- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A touchless interaction interface for observing medical imaging
摘要： Using volume rendering to generate 3D models is associated with the problem of missing features on areas of interest, which are possibly concealed by other information. This article presents a novel focus-and-context medical imaging observation system using gesture-based technique to build a touchless interactive environment. The system offers two types of medical imaging observation tool, namely, 3D section cutting tool and 3-axes cross-section synchronization tool, enabling users to quickly and easily observe tissue sections. Feature classification was achieved using region growing and size-based transfer approaches. Combined with view penetration function (cylinder and cone view penetration functions), the system allows for direct observation of hidden features. The analytical experimental results verified that the proposed system is easy to operate in a touchless environment and creates positive user experience regarding observation and interaction.
关键词： Focus and context,Touchless,Medical imaging,Volume rendering,Visualization
更新于2025-09-23 15:23:52
-
Development and first in-human use of a Raman spectroscopy guidance system integrated with a brain biopsy needle
摘要： Navigation-guided brain biopsies are the standard of care for diagnosis of several brain pathologies. However, imprecise targeting and tissue heterogeneity often hinder obtaining high-quality tissue samples, resulting in poor diagnostic yield. We report the development and first clinical testing of a navigation-guided fiberoptic Raman probe that allows surgeons to interrogate brain tissue in situ at the tip of the biopsy needle, prior to tissue removal. The 900μm diameter probe can detect high spectral quality Raman signals in both the fingerprint and high wavenumber spectral regions with minimal disruption to the neurosurgical workflow. The probe was tested in 3 brain tumor patients, and the acquired spectra in both normal brain and tumor tissue demonstrated the expected spectral features, indicating the quality of the data. As a proof-of-concept, we also demonstrate the consistency of the acquired Raman signal with different systems and experimental settings. Additional clinical development is planned to further evaluate the performance of the system and develop a statistical model for real-time tissue classification during the biopsy procedure.
关键词： biopsy,cancer,neurosurgery,optical systems,Raman spectroscopy,medical imaging
更新于2025-09-23 15:23:52
-
Image classification with quantum pre-training and auto-encoders
摘要： Computer vision has a wide range of applications from medical image analysis to robotics. Over the past few years, the field has been transformed by machine learning and stands to benefit from potential advances in quantum computing. The main challenge for processing images on current and near-term quantum devices is the size of the data such devices can process. Images can be large, multidimensional and have multiple color channels. Current machine learning approaches to computer vision that exploit quantum resources require a significant amount of manual pre-processing of the images in order to be able to fit them onto the device. This paper proposes a framework to address the problem of processing large scale data on small quantum devices. This framework does not require any dataset-specific processing or information and works on large, grayscale and RGB images. Furthermore, it is capable of scaling to larger quantum hardware architectures as they become available. In the proposed approach, a classical autoencoder is trained to compress the image data to a size that can be loaded onto a quantum device. Then, a Restricted Boltzmann Machine (RBM) is trained on the D-Wave device using the compressed data, and the weights from the RBM are then used to initialize a neural network for image classification. Results are demonstrated on two MNIST datasets and two medical imaging datasets.
关键词： quantum machine learning,medical imaging,Quantum computing,machine learning
更新于2025-09-23 15:23:52
-
Frame-based Programming, Stream-Based Processing for Medical Image Processing Applications
摘要： This paper presents and evaluates an approach to deploy image and video processing pipelines that are developed frame-oriented on a hardware platform that is stream-oriented, such as an FPGA. First, this calls for a specialized streaming memory hierarchy and accompanying software framework that transparently moves image segments between stages in the image processing pipeline. Second, we use softcore VLIW processors, that are targetable by a C compiler and have hardware debugging capabilities, to evaluate and debug the software before moving to a High-Level Synthesis flow. The algorithm development phase, including debugging and optimizing on the target platform, is often a very time consuming step in the development of a new product. Our proposed platform allows both software developers and hardware designers to test iterations in a matter of seconds (compilation time) instead of hours (synthesis or circuit simulation time).
关键词： Image processing,FPGA,Medical imaging
更新于2025-09-23 15:23:52
-
[Lecture Notes in Computational Vision and Biomechanics] Computer Aided Intervention and Diagnostics in Clinical and Medical Images Volume 31 || Segmentation of Type II Diabetic Patient’s Retinal Blood Vessel to Diagnose Diabetic Retinopathy
摘要： Diabetic Retinopathy is one of the ophthalmic reasons for visual deficiency. The favored fixate of consideration is on the estimation of deviation in the breadth of the retinal veins and the new vessel development. To witness the progressions, segmentation has to be made primarily. A framework to improve the quality of the segmentation result over pathological retinal images is proposed. The proposed method uses adaptive histogram equalizer for preprocessing, pulse coupled neural Network model for automatic feature vector generation and extraction of the retinal blood vessels. The test result represents that the proposed method is enhanced than other retinal competitive methods. The evaluation of the proposed approach is executed over standard public DRIVE, STARE, REVIEW, HRF, and DRIONS fundus image datasets. The proposed technique improves the segmentation results in terms of sensitivity, specificity, and accuracy.
关键词： Fundus image,Feature extraction,Diabetic Retinopathy,Retinal blood vessel,Medical imaging
更新于2025-09-23 15:22:29
-
[IEEE 2018 Joint Conference - Acoustics - Ustka, Poland (2018.9.11-2018.9.14)] 2018 Joint Conference - Acoustics - Crosstalk Effect in Medical Ultrasound Tomography Imaging
摘要： Ultrasound tomography (UT) is a modern method of medical imaging that has been intensively developed recently to diagnose female breasts in vivo. This method makes it possible to acquire images in various ultrasound modalities simultaneously - both transmission and reflection ones, without any focusing. Therefore, the ultrasound intensity level when scanning individual coronal breast sections is relatively low. Data for reconstruction of images is obtained by means of a multi-element array of small piezoceramic transducers spaced evenly on the inner side of the ring surrounding the breast immersed in water. The main problem with such arrangements is the occurrence of crosstalk, which introduces specific errors to measurement data. Crosstalk is a result of a deficiency in electrical or mechanical isolation between array elements. Such errors lead to distortions in the reconstructed images. In the paper, the effect of crosstalk in the ultrasound tomography ring array was examined and analyzed. The influence of crosstalk on the reconstructed images of the breast structure was shown as well. Conducted studies enabled the detection of the sources and paths of crosstalk and, as a consequence, it allowed us to improve the design of the multi-element ultrasonic transducer ring array, and to reduce crosstalk.
关键词： medical imaging,ultrasound tomography method,breast diagnosis,crosstalk effect
更新于2025-09-23 15:21:21
-
[IEEE 2018 3rd International Conference On Internet of Things: Smart Innovation and Usages (IoT-SIU) - Bhimtal (2018.2.23-2018.2.24)] 2018 3rd International Conference On Internet of Things: Smart Innovation and Usages (IoT-SIU) - A Method of Segmentation in 3D Medical Image for selection of Region of Interest (ROI).
摘要： In Medical Science manual segmentation process is very costly, time taking and in case of 3D medical images it takes more time and cost in compare to 2D medical images. 3D medical imaging technique provides more precise information of patient for diagnosis and segmentation of 3D medical images is needed for diagnosis and treatment. Here, we present a method for segmentation and selections of Region of Interest (ROI) according to our requirement in one frame and easily analyze image. Our and observe result data from 3D medical computational approach allowed the experts to select the ROI on execution level and free to compare results after each and every execution and identify the best suited result or best image which provides the larger information comparatively others image.
关键词： 3D Medical Imaging,Image Segmentation,Image Processing Techniques
更新于2025-09-23 15:21:21
-
Special Section Guest Editorial: Quantitative Imaging and the Pioneering Efforts of Laurence P. Clarke
摘要： Quantitative imaging is growing in popularity and clinical utility, and this special section of the Journal of Medical Imaging features articles that present results of this method across medical imaging modalities and applications. Quantitative imaging is the science of extracting numeric information from images to measure or predict a patient’s health. Larry Clarke was an early and enthusiastic champion of quantitative methods in medical imaging, and the fullness and diversity of this issue stand as a tribute to his dedication to the field. Sadly, Larry passed away in April 2016 before many aspects of his vision for quantitative imaging could be realized.
关键词： National Cancer Institute,Cancer Imaging Program,Medical Imaging,Quantitative Imaging,Laurence P. Clarke
更新于2025-09-23 15:21:01
-
MedGA: A novel evolutionary method for image enhancement in medical imaging systems
摘要： Medical imaging systems often require the application of image enhancement techniques to help physicians in anomaly/abnormality detection and diagnosis, as well as to improve the quality of images that undergo automated image processing. In this work we introduce MedGA, a novel image enhancement method based on Genetic Algorithms that is able to improve the appearance and the visual quality of images characterized by a bimodal gray level intensity histogram, by strengthening their two underlying sub-distributions. MedGA can be exploited as a pre-processing step for the enhancement of images with a nearly bimodal histogram distribution, to improve the results achieved by downstream image processing techniques. As a case study, we use MedGA as a clinical expert system for contrast-enhanced Magnetic Resonance image analysis, considering Magnetic Resonance guided Focused Ultrasound Surgery for uterine fibroids. The performances of MedGA are quantitatively evaluated by means of various image enhancement metrics, and compared against the conventional state-of-the-art image enhancement techniques, namely, histogram equalization, bi-histogram equalization, encoding and decoding Gamma transformations, and sigmoid transformations. We show that MedGA considerably outperforms the other approaches in terms of signal and perceived image quality, while preserving the input mean brightness. MedGA may have a significant impact in real healthcare environments, representing an intelligent solution for Clinical Decision Support Systems in radiology practice for image enhancement, to visually assist physicians during their interactive decision-making tasks, as well as for the improvement of downstream automated processing pipelines in clinically useful measurements.
关键词： Medical imaging systems,Genetic Algorithms,Uterine fibroids,Magnetic resonance imaging,Bimodal image histogram,Image enhancement
更新于2025-09-23 15:21:01
-
Interventional Oncology (Principles and Practice of Image-Guided Cancer Therapy) || Imaging in interventional oncology: Role of image guidance
摘要： Advances in medical imaging have created the opportunity for minimally invasive, image-guided oncologic care by allowing: (1) procedure planning; (2) device delivery; (3) intraprocedure monitoring; and (4) therapy assessment. Although most current image-guided therapy still utilizes standard diagnostic imaging equipment, interventional use of imaging equipment has in fact different priorities compared with diagnostic uses of such equipment. Therefore, interventional procedures prioritize imaging equipment that: (1) provides real-time imaging; (2) lowers radiation dose; and (3) provides greater physician access to the patient. In contrast to diagnostic imaging, lower image quality is an acceptable compromise for real-time imaging for interventional procedures. Patients have already undergone high-quality diagnostic imaging when they are referred to interventional therapies. Moreover, high-quality diagnostic imaging may require more time and more radiation dose than fast imaging of a restricted region of interest as performed for image guidance of interventions.
关键词： image-guided therapy,real-time imaging,physician access,medical imaging,radiation dose,interventional oncology
更新于2025-09-23 15:21:01