Pub Date : 2025-01-20DOI: 10.1109/TRPMS.2025.3531536
Pablo Cabrales;Víctor V. Onecha;David Izquierdo-García;Luis Mario Fraile;José Manuel Udías;Joaquín L. Herraiz
In proton therapy (PT), accurate dose delivery verification is critical for detecting treatment plan deviations. This can be achieved by imaging activated positron emitters with a positron emission tomography (PET) acquisition and converting the data into a delivered dose image. This work presents PROTOTWIN-PET (PROTOn therapy digital TWIN models for dose verification with PET), a patient-specific, deep learning (DL) and GPU-based workflow for 3-D dose verification. The proposed workflow generates a dataset of simulated, realistic 3-D PET and dose pairs that reflect possible clinical deviations in patient positioning and physical parameters. Using this dataset, a DL model is trained to estimate the delivered dose from the PET image, incorporating a deviation-predicting branch (DPB) to estimate patient positioning deviations. PROTOTWIN-PET is demonstrated on a two-field oropharyngeal cancer treatment plan, estimating the delivered dose in milliseconds with an average mean relative error of 0.6% and near-perfect gamma passing rates (3 mm, 3%). Positioning deviations are estimated on average within a tenth of a millimeter and degree. PROTOTWIN-PET can be implemented within the one-day interval between the plan CT acquisition and the first treatment session, potentially enabling timely treatment plan adjustments and maximizing the precision of PT. PROTOTWIN-PET is available at github.com/pcabrales/prototwin-pet.git.
在质子治疗（PT）中，准确的剂量传递验证对于检测治疗计划偏差至关重要。这可以通过使用正电子发射断层扫描（PET）采集对激活的正电子发射体进行成像并将数据转换为交付的剂量图像来实现。这项工作提出了PROTOTWIN-PET（用于PET剂量验证的质子治疗数字TWIN模型），这是一种针对患者的、基于深度学习（DL）和gpu的3d剂量验证工作流程。所提出的工作流程生成一个模拟的、真实的3-D PET和剂量对的数据集，这些数据集反映了患者体位和身体参数可能的临床偏差。使用该数据集，训练DL模型来估计PET图像中的放射剂量，并结合偏差预测分支（DPB）来估计患者的定位偏差。PROTOTWIN-PET在双场口咽癌治疗方案中得到验证，以毫秒为单位估计剂量，平均相对误差为0.6%，伽玛通过率接近完美（3 mm, 3%）。定位偏差估计平均在十分之一毫米和度以内。PROTOTWIN-PET可以在计划CT采集和第一次治疗之间的一天间隔内实施，有可能及时调整治疗计划并最大化PT的精度。PROTOTWIN-PET可在github.com/pcabrales/prototwin-pet.git上获得。
{"title":"PROTOTWIN-PET: A Deep Learning and GPU-Based Workflow for Dose Verification in Proton Therapy With PET","authors":"Pablo Cabrales;Víctor V. Onecha;David Izquierdo-García;Luis Mario Fraile;José Manuel Udías;Joaquín L. Herraiz","doi":"10.1109/TRPMS.2025.3531536","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3531536","url":null,"abstract":"In proton therapy (PT), accurate dose delivery verification is critical for detecting treatment plan deviations. This can be achieved by imaging activated positron emitters with a positron emission tomography (PET) acquisition and converting the data into a delivered dose image. This work presents PROTOTWIN-PET (PROTOn therapy digital TWIN models for dose verification with PET), a patient-specific, deep learning (DL) and GPU-based workflow for 3-D dose verification. The proposed workflow generates a dataset of simulated, realistic 3-D PET and dose pairs that reflect possible clinical deviations in patient positioning and physical parameters. Using this dataset, a DL model is trained to estimate the delivered dose from the PET image, incorporating a deviation-predicting branch (DPB) to estimate patient positioning deviations. PROTOTWIN-PET is demonstrated on a two-field oropharyngeal cancer treatment plan, estimating the delivered dose in milliseconds with an average mean relative error of 0.6% and near-perfect gamma passing rates (3 mm, 3%). Positioning deviations are estimated on average within a tenth of a millimeter and degree. PROTOTWIN-PET can be implemented within the one-day interval between the plan CT acquisition and the first treatment session, potentially enabling timely treatment plan adjustments and maximizing the precision of PT. PROTOTWIN-PET is available at github.com/pcabrales/prototwin-pet.git.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 6","pages":"821-831"},"PeriodicalIF":4.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10847605","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597712","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 : 2025-01-17DOI: 10.1109/TRPMS.2025.3531225
Hsin-Hsiung Huang;Zheyuan Zhu;Slun Booppasiri;Zhuo Chen;Shuo Pang;Chien-Min Kao
Positron emission tomography (PET) is an important modality for diagnosing diseases, such as cancer and Alzheimer’s disease, capable of revealing the uptake of radiolabeled molecules that target specific pathological markers of the diseases. Recently, positronium lifetime imaging (PLI) that adds to traditional PET the ability to explore properties of the tissue microenvironment beyond tracer uptake has been demonstrated with time-of-flight (TOF) PET and the use of nonpure positron emitters. However, achieving accurate reconstruction of lifetime images from data acquired by systems having a finite TOF resolution still presents a challenge. This article focuses on the 2-D PLI, introducing a maximum-likelihood estimation (MLE) method that employs an exponentially modified Gaussian (EMG) probability distribution that describes the positronium lifetime data produced by TOF PET. We evaluate the performance of our EMG-based MLE method against approaches using exponential likelihood functions and penalized surrogate methods. Results from computer-simulated data reveal that the proposed EMG-MLE method can yield quantitatively accurate lifetime images. We also demonstrate that the proposed MLE formulation can be extended to handle PLI data containing multiple positron populations.
{"title":"A Statistical Reconstruction Algorithm for Positronium Lifetime Imaging Using Time-of-Flight Positron Emission Tomography","authors":"Hsin-Hsiung Huang;Zheyuan Zhu;Slun Booppasiri;Zhuo Chen;Shuo Pang;Chien-Min Kao","doi":"10.1109/TRPMS.2025.3531225","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3531225","url":null,"abstract":"Positron emission tomography (PET) is an important modality for diagnosing diseases, such as cancer and Alzheimer’s disease, capable of revealing the uptake of radiolabeled molecules that target specific pathological markers of the diseases. Recently, positronium lifetime imaging (PLI) that adds to traditional PET the ability to explore properties of the tissue microenvironment beyond tracer uptake has been demonstrated with time-of-flight (TOF) PET and the use of nonpure positron emitters. However, achieving accurate reconstruction of lifetime images from data acquired by systems having a finite TOF resolution still presents a challenge. This article focuses on the 2-D PLI, introducing a maximum-likelihood estimation (MLE) method that employs an exponentially modified Gaussian (EMG) probability distribution that describes the positronium lifetime data produced by TOF PET. We evaluate the performance of our EMG-based MLE method against approaches using exponential likelihood functions and penalized surrogate methods. Results from computer-simulated data reveal that the proposed EMG-MLE method can yield quantitatively accurate lifetime images. We also demonstrate that the proposed MLE formulation can be extended to handle PLI data containing multiple positron populations.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 4","pages":"478-486"},"PeriodicalIF":4.6,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10844904","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761358","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 : 2025-01-16DOI: 10.1109/TRPMS.2025.3528728
Weijie Gan;Huidong Xie;Carl von Gall;Günther Platsch;Michael T. Jurkiewicz;Andrea Andrade;Udunna C. Anazodo;Ulugbek S. Kamilov;Hongyu An;Jorge Cabello
Anatomically guided positron emission tomography (PET) reconstruction using magnetic resonance imaging (MRI) information has been shown to have the potential to improve PET image quality. However, these improvements are limited to PET scans with paired MRI information. In this work, we employed a diffusion probabilistic model (DPM) to infer T1-weighted-MRI (deep-MRI) images from FDG-PET brain images. We then use the DPM-generated T1w-MRI to guide the PET reconstruction. The model was trained with brain FDG scans, and tested in datasets containing multiple levels of counts. Deep-MRI images appeared somewhat degraded and in some cases showed inaccuracies compared to the acquired MRI images. Regarding PET image quality, volume of interest analysis in different brain regions showed that both PET reconstructed images using the acquired and the deep-MRI images improved image quality compared to ordered subset expected maximum (OSEM). Same conclusions were found analysing the decimated datasets. A subjective evaluation performed by two physicians confirmed that OSEM scored consistently worse than the MRI-guided PET images and no significant differences were observed between the MRI-guided PET images. This proof of concept shows that it is possible to infer DPM-based MRI imagery to guide the PET reconstruction, enabling the possibility of changing reconstruction parameters, such as the strength of the prior on anatomically guided PET reconstruction in the absence of MRI.
{"title":"Pseudo-MRI-Guided PET Image Reconstruction Method Based on a Diffusion Probabilistic Model","authors":"Weijie Gan;Huidong Xie;Carl von Gall;Günther Platsch;Michael T. Jurkiewicz;Andrea Andrade;Udunna C. Anazodo;Ulugbek S. Kamilov;Hongyu An;Jorge Cabello","doi":"10.1109/TRPMS.2025.3528728","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3528728","url":null,"abstract":"Anatomically guided positron emission tomography (PET) reconstruction using magnetic resonance imaging (MRI) information has been shown to have the potential to improve PET image quality. However, these improvements are limited to PET scans with paired MRI information. In this work, we employed a diffusion probabilistic model (DPM) to infer T1-weighted-MRI (deep-MRI) images from FDG-PET brain images. We then use the DPM-generated T1w-MRI to guide the PET reconstruction. The model was trained with brain FDG scans, and tested in datasets containing multiple levels of counts. Deep-MRI images appeared somewhat degraded and in some cases showed inaccuracies compared to the acquired MRI images. Regarding PET image quality, volume of interest analysis in different brain regions showed that both PET reconstructed images using the acquired and the deep-MRI images improved image quality compared to ordered subset expected maximum (OSEM). Same conclusions were found analysing the decimated datasets. A subjective evaluation performed by two physicians confirmed that OSEM scored consistently worse than the MRI-guided PET images and no significant differences were observed between the MRI-guided PET images. This proof of concept shows that it is possible to infer DPM-based MRI imagery to guide the PET reconstruction, enabling the possibility of changing reconstruction parameters, such as the strength of the prior on anatomically guided PET reconstruction in the absence of MRI.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 4","pages":"412-420"},"PeriodicalIF":4.6,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10843797","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761569","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 : 2025-01-16DOI: 10.1109/TRPMS.2025.3530774
S. Di Giacomo;M. Ronchi;M. Amadori;G. Borghi;M. Carminati;C. Fiorini
machine learning (ML) accelerators represent an attractive area of research, offering the potential to streamline algorithmic complexity and handle massively parallel in-memory computations, with substantial improvements in energy efficiency and speed related to data transmission and processing. Analog computing can further boost ML acceleration due to its superior computational density compared to digital platforms and its ability to deal with analog data acquired from sensors. The analog approach to edge computing can be beneficial for signal processing in long-axial field-of-view (LA-FOV) scintillation detectors used in nuclear medical tomographic imaging (PET and SPECT). In such scenarios, the deployment of analog computations in close proximity to the sensors would significantly diminish the volume of data that must be digitized and transmitted, and ML reconstruction algorithms, such as neural networks (NNs), could enhance the image reconstruction process. We present an ASIC fabricated in 0.35-$mathrm { {mu }text {m}}$ CMOS technology implementing an analog NN featuring 64 inputs, two hidden layers of 20 neurons each, and two outputs. It is intended for use in the reconstruction of the 2-D position of interaction of gamma photons inside a monolithic scintillator crystal readout by a matrix of silicon photomultipliers (SiPMs) for PET/SPECT applications. This chip can interact directly with analog signals originating from the photosensors, and is able to provide the predicted interaction coordinates of the gamma-ray at its output. The vector-matrix multiplications for inference are executed in the charge domain using programmable switched capacitors (SC) organized in crossbar arrays. Experimental measurements of this first proof-of-concept prototype ASIC are reported, demonstrating the correct functionality of the NN circuit. With an energy efficiency of $50~{mathrm {GOPS/W}}$ and power consumption of $17~{mathrm {mW}}$ per inference, the achieved results are promising for the integration of the ASIC with the photodetector front-end for in situ analog computing.
{"title":"Experimental Validation of ANNA: Analog Neural Network ASIC for Event Positioning in Monolithic Scintillation Detectors","authors":"S. Di Giacomo;M. Ronchi;M. Amadori;G. Borghi;M. Carminati;C. Fiorini","doi":"10.1109/TRPMS.2025.3530774","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3530774","url":null,"abstract":"machine learning (ML) accelerators represent an attractive area of research, offering the potential to streamline algorithmic complexity and handle massively parallel in-memory computations, with substantial improvements in energy efficiency and speed related to data transmission and processing. Analog computing can further boost ML acceleration due to its superior computational density compared to digital platforms and its ability to deal with analog data acquired from sensors. The analog approach to edge computing can be beneficial for signal processing in long-axial field-of-view (LA-FOV) scintillation detectors used in nuclear medical tomographic imaging (PET and SPECT). In such scenarios, the deployment of analog computations in close proximity to the sensors would significantly diminish the volume of data that must be digitized and transmitted, and ML reconstruction algorithms, such as neural networks (NNs), could enhance the image reconstruction process. We present an ASIC fabricated in 0.35-<inline-formula> <tex-math>$mathrm { {mu }text {m}}$ </tex-math></inline-formula> CMOS technology implementing an analog NN featuring 64 inputs, two hidden layers of 20 neurons each, and two outputs. It is intended for use in the reconstruction of the 2-D position of interaction of gamma photons inside a monolithic scintillator crystal readout by a matrix of silicon photomultipliers (SiPMs) for PET/SPECT applications. This chip can interact directly with analog signals originating from the photosensors, and is able to provide the predicted interaction coordinates of the gamma-ray at its output. The vector-matrix multiplications for inference are executed in the charge domain using programmable switched capacitors (SC) organized in crossbar arrays. Experimental measurements of this first proof-of-concept prototype ASIC are reported, demonstrating the correct functionality of the NN circuit. With an energy efficiency of <inline-formula> <tex-math>$50~{mathrm {GOPS/W}}$ </tex-math></inline-formula> and power consumption of <inline-formula> <tex-math>$17~{mathrm {mW}}$ </tex-math></inline-formula> per inference, the achieved results are promising for the integration of the ASIC with the photodetector front-end for in situ analog computing.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 5","pages":"542-552"},"PeriodicalIF":4.6,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900602","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}
Megavoltage computed tomography (MVCT) on the tomotherapy system has been widely used as a tomographic imaging modality for image-guided radiotherapy. However, the quality of MVCT images is often compromised by poor tissue contrast and significant noise. Conventional networks designed to enhance CT quality typically require the clean ground-truth images, which are not feasible for MVCT. In this study, we introduce a semi-supervised framework named Semi-Diff, which leverages the denoising diffusion probabilistic model and the prior information sourced from kilovoltage computed tomography (KVCT) to address challenges in MVCT enhancement. Specifically, employing a discriminative prior learning method, we first learn a mapping function to estimate MVCT noise and perform state matching. With this state matching dictionary, we then represent the MVCT image as a sample from an intermediate posterior distribution within the diffusion Markov chain, which enables the reverse conditional sampling process of the diffusion model to start directly from the noisy MVCT images. To fully explore the prior information from the plan KVCT images of the same patients, we introduce a novel diffusion base network called RefNet, whose dynamic feature aggregation module can extract and align the relevant features from reference KVCT image to enhance image restoration performance. Quantitative evaluations using simulated digital phantom data show that the proposed Semi-Diff model achieves the average FSIM score of 0.954, PSNR score of 33.22 dB, and RMSE value of 0.023, demonstrating improvements of approximately 2.16% in FSIM, 0.59% in PSNR, and a reduction of 3.58% in RMSE compared to the best-performing baseline method. Results from physical phantom and patient data further validate the model’s superior performance in noise suppression and structural preservation.
{"title":"Semi-Supervised MVCT Enhancement Using Diffusion Model Refined With KVCT Priors","authors":"Mengxun Zheng;Long Tang;Peiwen Liang;Shuang Jin;Xiaotong Xu;Zhe Su;Hua Zhang","doi":"10.1109/TRPMS.2025.3529582","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3529582","url":null,"abstract":"Megavoltage computed tomography (MVCT) on the tomotherapy system has been widely used as a tomographic imaging modality for image-guided radiotherapy. However, the quality of MVCT images is often compromised by poor tissue contrast and significant noise. Conventional networks designed to enhance CT quality typically require the clean ground-truth images, which are not feasible for MVCT. In this study, we introduce a semi-supervised framework named Semi-Diff, which leverages the denoising diffusion probabilistic model and the prior information sourced from kilovoltage computed tomography (KVCT) to address challenges in MVCT enhancement. Specifically, employing a discriminative prior learning method, we first learn a mapping function to estimate MVCT noise and perform state matching. With this state matching dictionary, we then represent the MVCT image as a sample from an intermediate posterior distribution within the diffusion Markov chain, which enables the reverse conditional sampling process of the diffusion model to start directly from the noisy MVCT images. To fully explore the prior information from the plan KVCT images of the same patients, we introduce a novel diffusion base network called RefNet, whose dynamic feature aggregation module can extract and align the relevant features from reference KVCT image to enhance image restoration performance. Quantitative evaluations using simulated digital phantom data show that the proposed Semi-Diff model achieves the average FSIM score of 0.954, PSNR score of 33.22 dB, and RMSE value of 0.023, demonstrating improvements of approximately 2.16% in FSIM, 0.59% in PSNR, and a reduction of 3.58% in RMSE compared to the best-performing baseline method. Results from physical phantom and patient data further validate the model’s superior performance in noise suppression and structural preservation.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 5","pages":"667-679"},"PeriodicalIF":4.6,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900603","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 : 2025-01-13DOI: 10.1109/TRPMS.2025.3528953
Haixia Xie;Haijun Yu;Song Ni;Chuandong Tan;Genyuan Zhang;Zihao Wang;Meina Zhan;Fenglin Liu
Micro computed tomography (Micro-CT) is widely used across various fields for high-resolution imaging. Recently, our previous work developed a source translation-based computed tomography (STCT) model to achieve high-resolution imaging for large objects. However, when the sample size exceeds the field-of-view (FOV) of STCT, the traditional algorithms cannot recover the invisible null-space information from incomplete projection data. To address this issue, we propose the score-based generative null-space shuttles (SGNS) algorithm, which employs score-based generative models to learn prior information and restores missing null-space information through a null-space shuttle approach during the sampling process. To ensure consistency in the generated results, the measured data are introduced as ground truth information during the sampling phase. The numerical and physical experiments demonstrate our algorithm can effectively eliminate artifacts caused by insufficient projection data and recover more detailed image information. In addition, by using range-null space hallucination maps, we demonstrate the proposed algorithm can reliably and stably reconstruct cross-sectional images of objects beyond the FOV.
{"title":"Score-Based Generative Null-Space Shuttle for the Field-of-View of STCT Expansion","authors":"Haixia Xie;Haijun Yu;Song Ni;Chuandong Tan;Genyuan Zhang;Zihao Wang;Meina Zhan;Fenglin Liu","doi":"10.1109/TRPMS.2025.3528953","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3528953","url":null,"abstract":"Micro computed tomography (Micro-CT) is widely used across various fields for high-resolution imaging. Recently, our previous work developed a source translation-based computed tomography (STCT) model to achieve high-resolution imaging for large objects. However, when the sample size exceeds the field-of-view (FOV) of STCT, the traditional algorithms cannot recover the invisible null-space information from incomplete projection data. To address this issue, we propose the score-based generative null-space shuttles (SGNS) algorithm, which employs score-based generative models to learn prior information and restores missing null-space information through a null-space shuttle approach during the sampling process. To ensure consistency in the generated results, the measured data are introduced as ground truth information during the sampling phase. The numerical and physical experiments demonstrate our algorithm can effectively eliminate artifacts caused by insufficient projection data and recover more detailed image information. In addition, by using range-null space hallucination maps, we demonstrate the proposed algorithm can reliably and stably reconstruct cross-sectional images of objects beyond the FOV.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 6","pages":"776-787"},"PeriodicalIF":4.6,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597710","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 : 2025-01-09DOI: 10.1109/TRPMS.2025.3527874
Pedro M. C. C. Encarnação;Pedro M. M. Correia;Baharak Mehrdel;Isabella Bredwell;João F. C. A. Veloso;Javier Caravaca;Youngho Seo
Radiopharmaceutical therapy has demonstrated a high efficacy in the treatment of various tumor types. One of the radionuclides already used in the clinic is 177Lu, a beta emitter that also emits several photons imageable with single photon emission computed tomography (SPECT). Quantitative imaging of 177Lu is critical for developing new radiopharmaceuticals. Energy resolution is an important factor when imaging multiple photon emissions. Solid-state detectors offer a superior performance over scintillators, that are commonly used in commercially available preclinical SPECT scanners. This study demonstrates the feasibility of 99mTc and 177Lu quantitative imaging in mouse phantoms, individually and simultaneously, with a SPECT prototype built with four CdZnTe (CZT) detector heads and a custom-designed and energy-optimized parallel-hole tungsten collimator. With a custom implementation of the one-step late (OSL) image reconstruction algorithm, the system is capable of imaging energies from ~70 to 250 keV. Above 250 keV, images were significantly affected by septal penetration, consistent with the collimator design. A recovery coefficient within 25% was obtained for activities as low as 2 kBq/mL for 99mTc and 45% for 177Lu. Compared to a commercial NaI-based preclinical SPECT (VECTor4/CT), our prototype showed a superior energy resolution (<5% at 140 keV), a similar uniformity with a high-compact design.
{"title":"Individual and Simultaneous Imaging of ⁹⁹mTc and ¹⁷⁷Lu With a Preclinical Broad Energy-Spectrum CZT-Based SPECT","authors":"Pedro M. C. C. Encarnação;Pedro M. M. Correia;Baharak Mehrdel;Isabella Bredwell;João F. C. A. Veloso;Javier Caravaca;Youngho Seo","doi":"10.1109/TRPMS.2025.3527874","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3527874","url":null,"abstract":"Radiopharmaceutical therapy has demonstrated a high efficacy in the treatment of various tumor types. One of the radionuclides already used in the clinic is 177Lu, a beta emitter that also emits several photons imageable with single photon emission computed tomography (SPECT). Quantitative imaging of 177Lu is critical for developing new radiopharmaceuticals. Energy resolution is an important factor when imaging multiple photon emissions. Solid-state detectors offer a superior performance over scintillators, that are commonly used in commercially available preclinical SPECT scanners. This study demonstrates the feasibility of 99mTc and 177Lu quantitative imaging in mouse phantoms, individually and simultaneously, with a SPECT prototype built with four CdZnTe (CZT) detector heads and a custom-designed and energy-optimized parallel-hole tungsten collimator. With a custom implementation of the one-step late (OSL) image reconstruction algorithm, the system is capable of imaging energies from ~70 to 250 keV. Above 250 keV, images were significantly affected by septal penetration, consistent with the collimator design. A recovery coefficient within 25% was obtained for activities as low as 2 kBq/mL for 99mTc and 45% for 177Lu. Compared to a commercial NaI-based preclinical SPECT (VECTor4/CT), our prototype showed a superior energy resolution (<5% at 140 keV), a similar uniformity with a high-compact design.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 5","pages":"564-577"},"PeriodicalIF":4.6,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900518","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}
The study evaluates the performance of the DigitMI 930 positron emission tomography (PET)/CT system, featuring detector modules with an 1:1:1 coupling of the scintillation crystal, the photosensor, and the electronic readout channel, in adherence to the NEMA NU 2-2018 standard. Moreover, brain and whole-body images were used to assess image quality. The radial, tangential, and axial resolutions at a radial offset of 1 cm were 3.9, 3.9, and 3.7 mm, respectively. The average sensitivity was measured at 16.2 cps/kBq. The peak noise-equivalent count rate was calculated as 412.5 kcps at 34.5 kBq/mL. At an activity concentration of 5.3 kBq/mL, the scatter fraction was 37.5%, and the time-of-flight (TOF) resolution was 248.6 ps. The contrast recovery coefficient ranged from 70.6% to 87.7% with TOF reconstruction. Despite increased noise in shorter whole-body scans, critical lesions remained identifiable at 20-s durations per bed position. The DigitMI 930 PET/CT system demonstrates a strong overall performance, particularly noteworthy for its low spatial resolution to crystal size ratio in comparison to other clinical PET systems. Moreover, the clinical studies indicate that the DigitMI 930 PET/CT system is capable of generating high-quality clinical images with high sensitivity for detecting small lesions, even at low injection doses or short scanning times.
{"title":"Performance Evaluation of New PET/CT DigitMI 930","authors":"Bo Zhang;Bingxuan Li;Lei Fang;Xiaoyun Zhou;Ang Li;Xuan Zhang;Yang Liu;Zhuo Wang;Chien-Min Kao;Yuqing Liu;Xiaohua Zhu;Lin Wan;Peng Xiao;Xun Chen;Hidehiro Iida;Juhani Knuuti;Qingguo Xie","doi":"10.1109/TRPMS.2025.3526659","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3526659","url":null,"abstract":"The study evaluates the performance of the DigitMI 930 positron emission tomography (PET)/CT system, featuring detector modules with an 1:1:1 coupling of the scintillation crystal, the photosensor, and the electronic readout channel, in adherence to the NEMA NU 2-2018 standard. Moreover, brain and whole-body images were used to assess image quality. The radial, tangential, and axial resolutions at a radial offset of 1 cm were 3.9, 3.9, and 3.7 mm, respectively. The average sensitivity was measured at 16.2 cps/kBq. The peak noise-equivalent count rate was calculated as 412.5 kcps at 34.5 kBq/mL. At an activity concentration of 5.3 kBq/mL, the scatter fraction was 37.5%, and the time-of-flight (TOF) resolution was 248.6 ps. The contrast recovery coefficient ranged from 70.6% to 87.7% with TOF reconstruction. Despite increased noise in shorter whole-body scans, critical lesions remained identifiable at 20-s durations per bed position. The DigitMI 930 PET/CT system demonstrates a strong overall performance, particularly noteworthy for its low spatial resolution to crystal size ratio in comparison to other clinical PET systems. Moreover, the clinical studies indicate that the DigitMI 930 PET/CT system is capable of generating high-quality clinical images with high sensitivity for detecting small lesions, even at low injection doses or short scanning times.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 5","pages":"578-585"},"PeriodicalIF":4.6,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900638","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 : 2025-01-03DOI: 10.1109/TRPMS.2025.3525732
Lu Wen;Jianghong Xiao;Zhenghao Feng;Xiao Chen;Jiliu Zhou;Xingchen Peng;Yan Wang
Radiotherapy is a primary treatment for cancers to apply sufficient radiation dose to the planning target volume (PTV) while minimizing dose hazards to the organs at risk (OARs). Recently, convolutional neural network (CNN) has automated radiotherapy plan making by directly predicting the dose distribution maps. However, existing CNN-based methods ignore two critical dose distribution characteristics, i.e., 1) the spatial distribution of different dose values and 2) dose differences in the interior and exterior PTV, resulting in suboptimal predictions. In this article, we propose a distribution-driven deep network, named D3Net, to achieve automatic dose prediction by simultaneously considering its spatial distribution and dose differences. Concretely, D3Net is constructed by a traditional CNN framework embedded with a transformer encoder to extract both local and global dosimetric information. To investigate the spatial distribution of different dose values, we present an innovative discrete multidose constraint to measure multiple dose values in the predicted dose map with discrete dose masks. Besides, we design a PTV-guided triplet constraint to utilize the explicit geometry of PTV to refine dose feature representations in the interior and exterior PTV, thus facilitating the dose differences. The proposed method is validated on the two clinical datasets, achieving $| {{Delta }{D}}_{98} |$ values of 1.87 Gy for rectum (REC) cancer and 1.08 Gy for cervical cancer. The experimental results surpass those of other state-of-the-art (SOTA) methods, verifying that the predicted dose distribution of our method is more closed to the clinically approved one.
{"title":"D3Net: A Distribution-Driven Deep Network for Radiotherapy Dose Prediction","authors":"Lu Wen;Jianghong Xiao;Zhenghao Feng;Xiao Chen;Jiliu Zhou;Xingchen Peng;Yan Wang","doi":"10.1109/TRPMS.2025.3525732","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3525732","url":null,"abstract":"Radiotherapy is a primary treatment for cancers to apply sufficient radiation dose to the planning target volume (PTV) while minimizing dose hazards to the organs at risk (OARs). Recently, convolutional neural network (CNN) has automated radiotherapy plan making by directly predicting the dose distribution maps. However, existing CNN-based methods ignore two critical dose distribution characteristics, i.e., 1) the spatial distribution of different dose values and 2) dose differences in the interior and exterior PTV, resulting in suboptimal predictions. In this article, we propose a distribution-driven deep network, named D3Net, to achieve automatic dose prediction by simultaneously considering its spatial distribution and dose differences. Concretely, D3Net is constructed by a traditional CNN framework embedded with a transformer encoder to extract both local and global dosimetric information. To investigate the spatial distribution of different dose values, we present an innovative discrete multidose constraint to measure multiple dose values in the predicted dose map with discrete dose masks. Besides, we design a PTV-guided triplet constraint to utilize the explicit geometry of PTV to refine dose feature representations in the interior and exterior PTV, thus facilitating the dose differences. The proposed method is validated on the two clinical datasets, achieving <inline-formula> <tex-math>$| {{Delta }{D}}_{98} |$ </tex-math></inline-formula> values of 1.87 Gy for rectum (REC) cancer and 1.08 Gy for cervical cancer. The experimental results surpass those of other state-of-the-art (SOTA) methods, verifying that the predicted dose distribution of our method is more closed to the clinically approved one.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 4","pages":"497-507"},"PeriodicalIF":4.6,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10824860","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761464","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 : 2025-01-02DOI: 10.1109/TRPMS.2024.3519397
{"title":"IEEE Transactions on Radiation and Plasma Medical Sciences Information for Authors","authors":"","doi":"10.1109/TRPMS.2024.3519397","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3519397","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 1","pages":"C2-C2"},"PeriodicalIF":4.6,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10820139","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142912397","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}
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：