By integrating effective features of multi-modality medical images to provide richer information, multi-modality medical image fusion has been substantially used in computer-aided diagnosis applications. However, many existing fusion schemes do not consider how to eliminate the effects of the noise in source medical images and cannot provide enough details and textures for disease diagnosis. To address the problems above, we propose a new fidelity-driven optimization (FDO) reconstruction and details preserving guided-based fusion method for multi-modality medical images. To overcome the influence of noise in multi-modality medical images, a rank coefficient optimization method of low-rank approximation based on weighted mean curvature is proposed to reconstruct multi-modality medical image. Moreover, we propose an iterative detail preserving guided fusion (DPGF) method to integrate more textures and detail information of source multi-modality medical images, while ensuring high signal-to noise ratios. The experimental results show that the proposed method outperforms some of the state-of-the-art fusion methods. Specifically, the extensive experiments prove that our method has high robustness for noisy medical images, which also indicates the application prospects in diagnosis applications. Supplemental material and codes of this work are publicly available at https://github.com/VCMHE/FDO_DPGF.
14 April 2021 in IEEE Transactions on Instrumentation and Measurement
Multimodal medical image fusion technology has been widely used in various applications of clinical diagnosis, which aims to provide richer information by integrating effective features of multiple medical images. In this article, a novel fusion scheme based on region-preserving edge enhancement is proposed for medical images. The overlapping regions of source images that need to be fused are detected first. Next, according to the different visual features, the overlapping map is divided by Fuzzy c-means (FCM)-based algorithm. Then, different fusion strategies based on visual saliency and texture details are proposed for region-preserving and edge enhancement. Experimental results show that the proposed scheme can effectively highlight the visual features and retain key information. Furthermore, the performance of different medical images also demonstrates that the proposed method can obtain better results than those achieved by some of the state-of-the-art methods.
Image registration is an important research topic in medical image-guided therapy, which is dedicated to registering the high-dose imaging sequences with low-dose/faster means. Registering computer tomography (CT) scanning sequences with cone beam computer tomography (CBCT) scanning sequences is a typical application and has been widely used in CBCT-guided radiotherapy. The main problem is the difference in image clarity of these two image sequences. To solve this problem, for the single projection image sequence matching tasks encountered in medical practice, a novel local quality based curved section encoding strategy is proposed in this paper, which is called the high-quality curved section (HQCS). As an optimized cross-section regularly encoded along the sequence of image, this curved section could be used in order to solve the matching problem. Referencing the independent ground truth provided by medical image physicians, with an experiment combined with the four most widely used indicators used on image registration, matching performance of HQCS on CT/CBCT datasets was tested with varying clarity. Experimental results show that the proposed HQCS can register the CT/CBCT effectively and outperforms the commonly used methods. Specifically, the proposed HQCS has low time complexity and higher scalability, which indicates that the application enhanced the task of diagnosis.
In order to improve the adaptability of packaging paper and the high-speed packaging machine, we designed a set of non-contact precision inspection and evaluation system for the packaging paper products. A macro laser scanning sensor is installed on bi-axial linear motor for sampling the full dimension of paper on the negative pressure adsorption platform, the uniform sampling density is designed higher than 1100 spots/ mm2, and theoretical error of depth data is less than 0.02mm, this method solved two defects in contacting measurement: the data can't cover object's surface completely, and it is hard to avoid deformation of the measured object. Based on full covered data, this paper proposed the algorithms of Image visualization, indentation detection, contour fitting, 3D reconstruction, and a norm of parameters based on local frequency changes was designed by consulting with industrial demand. The experiment shows that this method can significantly reflect the micro differences. The system could export measurement report and provides an interactive measurement in 3D visualization window, so this work is helpful at development of process control in printing industry, such as defectiveness detection, adaptability verification.