- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[Lecture Notes in Computational Vision and Biomechanics] Computer Aided Intervention and Diagnostics in Clinical and Medical Images Volume 31 || A Hybrid Fusion of Multimodal Medical Images for the Enhancement of Visual Quality in Medical Diagnosis
摘要： In the ?eld of medical imaging, Multimodal Medical Image Fusion (MIF) is a method of extracting complementary information from diverse source images from different modalities such as Magnetic Resonance Imaging, Computed Tomography, Single Photon Emission Computed Tomography, and Positron Emission Tomography and coalescing them into a resultant image. Image fusion of multimodal medical images is the present-day studies in the ?eld of medical imaging, biomedical research, and radiation medicine and is widely familiar by medical and engineering ?elds. In medical image fusion, single method of fusion is not pro?cient as it always lags in information while comparing with other available techniques. Hence, fusion for hybrid image is used to perform the image processing by applying multiple fusion rules. The integration of these results was obtained together as a single image. In proposed system, Shearlet Transform (ST) and Principal Component Analysis (PCA) are used to apply integrated fusion. The fusion technique is applied for CT that is Computed Tomography and Magnetic Resonance Imaging (MRI) images, where these images are ?rst transformed using the Shearlet Transform and PCA is applied to the transformed images. Finally, the fusion image is acquired using Inverse Shearlet transform (IST). The proposed system performance is evaluated by using speci?c metrics, and it is demonstrated that the outcome of proposed integrated fusion performs better when compared to existing fusion techniques.
关键词： Image fusion,Medical image,Shearlet Transform (ST),Principal Component Analysis (PCA)
更新于2025-09-23 15:23:52
-
[IEEE 2018 9th International Conference on Information Technology in Medicine and Education (ITME) - Hangzhou, China (2018.10.19-2018.10.21)] 2018 9th International Conference on Information Technology in Medicine and Education (ITME) - MobMivs: Implementing an Efficient Medical Image Visualization System for Mobile Telemedicine
摘要： As medical devices have excellent resolutions and have become better connected to the Internet, doctors and patients are beginning to expect medical images to be available on mobile device for making a diagnosis or consultative viewing. However, the performance of querying and accessing medical images in anytime and anywhere using mobile device is still an issue. In this paper, we implement an medical image visualization system to efficiently query and access medical images by using smartphone, which has the following new features: 1) an on-demand data transmission method is implemented using DICOM web service, and only the required meta data and image region or series are transmitted to mobile device; 2) a high performance cache component is designed to cache the recently requested images, which takes up less storage and obtains higher performance; 3) a convenient way is introduced to quickly obtain a specific patient's studies by scanning a patient's barcode or quick response code. The performance and stability of our proposed method as well as the prototype system is evaluated with real DICOM data sets. The results show that our app obtains high performance and stability in both Wi-Fi and 4G mobile network, which is expected to be an effective tool for mobile telemedicine.
关键词： Mobile medical image system,Web service,Mobile device,DICOM
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) - Chongqing, China (2018.10.12-2018.10.14)] 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) - Medical image segmentation based on improved watershed algorithm
摘要： The watershed segmentation algorithm has the problem of over-segmentation. The paper proposed an improved watershed algorithm for medical image segmentation. Combined with improved gray morphological reconstruction and watershed algorithm, the segmentation of medical cells and brain CT images is improved, which improves the accuracy of image segmentation of medical tissues and organs and assists doctors to diagnose the diseases. The simulation results show that the improved algorithm can effectively suppress the over-segmentation for two different medical tissue images.
关键词： watershed algorithm,medical image,segmentation,grayscale morphology
更新于2025-09-23 15:23:52
-
[IEEE 2018 10th International Conference on Modelling, Identification and Control (ICMIC) - Guiyang (2018.7.2-2018.7.4)] 2018 10th International Conference on Modelling, Identification and Control (ICMIC) - Automatic Segmentation and 3D Reconstruction of Spine Based on FCN and Marching Cubes in CT Volumes
摘要： The spine is of great significance in the course of radiotherapy. The accurate location of the spine can provide reference for the determination of the tumor target area and the endanger organ in the radiotherapy plan. However, for some low-resolution areas of CT images, traditional methods cannot achieve a good segmentation effect. Due to the lack of data marked by doctors, there are few studies on the use of deep learning methods for segmentation of the spine. We use threshold segmentation and manual labeling methods to make our own data sets. This article combines the Fully Convolutional Neural Network (FCN) and the Marching Cubes (MC) algorithms to automatically segment and reconstruct the spine in the CT images. And we improved the network structure of FCN because FCN finally lost many details in one step down sampling. In the study, we used data from 40 patients, of which 30 were for training and 10 for testing. The final segmentation accuracy of the improved network is over 93%. The experimental results show that this method has a good segmentation effect and can better restore the shape of the spine and ribs. This preliminary result showed that our spine segmentation method had a great potential to reduce human efforts in labeling CT images in radiation therapy.
关键词： Fully Convolutional Neural Network,Spine,Medical Image,Marching Cubes
更新于2025-09-23 15:22:29
-
An Efficient Lossless ROI Image Compression Using Wavelet-Based Modified Region Growing Algorithm
摘要： Nowadays, medical imaging and telemedicine are increasingly being utilized on a huge scale. The expanding interest in storing and sending medical images brings a lack of adequate memory spaces and transmission bandwidth. To resolve these issues, compression was introduced. The main aim of lossless image compression is to improve accuracy, reduce the bit rate, and improve the compression efficiency for the storage and transmission of medical images while maintaining an acceptable image quality for diagnosis purposes. In this paper, we propose lossless medical image compression using wavelet transform and encoding method. Basically, the proposed image compression system comprises three modules: (i) segmentation, (ii) image compression, and (iii) image decompression. First, the input medical image is segmented into region of interest (ROI) and non-ROI using a modified region growing algorithm. Subsequently, the ROI is compressed by discrete cosine transform and set partitioning in hierarchical tree encoding method, and the non-ROI is compressed by discrete wavelet transform and merging-based Huffman encoding method. Finally, the compressed image combination of the compressed ROI and non-ROI is obtained. Then, in the decompression stage, the original medical image is extracted using the reverse procedure. The experimentation was carried out using different medical images, and the proposed method obtained better results compared to different other methods.
关键词： DWT,Medical image,non-ROI,modified region growing,DCT,region of interest,merging-based Huffman encoding,SPIHT
更新于2025-09-23 15:22:29
-
A Review of Point Feature Based Medical Image Registration
摘要： Point features, as the basis of lines, surfaces, and bodies, are commonly used in medical image registration. To obtain an elegant spatial transformation of extracted feature points, many point set matching algorithms (PMs) have been developed to match two point sets by optimizing multifarious distance functions. There are ample reviews related to medical image registration and PMs which summarize their basic principles and main algorithms separately. However, to data, detailed summary of PMs used in medical image registration in different clinical environments has not been published. In this paper, we provide a comprehensive review of the existing key techniques of the PMs applied to medical image registration according to the basic principles and clinical applications. As the core technique of the PMs, geometric transformation models are elaborated in this paper, demonstrating the mechanism of point set registration. We also focus on the clinical applications of the PMs and propose a practical classification method according to their applications in different clinical surgeries. The aim of this paper is to provide a summary of point-feature-based methods used in medical image registration and to guide doctors or researchers interested in this field to choose appropriate techniques in their research.
关键词： Assessment,Application,Point set matching,Medical image registration,Optimization
更新于2025-09-23 15:22:29
-
[Lecture Notes in Computational Vision and Biomechanics] Computer Aided Intervention and Diagnostics in Clinical and Medical Images Volume 31 || Secured Image Transmission in Medical Imaging Applications—A Survey
摘要： Radiology Information Systems (RIS) involves the transmission of medical images between the PACS server and the workstation over the network for analysis. The images during transmission are vulnerable due to the intruders, and it is essential to secure the images. Because processing the adulterated images is unethical and can mislead the radio diagnosis. The combination of image processing and the cryptographic techniques can resolve this problem to some extent. Over a period, the technology has improved a lot, and several images securing methods are discussed by various researchers. This review paper is an effort in reviewing the existing secured image transmission technologies, their pros, and cons and the scope of the future work.
关键词： Watermarking techniques,Medical image exchanging,DICOM,Joint encryption
更新于2025-09-23 15:22:29
-
Severity analysis of diabetic retinopathy in retinal images using hybrid structure descriptor and modified CNNs
摘要： Imaging which plays a central role in the diagnosis and treatment planning of diabetic retinopathy and severity is an important diagnostic indicator in treatment planning and results assessment. Retinal image classification is an increasing attention among researchers in the field of computer vision, as it plays an important role in disease diagnosis. Computer Aided Diagnosis (CAD) is in wide practice in clinical work for the location and anticipation of different kinds of variations; the automated image classification systems used for such applications must be significantly efficient in terms of accuracy since false detection may lead to fatal results. Another requirement is the high convergence rate which accounts for the practical feasibility of the system. The overall classification accuracy of the proposed HTF with MCNNs is 98.41%, but the existing methods HTF with SVM and HTF with CNNs produce 97.84% and 96.65% respectively.
关键词： Segmentation,SVM,Medical image processing,Microaneurysms,Diabetic retinopathy,Classification
更新于2025-09-23 15:19:57
-
Biorthogonal Halfband Perfect Reconstruction Filterbank for Multimodal Image Fusion
摘要： To design a wavelet filter bank which helps to detect more prominently continuous changes in tumor cells. In this paper, a method of designing two-channel wavelet base FIR filter bank using factorization of a half band filter is presented. Here factorization is done considering maximum vanishing moments for construction of decomposition as well as reconstruction filters. The 14 order maximally flat halfband filter is proposed with factorization, leading to design of 8/8 orthogonal and 9/7 & 6/10 symmetric filters. The fusion performance of designed wavelet filter bank is evaluated using various performance metrics, like, cross entropy, standard deviation, mean square error and PSNR. The results are compared with the Daubechies filter bank where db4 is used for implementation. It is clear from the results that designed filter bank improves fusion performance. Further, proposed filters have maximum number of vanishing moments which gives smooth scaling and wavelet functions and consequently provides flat frequency response. The designed 8/8 orthogonal wavelet filters are implemented in fusion application for multimodal biomedical images of a subject for detection of an abnormality (cancerous growth). The novelty of this method is the adaptive design of the filterbank for the given multimodal images, so that fused images shall have more clarity, further, it will help to improve the results with enhancement in the entropy levels of fused image.
关键词： Spectral Factorization,Medical Image Processing,Filter Banks,Multimodal Image Fusion,Wavelet Transforms,Half Band Filter
更新于2025-09-19 17:15:36
-
[IEEE 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Xi'an, China (2018.11.7-2018.11.10)] 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Image Classification Method in DR Image Based on Transfer Learning
摘要： Until now many cancer cases have been discovered in their early stages based on Computer Aided Diagnosis (CAD) system. There are many methods in the medical image processing field have been proposed to address this issue, and the result of these methods was deficient. Further, the application of AI in DR images is not widespread in hospitals. The classification process in the DR image is more difficult than other types of images. In this paper, we use transfer learning which is based on Inception V3 model to classify the DR images. We used the weight of Inception V3 model which was trained in the ImageNet dataset, and fine-tuning in our own dataset. Comparing to other proposed methods, our result had a higher accuracy.
关键词： DR images,Transfer Learning,medical image,CAD
更新于2025-09-19 17:15:36