Zhihua Wang

Diffusion models achieve remarkable image generation quality but suffer from slow inference due to hundreds of denoising steps. Consistency models alleviate this and enable one-step sampling by directly mapping noise to images with a U-Net generator, but they remain unstable and resource-hungry under small-batch training and can only generate images at fixed resolutions. These limitations motivate us to explore more efficient and flexible architectures. To this end, we propose a novel framework for efficient one-step flexible-resolution image generation. First, we represent images as continuous image functions based on implicit neural representations (INRs), which decouple image resolution from the total amount of the generated parameters and can be differentiably rendered at arbitrary resolutions. Then, we design a Transformer-based generator that directly outputs such continuous functions, providing an end-to-end architecture tailored for consistency training and stabilizing training under limited resources. To further improve convergence, we introduce an image reconstruction warm-up task that strengthens the function prediction module. Extensive experiments on one-step image generation demonstrate that our method significantly improves the stability and performance of consistency models under low-resource settings, while also enabling efficient any-resolution sampling.

Discrete Ordinary Differential Equations (ODEs) have been employed to develop lightweight deep neural networks in recent years. In this letter, we introduce a novel lightweight UNet variant called the neural memory Self-Supervised State Space Model (nmS4M-UNet) for medical image segmentation, where discrete ODEs serve as the decoder. The proposed nmS4M block has learnable gates and performs multi-head computation to enhance memory updates. Additionally, the nmS4M-UNet incorporates a self-supervised learning branch to improve feature extraction capabilities. The intermediate features are reused as partial input to the decoder, helping to mitigate network overfitting. The nmS4M-UNet reduces the number of parameters by 29.70% compared to the standard UNet. Experimental results on the PH2, ISIC2018, and BU-COCO datasets demonstrate that the proposed nmS4M-UNet achieves performance comparable to state-of-the-art models.

With the rapid advancement of deep learning, computer-aided diagnosis and treatment have become crucial in medicine. UNet is a widely used architecture for medical image segmentation, and various methods for improving UNet have been extensively explored. One popular approach is incorporating transformers, though their quadratic computational complexity poses challenges. Recently, State-Space Models (SSMs), exemplified by Mamba, have gained significant attention as a promising alternative due to their linear computational complexity. Another approach, neural memory Ordinary Differential Equations (nmODEs), exhibits similar principles and achieves good results. In this paper, we explore the respective strengths and weaknesses of nmODEs and SSMs and propose a novel architecture, the nmSSM decoder, which combines the advantages of both approaches. This architecture possesses powerful nonlinear representation capabilities while retaining the ability to preserve input and process global information. We construct nmSSM-UNet using the nmSSM decoder and conduct comprehensive experiments on the PH2, ISIC2018, and BU-COCO datasets to validate its effectiveness in medical image segmentation. The results demonstrate the promising application value of nmSSM-UNet. Additionally, we conducted ablation experiments to verify the effectiveness of our proposed improvements on SSMs and nmODEs.

The quality of medical images is crucial for accurately diagnosing and treating various diseases. However, current automated methods for assessing image quality are based on neural networks, which often focus solely on pixel distortion and overlook the significance of complex structures within the images. This study introduces a novel neural network model designed explicitly for automated image quality assessment that addresses pixel and semantic distortion. The model introduces an adaptive ranking mechanism enhanced with contrast sensitivity weighting to refine the detection of minor variances in similar images for pixel distortion assessment. More significantly, the model integrates a structure-aware learning module employing graph neural networks. This module is adept at deciphering the intricate relationships between an image’s semantic structure and quality. When evaluated on two ultrasound imaging datasets, the proposed method outshines existing leading models in performance. Additionally, it boasts seamless integration into clinical workflows, enabling real-time image quality assessment, crucial for precise disease diagnosis and treatment.

The traditional commissioning and testing each system chimney construction, information can't be shared, single point strong and overall weak, lack of professional, professional and external environment between the correlation analysis and centralized fusion of intuitive display. Through the research on key technologies such as multi-source information fusion, cross-platform information interconnection, data sharing, space-time synchronization, multi-graph collaborative linkage, and integrated display, the ‘multi-source information fusion integration platform’ was designed and developed. The application of Beijing-Zhangjiakou and other lines shows that the platform realizes the integration of information fusion among organizations (horizontal), specialties (vertical) and data (end-to-end), and improves the overall judgment, abnormal alarm, collaborative command and scientific decision-making level of testing and commissioning.

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage.

Malposition of the acetabular and femoral component has long been recognized as an important cause of dislocation after total hip replacement (THR) surgeries. In order to help surgeons improve the positioning accuracy of the components, a visual-aided system for THR surgeries that could estimate orientation and depth of femoral component is proposed. The sensors are fixed inside the femoral prosthesis trial and checkerboard patterns are printed on the internal surface of the acetabular prosthesis trial. An extended Kalman filter is designed to fuse the data from inertial sensors and the magnetometer orientation estimation. A novel image processing algorithm for depth estimation is developed. The algorithms have been evaluated under the simulation with rotation quaternion and translation vector and the experimental results shows that the root mean square error (RMSE) of the orientation estimation is less then 0.05 degree and the RMSE for depth estimation is 1mm. Finally, the femoral head is displayed in 3D graphics in real time to help surgeons with the component positioning.