are based on the active contours (snakes) and on a variety of modifications of gradient vector flow. The snakes have been used to locate objects in various applications of medical images. However, the main difficulty in applying the method is initialization. Therefore, we suggest a new method for automatic initialization of active contours based on phase portrait analysis (PPA) of the underlying vector field and a sequential initialization of trial multiple snakes. The PPA makes it possible to exclude the noise and artifacts and properly initialize the multiple snakes. In turn, the trial snakes allow us to differentiate between the seeds initialized inside and outside the desired object. While preceding methods require the manual selection of at least one seed point inside the object or rely on the particular distribution of the gray levels, the proposed method is fully automatic and robust to the noise, as can be seen from the tests with synthetic and real images.     

A collaborative contour detector by gradient and active contours for ultrasound kidney images

In the process of urinary system disease diagnosis, a complete kidney contour is crucial to estimate its size, area, volume and other properties. These properties can effectively help doctors diagnosis and prepare treatment plans. However, ultrasound images suffer from low signal-to-noise ratio, speckle, missing boundaries and other artefacts. Traditional contour detection algorithms can hardly extract a continuous and accurate kidney contour. To solve the problem, we propose a collaborative contour detector by gradient and active contour. It not only can make sure that the extracted contour is continuous and accurate but also is simple and suitable to use in practice. Both the simulated experiments and clinical experiments show that the proposed algorithm achieves a good performance in ultrasound kidney images and can effectively assist doctors in diagnosis.     

Automatic extraction of face contours in images and videos

The paper proposed an automatic and accurate extraction of the human face contour algorithm. Because a human face contour includes very important facial features to identifying or verifying a person, the accuracy of face contour extraction influences performance of face recognition. The automatic extraction human face contour algorithm includes a novel flowchart for improving accuracy of face contours extraction. To obtain the edge map of a face contour, the divided-and-conquer technique and Canny edge detector were used to avoid the features in the central part of face. The genetic algorithm is implemented to automatically find the parameters of Canny edge detector. Finally, the Poisson gradient vector flow (PGVF) active contour model used the edge map to extract face contours. Three datasets with temporal sequence images were tested for evaluation of the proposed algorithm. The experimental results demonstrated that the algorithm obtained accurate face contours.     

Fast edge integration based active contours for color images

In this paper, a novel geometric active contour model for color image is presented. It combines squared local contrast based alignment term about directional information of edge location as part of driving force, together with the improved geodesic active contour model containing Bays error based two-region segmentation information. And all these measures are integrated as a unified framework. Finally, an unconditionally stable and simple numerical scheme, including the narrow band and fast marching methods, is introduced for efficiently implementing this novel model. Experimental results on color image segmentation show that it can extract the contour of color images precisely and its performance is shown much better than the geodesic-aided C-V (GACV) method when directional information about edge location is supplied.     

Object segmentation in hyperspectral images using active contours and graph cuts

The interest in object segmentation on hyperspectral images is increasing and many approaches have been proposed to deal with this area. In this project, we developed an algorithm that combines both the active contours and the graph cut approaches for object segmentation in hyperspectral images. The active contours approach has the advantage of producing subregions with continuous boundaries. The graph cut approach has emerged as a technique for minimizing energy functions while avoiding the problems of local minima. Additionally, it guarantees continuity and produces smooth contours, free of self-crossing and uneven spacing problems. The algorithm uses the complete spectral signature of a pixel and also considers spatial neighbourhood for graph construction, thereby combining both spectral and spatial information present in the image. The algorithm is tested using real hyperspectral images taken from a variety of sensors, such as Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Hyperspectral Data Imagery Collection Experiment (HYDICE), and also taken by the SOC hyperspectral camera. This approach can segment different objects in an image. This algorithm can be applied in many fields and it should represent an important advance in the field of object segmentation.     

Automated breast cancer detection and classification using ultrasound images: A survey

Breast cancer is the second leading cause of death for women all over the world. Since the cause of the disease remains unknown, early detection and diagnosis is the key for breast cancer control, and it can increase the success of treatment, save lives and reduce cost. Ultrasound imaging is one of the most frequently used diagnosis tools to detect and classify abnormalities of the breast. In order to eliminate the operator dependency and improve the diagnostic accuracy, computer-aided diagnosis (CAD) system is a valuable and beneficial means for breast cancer detection and classification. Generally, a CAD system consists of four stages: preprocessing, segmentation, feature extraction and selection, and classification. In this paper, the approaches used in these stages are summarized and their advantages and disadvantages are discussed. The performance evaluation of CAD system is investigated as well.     

Automatic detection of the carotid lumen axis in B-mode ultrasound images

A new approach is introduced for the automatic detection of the lumen axis of the common carotid artery in B-mode ultrasound images. The image is smoothed using a Gaussian filter and then a dynamic programming scheme extracts the dominant paths of local minima of the intensity and the dominant paths of local maxima of the gradient magnitude with the gradient pointing downwards. Since these paths are possible estimates of the lumen axis and the far wall of a blood vessel, respectively, they are grouped together into pairs. Then, a pattern of two features is computed from each pair of paths and used as input to a linear discriminant classifier in order to select the pair of paths that correspond to the common carotid artery. The estimated lumen axis is the path of local minima of the intensity that belongs to the selected pair of paths. The proposed method is suited to real time processing, no user interaction is required and the number of parameters is minimal and easy to determine.     

Change detection of multispectral remote-sensing images using stationary wavelet transforms and integrated active contours

This article presents a change-detection approach for multispectral remote-sensing images. In our approach, we first exploit a wavelet-based, multi-resolution representation of the difference image. For each resolution scale, the multispectral difference image representation is considered as a 2-D Riemannian manifold embedded into a Riemannian manifold with a higher dimensionality. The integrated active contour (IAC) model is then applied to the multiband difference image representation to obtain a change-detection map at a given scale. In order to select a reasonable scale for each pixel, a measurement of regional homogeneity is defined by comparing the determinant of the metric with the average value of the metric’s determinant. For a single pixel, the final change-detection result is generated by selecting the change map on a reasonable scale. Experimental results obtained on multispectral remote-sensing images confirm the effectiveness of the proposed approach, although the time consumption of the approach is somewhat high. Our experiment achieved total error rates of 3.41%, 1.00%, and 1.95% for three data sets, which are comparable to other prevalent algorithms.     

Deep feature extraction and classification of breast ultrasound images

Controlled despeckling (structure/edges/feature preservation with smoothing the homogeneous areas) is a desired pre-processing step for the design of computer-aided diagnostic (CAD) systems using ultrasound images as the presence of speckle noise masks diagnostically important information making interpretation difficult even for experienced radiologist. For efficiently classifying the breast tumors, the conventional CAD system designs use hand-crafted features. However, these features are not robust to the variations in size, shape and orientation of the tumors resulting in lower sensitivity. Thus deep feature extraction and classification of breast ultrasound images have recently gained attention from research community. The deep networks come with an advantage of directly learning the representative features from the images. However, these networks are difficult to train from scratch if the representative training data is small in size. Therefore transfer learning approach for deep feature extraction and classification of medical images has been widely used. In the present work the performance of four pre-trained convolutional neural networks VGG-19, SqueezeNet, ResNet-18 and GoogLeNet has been evaluated for differentiating between benign and malignant tumor types. From the results of the experiments, it is noted that CAD system design using GoogLeNet architecture for deep feature extraction followed by correlation based feature selection and fuzzy feature selection using ANFC-LH yields highest accuracy of 98.0% with individual class accuracy value of 100% and 96% for benign and malignant classes respectively. For differentiating between the breast tumors, the proposed CAD system design can be utilized in routine clinical environment.

     

A statistical model for contours in images

In this paper, we describe a statistical model for the gradient vector field of the gray level in images validated by different experiments. Moreover, we present a global constrained Markov model for contours in images that uses this statistical model for the likelihood. Our model is amenable to an iterative conditional estimation (ICE) procedure for the estimation of the parameters; our model also allows segmentation by means of the simulated annealing (SA) algorithm, the iterated conditional modes (ICM) algorithm, or the modes of posterior marginals (MPM) Monte Carlo (MC) algorithm. This yields an original unsupervised statistical method for edge-detection, with three variants. The estimation and the segmentation procedures have been tested on a total of 160 images. Those tests indicate that the model and its estimation are valid for applications that require an energy term based on the log-likelihood ratio. Besides edge-detection, our model can be used for semiautomatic extraction of contours, localization of shapes, non-photo-realistic rendering; more generally, it might be useful in various problems that require a statistical likelihood for contours.     

Automatic computation of left ventricle ejection fraction from dynamic ultrasound images

Left Ventricle (LV) Ejection Fraction (EF) is a fundamental parameter for heart function assessment. Being based on border tracing, however, manual computation of EF is time-consuming and extremely prone to inter-and intraobserver variability. In this paper we present an automatic method for EF computation which provides results in agreement with those provided by expert observers. The segmentation strategy consists of two stages: first, the region of interest is identified by means of mimetic criteria; then, the identified region is used for initialization of an active contour based on a variational formulation of level set methods, which provides accurate segmentation of the LV cavity. Volume calculation is then performed according to the conventional Simpson’s rule and, finally, the EF is computed. The text was submitted by the authors in English. Umberto Barcaro is an Associate Professor at the Computer Science Department of Pisa University and an Associate Researcher at the Signals and Images Laboratory of the Institute of Information Science and Technologies of the National Research Council. He teaches Physics and Computer Science Laboratory at the Faculty of Pharmacy, and Signal Theory at the Faculty of Sciences. His research activity regards the automatic analysis of signals and images of clinical interest. In particular, he has studied spontaneous and evoked electroencephalographic and polygraphic signals, and ultrasound images. Davide Moroni (Magenta, 1977), M.Sc. in Mathematics honours degree from the University of Pisa in 2001, dipl. at the Scuola Normale Superiore of Pisa in 2002, PhD in Mathematics at the University of Rome “La Sapienza” in 2006, is a research fellow at the Institute of Information Science and Technologies of the Italian National Research Council, in Pisa. His main interests include geometric modeling, computational topology, image processing and medical imaging. At present he is involved in a number of European research projects working in discrete geometry and dynamic scene analysis. Ovidio Salvetti, director of research at the Institute of Information Science and Technologies (ISTI) of the Italian National Research Council (CNR), in Pisa, is working in the field of theoretical and applied computer vision. His fields of research are image analysis and understanding, pictorial information systems, spatial modeling, and intelligent processes in computer vision. He is a coauthor of four books and monographs and more than three hundred technical and scientific articles; he also possesses ten patents regarding systems and software tools for image processing. He has been a scientific coordinator of several national and European research and industrial projects, in collaboration with Italian and foreign research groups, in the fields of computer vision and high-performance computing for diagnostic imaging. He is member of the editorial boards of the international journals Pattern Recognition and Image Analysis and G. Ronchi Foundation Acts. He is at present the CNR contact person in ERCIM (the European Research Consortium for Informatics and Mathematics) for the Working Group on Vision and Image Understanding, member of IEEE and of the steering committee of a number of EU projects. He is head of the ISTI Signals and Images Laboratory.     

Fully automatic segmentation of breast ultrasound images based on breast characteristics in space and frequency domains

Due to the complicated structure of breast and poor quality of ultrasound images, accurately and automatically locating regions of interest (ROIs) and segmenting tumors are challenging problems for breast ultrasound (BUS) computer-aided diagnosis systems. In this paper, we propose a fully automatic BUS image segmentation approach for performing accurate and robust ROI generation, and tumor segmentation. In the ROI generation step, the proposed adaptive reference point (RP) generation algorithm can produce the RPs automatically based on the breast anatomy; and the multipath search algorithm generates the seeds accurately and fast. In the tumor segmentation step, we propose a segmentation framework in which the cost function is defined in terms of tumor?s boundary and region information in both frequency and space domains. First, the frequency constraint is built based on the newly proposed edge detector which is invariant to contrast and brightness; and then the tumor pose, position and intensity distribution are modeled to constrain the segmentation in the spatial domain. The well-designed cost function is graph-representable and its global optimum can be found. The proposed fully automatic segmentation method is applied to a BUS database with 184 cases (93 benign and 91 malignant), and the performance is evaluated by the area and boundary error metrics. Compared with the newly published fully automatic method, the proposed method is more accurate and robust in segmenting BUS images.     

Fuzzy cluster based neural network classifier for classifying breast tumors in ultrasound images

The performance of supervised classification algorithms is highly dependent on the quality of training data. Ambiguous training patterns may misguide the classifier leading to poor classification performance. Further, the manual exploration of class labels is an expensive and time consuming process. An automatic method is needed to identify noisy samples in the training data to improve the decision making process. This article presents a new classification technique by combining an unsupervised learning technique (i.e. fuzzy c-means clustering (FCM)) and supervised learning technique (i.e. back-propagation artificial neural network (BPANN)) to categorize benign and malignant tumors in breast ultrasound images. Unsupervised learning is employed to identify ambiguous examples in the training data. Experiments were conducted on 178 B-mode breast ultrasound images containing 88 benign and 90 malignant cases on MATLAB® software platform. A total of 457 features were extracted from ultrasound images followed by feature selection to determine the most significant features. Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC) and Mathew's correlation coefficient (MCC) were used to access the performance of different classifiers. The result shows that the proposed approach achieves classification accuracy of 95.862% when all the 457 features were used for classification. However, the accuracy is reduced to 94.138% when only 19 most relevant features selected by multi-criterion feature selection approach were used for classification. The results were discussed in light of some recently reported studies. The empirical results suggest that eliminating doubtful training examples can improve the decision making performance of expert systems. The proposed approach show promising results and need further evaluation in other applications of expert and intelligent systems.     

Segmentation of multiple salient closed contours from real images

Using a saliency measure based on the global property of contour closure, we have developed a segmentation method which identifies smooth closed contours bounding objects of unknown shape in real images. The saliency measure incorporates the Gestalt principles of proximity and good continuity that previous methods have also exploited. Unlike previous methods, we incorporate contour closure by finding the eigenvector with the largest positive real eigenvalue of a transition matrix for a Markov process where edges from the image serve as states. Element (i, j) of the transition matrix is the conditional probability that a contour which contains edge j will also contain edge i. We show how the saliency measure, defined for individual edges, can be used to derive a saliency relation, defined for pairs of edges, and further show that strongly-connected components of the graph representing the saliency relation correspond to smooth closed contours in the image. Finally, we report for the first time, results on large real images for which segmentation takes an average of about 10 seconds per object on a general-purpose workstation.     

Automatic breast cancer palpation robot: WAPRO-4

The robotic system WAPRO-4 capable of automatic palpation for breast cancer was constructed. The aim of this study was to palpate and diagnose breast cancer, without the help of a doctor, to contribute to detecting it in the early stage. The WAPRO-4 system consists of three parts: the measuring instrument, the locomotion unit, and the microcomputer system. The measuring instrument has four sensory rods which depress the mamma by their own weight independently of each other: the depth of their depression into the mamma is measured by linear differential transformers. The versatile industrial robot PANAROBO A 6256C (Matsushita Electric Instrument Corp.) was employed as a locomotion unit to operate the measuring instrument. The microcomputer system (PC-9801E; NEC Corp.) controls the locomotion unit and detects the tumour from the data collection. The software algorithm was constructed so as to detect only tumours while ignoring breathing and the configuration of the chest wall. Clinical tests were performed on 16 patients. The tumours of 15 patients were clearly detected. The tumour of the remaining patient could not be detected because of its small size. These results evidently show the effectiveness of the WAPRO-4 system as well as the capability of group testing of breast cancer by the automatic palpation system. The clinical tests demonstrated the need to improve the system to detect smaller tumours.     

Automatic analysis of moving images

Cine film and videotape are used to record a variety of natural processes in biology, medicine, meteorology, etc. This paper describes a system which detects and tracks moving objects from these records to obtain meaningful measures of their movements, such as linear and angular velocities. Features of the system are as follows. 1) In order to detect moving objects that are usually blurred, temporal differences of gray values (differences between consecutive frames) are used to separate moving objects from stationary objects, in addition to spatial differences of gray values. 2) The results of previous frames are used to guide feature extraction process of the next frame so that efficient processing of moving pictures which consists of a large number of frames is possible. 3) Uncertain parts in the current frame, such as occluded objects, are deduced using information of previous frames. 4) Misinterpreted or unknown parts in previous frames are reanalyzed using the results of later frames where those parts could be found.     

Automatic breast tumor detection in ABVS images based on convolutional neural network and superpixel patterns

Breast cancer is one of the most common female malignancies, as well as the second leading cause of mortality for women. Early detection and treatment can dramatically decrease the mortality rate. Recently, automated breast volume scanner (ABVS) has become one of the most frequently used diagnose methods for breast tumor screening because of its operator-independent and reproducible advantages. However, it is a challenging job to obtain the tumors’ accurate locations and shapes by reviewing hundreds of ABVS slices. In this paper, a novel computer-aided detection (CADe) system is developed to reduce clinicians’ reading time and improve the efficiency. The CADe system mainly contains three parts: tumor candidate acquisition, false-positive reduction and tumor segmentation. Firstly, a local phase-based approach is built to obtain breast tumor candidates for further recognition. Subsequently, a convolutional neural network (CNN) is applied to reduce false positives (FPs). The introduction of CNN can help to avoid complicated feature extraction as well as elevate the accuracy and efficiency. Finally, superpixel-based segmentation is used to outline the breast tumor. Here, superpixel-based local binary pattern (SLBP) is proposed to assist the segmentation, which improves the performance. The methods were evaluated on a clinical ABVS dataset whose abnormal cases were manually labeled by an experienced radiologist. The experiment results were mainly composed of two parts. At the FP reduction stage, the proposed CNN achieved 100% and 78.12% sensitivity with FPs/case of 2.16 and 0. At the segmentation stage, our SLBP obtained 82.34% true positive, 15.79% false positive and 83.59% Dice similarity. In summary, the proposed CADe system demonstrated promising potential to detect and outline breast tumors in ABVS images.