Quantitative Imaging in Medicine and Surgery最新文献

{"title":"The application of computational fluid dynamics in hepatic portal vein haemodynamics research: a narrative review.","authors":"Xian Wu, Hong Xiao, Lin Ma","doi":"10.21037/qims-24-1593","DOIUrl":"10.21037/qims-24-1593","url":null,"abstract":"<p><strong>Background and objective: </strong>The diagnosis and treatment of many liver diseases are related to the assessment of the hepatic portal vein (PV). Noninvasive methods (medical imaging) and invasive methods (hepatic vein catheterization) are commonly used to analyse the haemodynamic information of the PV. In recent years, computational fluid dynamics (CFD) has emerged as a transformative tool in haemodynamics research, revolutionizing the understanding of blood flow behaviour, especially in various artery systems. The purpose of this review is the following: (I) introduce clinicians to CFD as a novel tool and describe its role in PV assessment; and (II) for clinicians and researchers who already use CFD, outline the progress in the application of CFD to the PV.</p><p><strong>Methods: </strong>The English-language literature published from 1987 (when the first study supporting the study's aim appeared) to 2024 was selected for inclusion in a narrative review.</p><p><strong>Key content and findings: </strong>This narrative review commences with an overview of principles of CFD and methods in PV studies, which involve model establishment, grid partitioning, boundary condition formulation, and error analysis. The focus then shifts to CFD's impact on the examination of the PV under different conditions such as portal hypertension in liver cirrhosis, PV thrombosis, post-transjugular intrahepatic portosystemic shunt (TIPS) procedure, and evaluation of the PV after liver transplantation. Finally, challenges and future directions about the CFD application in PV are outlined.</p><p><strong>Conclusions: </strong>CFD has potential application value in PV haemodynamics, but of the few studies available, most involve only small samples. Therefore, more research is needed to clarify the feasibility and reliability of this new tool.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2605-2620"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948386/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Chemotherapy-induced focal liver injury mimicking colorectal liver metastasis: a case description.","authors":"Yue Yang, Keyu Zeng, Zhe Wu, Qiang Lu","doi":"10.21037/qims-24-338","DOIUrl":"10.21037/qims-24-338","url":null,"abstract":"","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2652-2657"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948374/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical success and safety of N-butyl cyanoacrylate in emergency embolization: is operator experience a key factor?","authors":"Rémi Grange, Vincent Habouzit, Julien Lanoiselee, Stéphanie Leroy, Nicolas Stacoffe, Nicolas Magand, Noémie Lutz, Claire Boutet, Sylvain Grange","doi":"10.21037/qims-24-1767","DOIUrl":"10.21037/qims-24-1767","url":null,"abstract":"<p><strong>Background: </strong>N-butyl-cyanoacrylate (NBCA) is seen as a challenging embolization agent to use, requiring a learning curve. The study aims to evaluate the safety, efficacy and impact of operator's experience of NBCA as an embolic agent in emergency transarterial embolization (TAE).</p><p><strong>Methods: </strong>All patients referred to University Hospital of Saint-Etienne who were treated by TAE with NBCA between January 1, 2016 and January 1, 2024 were retrospectively reviewed. The inclusion criteria were all patients ≥18 years old treated by TAE with NBCA. Demographic, biological and angiographic data were recorded. Clinical success was defined as resolution of signs and symptoms of bleeding during the 30-day follow-up period after TAE and without required endoscopic treatment, surgery, or repeat TAE or death of any cause. Predictive factors of early death (≤30 days) were assessed using univariate and multivariate analysis. Outcomes regarding operator's experience (more or less than 3 years in embolization) were reviewed.</p><p><strong>Results: </strong>During the study inclusion period, 113 patients (75, 66.4% males) for 113 procedures were included. The mean age was 64.1±14.1 years old. Clinical success was achieved in 93 (82.3%) patients. No major complication was recorded. There were 5 (4.4%) early rebleeding requiring 3 (2.7%) repeat TAE. Fifteen (13.3%) patients died within 30 days after the procedure. Operators with <3 years' experience had the same clinical outcomes as more experienced ones (P>0.05). In univariate analysis, hemodynamic instability, hemoglobin level <8 g/dL, and international normalized radio (INR) >1.5 were associated with early death. In multivariate analysis, hemodynamic instability was independently associated with early death [odds ratio (OR) =14.49; 95% confidence interval (CI): 2.33-282.1, P=0.01].</p><p><strong>Conclusions: </strong>Use of NBCA demonstrates a low rebleeding rate, and safety profile of TAE using NBCA. Operators' experience has no significant impact on clinical outcomes.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"1963-1976"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948373/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasound-based deep learning radiomics for multi-stage assisted diagnosis in reducing unnecessary biopsies of BI-RADS 4A lesions.","authors":"Xiangyu Lu, Yun Lu, Wuyuan Zhao, Yunliang Qi, Hongjuan Zhang, Wenhao Sun, Huaikun Zhang, Pei Ma, Ling Guan, Yide Ma","doi":"10.21037/qims-24-580","DOIUrl":"10.21037/qims-24-580","url":null,"abstract":"<p><strong>Background: </strong>Even with the Breast Imaging Reporting and Data System (BI-RADS) guiding risk stratification on ultrasound (US) images, inconsistencies in diagnostic accuracy still exist, leading patients being subjected to unnecessary biopsies in clinical practice. This study investigated the construction of deep learning radiomics (DLR) models to improve the diagnostic consistency and reduce the unnecessary biopsies for BI-RADS 4A lesions.</p><p><strong>Methods: </strong>A total of 746 patients with breast lesions were enrolled in this retrospective study. Two DLR models based on US images and clinical variables were developed to conduct breast lesion risk re-stratification as BI-RADS 3 or lower and BI-RADS 4A or higher (DLR_LH), while simultaneously identifying BI-RADS 4A lesions with low malignancy probabilities to avoid unnecessary biopsy (DLR_BM). A three-round reader study with a two-stage artificial intelligence (AI)-assisted diagnosis process was performed to verify the assistive capability and practical benefits of the models in clinical applications.</p><p><strong>Results: </strong>The DLR_LH model achieved areas under the receiver operating characteristic curve (AUCs) of 0.963 and 0.889 with sensitivities of 92.0% and 83.3%, in the internal and external validation cohorts, respectively. The DLR_BM model exhibited AUCs of 0.977 and 0.942, with sensitivities of 94.1% and 86.4%, respectively. Both models were evaluated using integrated features of US images and clinical variables. Ultimately, 27.7% of BI-RADS 4A lesions avoided unnecessary biopsies. In the three-round reader study, all readers achieved significantly higher diagnostic accuracy and specificity, while maintaining outstanding sensitivity comparable to human experts, both before and after model assistance (P<0.05). These findings demonstrate the positive impact of the DLR models in assisting radiologists to enhance their diagnostic capabilities.</p><p><strong>Conclusions: </strong>The models performed well in breast US imaging interpretation and BI-RADS risk re-stratification, and demonstrated potential in reducing unnecessary biopsies of BI-RADS 4A lesions, indicating the promising applicability of the DLR models in clinical diagnosis.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2512-2528"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948369/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multitask Swin Transformer for classification and characterization of pulmonary nodules in CT images.","authors":"Haizhe Jin, Cheng Yu, Jiahao Zhang, Renjie Zheng, Yongyan Fu, Yinan Zhao","doi":"10.21037/qims-24-1619","DOIUrl":"10.21037/qims-24-1619","url":null,"abstract":"<p><strong>Background: </strong>Early diagnosis of pulmonary nodules is essential for effective prevention and treatment of pulmonary cancer. However, the heterogeneous and complex characteristics of pulmonary nodules, such as shape, size, speculation, and texture, present significant challenges in clinical diagnosis, which computer-aided diagnosis (CAD) can help address. Moreover, the varied performance of deep learning methods in CAD and limited model interpretability often hinder clinicians' understanding of CAD results. In this study, we propose a multitask Swin Transformer (MTST) for classifying benign and malignant pulmonary nodules, which outputs nodule features as classification criteria.</p><p><strong>Methods: </strong>We introduce a MTST model for feature extraction, designed with a multitask layer that simultaneously outputs benign and malignant binary classification, multilevel classification, and a detailed analysis of pulmonary nodule features. In addition, we incorporate image augmentation using a U-Net generative adversarial network (GAN) model to enhance the training process.</p><p><strong>Results: </strong>Experimental findings on the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset demonstrate that the proposed MTST outperforms conventional convolutional neural networks (CNN)-based networks across multiple tasks. Specifically, MTST achieved an accuracy of 93.24% in binary classification of benign and malignant nodules and demonstrated superior performance in nodule feature evaluation. For multilevel classification of pulmonary nodules, the Swin Transformer achieved an accuracy of 95.73%. On the training, validation, and test sets (9,600/2,400/1,600 nodules), the MTST model achieved an accuracy of 93.74%, sensitivity of 91.55%, and specificity of 96.09%. The results indicate that the MTST model aligns well with clinical diagnostic practices, offering improved performance and reliability.</p><p><strong>Conclusions: </strong>The MTST model's efficacy in binary classification, multiclass classification, and feature evaluation confirms its potential as a valuable tool for CAD systems in clinical settings.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"1845-1861"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948416/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association of aberrant brain network connectivity with visual dysfunction in patients with nonarteritic anterior ischemic optic neuropathy: a pilot study.","authors":"Hui Wang, Xiaoling Yan, Na Ma, Qiong Wu, Qiuhuan Zhang, Jian Zhou, Pengde Guo","doi":"10.21037/qims-24-2062","DOIUrl":"10.21037/qims-24-2062","url":null,"abstract":"<p><strong>Background: </strong>Nonarteritic anterior ischemic optic neuropathy (NAION) is often accompanied by degeneration of optic nerve axons and ganglion cell apoptosis, but the mechanism of its effects on the cerebral cortex and visual centers is not clear. Graph theory analysis, as a quantitative tool for complex networks, has made it possible to characterize the topological alterations of brain networks in patients with NAION. The objective of this pilot study was to investigate the topological characteristics of functional brain networks in patients with NAION and to analyze their potential correlation with visual dysfunction.</p><p><strong>Methods: </strong>This prospective, cross-sectional study recruited 25 patients with NAION and 24 matched healthy controls (HCs) from Dongfang Hospital, Beijing University of Chinese Medicine. Following resting-state functional magnetic resonance imaging (rs-fMRI) scans, large-scale functional connectivity matrices of 90 regions were constructed. Graph theory was then used to compare global and local network parameters. Subsequently, network-based statistics (NBS) analysis was employed to detect differences in functional connectivity across the brain. Finally, correlations were assessed between the network topological properties and clinical variables.</p><p><strong>Results: </strong>Individuals with NAION, as compared to controls, exhibited significant decreases in normalized clustering coefficient (gamma; P=0.021), small-worldness (sigma; P=0.043), and local efficiency (Eloc; P=0.030), as well as a significant increase in the size of the largest connected component (LCC; P=0.039) of the network. Additionally, the LCC showed a negative association with gamma, sigma and global efficiency (Eg) but a positive correlation with the normalized characteristic path length (lambda) of the two groups (all P values <0.05). Regionally, patients exhibited changes in nodal centralities, particularly affecting the attention, visual, and salience networks. NBS analysis identified an interconnected subnetwork consisting of 49 nodes and 77 edges (P<0.001, NBS-corrected) that showed significantly higher connectivity in patients with NAION. The mean connectivity of this subnetwork was negatively correlated with the global topological parameters gamma, sigma, and Eg in the NAION group and gamma and sigma in the HCs but positively correlated with the LCC in both groups (all P values <0.05). Moreover, the nodal betweenness centrality of the left dorsolateral superior frontal gyrus exhibited a significant positive correlation with the visual field (VF) mean deviation (MD) in the NAION group (P<0.001).</p><p><strong>Conclusions: </strong>This study initially identified aberrant topological and connectivity changes in the functional brain networks associated with visual impairment in patients with NAION, thus expanding our existing understanding of the neurobiological mechanisms of NAION.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2362-2375"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948378/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved visualization of electron-density dual-energy computed tomography for lumbar disc disease over the standard gray-scale type and virtual noncalcium imaging.","authors":"Pengfeng Sun, Xiaoping Wu, Ming Gao, Xiaoyue Zhang, Duo Ma, Hongsheng Liu, Qiaoying Zhang, Jiayu Wu, Mingyue Ma, Yan Dong, Run Liu","doi":"10.21037/qims-24-1760","DOIUrl":"10.21037/qims-24-1760","url":null,"abstract":"<p><strong>Background: </strong>Dual-energy computed tomography (DECT) enhances tissue imaging characterization. However, no studies have evaluated the diagnostic accuracy of electron density (ED) for simultaneously displaying the lumbar disc and disc calcification. This retrospective study aimed to investigate the ability of ED to visualize lumbar disc disease as compared with standard computed tomography (SC) and virtual noncalcium (VNCa) imaging in order to provide a viable alternative for lumbar disc disease.</p><p><strong>Methods: </strong>From October 2023 to February 2024, we retrospectively analyzed data from 53 patients who underwent DECT and 3.0-T magnetic resonance imaging (MRI) within 2 weeks. The randomized SC, VNCa, and ED image sets were independently evaluated by four radiologists for visualization of the lumbar disc and disc calcification with an 8-week interval. Final disc calcification results were obtained by consensus, with the SC results serving as the reference standard. Two other experienced radiologists performed MRI evaluations as the lumbar disc reference standard. Diagnostic performance was compared for each image.</p><p><strong>Results: </strong>Among the 298 included lumbar discs, 183 lumbar disc herniations and bulges were revealed on MRI. As compared with VNCa and SC, ED showed higher overall sensitivity (91.3% <i>vs.</i> 88.9% <i>vs.</i> 78.0%), specificity (94.8% <i>vs.</i> 93.3% <i>vs.</i> 88.0%), and accuracy (92.6% <i>vs.</i> 90.6% <i>vs.</i> 81.9%) in visualizing lumbar disc herniation and bulging. The ED area under the curve (AUC) was higher than that of VNCa and SC (all P values <0.05), and ED identified all 40 (40/183) calcified discs shown on SC. In addition, diagnostic confidence and image quality of ED were higher than those of VNCa and SC (all P values <0.001).</p><p><strong>Conclusions: </strong>ED demonstrated higher diagnostic accuracy and confidence for visualizing the lumbar disc and disc calcification on the computed tomography (CT) images as compared to VNCa and SC.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2296-2308"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948433/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of high-frequency ultrasound in the early detection of pressure injury and evaluation of decompression treatment.","authors":"Rongchen Wang, Xinyi Tang, Li Qiu, Liyun Wang","doi":"10.21037/qims-24-1612","DOIUrl":"10.21037/qims-24-1612","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Pressure injury (PI) is an ischemic necrosis caused by long-term pressure on the local skin, which is common in the sacrococcygeal region of long-term bedridden patients. The main treatment for PI is decompression. The Braden scale is the primary clinical evaluation tool for PI, but it cannot quantitatively evaluate PI. High-frequency ultrasound (HFUS) can be used for the real-time quantitative evaluation of PI. This study used HFUS to qualitatively and quantitatively assess the soft tissues of the sacrococcygeal region in different risk PI groups to investigate any differences in HFUS manifestations and evaluate the efficacy of decompression treatment in stage 1 PI patients.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A total of 70 patients were recruited from the Intensive Care Unit at West China Hospital, Sichuan University, of whom, 28 were allocated to the case group (a moderate or higher risk for PI, and a Braden score of 15-17) and 42 were allocated to the control group (a very mild risk for PI, and a Braden score ≥18). HFUS was used to measure tissue thickness and ultrasonographic characteristics, as well as blood flow signals at 10 target sites along the transverse plane from the sacral protrusion to the top. Differences between groups were compared, and diagnostic efficacy was evaluated by a receiver operating characteristic (ROC) curve analysis, and the area under the curve (AUC) was calculated. A subgroup of 12 extremely high-risk patients receiving decompression treatment was also examined. The HFUS parameters were compared before and after treatment to evaluate efficacy.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In the case group, ultrasonographic uneven echo, unclear boundaries between adipose/muscular layers and dermis/adipose layers, and discontinuous deep/superficial fascia were more common closer to sacral protrusions (P&lt;0.05). The case group had thinner median and paraspinal fat layers at all 10 sites than the control group (P&lt;0.05). Certain sites (3, 5-7, and 9-10) in the case group had thicker epidermis (P&lt;0.05), while the muscle layer was thinner at sites 5-10 of the case group (P&lt;0.01). The ROC curve analysis indicated that the median and paraspinal fat layers could be used to effectively classify medium-high-risk patients with optimal performance at sites 3-5. The blood flow signal characteristics and composition ratios differed significantly between the case and control groups at each analyzed site (P&lt;0.05). No significant changes in the Braden scores were found following decompression therapy, but the thickness of the paraspinal fat layer at sites 3 and 4 and the thickness of the median spinal fat layer at site 4 increased significantly (P&lt;0.05). Further, the paraspinal fat layer thickness differed significantly between the initial and sixth ultrasound assessments (P&lt;0.05). Most participants experienced reduced blood flow at the targeted site after decompression treatment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;H","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2280-2295"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948384/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved prostate cancer diagnosis: upgraded prostate imaging reporting and data system (PI-RADS) scores by zoomed diffusion-weighted imaging enhance deep-learning-based computer-aided diagnosis accuracy.","authors":"Haining Long, Lei Hu, Liming Wei, Lisong Dai, Caixia Fu, Yichen Lu, Cancan Xu, Zhonghua Hu, Lei Wang, Zhihan Xu, Robert Grimm, Heinrich von Busch, Thomas Benkert, Ali Kamen, Bin Lou, Henkjan Huisman, Angela Tong, Tobias Penzkofer, Moon Hyung Choi, Ivan Shabunin, David Winkel, Pengyi Xing, Dieter Szolar, Fergus Coakley, Steven M Shea, Edyta Szurowska, Wangshu Zhu, Jungong Zhao","doi":"10.21037/qims-24-1263","DOIUrl":"10.21037/qims-24-1263","url":null,"abstract":"<p><strong>Background: </strong>A new diffusion-weighted imaging (DWI) technique, known as zoomed-field-of-view echo-planar DWI (z-DWI), has been developed to reduce geometric distortions and susceptibility artifacts and to achieve higher spatial resolution. However, it remains unclear whether z-DWI, compared with the traditional DWI technique, can enhance the diagnostic performance of deep-learning-based computer-aided diagnosis (DL-CAD) and radiologists using DL-CAD in detecting prostate cancer (PCa). This study aims to evaluate and compare the diagnostic performance and PI-RADS scores of DL-CAD in detecting PCa using conventional full-field-of-view single-shot echo-planar DWI (f-DWI) and advanced z-DWI and to extend this comparison to clinical practice, in which radiologists use DL-CAD.</p><p><strong>Methods: </strong>This study retrospectively included magnetic resonance imaging from 359 patients for suspected PCa. There were 496 prostate lesions included, with 253 (51%) being malignant. Using a DL-CAD system, images of f-DWI and z-DWI were uploaded separately to obtain the localizations and the prostate imaging reporting and data system (PI-RADS) scores of suspected malignant lesions. The results were compared to histopathologic results. The diagnostic performance of f-DWI and z-DWI were evaluated using the free-response receiver operating characteristics and the alternative free-response receiver operating characteristics curves. Discrepancies in PI-RADS scores were analyzed. Additionally, two radiologists participated in consensus reading images by using DL-CAD with different DWI techniques, and their performance and PI-RADS scores were compared. Lastly, the relationship between PI-RADS discrepancies and clinically significant prostate cancer (csPCa) risk was analyzed.</p><p><strong>Results: </strong>z-DWI enabled DL-CAD to exhibit better diagnostic performance [area under the curve (AUC), 0.857 <i>vs</i>. 0.841; P=0.02], with a higher mean PI-RADS score for PCa lesions (4.26 <i>vs</i>. 3.92; P<0.001), and improved scores for 66 PCa lesions compared to f-DWI. When radiologists used DL-CAD, z-DWI also enabled radiologists to exhibit a higher mean PI-RADS score for PCa lesions (4.31 <i>vs</i>. 4.02; P<0.001) and improved scores for 56 PCa lesions compared to f-DWI, however, no statistically significant difference was found in diagnostic performance (AUC, 0.887 <i>vs</i>. 0.881; P=0.16). In multivariable logistic regression analyses, upgraded PI-RADS scores by z-DWI were significantly associated with csPCa risk.</p><p><strong>Conclusions: </strong>z-DWI, in comparison to f-DWI, enhances the diagnostic performance of DL-CAD for PCa, assigning higher PI-RADS scores to malignant lesions. Despite offering limited improvement for radiologists using DL-CAD, z-DWI shows promise in enhancing the detection of csPCa.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2132-2145"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948435/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a prediction model of left ventricular systolic dysfunction in type 2 diabetes mellitus.","authors":"Li Chen, Fengzhen Liu, Yanling Luo, Lili Chen, Xia Li, Xiaolin Wang, Yu Zhao, Liangyun Guo, Chunquan Zhang","doi":"10.21037/qims-24-95","DOIUrl":"10.21037/qims-24-95","url":null,"abstract":"<p><strong>Background: </strong>Left ventricular longitudinal myocardial systolic dysfunction (LVSD) represents a critical risk factor for diabetes-related cardiovascular events. This study aimed to develop a well-calibrated and convenient risk prediction model to investigate early predictive risk of LVSD in type 2 diabetes mellitus (T2DM) patients with preserved left ventricular ejection fraction (LVEF), and to evaluate its performance.</p><p><strong>Methods: </strong>A total of 310 patients with T2DM from June 2020 to October 2021 at the Second Affiliated Hospital of Nanchang University were prospectively enrolled and randomly assigned to a training set (n=217) and a validation set (n=93) at a 7:3 ratio. Basic characteristics, laboratory tests, echocardiographic parameters, two-dimensional global longitudinal strain (GLS) parameters, and medication use were collected. LVSD in patients with T2DM with preserved LVEF was defined as an absolute value of GLS <18%. The least absolute shrinkage and selection operator (LASSO) regression was applied to optimize the screening variables, followed by multivariate logistic regression to identify independent risk factors for predicting LVSD, and a nomogram was established. The receiver operating characteristic (ROC) curves, area under the curve (AUC) values, calibration plot, and decision curve analysis (DCA) were used to verify and evaluate the nomogram's discrimination, calibration, and clinical validity.</p><p><strong>Results: </strong>A total of 8 independent risk predictors of LVSD in T2DM were extracted and incorporated into the nomogram, as evaluated using LASSO regression analysis and multivariate logistic regression analysis, including body mass index (BMI), T2DM duration, blood urea nitrogen (BUN), left ventricular (LV) mass index, E/e', diabetic retinopathy, diabetic peripheral neuropathy, and diabetic nephropathy. The nomogram indicated excellent prediction properties with AUC values of 0.922 and 0.918 for the training set and validation set, respectively. Further, the predictive nomogram demonstrated outstanding consistency between the predicted probability and the actual probability in terms of the calibration plots. DCA showed also that the predicted nomogram was clinically beneficial.</p><p><strong>Conclusions: </strong>This study identified independent risk factors for LVSD in patients with T2DM and developed a predictive nomogram. It allows for clinical decision-making to timely intervene or delay the occurrence of LVSD.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2581-2591"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948413/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}