Automatic detection of brain contours in MRI data sets

A software procedure is presented for fully automated detection of brain contours from single-echo 3-D MRI data, developed initially for scans with coronal orientation. The procedure detects structures in a head data volume in a hierarchical fashion. Automatic detection starts with a histogram-based thresholding step, whenever necessary preceded by an image intensity correction procedure. This step is followed by a morphological procedure which refines the binary threshold mask images. Anatomical knowledge, essential for the discrimination between desired and undesired structures, is implemented in this step through a sequence of conventional and novel morphological operations, using 2-D and 3-D operations. A final step of the procedure performs overlap tests on candidate brain regions of interest in neighboring slice images to propagate coherent 2-D brain masks through the third dimension. Results are presented for test runs of the procedure on 23 coronal whole-brain data sets, and one sagittal whole-brain data set. Finally, the potential of the technique for generalization to other problems is discussed, as well as limitations of the technique     

Estimation and detection of myocardial tags in MR image withoutuser-defined myocardial contours

Magnetic resonance (MR) tagging has been shown to be a useful technique for noninvasively measuring the deformation of an in vivo heart. An important step in analyzing tagged images is the identification of tag lines in each image of a cine sequence. Most existing tag identification algorithms require user defined myocardial contours. Contour identification, however, is time consuming and requires a considerable amount of user intervention. In this paper, a new method for identifying tag lines, which we call the ML/MAP method, is presented that does not require user defined myocardial contours. The ML/MAP method is composed of three stages. First, a set of candidate tag line centers is estimated across the entire region-of-interest (ROI) with a snake algorithm based on a maximum-likelihood (ML) estimate of the tag center. Next, a maximum a posteriori (MAP) hypothesis test is used to detect the candidate tag centers that are actually part of a tag line. Finally, a pruning algorithm is used to remove any detected tag line centers that do not meet a spatio-temporal continuity criterion. The ML/MAP method is demonstrated on data from ten in vivo human hearts.     

Hough transform detection of the longitudinal fissure in tomographic head images

A technique is presented for automatic detection of the longitudinal fissure in tomographic scans of the brain. The technique utilizes the planar nature of the fissure and is a three-dimensional variant of the Hough transform principle. Algorithmic and computational aspects of the technique are discussed. Results and performance on coronal and transaxial magnetic resonance data show that the algorithm is robust with respect to variations in image contrast in the data and to slight anatomic anomalies. A crucial resolution requirement in the data for accurate parameter estimations is a sufficient number of slices covering the whole brain. The Sobel magnitude edge operator, used for preprocessing, proved adequate for magnetic resonance scans with positive and negative brain/cerebrospinal fluid contrast.     

Automatic detection of oil spills in ERS SAR images

The authors present algorithms for the automatic detection of oil spills in SAR images. The developed framework consists of first detecting dark spots in the image, then computing a set of features for each dark spot, before the spot is classified as either an oil slick or a “lookalike” (other oceanographic phenomena which resemble oil slicks). The classification rule is constructed by combining statistical modeling with a rule-based approach. Prior knowledge about the higher probability for the presence of oil slicks around ships and oil platforms is incorporated into the model. In addition, knowledge about the external conditions like wind level and slick surroundings are taken into account. The presented algorithms are tested on 84 SAR images. The algorithm can discriminate between oil slicks and lookalikes with high accuracy, 94% of the oil slicks and 99% of the lookalikes were correctly classified     

Bayesian estimation of ventricular contours in angiographic images

A method for left ventricular contour determination in digital angiographic images is presented. The problem is formulated in a Bayesian framework, adopting as the estimation criterion the maximum a posterior probability (MAP). The true contour is modeled as a one-dimensional noncausal Gauss-Markov random field and the observed image is described as the superposition of an ideal image (deterministic function of the real contour) with white Gaussian noise. The proposed algorithm estimates simultaneously the contour and the model parameters by implementing an adaptive version of the iterated conditional modes algorithm. The convergence of this scheme is proved and its performance evaluated on both synthetic and real angiographic images. The method exhibits robustness against image artifacts and the contours obtained are considered good by expert clinicians. Being completely data-driven and fast, the proposed algorithm is suitable for routine clinical use.     

Automatic detection of breast nodule in the ultrasound images using CNN

Breast cancer is the most common cancer among women worldwide.Ultrasound is widely used as a harmless test for early breast cancer screening.The ultrasound network(USNet) model is presented.It is an improved object detection model specifically for breast nodule detection on ultrasound images.USNet improved the backbone network,optimized the generation of feature maps,and adjusted the loss function.Finally,USNet trained with real clinical data.The evaluation results show that the trained model has strong nodule detection ability.The mean average precision(mAP) value can reach 0.734 9.The nodule detection rate is 95.11%,and the in situ cancer detection rate is 79.65%.At the same time,detection speed can reach 27.3 frame per second(FPS),and the video data can be processed in real time.     

Automatic detection of ship target and motion direction in visual images

In this article, we focus on automatic ship target detection in visual images. The proposed approach consists of two stages. At the first stage, emphasis is placed on sea background suppression. A pre-processing technique is studied based on mean-shift smoothing algorithm. In this process, the improvement is that we associate the range bandwidth of mean-shift with local image properties, thus achieve the purpose of suppressing sea background while protecting ship target. At the second stage, a hierarchical ship target detection approach is developed. To begin with, region-of-interest (ROI) of ship target is coarsely identified via salient edge regions extraction. Then main body of ship target is located by projection, prior spatial structure information of ship target is used for further ROI refinement. After that, a post-processing procedure based on colour features is presented to obtain final detection results. One advantage of the proposed method is that motion direction of the ship target can also be estimated, which could provide important information for ship target tracking and monitoring. Tested on real visual ship target images supplied by the co-operator, experimental results show that the proposed algorithm can effectively detect big ship targets and its motion direction with various backgrounds in visual images.     

Automatic detection of prohibited items with small size in X-ray images

In this paper, we focus on the detection of prohibited items with small size, and establish an automatic detection model based on feature fusion single shot multibox detector (FSSD) architecture. Two modifications are carried out to improve the detection accuracy. Firstly, the semantic enrichment module (SEM) with dilated convolution is applied to extract the low level feature with strong semantic information. Secondly, a residual module (Res) with residual blocks is added in the multibox detection architecture in order to extract more adequate features for target detection. The simulation results have demonstrated a better performance of the proposed detection model for prohibited items with small size compared with the state-of-the-arts.     

Automatic bootstrapping and tracking of object contours

A new fully automatic object tracking and segmentation framework is proposed. The framework consists of a motion-based bootstrapping algorithm concurrent to a shape-based active contour. The shape-based active contour uses finite shape memory that is automatically and continuously built from both the bootstrap process and the active-contour object tracker. A scheme is proposed to ensure that the finite shape memory is continuously updated but forgets unnecessary information. Two new ways of automatically extracting shape information from image data given a region of interest are also proposed. Results demonstrate that the bootstrapping stage provides important motion and shape information to the object tracker. This information is found to be essential for good (fully automatic) initialization of the active contour. Further results also demonstrate convergence properties of the content of the finite shape memory and similar object tracking performance in comparison with an object tracker with unlimited shape memory. Tests with an active contour using a fixed-shape prior also demonstrate superior performance for the proposed bootstrapped finite-shape-memory framework and similar performance when compared with a recently proposed active contour that uses an alternative online learning model.     

城市街区星载光学遥感图像车辆目标自动检测方法

针对星载光学遥感图像城市街区复杂背景问题,提出一种车辆目标自动检测方法.首先,利用场景中植被背景的物理属性,通过多光谱波段抑制场景中的植被背景,然后,在分析城市街区地物形态反射率特性的基础上,利用全色波段并结合二值形态学方法抑制场景中的建筑物,最后,引入著名的RX算法对抑制后的图像进行车辆目标检测.将文中提出的方法应用于实际Quickbird影像的车辆目标检测,结果表明所提出的方法具有鲁棒性强,执行效率高,不需要人工辅助等方面的特点,可用于城市街区车辆目标的自动检测.     

Automatic extraction and tracking of the tongue contours

Computerized analysis of the tongue surface movement can provide valuable information to speech and swallowing research. Ultrasound technology is currently the most attractive modality for the tongue imaging mainly because of its high video frame rate. However, problems with ultrasound imaging, such as noise and echo artifacts, refractions, and unrelated reflections pose significant challenges for computer analysis of the tongue images and hence specific methods must be developed. This paper presents a system that is developed for automatic extraction and tracking of the tongue surface movements from ultrasound image sequences. The ultrasound images are supplied by the head and transducer support system (HATS), which was developed in order to fix the head and support the transducer under the chin in a known position without disturbing speech. In this work, we propose a novel scheme for the analysis of the tongue images using deformable contours. We incorporate novel mechanisms to 1) impose speech related constraints on the deformations; 2) perform spatiotemporal smoothing using a contour postprocessing stage; 3) utilize optical flow techniques to speed up the search process; and 4) propagate user supplied information to the analysis of all image frames. We tested the system's performance qualitatively and quantitatively in consultation with speech scientists. Our system produced contours that are within the range of manual measurement variations. The results of our system are extremely encouraging and the system can be used in practical speech and swallowing research in the field of otolaryngology.     

Automatic optic disc detection from retinal images by a line operator

Under the framework of computer-aided eye disease diagnosis, this paper presents an automatic optic disc (OD) detection technique. The proposed technique makes use of the unique circular brightness structure associated with the OD, i.e., the OD usually has a circular shape and is brighter than the surrounding pixels whose intensity becomes darker gradually with their distances from the OD center. A line operator is designed to capture such circular brightness structure, which evaluates the image brightness variation along multiple line segments of specific orientations that pass through each retinal image pixel. The orientation of the line segment with the minimum/maximum variation has specific pattern that can be used to locate the OD accurately. The proposed technique has been tested over four public datasets that include 130, 89, 40, and 81 images of healthy and pathological retinas, respectively. Experiments show that the designed line operator is tolerant to different types of retinal lesion and imaging artifacts, and an average OD detection accuracy of 97.4% is obtained.     

基于卷积神经网络的CT图自动检测深度学习

针对肺结节良恶性诊断的难度,采用自定义卷积神经网络对其进行建模分析。通过多次实验分析,构建得到了可以实现7层肺结节检测的卷积神经网络模型,在每层中都含有训练参数,得到13×13的卷积核。测试肺结节的算法通过4个指标进行评价,分别为准确性和特异性、敏感性和假阳率。PndCnn-7参数优化结果得到,学习率lr介于[0. 4,1. 05]范围内,需要处理的批次达到最少0. 75。13×13卷积核能够实现网络的快速收敛,并且不会引起震荡的现象。当epoch增大至50,则会引起误差的明显减小,使网络达到良好的收敛状态。     

Automatic ventricular cavity boundary detection from sequential ultrasound images using simulated annealing

An automatic algorithm has been developed for high-speed detection of cavity boundaries in sequential 2-D echocardiograms using an optimization algorithm called simulated annealing (SA). The algorithm has three stages. (1) A predetermined window of size nxm is decimated to size n'xm' after low-pass filtering. (2) An iterative radial gradient algorithm is employed to determine the center of gravity (CG) of the cavity. (3) 64 radii which originate from the CG defined in stage 2 are bounded by the high-probability region. Each bounded radius is defined as a link in a 1-D, 64-member cyclic Markov random field. This algorithm is unique in that it compounds spatial and temporal information along with a physical model in its decision rule, whereas most other algorithms base their decisions on spatial data alone. This is the first implementation of a relaxation algorithm for edge detection in echocardiograms. Results attained using this algorithm on real data have been highly encouraging.     

Scale space analysis and active contours for omnidirectional images.

A new generation of optical devices that generate images covering a larger part of the field of view than conventional cameras, namely catadioptric cameras, is slowly emerging. These omnidirectional images will most probably deeply impact computer vision in the forthcoming years, provided that the necessary algorithmic background stands strong. In this paper, we propose a general framework that helps define various computer vision primitives. We show that geometry, which plays a central role in the formation of omnidirectional images, must be carefully taken into account while performing such simple tasks as smoothing or edge detection. Partial differential equations (PDEs) offer a very versatile tool that is well suited to cope with geometrical constraints. We derive new energy functionals and PDEs for segmenting images obtained from catadioptric cameras and show that they can be implemented robustly using classical finite difference schemes. Various experimental results illustrate the potential of these new methods on both synthetic and natural images.     

How to compute the difference between tomographic images

An algorithm for estimating the difference between two tomographic images is proposed if the two data vectors are obtained in nonoverlapping time intervals. The algorithm takes advantage of statistical independence of the two vectors. The results are significantly different from the traditional approach in which the two images are reconstructed separately and then subtracted.     

Automatic scoliosis detection based on local centroids evaluationon moire topographic images of human backs

This paper presents a technique for automating human scoliosis detection by computer based on moiré topographic images of human backs. Scoliosis is a serious disease often suffered by teenagers. For prevention, screening is performed at schools in Japan employing a moiré method in which doctors inspect moiré images of subjects' backs visually. The inspection of a large number of moiré images collected by the school screening causes exhaustion of doctors and leads to misjudgment. Computer-aided diagnosis of scoliosis has, therefore, been requested eagerly by orthopedists. To automate the inspection process, unlike existent three-dimensional techniques, displacement of local centroids is evaluated two-dimensionally between the left-hand side and the right-hand side of the moiré images in the present technique. The technique was applied to real moiré images to draw a distinction between normal and abnormal cases. According to the leave-out method, the entire 120 image data (60 normal and 60 abnormal) were separated into three data sets. The linear discriminant function based on Mahalanobis distance was defined on the two-dimensional feature space employing one of the data sets containing 40 moiré images and classified 80 images in the remaining two sets. The technique finally achieved the average classification rate of 88.3%.     

Self-crossing detection and location for parametric active contours

Active contours are very popular tools for video tracking and image segmentation. Parameterized contours are used due to their fast evolution and have become the method of choice in the Sobolev context. Unfortunately, these contours are not easily adaptable to topological changes, and they may sometimes develop undesirable loops, resulting in erroneous results. To solve such topological problems, one needs an algorithm for contour self-crossing detection. We propose a simple methodology via simple techniques from differential topology. The detection is accomplished by inspecting the total net change of a given contour's angle, without point sorting and plane sweeping. We discuss the efficient implementation of the algorithm. We also provide algorithms for locating crossings by angle considerations and by plotting the four-connected lines between the discrete contour points. The proposed algorithms can be added to any parametric active-contour model. We show examples of successful tracking in real-world video sequences by Sobolev active contours and the proposed algorithms and provide ideas for further research.     

Automatic pupillometry from digital images

Determination of two-dimensional characteristics of the anterior surface of the eye is becoming increasingly important in modern optometry and ophthalmology practice. In particular, accurate estimation of the pupil size and centration is crucial in customized refractive surgery, corneal transplantation, and advanced contact lens fitting. The pupil parameters change under different lighting conditions so they often need to be related to some fixed reference such as the limbus outline. However, current commercial pupillometers do not estimate limbus position. We present a novel algorithm for automatic extraction of pupil parameters from digital images that takes the relative limbus information into account. The algorithm utilizes several customized image processing techniques that form a robust procedure which performs well for a wide range of clinical images. We apply the developed algorithm to images obtained by a standard digital camera, and specialized ophthalmic instruments such as a wavefront sensor and a high-speed imaging system.