Vascular segmentation plays an important role in medical image analysis. A novel technique for the automatic extraction of vascular trees from 2D medical images is presented, which combines Hessian-based multiscale filtering and a modified level set method. In the proposed algorithm, the morphological top-hat transformation is firstly adopted to attenuate background. Then Hessian-based multiscale filtering is used to enhance vascular structures by combining Hessian matrix with Gaussian convolution to tune the filtering response to the specific scales. Because Gaussian convolution tends to blur vessel boundaries, which makes scale selection inaccurate, an improved level set method is finally proposed to extract vascular structures by introducing an external constrained term related to the standard deviation of Gaussian function into the traditional level set. Our approach was tested on synthetic images with vascular-like structures and 2D slices extracted from real 3D abdomen magnetic resonance angiography (MRA) images along the coronal plane. The segmentation rates for synthetic images are above 95%. The results for MRA images demonstrate that the proposed method can extract most of the vascular structures successfully and accurately in visualization. Therefore, the proposed method is effective for the vascular tree extraction in medical images.

This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination.

Nonrigid multimodal image registration remains a challenging task in medical image processing and analysis. The structural representation (SR)-based registration methods have attracted much attention recently. However, the existing SR methods cannot provide satisfactory registration accuracy due to the utilization of hand-designed features for structural representation. To address this problem, the structural representation method based on the improved version of the simple deep learning network named PCANet is proposed for medical image registration. In the proposed method, PCANet is firstly trained on numerous medical images to learn convolution kernels for this network. Then, a pair of input medical images to be registered is processed by the learned PCANet. The features extracted by various layers in the PCANet are fused to produce multilevel features. The structural representation images are constructed for two input images based on nonlinear transformation of these multilevel features. The Euclidean distance between structural representation images is calculated and used as the similarity metrics. The objective function defined by the similarity metrics is optimized by L-BFGS method to obtain parameters of the free-form deformation (FFD) model. Extensive experiments on simulated and real multimodal image datasets show that compared with the state-of-the-art registration methods, such as modality-independent neighborhood descriptor (MIND), normalized mutual information (NMI), Weber local descriptor (WLD), and the sum of squared differences on entropy images (ESSD), the proposed method provides better registration performance in terms of target registration error (TRE) and subjective human vision.

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.