Narrow Results

Automatic retinal image registration is still a great challenge in computer aided diagnosis and screening system. In this paper, a new retinal image registration method is proposed based on the combination of blood vessel segmentation and scale invariant feature transform (SIFT) feature. The algorithm includes two stages: retinal image segmentation and registration. In the segmentation stage, the blood vessel is segmented by using the guided filter to enhance the vessel structure and the bottom-hat transformation to extract blood vessel. In the registration stage, the SIFT algorithm is adopted to detect the feature of vessel segmentation image, complemented by using a random sample consensus (RANSAC) algorithm to eliminate incorrect matches. We evaluate our method from both segmentation and registration aspects. For segmentation evaluation, we test our method on DRIVE database, which provides manually labeled images from two specialists. The experimental results show that our method achieves 0.9562 in accuracy (Acc), which presents competitive performance compare to other existing segmentation methods. For registration evaluation, we test our method on STARE database, and the experimental results demonstrate the superior performance of the proposed method, which makes the algorithm a suitable tool for automated retinal image analysis.

With the rapid development of multi-detector computed tomography (MDCT) that results in improving the temporal and spatial resolution of patient data, clinical use of computed tomographic angiography (CTA) is increasing. Vessel segmentation can be challenging in CTA, but is needed for isolation of vascular structures. In this paper, a novel method for computation of vesselness in CTA images is presented, including a CTA transfer function prior to the vesselness computation for reducing the artifacts caused by the false-positive responses of a Hessian-based line filter, as well as a hierarchical structure, called MIP-volume pyramid, for accelerating the computation of vesselness. Using the computed vesselness, we present an interactive segmentation method for each individual vessel by applying a vesselness speed function in a fast marching level set method. Our new method was shown to provide an effective and efficient way that allows vesselness to be applied to large CTA images. This method has been implemented successfully in CTA vessel segmentation and evaluation.

Separation of arteries and veins in the cerebral cortex is of significant importance in the studies of cortical hemodynamics, such as the changes of cerebral blood flow, perfusion or oxygen concentration in arteries and veins under different pathological and physiological conditions. Yet the cerebral vessel segmentation and vessel-type separation are challenging due to the complexity of cortical vessel characteristics and low spatial signal-to-noise ratio. In this work, we presented an effective full-field method to differentiate arteries and veins in cerebral cortex using dual-modal optical imaging technology including laser speckle imaging (LSI) and optical intrinsic signals (OIS) imaging. The raw contrast images were acquired by LSI and processed with enhanced laser speckle contrast analysis (eLASCA) algorithm. The vascular pattern was extracted and segmented using region growing algorithm from the eLASCA-based LSI. Meanwhile, OIS images were acquired alternatively with 630 and 870 nm to obtain an oxyhemoglobin concentration map over cerebral cortex. Then the separation of arteries and veins was accomplished by Otsu threshold segmentation algorithm based on the OIS information and segmentation of LSI. Finally, the segmentation and separation performances were assessed using area overlap measure (AOM). The segmentation and separation of cerebral vessels in cortical optical imaging have great potential applications in full-field cerebral hemodynamics monitoring and pathological study of cerebral vascular diseases, as well as in clinical intraoperative monitoring.

Laser speckle contrast imaging (LSCI) is a noninvasive, label-free technique that allows real-time investigation of the microcirculation situation of biological tissue. High-quality microvascular segmentation is critical for analyzing and evaluating vascular morphology and blood flow dynamics. However, achieving high-quality vessel segmentation has always been a challenge due to the cost and complexity of label data acquisition and the irregular vascular morphology. In addition, supervised learning methods heavily rely on high-quality labels for accurate segmentation results, which often necessitate extensive labeling efforts. Here, we propose a novel approach LSWDP for high-performance real-time vessel segmentation that utilizes low-quality pseudo-labels for nonmatched training without relying on a substantial number of intricate labels and image pairing. Furthermore, we demonstrate that our method is more robust and effective in mitigating performance degradation than traditional segmentation approaches on diverse style data sets, even when confronted with unfamiliar data. Importantly, the dice similarity coefficient exceeded 85% in a rat experiment. Our study has the potential to efficiently segment and evaluate blood vessels in both normal and disease situations. This would greatly benefit future research in life and medicine.

Retinal images have been widely used by clinicians for early diagnosis of ocular diseases. However, the quality of retinal images is often clinically unsatisfactory due to eye lesions and imperfect imaging processes. The non-uniform or poor illumination on retinal images hinders the pathological information and further impairs the diagnosis of ophthalmologists. To solve these issues, we propose a deep learning-based retinal image non-uniform illumination removal called NuI-Go, which combines the powerful capabilities of convolutional neural networks (CNNs) with the characteristics of retinal images with non-uniform illumination. Concretely, the proposed NuI-Go consists of three Recursive non-local encoder–decoder residual blocks (NEDRBs) for progressively enhancing the degraded retinal images. Each NEDRB contains a feature encoder module that captures the hierarchical feature representations, a non-local context module that models the context information, and a feature decoder module that recovers the details and spatial dimension. Extensive experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on both synthetic dataset and real retinal images. Besides, we further demonstrate the advantages of the proposed method for improving the performance of retinal vessel segmentation.

We present several methods for the analysis and visualization of vessel systems in 3D CT and MR image datasets, including segmentation, skeletonization, topological and morphometrical analysis methods. We describe a number of clinical and medical applications, including quantitative vessel diagnostic, automatic detection of aneurysms, liver surgery planning, and simulation of vascular trees. The applications are implemented as software prototypes based on a research and development platform for medical imaging and rapid application prototyping. Most of the applications have been evaluated under clinical conditions.