Journal of Computer Assisted Tomography最新文献

{"title":"Novel Edge-on-irradiated Si-based Photon-counting Detector CT for the Characterization of Cystic Renal Lesions.","authors":"Fides R Schwartz, Zhye Yin, Xue Rui, Steve Bache, Ehsan Samei, Grant M Stevens, Aria M Salyapongse, Timothy P Szczykutowicz, Daniele Marin","doi":"10.1097/RCT.0000000000001773","DOIUrl":"https://doi.org/10.1097/RCT.0000000000001773","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate an edge-on-irradiated silicon-based photon-counting detector CT (Deep Si-PCD-CT) prototype for quantification of iodine concentration and stability of HU values, as well as detectability of subtle features in simulated kidney parenchyma.</p><p><strong>Materials and methods: </strong>A phantom, simulating moderately and strongly enhancing kidney parenchyma (at 180 and 240 HU) inside a small, medium, and large patient (23, 30, 37 cm diameter, respectively), was scanned on a Deep Si-PCD-CT. Centered in the kidney parenchyma was a water-equivalent rod at 0 HU and a rod of 0.8 mg/mL iodine concentration to simulate a benign, mildly enhancing cystic renal lesion, as well as a rod with a 2 mm septum and 5 mm mural nodule. Accuracy and stability of HU values were evaluated with repeated ROI measurements across consecutive slices, while the septum and nodule were identified on standard polychromatic clinical images and iodine maps. Images were reconstructed with a soft tissue kernel at 0.417- and 0.625-mm slice-thickness without additional denoising.</p><p><strong>Results: </strong>Deep Si-PCD-CT produced accurate HU value measurements for water, intralesional iodine content, and renal parenchymal enhancement. The HU values were similarly variable from the ground truth values as compared with measurements from a commercial energy-integrating detector CT. The nodule and septum inside the phantom were successfully identified using the new Deep Si-PCD-CT prototype, while they were difficult to identify using the standard EID-CT at clinical window-level settings. The iodine maps created from the photon-counting detector CT displayed both the nodule and the septum well, facilitating quick identification.</p><p><strong>Conclusions: </strong>Deep Si-PCD-CT is a promising tool for the accurate measurement of HU values, as well as the detection of subtle features of complexity in cystic renal lesions. It has the potential to improve the diagnosis and management of cystic renal lesions.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144540403","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}

{"title":"Heterogeneity Habitats -Derived Radiomics of Gd-EOB-DTPA Enhanced MRI for Predicting Proliferation of Hepatocellular Carcinoma.","authors":"Shifang Sun, Yixing Yu, Shungen Xiao, Qi He, Zhen Jiang, Yanfen Fan","doi":"10.1097/RCT.0000000000001769","DOIUrl":"https://doi.org/10.1097/RCT.0000000000001769","url":null,"abstract":"<p><strong>Objective: </strong>To construct and validate the optimal model for preoperative prediction of proliferative HCC based on habitat-derived radiomics features of Gd-EOB-DTPA-Enhanced MRI.</p><p><strong>Methods: </strong>A total of 187 patients who underwent Gd-EOB-DTPA-enhanced MRI before curative partial hepatectomy were divided into training (n=130, 50 proliferative and 80 nonproliferative HCC) and validation cohort (n=57, 25 proliferative and 32 nonproliferative HCC). Habitat subregion generation was performed using the Gaussian Mixture Model (GMM) clustering method to cluster all pixels to identify similar subregions within the tumor. Radiomic features were extracted from each tumor subregion in the arterial phase (AP) and hepatobiliary phase (HBP). Independent sample t tests, Pearson correlation coefficient, and Least Absolute Shrinkage and Selection Operator (LASSO) algorithm were performed to select the optimal features of subregions. After feature integration and selection, machine-learning classification models using the sci-kit-learn library were constructed. Receiver Operating Characteristic (ROC) curves and the DeLong test were performed to compare the identified performance for predicting proliferative HCC among these models.</p><p><strong>Results: </strong>The optimal number of clusters was determined to be 3 based on the Silhouette coefficient. 20, 12, and 23 features were retained from the AP, HBP, and the combined AP and HBP habitat (subregions 1, 2, 3) radiomics features. Three models were constructed with these selected features in AP, HBP, and the combined AP and HBP habitat radiomics features. The ROC analysis and DeLong test show that the Naive Bayes model of AP and HBP habitat radiomics (AP-HBP-Hab-Rad) archived the best performance. Finally, the combined model using the Light Gradient Boosting Machine (LightGBM) algorithm, incorporating the AP-HBP-Hab-Rad, age, and AFP (Alpha-Fetoprotein), was identified as the optimal model for predicting proliferative HCC. For the training and validation cohort, the accuracy, sensitivity, specificity, and AUC were 0.923, 0.880, 0.950, 0.966 (95% CI: 0.937-0.994) and 0.825, 0.680, 0.937, 0.877 (95% CI: 0.786-0.969), respectively. In its validation cohort of the combined model, the AUC value was statistically higher than the other models (P<0.01).</p><p><strong>Conclusions: </strong>A combined model, including AP-HBP-Hab-Rad, serum AFP, and age using the LightGBM algorithm, can satisfactorily predict proliferative HCC preoperatively.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144540386","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}

{"title":"Quantitative Plaque Characteristics/Pericoronary Fat Attenuation Index and Acute Coronary Syndrome in Patients With Stable Angina Pectoris.","authors":"Defu Li, Yujin Wang, Tingting Zhu","doi":"10.1097/RCT.0000000000001718","DOIUrl":"10.1097/RCT.0000000000001718","url":null,"abstract":"<p><strong>Objective: </strong>Vascular inflammation affects acute coronary syndrome (ACS) occurrence in patients with stable angina. Coronary inflammation can be represented by the pericoronary fat attenuation index (FAI).This study investigated the quantitative prognostic value of plaque characteristics and FAI in patients with stable angina.</p><p><strong>Methods: </strong>Risk factors for ACS occurrence in patients with stable angina pectoris were retrospectively analyzed. The diagnostic value of FAI and plaque characteristics for ACS occurrence in these patients were determined; Kaplan-Meier curves were used to predict ACS event incidence.</p><p><strong>Results: </strong>After postpropensity score matching, data of 60 and 130 patients with and without ACS, respectively, were analyzed. Pericoronary FAI, lipid volume, and lipid percentage in the narrowest segment significantly improved ACS diagnosis in patients with stable angina. Luminal stenosis ≥50% and FAI >-88 Hounsfield units (HU) were independent risk factors for ACS occurrence in patients with stable angina. Perileft anterior descending artery (LAD) FAI >-88 HU better predicted ACS occurrence in patients with stable angina than did peri-LAD FAI ≤-88 HU.</p><p><strong>Conclusions: </strong>In patients with stable angina, lipid volume and percentage and pericoronary FAI improved the diagnostic ability of luminal stenosis for ACS occurrence. Furthermore, peri-LAD FAI >-88 HU could predict ACS occurrence.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":"587-594"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143059103","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}

{"title":"Artificial Intelligence in Computed Tomography Image Reconstruction: A Review of Recent Advances.","authors":"Ran Zhang, Timothy P Szczykutowicz, Giuseppe V Toia","doi":"10.1097/RCT.0000000000001734","DOIUrl":"10.1097/RCT.0000000000001734","url":null,"abstract":"<p><p>The development of novel image reconstruction algorithms has been pivotal in enhancing image quality and reducing radiation dose in computed tomography (CT) imaging. Traditional techniques like filtered back projection perform well under ideal conditions but fail to generate high-quality images under low-dose, sparse-view, and limited-angle conditions. Iterative reconstruction methods improve upon filtered back projection by incorporating system models and assumptions about the patient, yet they can suffer from patchy image textures. The emergence of artificial intelligence (AI), particularly deep learning, has further advanced CT reconstruction. AI techniques have demonstrated great potential in reducing radiation dose while preserving image quality and noise texture. Moreover, AI has exhibited unprecedented performance in addressing challenging CT reconstruction problems, including low-dose CT, sparse-view CT, limited-angle CT, and interior tomography. This review focuses on the latest advances in AI-based CT reconstruction under these challenging conditions.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":"521-530"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143501540","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}

{"title":"Different Imaging Evaluating Performances Between Glymphatic System and Motor Symptoms and Levodopa Responsiveness of Parkinson Disease.","authors":"Jin-Huan Deng, Han-Wen Zhang, Xin-Xin Lan, Yu-Feng Liu, Xiao-Lei Liu, Hua-Zhen Deng, Si-Ping Luo, Gui-Zhi Yao, He-Lv Wu, Biao Huang, Fan Lin","doi":"10.1097/RCT.0000000000001720","DOIUrl":"10.1097/RCT.0000000000001720","url":null,"abstract":"<p><strong>Background and purpose: </strong>Parkinson disease (PD) is defined by its unique motor symptoms, where responsiveness to levodopa (L-DOPA) is fundamental for management. Recent research has highlighted a significant relationship between PD symptoms and glymphatic dysfunction. This study endeavors to clarify the connection between glymphatic system functionality and initial motor symptoms in PD, utilizing imaging biomarkers to determine its predictive capacity for L-DOPA responsiveness (LR).</p><p><strong>Materials and methods: </strong>Retrospective study of 86 PD patients with 3.0-T MRI scans (July 2019 to March 2021), assessing the diffusion tensor image analysis along the perivascular space (DTI-ALPS) methods, enlarged perivascular spaces (ePVSs) load, and choroid plexus volume (CPV). Analyzed metrics versus the third part of the Unified Parkinson Disease Rating Scale (UPDRSIII) scores and %LR using linear regression, creating a %LR prediction model for the L-DOPA challenge. Explored relationships with age, sex, Hoehn and Yahr stage, Montreal Cognitive Assessment scores, and Mini-Mental State Examination score. Examined DTI-ALPS index, ePVSs, and CPV interrelations.</p><p><strong>Results: </strong>Pre-L-DOPA, UPDRSIII inversely correlated with DTI-ALPS index ( P =0.049), positively with bilateral basal ganglia ePVSs ( P <0.001). Age-adjusted BG-ePVSs-UPDRSIII link ( P <0.001). Post-L-DOPA, UPDRSIII correlated similarly and CPV was positive. %LR positively linked to DTI-ALPS index ( P <0.001), negatively to BG-ePVSs ( P =0.04), CPV ( P <0.001). Adjusted %LR-DTI-ALPS index positive ( P =0.005), %LR-CPV negative ( P =0.04). DTI-ALPS index, CPV predicted LCT outcomes (%LR ≥33%) with area under the curves 0.78, 0.79; accuracies 86.01%, 81.4%. The combined model area under the curve is 0.82, with an accuracy of 87.2%. Significant linear correlations were observed (CPV-DTI-ALPS, CPV-ePVSs, DTI-ALPS-ePVSs).</p><p><strong>Conclusions: </strong>A study affirms the link between glymphatic impairment, motor symptoms, and L-DOPA responses in PD. As glymphatic function declines, symptoms worsen, and L-DOPA effectiveness diminishes. The DTI-ALPS index and CPV emerge as potential predictors of PD patient LCT outcomes.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":"646-655"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143059125","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}

{"title":"Commentary: Foreword From the Editor-in-Chief to the Guest Section on Artificial Intelligence.","authors":"Eric P Tamm","doi":"10.1097/RCT.0000000000001779","DOIUrl":"https://doi.org/10.1097/RCT.0000000000001779","url":null,"abstract":"","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":"49 4","pages":"519"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144612169","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}

{"title":"Spectrum of Otological Manifestations in Treacher Collins Syndrome: A Case Series of 9 Patients.","authors":"Shehbaz Ansari, Eric R Basappa, Peter C Markee, Chanae Dixon, Sudeep H Bhabad","doi":"10.1097/RCT.0000000000001715","DOIUrl":"10.1097/RCT.0000000000001715","url":null,"abstract":"<p><p>Treacher Collins syndrome (TCS) is an uncommon congenital disorder predominantly involving craniofacial, orbital, and otological structures. The various ear malformations seen in 9 patients with TCS are described. TCS predominantly affects the external and middle ear structures, with inner ear structures being relatively spared, not unexpected given the dual embryological origin of the human ear. The external and middle ear malformations were categorized and graded as those involving the ear pinna, external auditory canal, tympanic cavity, ossicles, facial nerve canal, oval window, and bony labyrinth for all 9 patients. The ear malformations were symmetric in the majority, and the patients with higher grades of microtia were found to have a more severe category of other otological malformations.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":"662-668"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143059140","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}

{"title":"Commentary: The Future of Generative Artificial Intelligence in Radiology.","authors":"Nikhil Madhuripan","doi":"10.1097/RCT.0000000000001667","DOIUrl":"10.1097/RCT.0000000000001667","url":null,"abstract":"","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":"554-555"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142390920","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}

{"title":"Utility of Multiparametric Breast MRI Radiomics to Predict Cyclin D1 and TGF-β1 Expression.","authors":"Mengying Zheng, Jiaqi Xu, Shujie Yu, Zhenhua Zhao, Yu Zhang, Mingzhu Wei","doi":"10.1097/RCT.0000000000001717","DOIUrl":"10.1097/RCT.0000000000001717","url":null,"abstract":"<p><strong>Objective: </strong>To develop a machine learning model that integrates clinical features and multisequence MRI radiomics for noninvasively predicting the expression status of prognostic-related factors cyclin D1 and TGF-β1 in breast cancer, providing additional information for the clinical development of personalized treatment plans.</p><p><strong>Methods: </strong>A total of 123 breast cancer patients confirmed by surgical pathology were retrospectively enrolled in our Hospital from January 2016 to July 2022. The patients were randomly divided into a training group (87 cases) and a validation group (36 cases). Preoperative routine and dynamic contrast-enhanced magnetic resonance imaging scans of the breast were performed for treatment subjects. The region of interest was manually outlined, and texture features were extracted using AK software. Subsequently, the LASSO algorithm was employed for dimensionality reduction and feature selection to establish the MRI radiomics labels. The diagnostic efficacy and clinical value were assessed through receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA).</p><p><strong>Results: </strong>In the cyclin D1 cohort, the area under the receiver operating characteristic (ROC) curve in the clinical prediction model training and validation groups was 0.738 and 0.656, respectively. The multisequence MRI radiomics prediction model achieved an AUC of 0.874 and 0.753 in these respective groups, while the combined prediction model yielded an AUC of 0.892 and 0.785. In the TGF-β1 cohort, the ROC AUC for the clinical prediction model was found to be 0.693 and 0.645 in the training and validation groups, respectively. For the multiseries MRI radiomics prediction model, it achieved an AUC of 0.875 and 0.760 in these respective groups; whereas for the combined prediction model, it reached an AUC of 0.904 and 0.833. Decision curve analysis (DCA) demonstrated that both cohorts indicated a higher clinical application value for the combined prediction model compared with both individual models-clinical prediction model alone or radiomics model.</p><p><strong>Conclusion: </strong>The integration of clinical features and multisequence MRI radiomics in a combined modeling approach holds significant predictive value for the expression status of cyclin D1 and TGF-β1. The model provides a noninvasive, dynamic evaluation method that provides effective guidance for clinical treatment.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":"577-586"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142965138","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}

{"title":"Dynamic Contrast-enhanced MRI Processing Comparison for Distinguishing True Progression From Pseudoprogression in High-grade Glioma.","authors":"Ahmad Amer, Shehbaz Ansari, Apollo Krayyem, Suprateek Kundu, Swapnil Khose, Halyna Pokhylevych, Susana Calle, Chirag B Patel, Zixi Yang, Ho-Ling Anthony Liu, Jason M Johnson","doi":"10.1097/RCT.0000000000001716","DOIUrl":"10.1097/RCT.0000000000001716","url":null,"abstract":"<p><strong>Background: </strong>Treatment-related changes may occur due to radiation and temozolomide in glioblastoma and can mimic tumor progression on conventional MRI. DCE-MRI enables quantification of the extent of blood-brain barrier (BBB) disruption, providing information about areas of suspicious postcontrast T1 enhancement. We compared DCE-MRI processing methods for distinguishing true disease progression from pseudoprogression in high-grade gliomas (HGGs).</p><p><strong>Methods: </strong>We identified 110 patients with HGG treated with surgery and chemoradiation who underwent DCE-MRI to further interrogate areas of new/increasing enhancement. All patients had confirmatory surgery/biopsy with pathology-confirmed progression or pseudoprogression. Scans were performed at 3T and analyzed using nordicICE. The MCA, SSS, and Parker models are three standardized processing methodologies used to create k trans maps, a parameter that quantifies BBB permeability. Three equal regions of interest were placed at sites of peak contrast enhancement within each lesion. Data from each method was processed for mean and maximum k trans . We conducted several rounds of analysis and finalized a strategy on penalized support vector machines based on engineered features with bootstrap sampling.</p><p><strong>Results: </strong>The Parker method was significant for k trans maximum in the combined pathology and clinical as well as the pathology-only data sets. MCA and SSS did not perform well under the SVM classifier for pathology only. For clinical follow-up subjects, the Parker method yielded statistically significant results for maximum and mean k trans .</p><p><strong>Conclusions: </strong>The Parker method was effective in distinguishing PD and PsP for pathology and clinical data sets. MCA and SSS techniques were effective for the clinical data set.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":"656-661"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12237096/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143059096","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}