British Journal of Radiology最新文献

{"title":"Ovarian-Adnexal Reporting and Data System (O-RADS) MRI Scoring: Diagnostic Accuracy, Interobserver Agreement, and Applicability to Machine Learning.","authors":"Hüseyin Akkaya, Emin Demirel, Okan Dilek, Tuba Dalgalar Akkaya, Turgay Öztürkçü, Kübra Karaaslan Erişen, Zeynel Abidin Tas, Sevda Bas, Bozkurt Gülek","doi":"10.1093/bjr/tqae221","DOIUrl":"https://doi.org/10.1093/bjr/tqae221","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the interobserver agreement and diagnostic accuracy of ovarian-adnexal reporting and data system magnetic resonance imaging (O-RADS MRI) and applicability to machine learning.</p><p><strong>Material and methods: </strong>Dynamic contrast-enhanced pelvic MRI examinations 471 lesions were retrospectively analyzed and assessed by three radiologists according to O-RADS MRI criteria. Radiomic data were extracted from T2, and post-contrast fat-suppressed T1-weighted images. Using these data, an artificial neural network (ANN), support vector machine, random forest, and naive Bayes models were constructed.</p><p><strong>Results: </strong>Among all readers, the lowest agreement was found for the O-RADS 4 group (kappa: 0.669 (95% confidence interval [CI] 0.634-0.733)), followed by the O-RADS 5 group (kappa: 0.709 (95% CI 0.678-0.754)). O-RADS 4 predicted a malignancy with an area under the curve (AUC) value of 74.3% (95% CI 0.701-0.782), and O-RADS 5 with an AUC of 95.5% (95% CI 0.932-0.972),(p < 0.001). Among the machine learning models, ANN achieved the highest success, distinguishing O-RADS groups with an AUC of 0.948, a precision of 0.861, and a recall of 0.824.</p><p><strong>Conclusion: </strong>The interobserver agreement and diagnostic sensitivity of the O-RADS MRI in assigning O-RADS 4-5 were not perfect, indicating a need for structural improvement. Integrating artificial intelligence into MRI protocols may enhance their performance.</p><p><strong>Advances in knowledge: </strong>Machine learning can achieve high accuracy in the correct classification of O-RADS MRI. Malignancy prediction rates were 74% for O-RADS 4 and 95% for O-RADS 5.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543853","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":"Value of projectional imaging relative to cross-sectional imaging to assess catheter tip position in the superior vena cava: Evaluation of reader variability.","authors":"Giuseppe Gullo, David Christian Rotzinger, Pierre Frossard, Anaïs Colin, Guillaume Saliou, Salah Dine Qanadli","doi":"10.1093/bjr/tqae218","DOIUrl":"https://doi.org/10.1093/bjr/tqae218","url":null,"abstract":"<p><strong>Objectives: </strong>The assessment of correct positioning of central venous catheters (CVC) is of major concern to avoid complications.Vascular access associations have established the cavo-atrial junction (CAJ) as the most appropriate CVC tip location. Among the different chest X-ray (CXR) landmarks proposed for assessing tip position relative to the CAJ, only the pericardial reflection lies in the same plane as the vascular structures assessed. Although extensively used, CXR has been criticized for its difficulty in estimating catheter tip location.We aimed to evaluate the observer variability to determine tip positioning on CXR. CT imaging was used as a gold standard for tip identification.</p><p><strong>Material and methods: </strong>107 CT scans of patients wearing port access catheter devices realized at the XXX University Hospital between January and December 2021 were retrospectively analyzed. Distance from tip to cavo-atrial junction (DCAJ) was measured on topogram projectional imaging (PJ) and axial cross-sectional imaging (CS) by 2 × 2 observers (within and between evaluations). Observational statistics were reported using a paired t-test, repeatability coefficients (RC), and the intraclass correlation coefficient (ICC), and they were displayed comprehensively using Bland-Altman plots.</p><p><strong>Results: </strong>All ICC were >0.9, indicating excellent reliability. The mean difference between observers comparing CS and PJ was 0.13 ± 0.80 cm (P = 0.10) with outer 95% confidence limits of 1.92 cm and -2.17 cm and an RC of 1.79 cm.</p><p><strong>Conclusion: </strong>CXR tip-position reading remains an accurate method for determining CVC localization. However, the assessment variability on CXR is plus or minus 2 cm and should be considered.</p><p><strong>Advances in knowledge: </strong>Chest X-ray (CXR) for the assessment of tip position is subject to intra-individual and inter-individual variation. On CT, the variability is solely linked to determining the cavoatrial junction (CAJ) and represented about 1 cm. On CXR, there is a twofold challenge: the correct determination of the CAJ and the accurate identification of the catheter tip, leading to a greater variability of 2 cm.In clinical practice, while considering the 3 cm anatomical zone around the CAJ acceptable, operators should be aware of the 2 cm variability resulting from CXR assessment. To account for this variability and avoid the risk of positioning the tip beyond 3 cm from the CAJ (theoretically up to plus or minus 5 cm away from the CAJ), operators should reduce the CXR-based acceptable zone to 1 cm around the CAJ. This change may impact up to thirty percent of procedures.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543854","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":"The prognostic value of Epicardial and Pericoronary Adipose Tissue in Heart Failure with Preserved Ejection Fraction Using Coronary Computed Tomography Angiography.","authors":"Shuangxiang Lin, Chenjia Liu, Shuyue Wang, Xingfa Ding, Jiaxing Wu, Xinhong Wang, Sun Jianzhong","doi":"10.1093/bjr/tqae216","DOIUrl":"https://doi.org/10.1093/bjr/tqae216","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the prognostic significance of epicardial adipose tissue volume (EATv) and pericoronary adipose tissue attenuation (PCATa) in patients with heart failure with preserved ejection fraction (HFpEF).</p><p><strong>Methods: </strong>This retrospective study was based on HFpEF and controls who underwent coronary computed tomography angiography (CCTA) screening to rule out coronary disease. Comparisons of EATv and PCATa were made between HFpEF patients and a control group, employing statistical analyses including Kaplan-Meier and Cox regression to assess prognostic significance.</p><p><strong>Results: </strong>A total of 224 patients were retrospectively analyzed. The EATv was 56.1 cm3 ± 11.9 and PCATa in the right coronary artery (PCATa-RCA) was -74.7 HU ± 3.82 in HFpEF patients, which increased significantly compared with controls. Among them, 112 HFpEF patients (mean age: 71.9 ± 8.5 years; 40% male) were followed up for a median of 27 ± 0.6 months (range 2-47 months). EATv and PCATa-RCA were predictive of outcome with an optimal threshold of 56.29 cm3 and -71.17 HU, respectively. In Kaplan-Meier analysis, the high EATv and PCATa-RCA attenuation had significantly higher rates of composite outcomes (log-rank test, all P < 0.01). EATv and PCATa-RCA were independently predictive of outcome following adjustment for confounding variables (EATv: hazard ratio [HR] 1.03; 95% confidence interval [CI] (1.01-1.06); p < 0.01, PCTAa-RCA: HR 1.44; 95% CI 1.27-1.62; p < 0.001)).</p><p><strong>Conclusions: </strong>Increased EATv and PCATa-RCA are associated with worse clinical outcomes in HFpEF patients.</p><p><strong>Advances in knowledge: </strong>This study highlights the potential of CCTA-derived adipose tissue metrics as novel, non-invasive biomarkers for risk stratification in HFpEF.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142495547","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":"Post-Uterine Artery Embolization: 3-Day MRI Changes and Their Predictive Value for Therapeutic Efficacy in Symptomatic Uterine Fibroids.","authors":"Xuan-Yi Chen, Ming-Zhao Zhang, Jun-Kang Wang, Bo Li, Rong-Qing Qin, Yu-Bo Zhang, Chen-Yu Wan, Ruo-Chen Hu, Jia-Yang Zhu, Bing Zhou","doi":"10.1093/bjr/tqae213","DOIUrl":"https://doi.org/10.1093/bjr/tqae213","url":null,"abstract":"<p><strong>Objectives: </strong>To summarize and discuss3-days MRI changes after uterine artery embolization (UAE) and their predictive value for efficacy.</p><p><strong>Methods: </strong>From August 2016 to April 2023, 52 patients underwent enhanced MRI within 3 days post-embolization. We retrospectively analyzed clinical and imaging data, focusing on MR characteristics at the 3-day mark, comparing pre- and post-embolization images. Patients were categorized based on 3-day MR findings into complete and incomplete necrosis groups, with clinical efficacy compared over 6 months.</p><p><strong>Results: </strong>Our study included 30 cases of multiple leiomyomas and 22 of single leiomyomas. Postoperative MRI revealed complete necrosis in 31 tumors and incomplete necrosis in 21 tumors. At 3 days, MR ADC imaging showed increased signals in necrotic areas, mildly increased signals on T2-weighted images, and minimal changes on T1-weighted images. Six-month follow-up showed no significant difference in symptom improvement between groups (p = 0.524, p = 0.587, p = 0.615). However, a significant difference was found in leiomyoma volume reduction, with 70.63 ± 15.53% in the complete necrosis group and 51.36 ± 25.20% in the incomplete necrosis group (p＜0.001), highlighting the impact of necrosis extent on volumetric reduction.</p><p><strong>Conclusion: </strong>Short-term MRI changes after UAE can reflect changes in blood supply to fibroids and normal uterine tissue, and have good predictive value for medium-term embolization efficacy.</p><p><strong>Advances in knowledge: </strong>This study describes short-term MR manifestations of complete and incomplete embolism, aiding in predicting long-term outcome.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458543","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":"Abdominal Applications of Photon-Counting CT.","authors":"Khanin Khanungwanitkul, Olga Sliwicka, Fides Regina Schwartz","doi":"10.1093/bjr/tqae206","DOIUrl":"https://doi.org/10.1093/bjr/tqae206","url":null,"abstract":"<p><p>Photon-counting computed tomography (PCCT) has shown promising advancements in abdominal imaging in clinical use. Though more peer-reviewed primary literature is needed, this commentary explores PCCT's potential applications, focusing on enhancing diagnostic accuracy, optimizing radiation dose management, and improving patient care. PCCT offers improved spatial and contrast resolution, lower image noise, and reduced radiation dose. Increased spatial resolution provides better detail in abdominal imaging, aiding in the detection of small lesions and subtle pathological changes. However, this generates more images per scan, raising concerns about \"image overload\" in PACS, potentially leading to longer reading times and increased stress for radiologists. PCCT's improved contrast resolution enhances tissue differentiation, reducing the need for intravenous contrast agents. The technology's advanced tissue characterization provides several advantages, such as non-invasive and opportunistic liver disease evaluation and improved differentiation of renal and adrenal masses. PCCT's optimized radiation dose management is crucial for patients requiring frequent scans. Enhanced diagnostic accuracy through spectral information aids in tissue differentiation, improving confidence in diagnoses. Streamlined workflows, particularly in emergency settings, and oncologic imaging, are potential benefits, reducing the need for additional imaging studies. Future integration of PCCT into clinical practice requires collaboration, education, and research to fully harness its potential, ensuring optimized abdominal imaging and improved patient care.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142406153","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":"Evolving SPECT-CT technology.","authors":"Kathy P Willowson, Dale L Bailey","doi":"10.1093/bjr/tqae200","DOIUrl":"https://doi.org/10.1093/bjr/tqae200","url":null,"abstract":"<p><p>Both hardware and software developments have seen single photon emission computed tomography (SPECT)/X-ray computed tomography (CT) technology grow at a rapid rate. Such growth has been fuelled by the need for clinical applications and has provided inspiration for clinical developments, particularly with the expanding role of theranostics. Developments such as whole-body quantitative reconstructions, digital detectors, and recent multidetector 3D geometry have allowed SPECT to become comparable to PET on a number of fronts, with a particularly powerful role in biodistribution and dosimetry studies for both planning and evaluating radionuclide therapy. Whilst there remain fundamental challenges for SPECT such the limited spatial resolution and sensitivity, the unique opportunity to image long-lived radioisotopes and simultaneous multi-tracer studies, together with easily accessible equipment, makes SPECT/CT a valuable clinical asset. This review discusses developments in SPECT/CT technology and their clinical impact.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142388195","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":"Looking at the gender disparity in interventional radiology: a scoping review.","authors":"Courtney Moffitt, Eloise Powell","doi":"10.1093/bjr/tqae137","DOIUrl":"10.1093/bjr/tqae137","url":null,"abstract":"<p><strong>Objectives: </strong>The underrepresentation of women within interventional radiology (IR) is profound. This scoping review aims to evaluate the current literature on gender disparity within IR. To uncover relevant themes and research gaps to inform future research and to recommend changes aimed at increasing application and retention of women in IR.</p><p><strong>Methods: </strong>A review of MEDLINE, EMBASE, and Web of Science was conducted. Specific inclusion and exclusion criteria were used to gather all relevant literature. Thematic analysis of included literature highlighted themes and commonalities between papers.</p><p><strong>Results: </strong>Of 396 articles, only 15 met the inclusion criteria. Many papers were excluded due to their lack of relevance to the topic. Thematic analysis identified 6 themes radiation exposure, mentorship, male dominance, work-life balance, research, and early exposure to IR.</p><p><strong>Conclusions: </strong>Recommendations relating to each theme have been made. Establishing a high-quality mentoring scheme, for medical students, is the priority. Followed by accurate information, regarding radiation safety and teaching opportunities provided by medical schools and placement trusts, to demonstrate the value of IR and the need for a representative workforce.</p><p><strong>Advances in knowledge: </strong>With little research based primarily within the United Kingdom, this review has amalgamated results from papers published internationally to highlight potential factors influencing the gender disparity within IR. Realistic recommendations and future points of research aimed at creating gender parity that are appropriate towards both the United Kingdom and global institutions have been suggested.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1622-1626"},"PeriodicalIF":1.8,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11417366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141892911","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":"Automated estimation of thoracic rotation in chest X-ray radiographs: a deep learning approach for enhanced technical assessment.","authors":"Jiuai Sun, Pengfei Hou, Kai Li, Ling Wei, Ruifeng Zhao, Zhonghang Wu","doi":"10.1093/bjr/tqae149","DOIUrl":"10.1093/bjr/tqae149","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to develop an automated approach for estimating the vertical rotation of the thorax, which can be used to assess the technical adequacy of chest X-ray radiographs (CXRs).</p><p><strong>Methods: </strong>Total 800 chest radiographs were used to train and establish segmentation networks for outlining the lungs and spine regions in chest X-ray images. By measuring the widths of the left and right lungs between the central line of segmented spine and the lateral sides of the segmented lungs, the quantification of thoracic vertical rotation was achieved. Additionally, a life-size, full body anthropomorphic phantom was employed to collect chest radiographic images under various specified rotation angles for assessing the accuracy of the proposed approach.</p><p><strong>Results: </strong>The deep learning networks effectively segmented the anatomical structures of the lungs and spine. The proposed approach demonstrated a mean estimation error of less than 2° for thoracic rotation, surpassing existing techniques and indicating its superiority.</p><p><strong>Conclusions: </strong>The proposed approach offers a robust assessment of thoracic rotation and presents new possibilities for automated image quality control in chest X-ray examinations.</p><p><strong>Advances in knowledge: </strong>This study presents a novel deep-learning-based approach for the automated estimation of vertical thoracic rotation in chest X-ray radiographs. The proposed method enables a quantitative assessment of the technical adequacy of CXR examinations and opens up new possibilities for automated screening and quality control of radiographs.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1690-1695"},"PeriodicalIF":1.8,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11417390/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141981774","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":"Non-contrast abbreviated MRI for the detection of hepatocellular carcinoma in patients with Liver Imaging Reporting and Data System LR-3 and LR-4 observations in MRI.","authors":"Soe Thiha Maung, Natthaporn Tanpowpong, Minchanat Satja, Sombat Treeprasertsuk, Roongruedee Chaiteerakij","doi":"10.1093/bjr/tqae140","DOIUrl":"10.1093/bjr/tqae140","url":null,"abstract":"<p><strong>Background and aims: </strong>With ultrasound sensitivity limited in hepatocellular carcinoma (HCC) surveillance and few prospective studies on non-contrast abbreviated MRI (NC-AMRI), this study aimed to assess its diagnostic performance in detecting HCC.</p><p><strong>Methods: </strong>This prospective study involved cirrhotic patients with contrast-enhanced MRI (CE-MRI) Liver Imaging Reporting and Data System (LI-RADS) LR-3 and LR-4 observations detected during HCC surveillance. Patients underwent average 3 complete CE-MRI rounds at 3-6 months interval, with approximately 12-month follow-up. NC-AMRI included diffusion-weighted (DWI), T2-weighted imaging (T2WI), and T1-weighted imaging (T1WI). NC-AMRI protocol images were analysed for diagnostic performance, with subgroup analyses. CE-MRI and NC-AMRI images were independently reviewed by 2 experienced radiologists, with inter-reader agreement assessed with Kappa coefficient. The reference standard was the American Association for the Study of Liver Diseases-defined presence of arterial hypervascularity and washout during the portal-venous or delayed phases on CE-MRI.</p><p><strong>Results: </strong>In 166 CE-MRI follow-ups of 63 patients (median age: 63 years; 60.3% male, 39.7% female), 12 patients developed HCC, with average size of 19.6 mm. The NC-AMRI (DWI + T2WI + T1WI) showed 91.7% sensitivity (95%CI, 61.5-99.8) and 91.6% specificity (95%CI, 86.0-95.4), area under receiver operating characteristic 0.92 (95%CI, 0.83-1.00). Across different Body Mass Index categories, lesion size, Child-Turcotte-Pugh classes, Albumin-Bilirubin (ALBI) grades, and Model for End-Stage Liver Disease classes, sensitivity remained consistent. However, specificity differed significantly between ALBI grade 1 and 2 (86.7% vs. 98.4%, P = .010), and between viral and non-viral cirrhosis (93.8% vs. 80.8%, P = .010).</p><p><strong>Conclusions: </strong>NC-AMRI proved clinically feasible, and exhibits high diagnostic performance in HCC detection.</p><p><strong>Advances in knowledge: </strong>This study highlights efficacy of NC-AMRI in detecting HCC among cirrhotic patients with LR-3 and LR-4 observations, representing significant progress in HCC surveillance.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1671-1682"},"PeriodicalIF":1.8,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11417374/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141900980","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":"A dual-center study: can ultrasound radiomics differentiate type I and type II epithelial ovarian cancer patients with normal CA125 levels?","authors":"Lixuan Chen, Chenyang Jin, Bo Chen, Asta Debora, Weizeng Su, Qingwen Zhou, Shuai Zhou, Jinyan Bian, Yunjun Yang, Li Lan","doi":"10.1093/bjr/tqae144","DOIUrl":"10.1093/bjr/tqae144","url":null,"abstract":"<p><strong>Objective: </strong>CA125 is recommended by many countries as the primary screening test for ovarian cancer. But there are patients with ovarian cancer having normal CA125. We hope to identify the types of EOC with normal CA125 levels better by building a refined model based on the ultrasound radiomics, thus providing precise medical treatment for patients.</p><p><strong>Methods: </strong>We included 58 patients with EOC with normal CA125 from 2 centres, who were confirmed by preoperative ultrasound and pathology. We extracted 1130 radiomics features based on the tumour's region of interest from the most typical ultrasound image of each patient. We selected radiomics and clinical features by LASSO and logistic regression to construct Rad-score and clinical models, respectively. Receiver operating characteristic curves judged their test efficacy. On the basis of the combined model, we developed a nomogram.</p><p><strong>Results: </strong>Area under the curves (AUCs) of 0.93 and 0.83 were achieved in both the training and test groups for the combined model. There were similar AUCs between the Rad-score and clinical models of 0.82 and 0.80, respectively. By analysing the calibration curves, it was determined that the nomogram matched actual observations in the training cohort.</p><p><strong>Conclusion: </strong>Ultrasound radiomics can differentiate type I and type II EOC with normal CA125 levels.</p><p><strong>Advances in knowledge: </strong>This study is the first to focus on EOC cases with normal level of CA125. The subset of patients constituting 20% of the disease population may require more refined radiomics models.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1706-1712"},"PeriodicalIF":1.8,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11417353/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142035320","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}