Tomography最新文献_第10页

Dedicated Cone-Beam Breast CT: Reproducibility of Volumetric Glandular Fraction with Advanced Image Reconstruction Methods 专用锥形束乳腺CT:用先进的图像重建方法再现体积腺体分数

4区医学

Tomography Pub Date : 2023-11-02 DOI: 10.3390/tomography9060160

Srinivasan Vedantham, Hsin Wu Tseng, Zhiyang Fu, Hsiao-Hui Sherry Chow

{"title":"Dedicated Cone-Beam Breast CT: Reproducibility of Volumetric Glandular Fraction with Advanced Image Reconstruction Methods","authors":"Srinivasan Vedantham, Hsin Wu Tseng, Zhiyang Fu, Hsiao-Hui Sherry Chow","doi":"10.3390/tomography9060160","DOIUrl":"https://doi.org/10.3390/tomography9060160","url":null,"abstract":"Dedicated cone-beam breast computed tomography (CBBCT) is an emerging modality and provides fully three-dimensional (3D) images of the uncompressed breast at an isotropic voxel resolution. In an effort to translate this modality to breast cancer screening, advanced image reconstruction methods are being pursued. Since radiographic breast density is an established risk factor for breast cancer and CBBCT provides volumetric data, this study investigates the reproducibility of the volumetric glandular fraction (VGF), defined as the proportion of fibroglandular tissue volume relative to the total breast volume excluding the skin. Four image reconstruction methods were investigated: the analytical Feldkamp–Davis–Kress (FDK), a compressed sensing-based fast, regularized, iterative statistical technique (FRIST), a fully supervised deep learning approach using a multi-scale residual dense network (MS-RDN), and a self-supervised approach based on Noise-to-Noise (N2N) learning. Projection datasets from 106 women who participated in a prior clinical trial were reconstructed using each of these algorithms at a fixed isotropic voxel size of (0.273 mm3). Each reconstructed breast volume was segmented into skin, adipose, and fibroglandular tissues, and the VGF was computed. The VGF did not differ among the four reconstruction methods (p = 0.167), and none of the three advanced image reconstruction algorithms differed from the standard FDK reconstruction (p > 0.862). Advanced reconstruction algorithms developed for low-dose CBBCT reproduce the VGF to provide quantitative breast density, which can be used for risk estimation.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"12 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135933941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessment of Computed Tomography Perfusion Research Landscape: A Topic Modeling Study 计算机断层扫描灌注研究景观评估:主题建模研究

4区医学

Tomography Pub Date : 2023-11-01 DOI: 10.3390/tomography9060158

Burak B. Ozkara, Mert Karabacak, Konstantinos Margetis, Vivek S. Yedavalli, Max Wintermark, Sotirios Bisdas

{"title":"Assessment of Computed Tomography Perfusion Research Landscape: A Topic Modeling Study","authors":"Burak B. Ozkara, Mert Karabacak, Konstantinos Margetis, Vivek S. Yedavalli, Max Wintermark, Sotirios Bisdas","doi":"10.3390/tomography9060158","DOIUrl":"https://doi.org/10.3390/tomography9060158","url":null,"abstract":"The number of scholarly articles continues to rise. The continuous increase in scientific output poses a challenge for researchers, who must devote considerable time to collecting and analyzing these results. The topic modeling approach emerges as a novel response to this need. Considering the swift advancements in computed tomography perfusion (CTP), we deem it essential to launch an initiative focused on topic modeling. We conducted a comprehensive search of the Scopus database from 1 January 2000 to 16 August 2023, to identify relevant articles about CTP. Using the BERTopic model, we derived a group of topics along with their respective representative articles. For the 2020s, linear regression models were used to identify and interpret trending topics. From the most to the least prevalent, the topics that were identified include “Tumor Vascularity”, “Stroke Assessment”, “Myocardial Perfusion”, “Intracerebral Hemorrhage”, “Imaging Optimization”, “Reperfusion Therapy”, “Postprocessing”, “Carotid Artery Disease”, “Seizures”, “Hemorrhagic Transformation”, “Artificial Intelligence”, and “Moyamoya Disease”. The model provided insights into the trends of the current decade, highlighting “Postprocessing” and “Artificial Intelligence” as the most trending topics.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"36 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135270922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reporting Diagnostic Reference Levels for Paediatric Patients Undergoing Brain Computed Tomography 报告儿科患者接受脑计算机断层扫描的诊断参考水平

4区医学

Tomography Pub Date : 2023-11-01 DOI: 10.3390/tomography9060159

Ali Alhailiy, Essam Alkhybari, Sultan Alghamdi, Nada Fisal, Sultan Aldosari, Salman Albeshan

{"title":"Reporting Diagnostic Reference Levels for Paediatric Patients Undergoing Brain Computed Tomography","authors":"Ali Alhailiy, Essam Alkhybari, Sultan Alghamdi, Nada Fisal, Sultan Aldosari, Salman Albeshan","doi":"10.3390/tomography9060159","DOIUrl":"https://doi.org/10.3390/tomography9060159","url":null,"abstract":"Brain computed tomography (CT) is a diagnostic imaging tool routinely used to assess all paediatric neurologic disorders and other head injuries. Despite the continuous development of paediatric CT imaging, radiation exposure remains a concern. Using diagnostic reference levels (DRLs) helps to manage the radiation dose delivered to patients, allowing one to identify an unusually high dose. In this paper, we propose DRLs for paediatric brain CT examinations in Saudi clinical practices and compare the findings with those of other reported DRL studies. Data including patient and scanning protocols were collected retrospectively from three medical cities for a total of 225 paediatric patients. DRLs were derived for four different age groupings. The resulting DRL values for the dose–length product (DLP) for the age groups of newborns (0–1 year), 1-y-old (1–5 years), 5-y-old (5–10 years) and 10-y-old (10–15 years) were 404 mGy cm, 560 mGy cm, 548 mGy cm, and 742 mGy cm, respectively. The DRLs for paediatric brain CT imaging are comparable to or slightly lower than other DRLs due to the current use of dose optimisation strategies. This study emphasises the need for an international standardisation for the use of weight group categories in DRL establishment for paediatric care in order to provide a more comparable measurement of dose quantities across different hospitals globally.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"34 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135270646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Idiopathic Normal Pressure Hydrocephalus: The Real Social and Economic Burden of a Possibly Enormous Underdiagnosis Problem 特发性常压脑积水:一个可能巨大的诊断不足问题的真正社会和经济负担

4区医学

Tomography Pub Date : 2023-10-30 DOI: 10.3390/tomography9060157

Gianpaolo Petrella, Silvia Ciarlo, Stefania Elia, Rita Dal Piaz, Paolo Nucera, Angelo Pompucci, Mauro Palmieri, Alessandro Pesce

{"title":"Idiopathic Normal Pressure Hydrocephalus: The Real Social and Economic Burden of a Possibly Enormous Underdiagnosis Problem","authors":"Gianpaolo Petrella, Silvia Ciarlo, Stefania Elia, Rita Dal Piaz, Paolo Nucera, Angelo Pompucci, Mauro Palmieri, Alessandro Pesce","doi":"10.3390/tomography9060157","DOIUrl":"https://doi.org/10.3390/tomography9060157","url":null,"abstract":"Normal Pressure Hydrocephalus (iNPH) typically affects the elderly and can cause cognitive decline, resulting in its differential diagnosis with other neurodegenerative conditions. Moreover, it is probably underdiagnosed; such under- and misdiagnosis prevents the patient from receiving the right treatment and significantly affects the quality of life and life expectancy. This investigation is an in-depth analysis of the actual incidence of iNPH in the population of the province served by our hospital (circa 580,000 individuals). The first phase of this study was conducted by visualizing a total of 1232 brain CT scans performed in the Emergency Departments of the four hospitals of our network on patients who were admitted for different complaints yet screened as suspicious for iNPH. Subsequently, corresponding Emergency Department medical records were investigated to understand the medical history of each patient in search of elements attributable to an alteration of CSF dynamics. The cohort of positive CT scans, according to the radiological and clinical inclusion criteria, included 192 patients. Among the reasons to require acute medical care, “Fall” was the most common. The cumulative incidence of CT scans suggestive of iNPH among the patients undergoing CT scans was as high as 15.58%, and the period prevalence calculated for the total amount of patients accessing the Emergency Departments was 1.084%. The real incidence of iNPH in the population may be underestimated, and the social burden linked to the assistance of patients suffering from such untreated conditions could be significantly relieved.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"70 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136023318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-Riding Conus Medullaris Syndrome: A Case Report and Literature Review—Its Comparison with Cauda Equina Syndrome 高椎圆锥综合征1例并文献复习——与马尾综合征的比较

4区医学

Tomography Pub Date : 2023-10-27 DOI: 10.3390/tomography9060156

Ya-Lin Huang, Shin-Tsu Chang

{"title":"High-Riding Conus Medullaris Syndrome: A Case Report and Literature Review—Its Comparison with Cauda Equina Syndrome","authors":"Ya-Lin Huang, Shin-Tsu Chang","doi":"10.3390/tomography9060156","DOIUrl":"https://doi.org/10.3390/tomography9060156","url":null,"abstract":"Introduction: Conus medullaris syndrome (CMS) is a distinctive spinal cord injury (SCI), which presents with varying degrees of upper motor neuron signs (UMNS) and lower motor neuron signs (LMNS). Herein, we present a case with a burst fracture injury at the proximal Conus Medullaris (CM). Case Presentation: A 48-year-old Taiwanese male presenting with lower back pain and paraparesis was having difficulty standing independently after a traumatic fall. An Imaging survey showed an incomplete D burst fracture of the T12 vertebra. Posterior decompression surgery was subsequently performed. However, spasticity and back pain persisted for four months after surgical intervention. Follow-up imaging with single photon emission computed tomography (SPECT) and a whole body bone scan both showed an increased uptake in the T12 vertebra. Conclusion: The high-riding injury site for CMS is related to a more exclusive clinical representation of UMNS. Our case’s persistent UMNS and scintigraphy findings during follow-up showcase the prolonged recovery period of a UMN injury. In conclusion, our study provides a different perspective on approaching follow-up for CM injuries, namely using scientigraphy techniques to confirm localization of persistent injury during the course of post-operative rehabilitation. Furthermore, we also offered a new technique for analyzing the location of lumbosacral injuries, and that is to measure the location of the injury relative to the tip of the CM. This, along with clinical neurological examination, assesses the extent to which the UMN is involved in patients with CMS, and is possibly a notable predictive tool for clinicians for the regeneration time frame and functional outcome of patients with lumbosacral injuries in the future.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136317419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Tomosynthesis Broken Halo Sign: Diagnostic Utility for the Classification of Newly Diagnosed Breast Tumors 断层合成断晕征:对新诊断乳腺肿瘤分类的诊断价值

4区医学

Tomography Pub Date : 2023-10-24 DOI: 10.3390/tomography9060155

Johannes Deeg, Michael Swoboda, Daniel Egle, Verena Wieser, Afschin Soleiman, Valentin Ladenhauf, Malik Galijasevic, Birgit Amort, Silke Haushammer, Martin Daniaux, Leonhard Gruber

{"title":"The Tomosynthesis Broken Halo Sign: Diagnostic Utility for the Classification of Newly Diagnosed Breast Tumors","authors":"Johannes Deeg, Michael Swoboda, Daniel Egle, Verena Wieser, Afschin Soleiman, Valentin Ladenhauf, Malik Galijasevic, Birgit Amort, Silke Haushammer, Martin Daniaux, Leonhard Gruber","doi":"10.3390/tomography9060155","DOIUrl":"https://doi.org/10.3390/tomography9060155","url":null,"abstract":"Background: Compared to conventional 2D mammography, digital breast tomosynthesis (DBT) offers greater breast lesion detection rates. Ring-like hypodense artifacts surrounding dense lesions are a common byproduct of DBT. This study’s purpose was to assess whether minuscule changes spanning this halo—termed the “broken halo sign”—could improve lesion classification. Methods: This retrospective study was approved by the local ethics review board. After screening 288 consecutive patients, DBT studies of 191 female participants referred for routine mammography with a subsequent histologically verified finding of the breast were assessed. Examined variables included patient age, histological diagnosis, architectural distortion, maximum size, maximum halo depth, conspicuous margins, irregular shape and broken halo sign. Results: While a higher halo strength was indicative of malignancy in general (p = 0.031), the broken halo sign was strongly associated with malignancy (p < 0.0001, odds ratio (OR) 6.33), alongside architectural distortion (p = 0.012, OR 3.49) and a diffuse margin (p = 0.006, OR 5.49). This was especially true for denser breasts (ACR C/D), where the broken halo sign was the only factor predicting malignancy (p = 0.03, 5.22 OR). Conclusion: DBT-associated halo artifacts warrant thorough investigation in newly found breast lesions as they are associated with malignant tumors. The “broken halo sign”—the presence of small lines of variable diameter spanning the peritumoral areas of hypodensity—is a strong indicator of malignancy, especially in dense breasts, where architectural distortion may be obfuscated due to the surrounding tissue.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135266040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Role of Contrast-Enhanced Ultrasound (CEUS) in the Detection of Neoplastic Portal Vein Thrombosis in Patients with Hepatocellular Carcinoma. 造影增强超声（CEUS）在检测肝细胞癌患者门静脉新生血栓形成中的作用。

IF 1.9 4区医学

Tomography Pub Date : 2023-10-20 DOI: 10.3390/tomography9050154

Lucia Cerrito, Maria Elena Ainora, Silvino Di Francesco, Linda Galasso, Antonio Gasbarrini, Maria Assunta Zocco

{"title":"The Role of Contrast-Enhanced Ultrasound (CEUS) in the Detection of Neoplastic Portal Vein Thrombosis in Patients with Hepatocellular Carcinoma.","authors":"Lucia Cerrito, Maria Elena Ainora, Silvino Di Francesco, Linda Galasso, Antonio Gasbarrini, Maria Assunta Zocco","doi":"10.3390/tomography9050154","DOIUrl":"10.3390/tomography9050154","url":null,"abstract":"Hepatocellular carcinoma (HCC) is the principal primary liver cancer and one of the most frequent malignant tumors worldwide in patients with chronic liver disease. When diagnosed at an advanced stage, it is often associated with portal vein tumor thrombosis (PVTT), which heavily affects patients' prognosis. Imaging evaluation is crucial in PVTT detection and staging; computed tomography and magnetic resonance are the principal diagnostic tools. Contrast-enhanced ultrasound (CEUS) is a non-invasive and easily repeatable method that can also be used in patients with impaired renal function. It represents an important means for the identification of PVTT, particularly differentiating neoplastic and non-neoplastic thrombosis through the analysis of ultrasound enhancement characteristics of the thrombosis (arterial hyperenhancement and portal washout), thus allowing more refined disease staging, appropriate treatment planning, and response evaluation, along with prognosis assessment.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"9 5","pages":"1976-1986"},"PeriodicalIF":1.9,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610687/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54232090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Biliary Leak after Pediatric Liver Transplantation Treated by Percutaneous Transhepatic Biliary Drainage-A Case Series. 经皮肝内胆管引流治疗小儿肝移植术后胆漏——病例系列。

IF 1.9 4区医学

Tomography Pub Date : 2023-10-19 DOI: 10.3390/tomography9050153

Michael Doppler, Christin Fürnstahl, Simone Hammer, Michael Melter, Niklas Verloh, Hans Jürgen Schlitt, Wibke Uller

{"title":"Biliary Leak after Pediatric Liver Transplantation Treated by Percutaneous Transhepatic Biliary Drainage-A Case Series.","authors":"Michael Doppler, Christin Fürnstahl, Simone Hammer, Michael Melter, Niklas Verloh, Hans Jürgen Schlitt, Wibke Uller","doi":"10.3390/tomography9050153","DOIUrl":"10.3390/tomography9050153","url":null,"abstract":"Background: Biliary leaks are a severe complication after pediatric liver transplantation (pLT), and successful management is challenging.Objectives: The aim of this case series was to assess the outcome of percutaneous transhepatic biliary drainage (PTBD) in children with bile leaks following pLT. The necessity of additional percutaneous bilioma drainage and laboratory changes during therapy and follow-up was documented.Material and methods: All children who underwent PTBD for biliary leak following pLT were included in this consecutive retrospective single-center study and analyzed regarding site of leak, management of additional bilioma, treatment response, and patient and transplant survival. The courses of inflammation, cholestasis parameters, and liver enzymes were retrospectively reviewed.Results: Ten children underwent PTBD treatment for biliary leak after pLT. Seven patients presented with leakage at the hepaticojejunostomy, two with leakage at the choledocho-choledochostomy and one with a bile leak because of an overlooked segmental bile duct. In terms of the mean, the PTBD treatment started 40.3 ± 31.7 days after pLT. The mean duration of PTBD treatment was 109.7 ± 103.6 days. Additional percutaneous bilioma drainage was required in eight cases. Bile leak treatment was successful in all cases, and no complications occurred. The patient and transplant survival rate was 100%. CRP serum level, leukocyte count, gamma-glutamyl transferase (GGT), and total and direct bilirubin level decreased significantly during treatment with a very strong effect size. Additionally, the gamma-glutamyl transferase level showed a statistically significant reduction during follow-up.Conclusions: PTBD is a very successful strategy for bile leak therapy after pLT.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"9 5","pages":"1965-1975"},"PeriodicalIF":1.9,"publicationDate":"2023-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610565/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54232079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of a Deep Learning Reconstruction for High-Quality T2-Weighted Breast Magnetic Resonance Imaging. 高质量T2加权乳腺磁共振成像的深度学习重建评估。

IF 1.9 4区医学

Tomography Pub Date : 2023-10-18 DOI: 10.3390/tomography9050152

Timothy J Allen, Leah C Henze Bancroft, Orhan Unal, Lloyd D Estkowski, Ty A Cashen, Frank Korosec, Roberta M Strigel, Frederick Kelcz, Amy M Fowler, Alison Gegios, Janice Thai, R Marc Lebel, James H Holmes

{"title":"Evaluation of a Deep Learning Reconstruction for High-Quality T2-Weighted Breast Magnetic Resonance Imaging.","authors":"Timothy J Allen, Leah C Henze Bancroft, Orhan Unal, Lloyd D Estkowski, Ty A Cashen, Frank Korosec, Roberta M Strigel, Frederick Kelcz, Amy M Fowler, Alison Gegios, Janice Thai, R Marc Lebel, James H Holmes","doi":"10.3390/tomography9050152","DOIUrl":"10.3390/tomography9050152","url":null,"abstract":"Deep learning (DL) reconstruction techniques to improve MR image quality are becoming commercially available with the hope that they will be applicable to multiple imaging application sites and acquisition protocols. However, before clinical implementation, these methods must be validated for specific use cases. In this work, the quality of standard-of-care (SOC) T2w and a high-spatial-resolution (HR) imaging of the breast were assessed both with and without prototype DL reconstruction. Studies were performed using data collected from phantoms, 20 retrospectively collected SOC patient exams, and 56 prospectively acquired SOC and HR patient exams. Image quality was quantitatively assessed via signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness. Qualitatively, all in vivo images were scored by either two or four radiologist readers using 5-point Likert scales in the following categories: artifacts, perceived sharpness, perceived SNR, and overall quality. Differences in reader scores were tested for significance. Reader preference and perception of signal intensity changes were also assessed. Application of the DL resulted in higher average SNR (1.2-2.8 times), CNR (1.0-1.8 times), and image sharpness (1.2-1.7 times). Qualitatively, the SOC acquisition with DL resulted in significantly improved image quality scores in all categories compared to non-DL images. HR acquisition with DL significantly increased SNR, sharpness, and overall quality compared to both the non-DL SOC and the non-DL HR images. The acquisition time for the HR data only required a 20% increase compared to the SOC acquisition and readers typically preferred DL images over non-DL counterparts. Overall, the DL reconstruction demonstrated improved T2w image quality in clinical breast MRI.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"9 5","pages":"1949-1964"},"PeriodicalIF":1.9,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611328/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54232082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers. FDG PET图像中癌症的头部和颈部分割：卷积神经网络和视觉变换器的性能比较。

IF 1.9 4区医学

Tomography Pub Date : 2023-10-18 DOI: 10.3390/tomography9050151

Xiaofan Xiong, Brian J Smith, Stephen A Graves, Michael M Graham, John M Buatti, Reinhard R Beichel

{"title":"Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers.","authors":"Xiaofan Xiong, Brian J Smith, Stephen A Graves, Michael M Graham, John M Buatti, Reinhard R Beichel","doi":"10.3390/tomography9050151","DOIUrl":"10.3390/tomography9050151","url":null,"abstract":"Convolutional neural networks (CNNs) have a proven track record in medical image segmentation. Recently, Vision Transformers were introduced and are gaining popularity for many computer vision applications, including object detection, classification, and segmentation. Machine learning algorithms such as CNNs or Transformers are subject to an inductive bias, which can have a significant impact on the performance of machine learning models. This is especially relevant for medical image segmentation applications where limited training data are available, and a model's inductive bias should help it to generalize well. In this work, we quantitatively assess the performance of two CNN-based networks (U-Net and U-Net-CBAM) and three popular Transformer-based segmentation network architectures (UNETR, TransBTS, and VT-UNet) in the context of HNC lesion segmentation in volumetric [F-18] fluorodeoxyglucose (FDG) PET scans. For performance assessment, 272 FDG PET-CT scans of a clinical trial (ACRIN 6685) were utilized, which includes a total of 650 lesions (primary: 272 and secondary: 378). The image data used are highly diverse and representative for clinical use. For performance analysis, several error metrics were utilized. The achieved Dice coefficient ranged from 0.833 to 0.809 with the best performance being achieved by CNN-based approaches. U-Net-CBAM, which utilizes spatial and channel attention, showed several advantages for smaller lesions compared to the standard U-Net. Furthermore, our results provide some insight regarding the image features relevant for this specific segmentation application. In addition, results highlight the need to utilize primary as well as secondary lesions to derive clinically relevant segmentation performance estimates avoiding biases.","PeriodicalId":51330,"journal":{"name":"Tomography","volume":"9 5","pages":"1933-1948"},"PeriodicalIF":1.9,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611182/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54232083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0