Pub Date : 2024-01-04DOI: 10.1109/TRPMS.2024.3349563
A. Sarno;R. M. Tucciariello;M. E. Fantacci;A. C. Traino;C. Valero;M. Stasi
In-silico clinical trials with digital patient models and simulated devices are an alternative to expensive and long clinical trials on patient population for testing X-ray breast imaging apparatuses. In this work, we simulated a linear-response a-Se detector as an X-ray absorber, neglecting some physical processes, such as electro-hole tracking and thermal noise. In order to tune characteristics of the simulated images toward those of the clinical scanners, the detector response curve, modulation transfer function (MTF), and normalized noise power spectrum (NNPS) were measured on a clinical mammographic unit. The same tests were replicated in-silico via a custom-made Monte Carlo code in order to define a suitable model to modify simulated images and to have realistic pixel values, noise, and spatial resolution. The proposed approach resulted to restore the slope and the magnitude of the NNPS in simulated images toward curves evaluated on a clinical scanner. Similarly, the proposed strategy for tuning noise and spatial resolution in simulated images led to a contrast-to-noise ratio (CNR) evaluated on a custom-made phantom which differed from those in measured images less than 16% in absolute value.
在测试 X 射线乳腺成像设备时，利用患者数字模型和模拟设备进行的模拟临床试验是一种替代昂贵而漫长的患者群体临床试验的方法。在这项工作中，我们模拟了作为 X 射线吸收器的线性响应 a-Se 探测器，忽略了一些物理过程，如电孔跟踪和热噪声。为了将模拟图像的特性调整为临床扫描仪的特性，我们在临床乳腺 X 射线照相设备上测量了探测器响应曲线、调制传递函数（MTF）和归一化噪声功率谱（NNPS）。为了定义一个合适的模型来修改模拟图像，并获得真实的像素值、噪声和空间分辨率，我们通过定制的蒙特卡洛代码在实验室中复制了相同的测试。所提出的方法使模拟图像中 NNPS 的斜率和幅度恢复到临床扫描仪上评估的曲线。同样，所提出的在模拟图像中调整噪声和空间分辨率的策略使在定制模型上评估的对比度-噪声比（CNR）与测量图像中的对比度-噪声比绝对值相差不到 16%。
{"title":"A Model for a Linear a-Se Detector in Simulated X-Ray Breast Imaging With Monte Carlo Software","authors":"A. Sarno;R. M. Tucciariello;M. E. Fantacci;A. C. Traino;C. Valero;M. Stasi","doi":"10.1109/TRPMS.2024.3349563","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3349563","url":null,"abstract":"In-silico clinical trials with digital patient models and simulated devices are an alternative to expensive and long clinical trials on patient population for testing X-ray breast imaging apparatuses. In this work, we simulated a linear-response a-Se detector as an X-ray absorber, neglecting some physical processes, such as electro-hole tracking and thermal noise. In order to tune characteristics of the simulated images toward those of the clinical scanners, the detector response curve, modulation transfer function (MTF), and normalized noise power spectrum (NNPS) were measured on a clinical mammographic unit. The same tests were replicated in-silico via a custom-made Monte Carlo code in order to define a suitable model to modify simulated images and to have realistic pixel values, noise, and spatial resolution. The proposed approach resulted to restore the slope and the magnitude of the NNPS in simulated images toward curves evaluated on a clinical scanner. Similarly, the proposed strategy for tuning noise and spatial resolution in simulated images led to a contrast-to-noise ratio (CNR) evaluated on a custom-made phantom which differed from those in measured images less than 16% in absolute value.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 3","pages":"263-268"},"PeriodicalIF":4.4,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10380795","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140031665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1109/TRPMS.2023.3342597
{"title":"IEEE Transactions on Radiation and Plasma Medical Sciences Information for Authors","authors":"","doi":"10.1109/TRPMS.2023.3342597","DOIUrl":"https://doi.org/10.1109/TRPMS.2023.3342597","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 1","pages":"C3-C3"},"PeriodicalIF":4.4,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10379498","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139081258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1109/TRPMS.2023.3342599
{"title":"IEEE Transactions on Radiation and Plasma Medical Sciences Publication Information","authors":"","doi":"10.1109/TRPMS.2023.3342599","DOIUrl":"https://doi.org/10.1109/TRPMS.2023.3342599","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 1","pages":"C2-C2"},"PeriodicalIF":4.4,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10379474","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139081285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Low-dose emission tomography (ET) plays a crucial role in medical imaging, enabling the acquisition of functional information for various biological processes while minimizing the patient dose. However, the inherent randomness in the photon counting process is a source of noise which is amplified in low-dose ET. This review article provides an overview of existing post-processing techniques, with an emphasis on deep neural network (NN) approaches. Furthermore, we explore future directions in the field of NN-based low-dose ET. This comprehensive examination sheds light on the potential of deep learning in enhancing the quality and resolution of low-dose ET images, ultimately advancing the field of medical imaging.
低剂量发射断层扫描（ET）在医学成像中起着至关重要的作用，它能获取各种生物过程的功能信息，同时最大限度地减少病人的剂量。然而，光子计数过程中固有的随机性是噪声的来源之一，而低剂量 ET 会放大这种噪声。这篇综述文章概述了现有的后处理技术，重点介绍了深度神经网络 (NN) 方法。此外，我们还探讨了基于 NN 的低剂量 ET 领域的未来发展方向。这一全面研究揭示了深度学习在提高低剂量 ET 图像质量和分辨率方面的潜力，最终推动医学成像领域的发展。
{"title":"A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising With Neural Network Approaches","authors":"Alexandre Bousse;Venkata Sai Sundar Kandarpa;Kuangyu Shi;Kuang Gong;Jae Sung Lee;Chi Liu;Dimitris Visvikis","doi":"10.1109/TRPMS.2023.3349194","DOIUrl":"10.1109/TRPMS.2023.3349194","url":null,"abstract":"Low-dose emission tomography (ET) plays a crucial role in medical imaging, enabling the acquisition of functional information for various biological processes while minimizing the patient dose. However, the inherent randomness in the photon counting process is a source of noise which is amplified in low-dose ET. This review article provides an overview of existing post-processing techniques, with an emphasis on deep neural network (NN) approaches. Furthermore, we explore future directions in the field of NN-based low-dose ET. This comprehensive examination sheds light on the potential of deep learning in enhancing the quality and resolution of low-dose ET images, ultimately advancing the field of medical imaging.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 4","pages":"333-347"},"PeriodicalIF":4.4,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10379513","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139138824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-27DOI: 10.1109/TRPMS.2023.3347602
Jiale Wang;Rui Guo;Ying Miao;Song Xue;Yu Zhang;Kuangyu Shi;Guoyan Zheng;Biao Li
Deep learning models have shown great potential in reducing low-dose (LD) positron emission tomography (PET) image noise by estimating full-dose (FD) images from the corresponding LD images. Those models, however, when trained on paired LD-FD PET images from a source scanner, fail to generalize well when applied to LD PET images from a target scanner, due to a phenomenon called “domain drift.” In this study, we present a method for cross-scanner LD PET image noise reduction. This is done via a self-ensembling framework using a limited number of paired LD-FD PET images and a large number of LD PET images from the target scanner. The self-ensembling framework leverages the paired 2-D slices from both scanners to learn a regression model. It additionally incorporates a consistency loss on the LD PET images from the target scanner to enhance the model’s generalization capability. We conduct experiments on three datasets, respectively, acquired from three different scanners, including a GE Discovery MI (DMI) scanner, a Siemens Biograph Vision 450 (Vision) scanner, and a UI uMI 780 (uMI) scanner. Results from our comprehensive experiments demonstrate the generalization capability of our method.
深度学习模型通过从相应的低剂量（LD）图像中估计全剂量（FD）图像，在减少低剂量（LD）正电子发射断层扫描（PET）图像噪声方面显示出巨大的潜力。然而，当这些模型在来自源扫描仪的成对 LD-FD PET 图像上进行训练时，由于一种称为 "域漂移 "的现象，当应用到来自目标扫描仪的 LD PET 图像时，这些模型不能很好地泛化。在这项研究中，我们提出了一种跨扫描仪 LD PET 图像降噪方法。该方法通过一个自组装框架来实现，该框架使用数量有限的配对 LD-FD PET 图像和大量来自目标扫描仪的 LD PET 图像。自组装框架利用两台扫描仪的配对二维切片来学习回归模型。此外，它还在目标扫描仪的 LD PET 图像上加入了一致性损失，以增强模型的泛化能力。我们在三个数据集上进行了实验，这三个数据集分别来自三个不同的扫描仪，包括 GE Discovery MI（DMI）扫描仪、Siemens Biograph Vision 450（Vision）扫描仪和 UI uMI 780（uMI）扫描仪。综合实验结果证明了我们方法的通用能力。
{"title":"Cross-Scanner Low-Dose Brain-PET Image Noise Reduction With Self-Ensembling","authors":"Jiale Wang;Rui Guo;Ying Miao;Song Xue;Yu Zhang;Kuangyu Shi;Guoyan Zheng;Biao Li","doi":"10.1109/TRPMS.2023.3347602","DOIUrl":"https://doi.org/10.1109/TRPMS.2023.3347602","url":null,"abstract":"Deep learning models have shown great potential in reducing low-dose (LD) positron emission tomography (PET) image noise by estimating full-dose (FD) images from the corresponding LD images. Those models, however, when trained on paired LD-FD PET images from a source scanner, fail to generalize well when applied to LD PET images from a target scanner, due to a phenomenon called “domain drift.” In this study, we present a method for cross-scanner LD PET image noise reduction. This is done via a self-ensembling framework using a limited number of paired LD-FD PET images and a large number of LD PET images from the target scanner. The self-ensembling framework leverages the paired 2-D slices from both scanners to learn a regression model. It additionally incorporates a consistency loss on the LD PET images from the target scanner to enhance the model’s generalization capability. We conduct experiments on three datasets, respectively, acquired from three different scanners, including a GE Discovery MI (DMI) scanner, a Siemens Biograph Vision 450 (Vision) scanner, and a UI uMI 780 (uMI) scanner. Results from our comprehensive experiments demonstrate the generalization capability of our method.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 4","pages":"391-401"},"PeriodicalIF":4.4,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140342654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-19DOI: 10.1109/TRPMS.2023.3344399
Shirin Pourashraf;Joshua W. Cates;Craig S. Levin
This article focuses on adapting linearization strategies for annihilation photon energy measurement for a time-of-flight (TOF) positron emission tomography (PET) system that achieves $sim 100$ picosecond (ps) full-width at half maximum (FWHM) coincidence time resolution (CTR). We have adapted the method of dynamic TOT (DynTOT) for our scalable TOF-PET detector readout electronics to linearize the energy spectra while maintaining $sim 100$ ps FWHM CTR. The linear response of the resulting DynTOT circuit facilitates improved energy performance compared with conventional time-over-threshold (TOT). Our detector design has the capability to position the 3-D coordinates of one or more 511-keV photon interactions. To facilitate this goal, DynTOT’s linearity across the entire energy range enables accurate measurement of low-energy interactions that is required for more accurate positioning of intercrystal scatter events. This DynTOT block is implemented by off-the-shelf discrete components and consumes only 11 mW power per detector layer unit design comprising 24:1 multiplexed energy and timing channels. We first validated the performance of DynTOT using single $3times 3times10$ mm3 LGSO scintillation crystals side-coupled to arrays of three $3times3$ mm2 SiPMs which achieved 511-keV photopeak energy resolutions of 13.6 ± 0.4%, 13.0 ± 0.8%, and 17.1 ± 0.6% for conventional pulse height, DynTOT, and conventional TOT methods, respectively. Then, we stretched by roughly 7-fold the DynTOT digital pulses (energy) generated from side-coupling $2times4$ array of $3times 3times10$ mm3 crystals to 24 SiPMs, and achieved 511-keV photopeak energy resolutions of 11.8 ± 0.7% with a dynamic range from less than 60 to 1274 keV, making that suitable for methods of accurate 3-D positioning of intercrystal-scatter interactions. Moreover, CTR with a highly multiplexed timing circuit was measured using these extended DynTOT pulses for energy gating, resulting in an average 108 ± 1.3 ps FWHM CTR.
{"title":"A Scalable Dynamic TOT Circuit for a 100 ps TOF-PET Detector Design to Improve Energy Linearity and Dynamic Range","authors":"Shirin Pourashraf;Joshua W. Cates;Craig S. Levin","doi":"10.1109/TRPMS.2023.3344399","DOIUrl":"https://doi.org/10.1109/TRPMS.2023.3344399","url":null,"abstract":"This article focuses on adapting linearization strategies for annihilation photon energy measurement for a time-of-flight (TOF) positron emission tomography (PET) system that achieves \u0000<inline-formula> <tex-math>$sim 100$ </tex-math></inline-formula>\u0000 picosecond (ps) full-width at half maximum (FWHM) coincidence time resolution (CTR). We have adapted the method of dynamic TOT (DynTOT) for our scalable TOF-PET detector readout electronics to linearize the energy spectra while maintaining \u0000<inline-formula> <tex-math>$sim 100$ </tex-math></inline-formula>\u0000 ps FWHM CTR. The linear response of the resulting DynTOT circuit facilitates improved energy performance compared with conventional time-over-threshold (TOT). Our detector design has the capability to position the 3-D coordinates of one or more 511-keV photon interactions. To facilitate this goal, DynTOT’s linearity across the entire energy range enables accurate measurement of low-energy interactions that is required for more accurate positioning of intercrystal scatter events. This DynTOT block is implemented by off-the-shelf discrete components and consumes only 11 mW power per detector layer unit design comprising 24:1 multiplexed energy and timing channels. We first validated the performance of DynTOT using single \u0000<inline-formula> <tex-math>$3times 3times10$ </tex-math></inline-formula>\u0000 mm3 LGSO scintillation crystals side-coupled to arrays of three \u0000<inline-formula> <tex-math>$3times3$ </tex-math></inline-formula>\u0000 mm2 SiPMs which achieved 511-keV photopeak energy resolutions of 13.6 ± 0.4%, 13.0 ± 0.8%, and 17.1 ± 0.6% for conventional pulse height, DynTOT, and conventional TOT methods, respectively. Then, we stretched by roughly 7-fold the DynTOT digital pulses (energy) generated from side-coupling \u0000<inline-formula> <tex-math>$2times4$ </tex-math></inline-formula>\u0000 array of \u0000<inline-formula> <tex-math>$3times 3times10$ </tex-math></inline-formula>\u0000 mm3 crystals to 24 SiPMs, and achieved 511-keV photopeak energy resolutions of 11.8 ± 0.7% with a dynamic range from less than 60 to 1274 keV, making that suitable for methods of accurate 3-D positioning of intercrystal-scatter interactions. Moreover, CTR with a highly multiplexed timing circuit was measured using these extended DynTOT pulses for energy gating, resulting in an average 108 ± 1.3 ps FWHM CTR.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 3","pages":"237-247"},"PeriodicalIF":4.4,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140031610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-13DOI: 10.1109/TRPMS.2023.3342709
Fellype do Nascimento;Aline da Graça Sampaio;Noala Vicensoto Moreira Milhan;Aline Vidal Lacerda Gontijo;Philipp Mattern;Torsten Gerling;Eric Robert;Cristiane Yumi Koga-Ito;Konstantin Georgiev Kostov
Plasma sources suitable to generate low-temperature plasmas has been fundamental for the advances in plasma medicine. In this research field, plasma sources must comply with stringent conditions for clinical applications. The main requirement to be met is the patient and operator’s safety and the ethical requirement of effectivity, which encompasses the electrical regulations, potential device toxicity, and effectiveness in relation to the desired treatment. All these issues are addressed by the German prestandard DIN SPEC 91315:2014–06 (DINSpec), which deals with the safety limits, risk assessment, and biological efficacy of plasma sources aimed for medical applications. In this work, a low cost, user-friendly, and flexible atmospheric pressure plasma jet (APPJ) device was characterized following the DINSpec guidelines. The device, which is still under development, proved to be safe for medical applications. It is capable of producing an APPJ with low patient leakage current and ultraviolet emission, gas temperature lower than 40 °C, production of harmful gases within the safety limits and low cytotoxicity. The most differentiating feature is that the device presented good antimicrobial efficacy even operating at frequency of the order of just a few hundred Hz, a value below that of most devices reported in the literature.
适合产生低温等离子体的等离子体源是等离子体医学发展的基础。在这一研究领域，等离子源必须符合临床应用的严格条件。需要满足的主要要求是病人和操作者的安全以及有效性的道德要求，其中包括电气法规、潜在的设备毒性以及与所需治疗相关的有效性。德国预标准 DIN SPEC 91315:2014-06（DINSpec）解决了所有这些问题，该标准涉及医疗应用等离子源的安全限制、风险评估和生物功效。在这项工作中，我们根据 DINSpec 指南，对一种低成本、用户友好且灵活的常压等离子体喷射（APPJ）设备进行了鉴定。该设备仍在开发中，但已证明可安全用于医疗应用。它能够生产出患者漏电流和紫外线辐射低、气体温度低于 40 {/deg}C、有害气体产生量在安全范围内、细胞毒性低的 APPJ。最与众不同的是，该设备即使在几百赫兹的频率下工作，也能产生良好的抗菌效果，这一数值低于文献中报道的大多数设备。
{"title":"A Low Cost, Flexible Atmospheric Pressure Plasma Jet Device With Good Antimicrobial Efficiency","authors":"Fellype do Nascimento;Aline da Graça Sampaio;Noala Vicensoto Moreira Milhan;Aline Vidal Lacerda Gontijo;Philipp Mattern;Torsten Gerling;Eric Robert;Cristiane Yumi Koga-Ito;Konstantin Georgiev Kostov","doi":"10.1109/TRPMS.2023.3342709","DOIUrl":"10.1109/TRPMS.2023.3342709","url":null,"abstract":"Plasma sources suitable to generate low-temperature plasmas has been fundamental for the advances in plasma medicine. In this research field, plasma sources must comply with stringent conditions for clinical applications. The main requirement to be met is the patient and operator’s safety and the ethical requirement of effectivity, which encompasses the electrical regulations, potential device toxicity, and effectiveness in relation to the desired treatment. All these issues are addressed by the German prestandard DIN SPEC 91315:2014–06 (DINSpec), which deals with the safety limits, risk assessment, and biological efficacy of plasma sources aimed for medical applications. In this work, a low cost, user-friendly, and flexible atmospheric pressure plasma jet (APPJ) device was characterized following the DINSpec guidelines. The device, which is still under development, proved to be safe for medical applications. It is capable of producing an APPJ with low patient leakage current and ultraviolet emission, gas temperature lower than 40 °C, production of harmful gases within the safety limits and low cytotoxicity. The most differentiating feature is that the device presented good antimicrobial efficacy even operating at frequency of the order of just a few hundred Hz, a value below that of most devices reported in the literature.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 3","pages":"307-322"},"PeriodicalIF":4.4,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139310856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article reviews the deep learning methods for computed tomography image denoising and deblurring separately and simultaneously. Then, we discuss promising directions in this field, such as a combination with large-scale pretrained models and large language models. Currently, deep learning is revolutionizing medical imaging in a data-driven manner. With rapidly evolving learning paradigms, related algorithms and models are making rapid progress toward clinical applications.
{"title":"CT Image Denoising and Deblurring With Deep Learning: Current Status and Perspectives","authors":"Yiming Lei;Chuang Niu;Junping Zhang;Ge Wang;Hongming Shan","doi":"10.1109/TRPMS.2023.3341903","DOIUrl":"https://doi.org/10.1109/TRPMS.2023.3341903","url":null,"abstract":"This article reviews the deep learning methods for computed tomography image denoising and deblurring separately and simultaneously. Then, we discuss promising directions in this field, such as a combination with large-scale pretrained models and large language models. Currently, deep learning is revolutionizing medical imaging in a data-driven manner. With rapidly evolving learning paradigms, related algorithms and models are making rapid progress toward clinical applications.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 2","pages":"153-172"},"PeriodicalIF":4.4,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139676142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-08DOI: 10.1109/TRPMS.2023.3340955
Hang Xu;Alessandro Perelli
In this work, we present a novel self-supervised method for low-dose computed tomography (LDCT) reconstruction. Reducing the radiation dose to patients during a computed tomography (CT) scan is a crucial challenge since the quality of the reconstruction highly degrades because of low photons or limited measurements. Supervised deep learning DL methods have shown the ability to remove noise in images but require accurate ground truth which can be obtained only by performing additional high-radiation CT scans. Therefore, we propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN). Based on the noise2inverse (N2I) method, we enforce in the training loss the equivariant property of rotation transformation, which is induced by the CT imaging system, to improve the quality of the CT image in a lower dose. Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented noise2inverse (RAN2I) method keeps better-image quality over a different range of sampling angles. Finally, the quantitative results demonstrate that RAN2I achieves higher-image quality compared to N2I, and experimental results of RAN2I on real projection data show comparable performance to supervised learning.
{"title":"Rotational Augmented Noise2Inverse for Low-Dose Computed Tomography Reconstruction","authors":"Hang Xu;Alessandro Perelli","doi":"10.1109/TRPMS.2023.3340955","DOIUrl":"10.1109/TRPMS.2023.3340955","url":null,"abstract":"In this work, we present a novel self-supervised method for low-dose computed tomography (LDCT) reconstruction. Reducing the radiation dose to patients during a computed tomography (CT) scan is a crucial challenge since the quality of the reconstruction highly degrades because of low photons or limited measurements. Supervised deep learning DL methods have shown the ability to remove noise in images but require accurate ground truth which can be obtained only by performing additional high-radiation CT scans. Therefore, we propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN). Based on the noise2inverse (N2I) method, we enforce in the training loss the equivariant property of rotation transformation, which is induced by the CT imaging system, to improve the quality of the CT image in a lower dose. Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented noise2inverse (RAN2I) method keeps better-image quality over a different range of sampling angles. Finally, the quantitative results demonstrate that RAN2I achieves higher-image quality compared to N2I, and experimental results of RAN2I on real projection data show comparable performance to supervised learning.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 2","pages":"208-221"},"PeriodicalIF":4.4,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138959144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-07DOI: 10.1109/TRPMS.2023.3340154
Bingkai Wang;Xu Yan;Zilan Xiong
Besides the charged particles and neutral reactive species, the temperature effect is another significant issue needs to concern during the plasma treatment of biological tissue, which has effects on therapeutic efficacy and the risk of burns. Due to the influence of multiple factors on the temperature effect, it’s a complex nonlinear problem. In this study, temperature rise and distribution uniformity under different parameters and moving trajectories on porcine skin were investigated, and then a surface temperature control strategy was proposed. A 3-D electric motor control platform was constructed for the jet moving during the treatment. First, the effects of factors, such as distance, voltage, and flow rate on temperature variation over porcine skin surface, were analyzed, and the trends of temperature variation under single-factor influence were summarized. Then, the temperature distribution of fixed-point treatment and the temperature superposition effect on the tissue surface under different trajectories were explored, and a trajectory scheme for achieving homogeneous temperature distribution was proposed. Finally, a closed-loop control model was designed to achieve the control objectives of constant temperature holding over a certain surface area and resistance to high-temperature interference in real time. This control scheme also has reference significance for other surface treatments such as material processing.
{"title":"Temperature Control Strategies of Atmospheric Plasma Jet for Tissue Treatment","authors":"Bingkai Wang;Xu Yan;Zilan Xiong","doi":"10.1109/TRPMS.2023.3340154","DOIUrl":"https://doi.org/10.1109/TRPMS.2023.3340154","url":null,"abstract":"Besides the charged particles and neutral reactive species, the temperature effect is another significant issue needs to concern during the plasma treatment of biological tissue, which has effects on therapeutic efficacy and the risk of burns. Due to the influence of multiple factors on the temperature effect, it’s a complex nonlinear problem. In this study, temperature rise and distribution uniformity under different parameters and moving trajectories on porcine skin were investigated, and then a surface temperature control strategy was proposed. A 3-D electric motor control platform was constructed for the jet moving during the treatment. First, the effects of factors, such as distance, voltage, and flow rate on temperature variation over porcine skin surface, were analyzed, and the trends of temperature variation under single-factor influence were summarized. Then, the temperature distribution of fixed-point treatment and the temperature superposition effect on the tissue surface under different trajectories were explored, and a trajectory scheme for achieving homogeneous temperature distribution was proposed. Finally, a closed-loop control model was designed to achieve the control objectives of constant temperature holding over a certain surface area and resistance to high-temperature interference in real time. This control scheme also has reference significance for other surface treatments such as material processing.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 1","pages":"105-112"},"PeriodicalIF":4.4,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139081229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：