Medical image registration plays an important role in medical diagnosis and treatment planning. However, the current registration methods based on deep learning still face some challenges, such as insufficient ability to extract global information, large number of network model parameters, slow reasoning speed and so on. Therefore, this paper proposed a new model LCU-Net, which used parallel lightweight convolution to improve the ability of global information extraction. The problem of large number of network parameters and slow inference speed was solved by multi-scale fusion. The experimental results showed that the Dice coefficient of LCU-Net reached 0.823, the Hausdorff distance was 1.258, and the number of network parameters was reduced by about one quarter compared with that before multi-scale fusion. The proposed algorithm shows remarkable advantages in medical image registration tasks, and it not only surpasses the existing comparison algorithms in performance, but also has excellent generalization performance and wide application prospects.
To address the issue of a large number of network parameters and substantial floating-point operations in deep learning networks applied to image segmentation for cardiac magnetic resonance imaging (MRI), this paper proposes a lightweight dilated parallel convolution U-Net (DPU-Net) to decrease the quantity of network parameters and the number of floating-point operations. Additionally, a multi-scale adaptation vector knowledge distillation (MAVKD) training strategy is employed to extract latent knowledge from the teacher network, thereby enhancing the segmentation accuracy of DPU-Net. The proposed network adopts a distinctive way of convolutional channel variation to reduce the number of parameters and combines with residual blocks and dilated convolutions to alleviate the gradient explosion problem and spatial information loss that might be caused by the reduction of parameters. The research findings indicate that this network has achieved considerable improvements in reducing the number of parameters and enhancing the efficiency of floating-point operations. When applying this network to the public dataset of the automatic cardiac diagnosis challenge (ACDC), the dice coefficient reaches 91.26%. The research results validate the effectiveness of the proposed lightweight network and knowledge distillation strategy, providing a reliable lightweighting idea for deep learning in the field of medical image segmentation.
To address the challenges faced by current brain midline segmentation techniques, such as insufficient accuracy and poor segmentation continuity, this paper proposes a deep learning network model based on a two-stage framework. On the first stage of the model, prior knowledge of the feature consistency of adjacent brain midline slices under normal and pathological conditions is utilized. Associated midline slices are selected through slice similarity analysis, and a novel feature weighting strategy is adopted to collaboratively fuse the overall change characteristics and spatial information of these associated slices, thereby enhancing the feature representation of the brain midline in the intracranial region. On the second stage, the optimal path search strategy for the brain midline is employed based on the network output probability map, which effectively addresses the problem of discontinuous midline segmentation. The method proposed in this paper achieved satisfactory results on the CQ500 dataset provided by the Center for Advanced Research in Imaging, Neurosciences and Genomics, New Delhi, India. The Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and normalized surface Dice (NSD) were 67.38 ± 10.49, 24.22 ± 24.84, 1.33 ± 1.83, and 0.82 ± 0.09, respectively. The experimental results demonstrate that the proposed method can fully utilize the prior knowledge of medical images to effectively achieve accurate segmentation of the brain midline, providing valuable assistance for subsequent identification of the brain midline by clinicians.
Aiming at the problems of low accuracy and large difference of segmentation boundary distance in anterior cruciate ligament (ACL) image segmentation of knee joint, this paper proposes an ACL image segmentation model by fusing dilated convolution and residual hybrid attention U-shaped network (DRH-UNet). The proposed model builds upon the U-shaped network (U-Net) by incorporating dilated convolutions to expand the receptive field, enabling a better understanding of the contextual relationships within the image. Additionally, a residual hybrid attention block is designed in the skip connections to enhance the expression of critical features in key regions and reduce the semantic gap, thereby improving the representation capability for the ACL area. This study constructs an enhanced annotated ACL dataset based on the publicly available Magnetic Resonance Imaging Network (MRNet) dataset. The proposed method is validated on this dataset, and the experimental results demonstrate that the DRH-UNet model achieves a Dice similarity coefficient (DSC) of (88.01±1.57)% and a Hausdorff distance (HD) of 5.16±0.85, outperforming other ACL segmentation methods. The proposed approach further enhances the segmentation accuracy of ACL, providing valuable assistance for subsequent clinical diagnosis by physicians.
Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, QAB/F, information entropy (IE), spatial frequency (SF), structural similarity (SSIM), mutual information (MI) and visual information fidelity for fusion (VIFF) were 2.0%, 6.3%, 7.0%, 5.5%, 9.0% and 3.3% higher than the best test results, respectively. The fused image can be effectively applied to medical diagnosis to further improve the diagnostic efficiency.
Most current medical image segmentation models are primarily built upon the U-shaped network (U-Net) architecture, which has certain limitations in capturing both global contextual information and fine-grained details. To address this issue, this paper proposes a novel U-shaped network model, termed the Multi-View U-Net (MUNet), which integrates self-attention and multi-view attention mechanisms. Specifically, a newly designed multi-view attention module is introduced to aggregate semantic features from different perspectives, thereby enhancing the representation of fine details in images. Additionally, the MUNet model leverages a self-attention encoding block to extract global image features, and by fusing global and local features, it improves segmentation performance. Experimental results demonstrate that the proposed model achieves superior segmentation performance in coronary artery image segmentation tasks, significantly outperforming existing models. By incorporating self-attention and multi-view attention mechanisms, this study provides a novel and efficient modeling approach for medical image segmentation, contributing to the advancement of intelligent medical image analysis.
This article aims to combine deep learning with image analysis technology and propose an effective classification method for distal radius fracture types. Firstly, an extended U-Net three-layer cascaded segmentation network was used to accurately segment the most important joint surface and non joint surface areas for identifying fractures. Then, the images of the joint surface area and non joint surface area separately were classified and trained to distinguish fractures. Finally, based on the classification results of the two images, the normal or ABC fracture classification results could be comprehensively determined. The accuracy rates of normal, A-type, B-type, and C-type fracture on the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81, respectively. The proposed automatic recognition method is generally better than experts, and can be used for preliminary auxiliary diagnosis of distal radius fractures in scenarios without expert participation.
High resolution (HR) magnetic resonance images (MRI) or computed tomography (CT) images can provide clearer anatomical details of human body, which facilitates early diagnosis of the diseases. However, due to the imaging system, imaging environment and human factors, it is difficult to obtain clear high-resolution images. In this paper, we proposed a novel medical image super resolution (SR) reconstruction method via multi-scale information distillation (MSID) network in the non-subsampled shearlet transform (NSST) domain, namely NSST-MSID network. We first proposed a MSID network that mainly consisted of a series of stacked MSID blocks to fully exploit features from images and effectively restore the low resolution (LR) images to HR images. In addition, most previous methods predict the HR images in the spatial domain, producing over-smoothed outputs while losing texture details. Thus, we viewed the medical image SR task as the prediction of NSST coefficients, which make further MSID network keep richer structure details than that in spatial domain. Finally, the experimental results on our constructed medical image datasets demonstrated that the proposed method was capable of obtaining better peak signal to noise ratio (PSNR), structural similarity (SSIM) and root mean square error (RMSE) values and keeping global topological structure and local texture detail better than other outstanding methods, which achieves good medical image reconstruction effect.
Non-rigid registration plays an important role in medical image analysis. U-Net has been proven to be a hot research topic in medical image analysis and is widely used in medical image registration. However, existing registration models based on U-Net and its variants lack sufficient learning ability when dealing with complex deformations, and do not fully utilize multi-scale contextual information, resulting insufficient registration accuracy. To address this issue, a non-rigid registration algorithm for X-ray images based on deformable convolution and multi-scale feature focusing module was proposed. First, it used residual deformable convolution to replace the standard convolution of the original U-Net to enhance the expression ability of registration network for image geometric deformations. Then, stride convolution was used to replace the pooling operation of the downsampling operation to alleviate feature loss caused by continuous pooling. In addition, a multi-scale feature focusing module was introduced to the bridging layer in the encoding and decoding structure to improve the network model’s ability of integrating global contextual information. Theoretical analysis and experimental results both showed that the proposed registration algorithm could focus on multi-scale contextual information, handle medical images with complex deformations, and improve the registration accuracy. It is suitable for non-rigid registration of chest X-ray images.
This study proposes an automated neurofibroma detection method for whole-body magnetic resonance imaging (WBMRI) based on radiomics and ensemble learning. A dynamic weighted box fusion mechanism integrating two dimensional (2D) object detection and three dimensional (3D) segmentation is developed, where the fusion weights are dynamically adjusted according to the respective performance of the models in different tasks. The 3D segmentation model leverages spatial structural information to effectively compensate for the limited boundary perception capability of 2D methods. In addition, a radiomics-based false positive reduction strategy is introduced to improve the robustness of the detection system. The proposed method is evaluated on 158 clinical WBMRI cases with a total of 1,380 annotated tumor samples, using five-fold cross-validation. Experimental results show that, compared with the best-performing single model, the proposed approach achieves notable improvements in average precision, sensitivity, and overall performance metrics, while reducing the average number of false positives by 17.68. These findings demonstrate that the proposed method achieves high detection accuracy with enhanced false positive suppression and strong generalization potential.
