检索结果-内蒙古大学图书馆

A deep convolutional neural network for simultaneous denoising and deblurring in computed tomography

JOURNAL OF INSTRUMENTATION 2020年第12期15卷

作者： Yim, D. Kim, B. Lee, S. Konyang Univ Dept Med Sci 158 Gwanjeodong Ro Daejeon South Korea Konyang Univ Dept Radiol Sci 158 Gwanjeodong Ro Daejeon South Korea

Computed tomography (CT) has been commonly used for providing medical images. However, CT scans have a potential risk of side-effect due to high radiation dose. In order to overcome this limitation, low-dose CT imaging techniques have been developed by using novel scanners, reconstruction algorithms and adjusted scanning protocols. In spite of these strategies, the conventional low-dose CT imaging techniques are hard to compromise between radiation dose and image quality, leading to noise, blur and artifacts in CT images. These drawbacks of the conventional techniques degrade diagnostic accuracy. In this study, we proposed a deep convolutional neural network (CNN)-based low-dose CT imaging technique for simultaneously reducing noise and blur at once. The proposed method, called denoising and deblurring CNN (DnDbCNN), consisted of two networks, and each network was separately trained for reducing noise and blur in CT images. For combining the trained networks, a convolutional layer was added between the two trained networks, and the combined network was re-trained to update the weights of each layer. Denoising convolutional neural network (DnCNN) and super-resolution convolutional neural network (SRCNN) were also implemented for comparison. We evaluated the performance of the DnDbCNN in terms of mean-square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), coefficient-of-variation (COV) and modulation transfer function (MTF). The results showed that the DnDbCNN improved the noise property, spatial resolution and quantitative accuracy of CT images, and the performance of the DnDbCNN was superior to the conventional methods. As a result, the DnDbCNN can simultaneously reduce noise and blur by combining two networks through three training steps. Therefore, the DnDbCNN has a potential for improving CT image quality with low radiation dose and enables precise diagnosis.

关键词： computerized Tomography (CT) and Computed Radiography (CR) medical-image reconstruction methods and algorithms, computer-aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Preliminary performance evaluation of adjustable-FOV full-body PET

引用

JOURNAL OF INSTRUMENTATION 2020年第6期15卷

作者： Ozsahin, I. Near East Univ Fac Engn Dept Biomed Engn Mersin 10 TRNC TR-99138 Nicosia Turkey Near East Univ DESAM Inst Mersin 10 TRNC TR-99138 Nicosia Turkey

Recent developments in molecular imaging have led to increases in the performance and area of utilization of positron emission tomography (PET) systems. There are several ways that PET system sensitivity can be increased including changing the scanner's geometry. I recently proposed a novel PET design with adjustable field of view (FOV) to improve the system sensitivity up to 40 times higher than the conventional systems, depending on the size of the transaxial FOV. This study aims to evaluate the spatial resolution characteristics of the proposed design. Geant4-based Architecture for Medicine Oriented Simulations (GAMOS) toolkit was used to simulate the system. The proposed PET geometry was designed to cover and scan the full-body of the patient in one bed position. The spatial resolution tests were conducted using a point like source placed at different locations throughout the FOV when the transaxial FOV of the scanner was changed from 70 cm to 30 cm. The results showed that the spatial resolution slightly degrades when the FOV is reduced.

关键词： Gamma camera, SPECT, PET PET/CT, coronary CT angiography (CTA) medical-image reconstruction methods and algorithms, computer-aided diagnosis medical-image reconstruction methods and algorithms, computer-aided software

来源：评论

学校读者我要写书评

暂无评论

Visualization of radiotracers for SPECT imaging using a Timepix detector with a coded aperture

引用

JOURNAL OF INSTRUMENTATION 2020年第6期15卷

作者： Rozhkov, V Chelkov, G. Hernandez, I Ivanov, O. Kozhevnikov, D. Leyva, A. Perera, A. Rastorguev, D. Smolyanskiy, P. Torres, L. Zhemchugov, A. Joint Inst Nucl Res Dubna Russia Isotopes Ctr Mayabeque Cuba Natl Res Ctr Kurchatov Inst Moscow Russia Ctr Technol Applicat & Nucl Dev Havana Cuba Moscow Inst Phys & Technol Dolgoprudnyi Russia

The work shows the ability to visualize radiotracers used in SPECT with a system based on a coded aperture mask and a hybrid pixel Timepix detector with the CdTe sensor. Characterization of the system using X-rays and radioactive sources confirms that the spatial resolution of less than 1 mm with a field of view 3 cm x 3 cm can be achieved. The results of a simulation study to determine the expected spatial resolution of the system in the focal plane for the various radionuclides is presented. The possibility of using this system with a thin (1 mm) coded aperture mask for reconstructing images of gamma emitters with the energy up to 180 keV is demonstrated.

关键词： Gamma camera, SPECT, PET PET/CT, coronary CT angiography (CTA) image reconstruction in medical imaging medical-image reconstruction methods and algorithms, computer-aided diagnosis Hybrid detectors

来源：评论

学校读者我要写书评

暂无评论

Soft-tissue radiography using multi-scale convolutional neural networks

引用

JOURNAL OF INSTRUMENTATION 2020年第1期15卷

作者： Ha, S. Youn, H. Kim, H. K. Pusan Natl Univ Sch Mech Engn Busandaehak Ro 63Beon Gil Busan 46241 South Korea Vatech Co Ltd Med Syst Lab Samsung 1 Ro 2 Gil Hwaseong Si 18449 Gyeonggi Do South Korea Pusan Natl Univ Ctr Adv Med Engn Res Busandaehak Ro 63Beon Gil Busan 46241 South Korea

Dual-energy imaging techniques based on the fast kVp switching and the sandwich detector can enhance the conspicuity in digital radiography. Deep learning is an alternative promising approach to obtain dual-energy images without hardware cost and additional patient dose. This paper extends the well-known multi-scale U-net to preserve high-frequency information so as to be applicable to structural filtering of medical images with minimal loss of information. The performance of modified versions of the U-net is presented in comparison with the conventional U-net architecture. Limitation of the modified networks is also discussed.

关键词： medical-image reconstruction methods and algorithms, computer-aided diagnosis image reconstruction in medical imaging X-ray radiography and digital radiography (DR)

来源：评论

学校读者我要写书评

暂无评论

Simulation of novel scintillator crystals for brain PET

引用

JOURNAL OF INSTRUMENTATION 2020年第5期15卷

作者： Ozsahin, I. Ozsahin, D. Uzun Makarov, P. A. Musa, M. S. Mok, G. S. P. Univ Macau Fac Sci & Technol Dept Elect & Comp Engn Biomed Imaging Lab Macau Peoples R China Near East Univ Fac Engn Dept Biomed Engn Mersin 10 TRNC TR-99138 Nicosia Turkey Near East Univ DESAM Inst Mersin 10 TRNC TR-99138 Nicosia Turkey Near East Univ Innovat & Informat Technol Ctr Mersin 10 TRNC TR-99138 Nicosia Turkey Univ Macau Fac Hlth Sci Macau Peoples R China

In the last decade, different positron emission tomography (PET) crystals have been proposed for brain PET detectors. Brain PET cameras with restricted field of view to a smaller size to cover the brain can both exhibit significantly higher performance and lower the cost when compared to conventional whole-body PET scanners. The existing designs based on scintillation crystals employ the most commonly known materials such as lutetium oxyorthosilicate and bismuth germanate. This is due to their relatively good parameters such as high light yield and density. The main drawback of using scintillation crystals is that they have a modest energy resolution. In this study, a brain PET scanner was designed and simulated using a Geant4 Application for Tomographic Emission (GATE) toolkit. The performances of five crystals, namely strontium hafnate, gadolinium aluminium gallium garnet, gadolinium yttrium gallium aluminium garnet, gadolinium lutetium gallium aluminium garnet, and lutetium oxyorthosilicate for comparison, were evaluated in terms of sensitivity, spatial resolution, and count rate. The performance evaluation results showed that among the suggested scintillators, strontium hafnate can be considered as a promising alternative detector for high performance brain PET systems.

来源：评论

学校读者我要写书评

暂无评论

Multispectral photon-counting for medical imaging and beam characterization

引用

JOURNAL OF INSTRUMENTATION 2020年第2期15卷

作者： Brucken, E. Bharthuar, S. Emzir, M. Golovleva, M. Gadda, A. Hostettler, R. Harkonen, J. Kirschenmann, S. Litichevskyi, V. Luukka, P. Martikainen, L. Naaranoja, T. Ninca, I. Ott, J. Petrow, H. Purisha, Z. Siiskonen, T. Sarkka, S. Tikkanen, J. Tuuva, T. Winkler, A. Univ Helsinki Helsinki Inst Phys Gustaf Hallstromin Katu 2 FI-00014 Helsinki Finland Lappeenranta Lahti Univ Technol LUT Yliopistonkatu 34 FI-53850 Lappeenranta Finland Aalto Univ Otakaari 24 FI-00076 Espoo Finland Rudjer Boskovic Inst Zagreb 1000 Croatia Radiat & Nucl Safety Author STUK Laippatie 4 FI-00880 Helsinki Finland Detect Technol Oyj Otakaari 5A FI-02150 Espoo Finland

We present the current status of our project of developing a photon counting detector for medical imaging. An example motivation lays in producing a monitoring and dosimetry device for boron neutron capture therapy, currently not commercially available. Our approach combines in-house developed detectors based on cadmium telluride or thick silicon with readout chip technology developed for particle physics experiments at CERN. Here we describe the manufacturing process of our sensors as well as the processing steps for the assembly of first prototypes. The prototypes use currently the PSI46digV2.1-r readout chip. The accompanying readout electronics chain that was used for first measurements will also be discussed. Finally we present an advanced algorithm developed by us for image reconstruction using such photon counting detectors with focus on boron neutron capture therapy. This work is conducted within a consortium of Finnish research groups from Helsinki Institute of Physics, Aalto University, Lappeenranta-Lahti University of Technology LUT and Radiation and Nuclear Safety Authority (STUK) under the RADDESS program of Academy of Finland.

关键词： Gamma telescopes medical-image reconstruction methods and algorithms, computer-aided diagnosis Neutron detectors (cold, thermal, fast neutrons) X-ray detectors

来源：评论

学校读者我要写书评

暂无评论

Evaluation and simulation of breast cancer imaging devices using multi-criteria decision theory

引用

JOURNAL OF INSTRUMENTATION 2020年第5期15卷

作者： Erdagli, H. Ozsahin, D. Uzun Uzun, B. Near East Univ Dept Biomed Engn Near East BlvdTRNC Mersin 10 TR-99138 Nicosia Turkey Near East Univ DESAM Inst Near East BlvdTRNC Mersin 10 TR-99138 Nicosia Turkey Massachusetts Gen Hosp Gordon Ctr Med Imaging 125 Nashua St Boston MA 02114 USA Harvard Med Sch 125 Nashua St Boston MA 02114 USA Near East Univ Dept Math Near East BlvdTRNC Mersin 10 TR-99138 Nicosia Turkey

Breast cancer is the most common type of cancer seen in women. The incidence of breast cancer increases with age. The most important factor in breast cancer is that it is diagnosed before spreading to other organs by the blood or lymph circulation. When cancer is diagnosed at an early stage, the success rate of breast cancer treatment is over 90%. For this reason, breast cancer imaging devices should be used for early diagnosis of breast cancer. The main aim of this study is to shed more light on the parameters that affect the different imaging device alternatives for breast cancer and how these parameters affect the preference ranking of each imaging technique. In this study, the most commonly used imaging devices for breast cancer are analysed based on various parameters that are likely to affect the outcome of the imaging methods. These parameters are the cost per scan, cost of the device, radiation dose, specificity, sensitivity, total scan time, spatial resolution, comparison with the natural radiation exposure, real 3D, compression and claustrophobia. According to this study, positron emission mammography and breast computed tomography are the best breast cancer imaging techniques for both patients and hospitals. The analysis and ranking were evaluated and compared using fuzzy PROMETHEE, a multi-criteria decision-making technique.

关键词： computerized Tomography (CT) and Computed Radiography (CR) Gamma camera , SPECT, PET PET/CT, coronaryCTangiography (CTA) medical-image reconstruction methods and algorithms, computer-aided diagnosis X-ray mammography and scinto- and MRI-mammography

来源：评论

学校读者我要写书评

暂无评论

Tomographic imaging with Compton PET modules: ideal case and first implementation

引用

JOURNAL OF INSTRUMENTATION 2021年第4期16卷 T04007页

作者： Peng, P. Zhang, M. Zeraatkar, N. Qi, J. Cherry, S. R. Univ Calif Davis Dept Biomed Engn One Shields Ave Davis CA 95616 USA

In our previous studies, we demonstrated that the Compton PET module, a layer structure PET detector with side readout, can provide high performance in terms of spatial/energy/timing resolution, as well as high gamma ray detection efficiency. In this study, we investigate how to translate the high performance of the detector module into good quality reconstructed tomographic images. This study is performed using GATE simulation, as well as with physical experiments. Similar detector geometry is used in the simulation and experiment: two identical 4-layer detector modules are placed with face to face distance of 56 mm. In the simulation study, each layer consists of a 1-mm-pitch pixelated crystal array. In the experimental study, each layer is a monolithic crystal, which is virtually binned into 1 mm(2) cells to group single events according to the gamma ray interaction locations. A customized Derenzo phantom was placed between the two detector modules. By rotating the phantom using a motorized rotary stage, data along lines of response (LORs) at different angles were collected for reconstructing the tomographic image. The same reconstruction algorithm was used for both simulation and experimental studies. The results demonstrate that the simulation study could resolve 0.8 mm rods while the experimental study was able to resolve 1.0 mm rods.

来源：评论

学校读者我要写书评

暂无评论

Mammogram density classification using deep convolutional neural network

引用

JOURNAL OF INSTRUMENTATION 2021年第1期16卷

作者： Nithya, R. Santhi, B. SASTRA Deemed Univ Sch Comp Thanjavur 613402 Tamil Nadu India

Artificial intelligence plays an important role in the classification of medical images for computerized diagnosis of the disease. The computer-aided medical imaging analysis system is developed for breast tissue density classification in mammogram images. Mammogram density is considered as significant predictive markers for breast cancer detection, treatment and management. Recently, deep learning techniques achieved impressive results in computer-assisted disease diagnosis. The deep learning technique such as the convolution neural network (CNN) is used for automated classification of mammogram density as fatty, dense and glandular. This study investigates how computer-aided medical imaging analysis system provides a reliable classification of mammogram density. The proposed methodology is evaluated using a mini-MIAS (Mammogram image Analysis Society) database. We obtained an average accuracy of 98.5%. So, the proposed CAD system aids the clinicians in the classification of mammogram density.

关键词： medical-image reconstruction methods and algorithms, computer-aided diagnosis medical-image reconstruction methods and algorithms, computer-aided software X-ray mammography and scinto- and MRI-mammography

来源：评论

学校读者我要写书评

暂无评论

Simulation of novel scintillator crystals for brain PET

Simulation of novel scintillator crystals for brain PET

引用

15th Topical Seminar on Innovative Particle and Radiation Detectors (IPRD)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：