Novel anti-VEGFR2 antibody-conjugated nanobubbles for targeted ultrasound molecular imaging in a rabbit VX2 hepatic tumor model.

Nanobubbles (NBs), as ultrasound contrast agents, possess the potential for clinical applications in targeted ultrasound molecular imaging due to their small diameters and the specific molecular markers attached. Previous research studies mainly focused on the tumor-specific recruitment capability or drug carriers based on subcutaneous tumor models. In clinical trials, orthotopic tumor models are considered more clinically relevant and better predictive models for assessing drug efficacy compared to standard subcutaneous models. Here, we first prepared uniform-sized NBs with a soft chitosan-lipid membrane containing perfluoropropane gas and then anti-VEGFR2 antibodies were incorporated into NB membranes in order to achieve targeting ability toward tumor angiogenesis. The results of physicochemical characterization (the average size of 260.9 ± 3.3 nm and a PDI of 0.168 ± 0.036, n = 3) indicated that the targeted nanobubbles (tNBsv) have a spherical morphology and a vacant core. In vitro experiments found that the contrast enhancement abilities of tNBsv are similar to those of commercial SonoVue. In in vivo experiments, the orthotopic model of the rabbit VX2 hepatic tumor was used to evaluate the targeted binding ability of tNBsv toward tumor angiogenesis. Ultrasound sonograms revealed that tNBsv achieved the peak intensity of ultrasound imaging enhancement in the region of peripheral vasculature of VX2 tumors over non-targeted NBs or SonoVue, and the imaging time was longer than that of the other two. Ex vivo fluorescence imaging and examination using a confocal laser scanning microscope further verified that tNBsv were capable of binding to tumor angiogenesis. These results from our studies suggested that tNBsv are useful to develop an ultrasound imaging probe to evaluate anti-angiogenic cancer therapy by monitoring tumor angiogenesis.

Automatic interictal epileptiform discharge (IED) detection based on convolutional neural network (CNN).

Clinical diagnosis of epilepsy significantly relies on identifying interictal epileptiform discharge (IED) in electroencephalogram (EEG). IED is generally interpreted manually, and the related process is very time-consuming. Meanwhile, the process is expert-biased, which can easily lead to missed diagnosis and misdiagnosis. In recent years, with the development of deep learning, related algorithms have been used in automatic EEG analysis, but there are still few attempts in IED detection. This study uses the currently most popular convolutional neural network (CNN) framework for EEG analysis for automatic IED detection. The research topic is transferred into a 4-labels classification problem. The algorithm is validated on the long-term EEG of 11 pediatric patients with epilepsy. The computational results confirm that the CNN-based model can obtain high classification accuracy, up to 87%. The study may provide a reference for the future application of deep learning in automatic IED detection.

A thermosensitive Pickering gel emulsion with a high oil-water ratio for long-term X-ray imaging and permanent embolization of arteries.

Iodized oil has an excellent X-ray imaging effect, but it shows poor embolization performance. When used as an embolic agent, it is easily washed off by the blood flow and eliminated from the body. Therefore, it is essential to use iodized oil in combination with solid embolic agents such as gelatin sponge or to perform multiple embolization procedures to achieve the therapeutic effect. In the present study, a poly(N-isopropyl acrylamide)-co-acrylic acid (PNCAA) temperature-sensitive nanogel was synthesized by emulsion polymerization; the nanogel was then emulsified with iodized oil to prepare a thermosensitive iodized oil Pickering gel emulsion (TIPE). The oil-water (O/W) ratio of an O/W emulsion system can reach 4 : 6. When injected into the body, TIPE transforms into a nonflowing coagulated state at physiological temperature; the iodized oil is locked in the emulsion structure, thereby achieving local embolization and continuous imaging effects, which not only retain the X-ray imaging effect of the iodized oil but also improve its embolization effect. Subsequently, we further evaluated renal artery embolization in a normal rabbit renal artery model, and the results showed that TIPE shows a long-term conformal embolization performance and excellent long-term X-ray imaging ability.

Temperature sensitive nanogels for real-time imaging during transcatheter arterial embolization.

Several vascular embolization materials are commonly used in clinical practice, however, having application defects of varying degrees, such as poor intraoperative imaging and easy recanalization of embolized blood vessels, they are challenging for application during Transcatheter arterial embolization (TAE). Thus, an intraoperative visible vascular embolization material with good embolization effect and biocompatibility can improve transcatheter arterial embolization clinical efficacy to some extent. Our study aimed to synthesize a novel vascular embolization material that can achieve complete embolization of arterial trunks and peripheral vessels, namely poly (N-isopropyl acrylamide)-co-acrylic acid nanogel (NIPAM-co-AA). Iohexol 200 mg/mL was co-assembled with 7 wt% NIPAM-co-AA nanogel to create an intelligent thermosensitive radiopaque nanogel (INCA), which achieves a good intraoperative imaging effect and is convenient for transcatheter arterial bolus injection due to its good fluidity and temperature-sensitive sol-gel phase transition. The normal rabbit kidney embolism model further confirmed that INCA could effectively use Digital subtraction angiography (DSA) to achieve intraoperative imaging, and real-time monitoring of the embolization process could avoid mis-embolization and leakage. Meanwhile, in a 42-day study, INCA demonstrated an excellent embolization effect on the right renal artery of New Zealand white rabbits, with no vascular recanalization and ischemic necrosis and calcification remaining. As a result, this radiopaque thermosensitive nanogel has the potential to be an intelligent thermosensitive medical vascular embolization material, providing dual benefits in TAE intraoperative imaging and long-term postoperative embolization while effectively addressing the shortcomings and challenges of commonly used clinical vascular embolization agents.

Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model.

Prostate cancer remains a major health concern among elderly men. Deep learning is a state-of-the-art technique for MR image-based prostate cancer diagnosis, but one of major bottlenecks is the severe lack of annotated MR images. The traditional and Generative Adversarial Network (GAN)-based data augmentation methods cannot ensure the quality and the diversity of generated training samples. In this paper, we have proposed a novel GAN model for synthesis of MR images by utilizing its powerful ability in modeling the complex data distributions. The proposed model is designed based on the architecture of deep convolutional GAN. To learn the more equivariant representation of images that is robust to the changes in the pose and spatial relationship of objects in the images, the capsule network is applied to replace CNN used in the discriminator of regular GAN. Meanwhile, the least squares loss has been adopted for both the generator and discriminator in the proposed GAN to address the vanishing gradient problem of sigmoid cross entropy loss function in regular GAN. Extensive experiments are conducted on the simulated and real MR images. The results demonstrate that the proposed capsule network-based GAN model can generate more realistic and higher quality MR images than the compared GANs. The quantitative comparisons show that among all evaluated models, the proposed GAN generally achieves the smallest Kullback-Leibler divergence values for image generation task and provides the best classification performance when it is introduced into the deep learning method for image classification task.

Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising.

Magnetic resonance (MR) images are often corrupted by Rician noise which degrades the accuracy of image-based diagnosis tasks. The nonlocal means (NLM) method is a representative filter in denoising MR images due to its competitive denoising performance. However, the existing NLM methods usually exploit the gray-level information or hand-crafted features to evaluate the similarity between image patches, which is disadvantageous for preserving the image details while smoothing out noise. In this paper, an improved nonlocal means method is proposed for removing Rician noise in MR images by using the refined similarity measures. The proposed method firstly extracts the intrinsic features from the pre-denoised image using a shallow convolutional neural network named Laplacian eigenmaps network (LEPNet). Then, the extracted features are used for computing the similarity in the NLM method to produce the denoised image. Finally, the method noise of the denoised image is utilized to further improve the denoising performance. Specifically, the LEPNet model is composed of two cascaded convolutional layers and a nonlinear output layer, in which the Laplacian eigenmaps are employed to learn the filter bank in the convolutional layers and the Leaky Rectified Linear Unit activation function is used in the final output layer to output the nonlinear features. Due to the advantage of LEPNet in recovering the geometric structure of the manifold in the low-dimension space, the features extracted by this network can facilitate characterizing the self-similarity better than the existing NLM methods. Experiments have been performed on the BrainWeb phantom and the real images. Experimental results demonstrate that among several compared denoising methods, the proposed method can provide more effective noise removal and better details preservation in terms of human vision and such objective indexes as peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).

PCANet based nonlocal means method for speckle noise removal in ultrasound images.

Speckle reduction remains a critical issue for ultrasound image processing and analysis. The nonlocal means (NLM) filter has recently attached much attention due to its competitive despeckling performance. However, the existing NLM methods usually determine the similarity between two patches by directly utilizing the gray-level information of the noisy image, which renders it difficult to represent the structural similarity of ultrasound images effectively. To address this problem, the NLM method based on the simple deep learning baseline named PCANet is proposed by introducing the intrinsic features of image patches extracted by this network rather than the pixel intensities into the pixel similarity computation. In this approach, the improved two-stage PCANet is proposed by using Parametric Rectified Linear Unit (PReLU) activation function instead of the binary hashing and block histograms in the original PCANet. This model is firstly trained on the ultrasound database to learn the convolution kernels. Then, the trained PCANet is utilized to extract the intrinsic features from the image patches in the pre-denoised version of the noisy image to be despeckled. These obtained features are concatenated together to determine the structural similarity between image patches in the NLM method, based on which the weighted mean of all pixels in a search window is computed to produce the final despeckled image. Extensive experiments have been conducted on a variety of images to demonstrate the superiority of the proposed method over several well-known despeckling algorithm and the PCANet based NLM method using ReLU function and sigmoid function. Visual inspection indicates that the proposed method outperforms the compared methods in reducing speckle noise and preserving image details. The quantitative comparisons show that among all the evaluated methods, our method produces the best structural similarity index metrics (SSIM) values for the synthetic image, as well as the highest equivalent number of looks (ENL) value for the simulated image and the clinical ultrasound images.