While level sets have demonstrated a great potential for 3D medicalimage segmentation, their usefulness has been limited by two problems. First, 3D level sets are relatively slow to compute. Second, their formulation...
详细信息
While level sets have demonstrated a great potential for 3D medicalimage segmentation, their usefulness has been limited by two problems. First, 3D level sets are relatively slow to compute. Second, their formulation usually entails several free parameters which can be very difficult to correctly tune for specific applications. This paper presents a tool for 3D segmentation that relies on level-set surface models computed at interactive rates on commodity graphics cards (CPUs). The interactive rates for solving the level-set PDE give the user immediate feedback on the parameter settings, and thus users can tune three separate parameters and control the shape of the model in real time. We have found that this interactivity enables users to produce good, reliable segmentation, as supported by qualitative and quantitative results.
Through an understanding of the image formation process, diagnostically important facts about the internal structure and composition of pigmented skin lesions can be derived from their colour images. A physics-based m...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)9783540442240
Through an understanding of the image formation process, diagnostically important facts about the internal structure and composition of pigmented skin lesions can be derived from their colour images. A physics-based model of tissue colouration provides a cross-reference between image colours and the underlying histological parameters. It is constructed by computing the spectral composition of light remitted from the skin given parameters specifying its structure and optical properties. The model is representative of all the normal human skin colours. irrespective of racial origin, age or gender. Abnormal skin colours do not conform to this model and thus can be detected. Once the model is constructed, for each pixel in a colour image its histological parameters are computed from the model. Represented as images, these 'parametric maps' show the concentration of dermal and epidermal melanin, blood and collagen thickness across the imaged skin as well as locations where abnormal colouration exists. In a clinical study the parametric maps were used by a clinician to detect the presence of malignant melanoma in a set of 348 pigmented lesions imaged using a commercial device, the SIAscope. Logistic regression identified the presence of melanin in the dermis, the abnormal distribution of blood within the lesion and the lesion size as the most diagnostically informative features. Classification based on these features showed 80.1% sensitivity and 82.7% specificity in melanoma detection. (C) 2003 Elsevier B.V. All rights reserved.
We present a systematic approach to generate pixel-wise parametric maps from contrast-enhanced MR myocardial perfusion images. A surface coil intensity correction algorithm is used to compensate the myocardial intensi...
详细信息
Previous research on Trans-urethral Ultrasound (TUUS) imaging has shown promise that TUUS will become a viable new intra-operative tool. Prior work focused on the processing of TUUS data in order to obtain useful clin...
详细信息
ISBN:
(数字)9783540399032
ISBN:
(纸本)9783540204640
Previous research on Trans-urethral Ultrasound (TUUS) imaging has shown promise that TUUS will become a viable new intra-operative tool. Prior work focused on the processing of TUUS data in order to obtain useful clinical information, however intra-operative imaging issues (real-time feedback) have not been fully addressed. This paper describes a unique framework for efficient processing which can be used for intra-operative imaging. The methods describe a segmentation pipeline which meet the requirements of intra-operative imaging in prostate brachytherapy. The implementation of the process is described and the process is evaluated for efficiency and accuracy.
In this paper, an algorithm for the semiautomatic segmentation of medicalimage series is proposed by combining the live wire algorithm and the active contour model. Firstly the accurate segmented results of one or mo...
详细信息
ISBN:
(纸本)081945138X
In this paper, an algorithm for the semiautomatic segmentation of medicalimage series is proposed by combining the live wire algorithm and the active contour model. Firstly the accurate segmented results of one or more slices in a medicalimage series are obtained by the livewire algorithm and the watershed transform. Based on the segmentation of previous slices, the computer will segment the nearby slice using the modified active contour model automatically. To make full use of the correlative information between contiguous slices, we introduce a gay-scale model to the boundary points of the active contour model to record the local region characters of the desired object in the segmented slice and replace the external energy of the traditional active contour model with the energy decided by the likelihood of the gray-scale model. Moreover we introduce the active region concept of the snake to improve the segmentation accuracy. Experiment shows that our algorithm can obtain the boundary of the desired object from a series of medicalimages quickly and reliably with only little user intervention.
In this paper, we propose a hybrid similarity measure for 2D-3D image registration that is a weighted combination of an intensity-based image similarity measure and a point-based measure incorporating a single fiducia...
详细信息
In this paper, we propose a hybrid similarity measure for 2D-3D image registration that is a weighted combination of an intensity-based image similarity measure and a point-based measure incorporating a single fiducial marker. We evaluate its accuracy and robustness using gold-standard clinical spine image data. The use of one fiducial marker substantially improves registration accuracy and robustness.
Mutual Information is perhaps the most widely used multimodality image registration method. A crucial step in mutual information is the estimation of the probability density function (pdf). In most cases, the Parzen w...
详细信息
This paper proposes methods for automated extraction of emphysematous lesions from three-dimensional (3-D) CT images and quantitative evaluation of their distribution pattern. We employ 3-D image processing techniques...
详细信息
This paper proposes methods for automated extraction of emphysematous lesions from three-dimensional (3-D) CT images and quantitative evaluation of their distribution pattern. We employ 3-D image processing techniques on computer-aided diagnosis of pulmonary emphysema. Emphysematous lesions are automatically extracted by a region growing method. To analyze spatial distribution of the detected low-attenuation areas, we examine the relations between emphysematous lesions and bronchi or pulmonary blood vessels using Euclidean distance transformation. Experimental results show that the methods could be used to extract emphysematous lesions appropriately and could quantitatively evaluate their distribution pattern.
We present a computational approach to support gestational age determination of premature newborns. This knowledge is fundamental to guide postnatal treatment and increase survival chances. However, current approaches...
详细信息
ISBN:
(数字)9783540399032
ISBN:
(纸本)9783540204640
We present a computational approach to support gestational age determination of premature newborns. This knowledge is fundamental to guide postnatal treatment and increase survival chances. However, current approaches are both invasive and do not generate precise results. This paper presents an original and non-invasive method to determine the gestational age based on information supplied by plantar surface images. These images present many details and patterns but to date have not received attention from the image processing community. We provide a computational tool with suitable facilities to allow the image analysis, either automatically or user-driven. Besides its importance to Neonatology, this work represents a contribution of computer Vision concepts to medical Imaging. The experimental results confirm the relationship between the plantar surface features and newborn gestational age.
Intraoperative brain deformation is one of the most contributing factors to the inaccuracy of image-guided neurosurgery systems. One option for correcting for this deformation is to acquire 3D ultrasound images during...
详细信息
暂无评论