Roberta Vaccarino, Melker Wachtmeister, Angelos Karelis, Elisabet Marinko, Jianming Sun, Timothy Resch, Björn Sonesson, Nuno V Dias
{"title":"The role of CT-assessed sarcopenia and visceral adipose tissue in predicting long-term survival in patients undergoing elective endovascular infrarenal aortic repair.","authors":"Roberta Vaccarino, Melker Wachtmeister, Angelos Karelis, Elisabet Marinko, Jianming Sun, Timothy Resch, Björn Sonesson, Nuno V Dias","doi":"10.1093/bjr/tqae114","DOIUrl":"10.1093/bjr/tqae114","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate if ileo-psoas muscle size and visceral adipose tissue (VAT) can predict long-term survival after endovascular aneurysm repair (EVAR).</p><p><strong>Methods: </strong>Patients who underwent EVAR between 2004 and 2012 in a single centre were included. Total psoas muscle area (TPA), abdominal VAT area, subcutaneous adipose tissue (SAT), and total adipose tissue were measured on the preoperative CT. Primary endpoint was all-cause mortality. Values are presented as median and interquartile range or absolute number and percentage. Cox regression analyses were performed to assess the associations with mortality.</p><p><strong>Results: </strong>Two hundred and eighty-four patients could be included in the study. During a median follow-up of 8 (4-11) years, 223 (79.9%) patients died. Age (P ≤ .001), cardiovascular (P = .041), cerebrovascular (P = .009), renal diseases (P = .002), and chronic obstructive pulmonary disease (P ≤ .001) were independently associated with mortality. TPA was associated with mortality in a univariate (P = .040), but not in a multivariate regression model (P = .764). No significant association was found between mortality and TPA index (P = .103) or any of the adiposity measurements with the exception of SAT (P = .040). However, SAT area loss in a multivariate analysis (P = .875).</p><p><strong>Conclusions: </strong>Assessment of core muscle size and VAT did not contribute to improving the prediction of long-term survival after EVAR.</p><p><strong>Advances in knowledge: </strong>The finding of this study contradicts the previously claimed utility of core muscle size and VAT in predicting long-term survival after EVAR.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1461-1466"},"PeriodicalIF":1.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11256935/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141287800","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}
Huan Li, Dai Zhang, Jinxia Pei, Jingmei Hu, Xiaohu Li, Bin Liu, Longsheng Wang
{"title":"Dual-energy computed tomography iodine quantification combined with laboratory data for predicting microvascular invasion in hepatocellular carcinoma: a two-centre study.","authors":"Huan Li, Dai Zhang, Jinxia Pei, Jingmei Hu, Xiaohu Li, Bin Liu, Longsheng Wang","doi":"10.1093/bjr/tqae116","DOIUrl":"10.1093/bjr/tqae116","url":null,"abstract":"<p><strong>Objectives: </strong>Microvascular invasion (MVI) is a recognized biomarker associated with poorer prognosis in patients with hepatocellular carcinoma. Dual-energy computed tomography (DECT) is a highly sensitive technique that can determine the iodine concentration (IC) in tumour and provide an indirect evaluation of internal microcirculatory perfusion. This study aimed to assess whether the combination of DECT with laboratory data can improve preoperative MVI prediction.</p><p><strong>Methods: </strong>This retrospective study enrolled 119 patients who underwent DECT liver angiography at 2 medical centres preoperatively. To compare DECT parameters and laboratory findings between MVI-negative and MVI-positive groups, Mann-Whitney U test was used. Additionally, principal component analysis (PCA) was conducted to determine fundamental components. Mann-Whitney U test was applied to determine whether the principal component (PC) scores varied across MVI groups. Finally, a general linear classifier was used to assess the classification ability of each PC score.</p><p><strong>Results: </strong>Significant differences were noted (P < .05) in alpha-fetoprotein (AFP) level, normalized arterial phase IC, and normalized portal phase IC between the MVI groups in the primary and validation datasets. The PC1-PC4 accounted for 67.9% of the variance in the primary dataset, with loadings of 24.1%, 16%, 15.4%, and 12.4%, respectively. In both primary and validation datasets, PC3 and PC4 were significantly different across MVI groups, with area under the curve values of 0.8410 and 0.8373, respectively.</p><p><strong>Conclusions: </strong>The recombination of DECT IC and laboratory features based on varying factor loadings can well predict MVI preoperatively.</p><p><strong>Advances in knowledge: </strong>Utilizing PCA, the amalgamation of DECT IC and laboratory features, considering diverse factor loadings, showed substantial promise in accurately classifying MVI. There have been limited endeavours to establish such a combination, offering a novel paradigm for comprehending data in related research endeavours.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1467-1475"},"PeriodicalIF":1.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11256957/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141316788","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}
Perry J Pickhardt, Vincenzo K Wong, Vincent Mellnick, Mark Sugi, Yashant Aswani
{"title":"Abdominal CT findings characteristic of Castleman disease: multi-centre review of 76 adult cases with abdominopelvic nodal involvement.","authors":"Perry J Pickhardt, Vincenzo K Wong, Vincent Mellnick, Mark Sugi, Yashant Aswani","doi":"10.1093/bjr/tqae111","DOIUrl":"10.1093/bjr/tqae111","url":null,"abstract":"<p><strong>Objective: </strong>Characterize the CT findings of abdominopelvic Castleman disease, including a new observation involving the perinodal fat.</p><p><strong>Methods: </strong>Multi-centre search at 5 institutions yielded 76 adults (mean age, 42.1 ± 14.3 years; 38 women/38 men) meeting inclusion criteria of histopathologically proven Castleman disease with nodal involvement at abdominopelvic CT. Retrospective review of the dominant nodal mass was assessed for size, attenuation, and presence of calcification, and for prominence and soft-tissue infiltration of the perinodal fat. Hypervascular nodal enhancement was based on both subjective and objective comparison with aortic blood pool attenuation.</p><p><strong>Results: </strong>Abdominal involvement was unicentric in 48.7% (37/76) and multicentric in 51.3% (39/76), including 31 cases with extra-abdominal involvement. Histopathologic subtypes included hyaline vascular variant (HVV), plasma cell variant (PCV), mixed HVV/PCV, and HHV-8 variant in 39, 25, 3 and 9 cases, respectively. The dominant nodal mass measured 4.4 ± 1.9 cm and 3.2 ± 1.7 cm in mean long- and short-axis, respectively, and appeared hypervascular in 58.6% (41/70 with IV contrast). Internal calcification was seen in 22.4% (17/76). Infiltration of the perinodal fat, with or without hypertrophy, was present in 56.6% (43/76), more frequent with hypervascular vs non-hypervascular nodal masses (80.5% vs 20.7%; P < .001). Among HVV cases, 76.9% were unicentric, 71.1% appeared hypervascular, and 69.2% demonstrated perinodal fat infiltration.</p><p><strong>Conclusion: </strong>Hypervascular nodal masses demonstrating prominence and infiltration of perinodal fat at CT can suggest the specific diagnosis of Castleman disease, especially the HVV.</p><p><strong>Advances in knowledge: </strong>Abdominopelvic nodal masses that demonstrate hypervascular enhancement and prominent infiltration of the perinodal fat at CT can suggest the diagnosis of Castleman disease, but nonetheless requires tissue sampling.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1431-1436"},"PeriodicalIF":1.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11256932/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141236876","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}
Xiangyu Lu, Yingying Jia, Hongjuan Zhang, Ruichao Wu, Wuyuan Zhao, Zihuan Yao, Fang Nie, Yide Ma
{"title":"Deep learning-based and BI-RADS guided radiomics model for automatic tumor-infiltrating lymphocytes evaluation in breast cancer.","authors":"Xiangyu Lu, Yingying Jia, Hongjuan Zhang, Ruichao Wu, Wuyuan Zhao, Zihuan Yao, Fang Nie, Yide Ma","doi":"10.1093/bjr/tqae129","DOIUrl":"https://doi.org/10.1093/bjr/tqae129","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate an interpretable radiomics model consistent with clinical decision-making process and realize automatic prediction of tumor-infiltrating lymphocytes (TILs) levels in breast cancer (BC) from ultrasound (US) images.</p><p><strong>Methods: </strong>A total of 378 patients with invasive BC confirmed by pathological results were retrospectively enrolled in this study. Radiomics features were extracted guided by the BI-RADS lexicon from the regions of interest(ROIs) segmented with deep learning models. After features selected using the least absolute shrinkage and selection operator(LASSO) regression, four machine learning classifiers were used to establish the radiomics signature(Rad-score). Then, the integrated model was developed on the basis of the best Rad-score incorporating the independent clinical factors for TILs levels prediction.</p><p><strong>Results: </strong>Tumors were segmented using the deep learning models with accuracy of 97.2%, sensitivity of 93.4%, specificity of 98.1%, and the posterior areas were also obtained. Eighteen morphology and texture related features were extracted from the ROIs and fourteen features were selected to construct the Rad-score models. Combined with independent clinical characteristics, the integrated model achieved an area under the curve (AUC) of 0.889(95% CI,0.739,0.990) in the validation cohort and outperformed the traditional radiomics model with AUC of 0.756(0.649-0862) depended on hundreds of feature items.</p><p><strong>Conclusions: </strong>This study established a promising model for TILs levels prediction with numerable interpretable features and showed great potential to help decision-making and clinical applications.</p><p><strong>Advances in knowledge: </strong>Imaging-based biomarkers has provides non-invasive ways for TILs levels evaluation in BC. Our model combining the BI-RADS guided radiomics features and clinical data outperformed the traditional radiomics approaches.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141598531","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}
Julien Garnon, Roberto Luigi Cazzato, Pierre-Alexis Autrusseau, Guillaume Koch, Julia Weiss, Justine Gantzer, Jean-Emmanuel Kurtz, Afshin Gangi
{"title":"Desmoid fibromatosis: IR (sometimes) to the rescue for an atypical disease.","authors":"Julien Garnon, Roberto Luigi Cazzato, Pierre-Alexis Autrusseau, Guillaume Koch, Julia Weiss, Justine Gantzer, Jean-Emmanuel Kurtz, Afshin Gangi","doi":"10.1093/bjr/tqae128","DOIUrl":"https://doi.org/10.1093/bjr/tqae128","url":null,"abstract":"<p><p>Desmoid fibromatosis is a rare locally aggressive soft tissue tumor that is characterized as benign as it cannot metastasize. It was managed until recently like sarcomas, i.e with radical surgical resection combined or not with radiotherapy. However, this approach was associated with a high rate of recurrence and significant morbidity. The management of this disease has progressively changed to a more conservative approach given the fact that desmoid fibromatosis may spontaneously stop to grow or even shrink in more than half of the cases. Should treatment be required, recent guidelines recommend choosing between systemic therapies, which include principally chemotherapy and tyrosine kinase inhibitors, and local treatments. And this is where the interventional radiologist may have an important role to treat the disease. Various ablation modalities have been reported in the literature to treat desmoid fibromatosis, notably high-intensity focused ultrasound and cryoablation. Results are promising and cryoablation is now mentioned in recent guidelines. The interventional radiologist should nevertheless apprehend the disease in its globality to understand the place of percutaneous treatments among the other therapeutic options. The goal of this review is therefore to present and discuss the role of interventional radiology (IR) in the management of DF.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141598532","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}
Bo Sun, Lei Chen, Yu Lei, Lijie Zhang, Tao Sun, Yiming Liu, Chuansheng Zheng
{"title":"Sorafenib plus transcatheter arterial chemoembolization with or without camrelizumab for the treatment of intermediate and advanced hepatocellular carcinoma.","authors":"Bo Sun, Lei Chen, Yu Lei, Lijie Zhang, Tao Sun, Yiming Liu, Chuansheng Zheng","doi":"10.1093/bjr/tqae087","DOIUrl":"10.1093/bjr/tqae087","url":null,"abstract":"<p><strong>Objectives: </strong>To compare the efficacy and safety of transcatheter arterial chemoembolization (TACE) combined with sorafenib and camrelizumab or with sorafenib alone in patients with intermediate or advanced hepatocellular carcinoma (HCC).</p><p><strong>Methods: </strong>We retrospectively analysed 78 patients with intermediate or advanced HCC who were treated at our centres between January 2018 and December 2021. Twenty-six of them received sorafenib and camrelizumab plus TACE (the TACE + Sor + C group), while 52 received TACE and sorafenib (the TACE + Sor group). Overall survival (OS), progression-free survival (PFS), and adverse events (AEs) were evaluated. Univariate and multivariate analyses were used to determine the factors affecting survival.</p><p><strong>Results: </strong>The median OS (22 vs 10 months, P < .001) and median PFS (11 vs 6 months, P = .008) of the TACE + Sor + C group were significantly higher than those of the TACE + Sor group. Multivariate analysis showed that compared with TACE + Sor + C, TACE + Sor increased the risk of all-cause mortality and tumour progression. For grade I and II AEs, the incidence of skin capillary hyperplasia and hypothyroidism in the TACE + Sor + C group was significantly higher than that in the TACE + Sor group. For serious AEs (grade III or IV), there was no significant difference in any adverse reaction between the 2 groups (P > .05).</p><p><strong>Conclusion: </strong>Patients with intermediate or advanced HCC appeared to benefit more in terms of survival from TACE + Sor + C than from TACE + Sor, and the AEs were tolerable.</p><p><strong>Advances in knowledge: </strong>(1) Subgroup analysis demonstrated that TACE + sorafenib + camrelizumab could benefit HCC patients regardless of whether they had portal vein tumour thrombosis, Barcelona Clinic Liver Cancer B or C, or CHILD A or B; (2) We reported the immunotherapy-related AEs occurred with a significantly higher incidence in triple treatment, but all the AEs are tolerable.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1320-1327"},"PeriodicalIF":1.8,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11186562/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140849296","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}
Jae-Kyun Ryu, Ki Hwan Kim, Chuluunbaatar Otgonbaatar, Da Som Kim, Hackjoon Shim, Jung Wook Seo
{"title":"Improved stent sharpness evaluation with super-resolution deep learning reconstruction in coronary CT angiography.","authors":"Jae-Kyun Ryu, Ki Hwan Kim, Chuluunbaatar Otgonbaatar, Da Som Kim, Hackjoon Shim, Jung Wook Seo","doi":"10.1093/bjr/tqae094","DOIUrl":"10.1093/bjr/tqae094","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to assess the impact of super-resolution deep learning reconstruction (SR-DLR) on coronary CT angiography (CCTA) image quality and blooming artifacts from coronary artery stents in comparison to conventional methods, including hybrid iterative reconstruction (HIR) and deep learning-based reconstruction (DLR).</p><p><strong>Methods: </strong>A retrospective analysis included 66 CCTA patients from July to November 2022. Major coronary arteries were evaluated for image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Stent sharpness was quantified using 10%-90% edge rise slope (ERS) and 10%-90% edge rise distance (ERD). Qualitative analysis employed a 5-point scoring system to assess overall image quality, image noise, vessel wall, and stent structure.</p><p><strong>Results: </strong>SR-DLR demonstrated significantly lower image noise compared to HIR and DLR. SNR and CNR were notably higher in SR-DLR. Stent ERS was significantly improved in SR-DLR, with mean ERD values of 0.70 ± 0.20 mm for SR-DLR, 1.13 ± 0.28 mm for HIR, and 0.85 ± 0.26 mm for DLR. Qualitatively, SR-DLR scored higher in all categories.</p><p><strong>Conclusions: </strong>SR-DLR produces images with lower image noise, leading to improved overall image quality, compared with HIR and DLR. SR-DLR is a valuable image reconstruction algorithm for enhancing the spatial resolution and sharpness of coronary artery stents without being constrained by hardware limitations.</p><p><strong>Advances in knowledge: </strong>The overall image quality was significantly higher in SR-DLR, resulting in sharper coronary artery stents compared to HIR and DLR.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1286-1294"},"PeriodicalIF":1.8,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11186566/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140907792","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}
Heng Zhang, Lin Hu, Fanghui Qin, Jun Chang, Yanqi Zhong, Weiqiang Dou, Shudong Hu, Peng Wang
{"title":"Synthetic MRI and diffusion-weighted imaging for differentiating nasopharyngeal lymphoma from nasopharyngeal carcinoma: combination with morphological features.","authors":"Heng Zhang, Lin Hu, Fanghui Qin, Jun Chang, Yanqi Zhong, Weiqiang Dou, Shudong Hu, Peng Wang","doi":"10.1093/bjr/tqae095","DOIUrl":"10.1093/bjr/tqae095","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate the feasibility of synthetic MRI (syMRI), diffusion-weighted imaging (DWI), and their combination with morphological features for differentiating nasopharyngeal lymphoma (NPL) from nasopharyngeal carcinoma (NPC).</p><p><strong>Methods: </strong>Sixty-nine patients with nasopharyngeal tumours (NPL, n = 22; NPC, n = 47) who underwent syMRI and DWI were retrospectively enrolled between October 2020 and May 2022. syMRI and DWI quantitative parameters (T1, T2, PD, ADC) and morphological features were obtained. Diagnostic performance was assessed by independent sample t-test, chi-square test, logistic regression analysis, receiver operating characteristic curve (ROC), and DeLong test.</p><p><strong>Results: </strong>NPL has significantly lower T2, PD, and ADC values compared to NPC (all P < .05), whereas no significant difference was found in T1 value between these two entities (P > .05). The morphological features of tumour type, skull-base involvement, Waldeyer ring involvement, and lymph nodes involvement region were significantly different between NPL and NPC (all P < .05). The syMRI (T2 + PD) model has better diagnostic efficacy, with AUC, sensitivity, specificity, and accuracy of 0.875, 77.27%, 89.36%, and 85.51%. Compared with syMRI model, syMRI + Morph (PD + Waldeyer ring involvement + lymph nodes involvement region), syMRI + DWI (T2 + PD + ADC), and syMRI + DWI + Morph (PD + ADC + skull-base involvement + Waldeyer ring involvement) models can further improve the diagnostic efficiency (all P < .05). Furthermore, syMRI + DWI + Morph model has excellent diagnostic performance, with AUC, sensitivity, specificity, and accuracy of 0.986, 95.47%, 97.87%, and 97.10%, respectively.</p><p><strong>Conclusion: </strong>syMRI and DWI quantitative parameters were helpful in discriminating NPL from NPC. syMRI + DWI + Morph model has the excellent diagnostic efficiency in differentiating these two entities.</p><p><strong>Advances in knowledge: </strong>syMRI + DWI + morphological feature method can differentiate NPL from NPC with excellent diagnostic performance.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1278-1285"},"PeriodicalIF":1.8,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11186575/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140907797","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}
{"title":"AI-accelerated prostate MRI: a systematic review.","authors":"Ciaran Reinhardt, Hayley Briody, Peter J MacMahon","doi":"10.1093/bjr/tqae093","DOIUrl":"10.1093/bjr/tqae093","url":null,"abstract":"<p><strong>Background: </strong>Prostate cancer ranks among the most prevalent cancers affecting men globally. While conventional MRI serves as a diagnostic tool, its extended acquisition time, associated costs, and strain on healthcare systems, underscore the necessity for more efficient methods. The emergence of AI-acceleration in prostate MRI offers promise to mitigate these challenges.</p><p><strong>Methods: </strong>A systematic review of studies looking at AI-accelerated prostate MRI was conducted, with a focus on acquisition time along with various qualitative and quantitative measurements.</p><p><strong>Results: </strong>Two primary findings were observed. Firstly, all studies indicated that AI-acceleration in MRI achieved notable reductions in acquisition times without compromising image quality. This efficiency offers potential clinical advantages, including reduced scan durations, improved scheduling, diminished patient discomfort, and economic benefits. Secondly, AI demonstrated a beneficial effect in reducing or maintaining artefact levels in T2-weighted images despite this accelerated acquisition time. Inconsistent results were found in all other domains, which were likely influenced by factors such as heterogeneity in methodologies, variability in AI models, and diverse radiologist profiles. These variances underscore the need for larger, more robust studies, standardization, and diverse training datasets for AI models.</p><p><strong>Conclusion: </strong>The integration of AI-acceleration in prostate MRI thus far shows some promising results for efficient and enhanced scanning. These advancements may fill current gaps in early detection and prognosis. However, careful navigation and collaborative efforts are essential to overcome challenges and maximize the potential of this innovative and evolving field.</p><p><strong>Advances in knowledge: </strong>This article reveals overall significant reductions in acquisition time without compromised image quality in AI-accelerated prostate MRI, highlighting potential clinical and diagnostic advantages.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1234-1242"},"PeriodicalIF":1.8,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11186563/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140890887","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}
{"title":"Artificial intelligence-based tools with automated segmentation and measurement on CT images to assist accurate and fast diagnosis in acute pancreatitis.","authors":"Xuhang Pan, Kaijian Jiao, Xinyu Li, Linshuang Feng, Yige Tian, Lei Wu, Peng Zhang, Kejun Wang, Suping Chen, Bo Yang, Wen Chen","doi":"10.1093/bjr/tqae091","DOIUrl":"10.1093/bjr/tqae091","url":null,"abstract":"<p><strong>Objectives: </strong>To develop an artificial intelligence (AI) tool with automated pancreas segmentation and measurement of pancreatic morphological information on CT images to assist improved and faster diagnosis in acute pancreatitis.</p><p><strong>Methods: </strong>This study retrospectively contained 1124 patients suspected for AP and received non-contrast and enhanced abdominal CT examination between September 2013 and September 2022. Patients were divided into training (N = 688), validation (N = 145), testing dataset [N = 291; N = 104 for normal pancreas, N = 98 for AP, N = 89 for AP complicated with PDAC (AP&PDAC)]. A model based on convolutional neural network (MSAnet) was developed. The pancreas segmentation and measurement were performed via eight open-source models and MSAnet based tools, and the efficacy was evaluated using dice similarity coefficient (DSC) and intersection over union (IoU). The DSC and IoU for patients with different ages were also compared. The outline of tumour and oedema in the AP and were segmented by clustering. The diagnostic efficacy for radiologists with or without the assistance of MSAnet tool in AP and AP&PDAC was evaluated using receiver operation curve and confusion matrix.</p><p><strong>Results: </strong>Among all models, MSAnet based tool showed best performance on the training and validation dataset, and had high efficacy on testing dataset. The performance was age-affected. With assistance of the AI tool, the diagnosis time was significantly shortened by 26.8% and 32.7% for junior and senior radiologists, respectively. The area under curve (AUC) in diagnosis of AP was improved from 0.91 to 0.96 for junior radiologist and 0.98 to 0.99 for senior radiologist. In AP&PDAC diagnosis, AUC was increased from 0.85 to 0.92 for junior and 0.97 to 0.99 for senior.</p><p><strong>Conclusion: </strong>MSAnet based tools showed good pancreas segmentation and measurement performance, which help radiologists improve diagnosis efficacy and workflow in both AP and AP with PDAC conditions.</p><p><strong>Advances in knowledge: </strong>This study developed an AI tool with automated pancreas segmentation and measurement and provided evidence for AI tool assistance in improving the workflow and accuracy of AP diagnosis.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1268-1277"},"PeriodicalIF":1.8,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11186564/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140907816","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}