Insights into Imaging最新文献

{"title":"Imaging of elbow entrapment neuropathies.","authors":"Domenico Albano, Gabriella Di Rocco, Salvatore Gitto, Francesca Serpi, Stefano Fusco, Paolo Vitali, Massimo Galia, Carmelo Messina, Luca Maria Sconfienza","doi":"10.1186/s13244-025-01901-1","DOIUrl":"10.1186/s13244-025-01901-1","url":null,"abstract":"<p><p>Entrapment neuropathies at the elbow are common in clinical practice and require an accurate diagnosis for effective management. Understanding the imaging characteristics of these conditions is essential for confirming diagnoses and identifying underlying causes. Ultrasound serves as the primary imaging modality for evaluating nerve structure and movement, while MRI is superior for detecting muscle denervation. Plain radiography and CT play a minor role and can be used for the evaluation of bony structures and calcifications/ossifications. Comprehensive knowledge of anatomical landmarks, nerve pathways, and compression sites is crucial for clinicians to accurately interpret imaging and guide appropriate treatment strategies for entrapments of ulnar, median, and radial nerves, and their branches. CRITICAL RELEVANCE STATEMENT: Accurate imaging and anatomical knowledge are essential for diagnosing elbow entrapment neuropathies. Ultrasound is the preferred modality for assessing nerve structure and motion, while MRI excels in detecting muscle denervation and guiding effective management of ulnar, median, and radial nerve entrapments. KEY POINTS: Ultrasound is the primary modality for assessing nerve structure and stability. Findings include nerve structural loss, isoechogenicity, thickening, and hyper-vascularization. MRI provides a comprehensive evaluation of the elbow and accurate muscle assessment. Imaging allows the identification of compressive causes, including anatomical variants, masses, or osseous anomalies. Awareness of anatomical landmarks, nerve pathways, and compression sites is essential.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"24"},"PeriodicalIF":4.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065394","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":"Recognising the role of radiographers in MR safety and the contributions of the European Federation of Radiographer Societies.","authors":"Anke De Bock, Jonathan McNulty, Andrew England","doi":"10.1186/s13244-024-01897-0","DOIUrl":"10.1186/s13244-024-01897-0","url":null,"abstract":"","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"21"},"PeriodicalIF":4.1,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11748646/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143004715","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":"Diagnostic performance of CT for extrarenal fat invasion in renal cell carcinoma: a meta-analysis and systematic review.","authors":"Junchao Ma, Enyu Yuan, Shijian Feng, Jin Yao, Chunlei He, Yuntian Chen, Bin Song","doi":"10.1186/s13244-024-01889-0","DOIUrl":"10.1186/s13244-024-01889-0","url":null,"abstract":"<p><strong>Objectives: </strong>Renal cell carcinoma (RCC) with extrarenal fat (perinephric or renal sinus fat) invasion is the main evidence for the T3a stage. Currently, computed tomography (CT) is still the primary modality for staging RCC. This study aims to determine the diagnostic performance of CT in RCC patients with extrarenal fat invasion.</p><p><strong>Methods: </strong>The PubMed, Web of Science, Cochrane Library, and EMBASE databases were systematically searched up to October 11, 2023. Study quality was assessed by the QUADAS-2 tool. Standard methods recommended for meta-analyses of diagnostic evaluation were used. Heterogeneity was analyzed through meta-regression analysis.</p><p><strong>Results: </strong>Fifteen studies were included in this meta-analysis. Among them, six studies focused on perinephric fat invasion (PFI) only, four on renal sinus fat invasion (RSFI) only, and five on both. Pooled weighted estimates of sensitivity, specificity, area of SROC curve, PLR, and negative likelihood ratio (NLR) of CT for PFI were 0.69 (95% CI: 0.55-0.79), 0.82 (95% CI: 0.69-0.90), 0.81 (95% CI: 0.77-0.84), 3.85 (95% CI: 2.22-6.67), and 0.38 (95% CI: 0.27-0.55). Pooled weighted estimates of sensitivity, specificity, area of SROC curve, PLR, and NLR of CT for RSFI were 0.81 (95% CI: 0.76-0.85), 0.79 (95% CI: 0.66-0.88), 0.82 (95% CI: 0.78-0.85), 3.91 (95% CI: 2.26-6.77), and 0.24 (95% CI: 0.18-0.31).</p><p><strong>Conclusion: </strong>CT has the ability to detect the PFI and RSFI in patients with RCC. However, the diagnostic performance of CT has suffered from the limitation of slightly lower accuracy, resulting from the low positive sample in the current studies. Additionally, the current PLR is low.</p><p><strong>Critical relevance statement: </strong>This study provides radiologists and urologists with a systematic and comprehensive summary of CT and CT-related morphological features in assessing extrarenal fat invasion in patients with RCC.</p><p><strong>Key points: </strong>CT can detect extrarenal fat invasion in patients with RCC, but the diagnostic performance is inconsistent. The diagnostic performance of CT is acceptable, but primarily affected by the low positive rate of included patients. Further large-scale trials are necessary to determine the true diagnostic capabilities of CT for extrarenal fat invasion.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"19"},"PeriodicalIF":4.1,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11735820/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142983503","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":"Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study.","authors":"Kexin Wang, Ning Luo, Zhaonan Sun, Xiangpeng Zhao, Lilan She, Zhangli Xing, Yuntian Chen, Chunlei He, Pengsheng Wu, Xiangpeng Wang, ZiXuan Kong","doi":"10.1186/s13244-024-01865-8","DOIUrl":"10.1186/s13244-024-01865-8","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the feasibility of utilizing artificial intelligence (AI)-predicted biparametric MRI (bpMRI) image features for predicting the aggressiveness of prostate cancer (PCa).</p><p><strong>Materials and methods: </strong>A total of 878 PCa patients from 4 hospitals were retrospectively collected, all of whom had pathological results after radical prostatectomy (RP). A pre-trained AI algorithm was used to select suspected PCa lesions and extract lesion features for model development. The study evaluated five prediction methods, including (1) A clinical-imaging model of clinical features and image features of suspected PCa lesions selected by AI algorithm, (2) the PIRADS category, (3) a conventional radiomics model, (4) a deep-learning bases radiomics model, and (5) biopsy pathology.</p><p><strong>Results: </strong>In the externally validated dataset, the deep learning-based radiomics model showed the highest area under the curve (AUC 0.700 to 0.791). It exceeded the clinical-imaging model (AUC 0.597 to 0.718), conventional radiomic model (AUC 0.566 to 0.632), PIRADS score (AUC 0.554 to 0.613), and biopsy pathology (AUC 0.537 to 0.578). The AUC predicted by the model did not show a statistically significant difference among the three externally verified hospitals (p > 0.05).</p><p><strong>Conclusion: </strong>Deep-learning radiomics models utilizing AI-extracted image features from bpMRI images can potentially be used to predict PCa aggressiveness, demonstrating a generalized ability for external validation.</p><p><strong>Critical relevance statement: </strong>Predicting the aggressiveness of prostate cancer (PCa) is important for formulating the best treatment plan for patients. The radiomic model based on deep learning is expected to provide an objective and non-invasive method for evaluating the aggressiveness of PCa.</p><p><strong>Key points: </strong>Predicting the aggressiveness of PCa is important for patients to obtain the best treatment options. The deep learning-based radiomics model can predict the aggressiveness of PCa with high accuracy. The model has good universality when tested on multiple external datasets.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"20"},"PeriodicalIF":4.1,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11735704/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142983505","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":"Thoracolumbar fascia ultrasound shear strain differs between low back pain and asymptomatic individuals: expanding the evidence.","authors":"Norio Tomita, Marie-Hélène Roy-Cardinal, Boris Chayer, Stacey Daher, Ameer Attiya, Aline Boulanger, Nathaly Gaudreault, Guy Cloutier, Nathalie J Bureau","doi":"10.1186/s13244-024-01895-2","DOIUrl":"10.1186/s13244-024-01895-2","url":null,"abstract":"<p><strong>Objectives: </strong>To compare thoracolumbar fascia (TLF) shear strain between individuals with and without nonspecific low back pain (NSLBP), investigate its correlation with symptoms, and assess a standardized massage technique's impact on TLF shear strain.</p><p><strong>Methods: </strong>Participants were prospectively enrolled between February 2021 and June 2022. Pre- and post-intervention TLF ultrasound and pain/disability questionnaires were conducted. Cumulated (C|ShS|_L) and maximum (Max|ShS|_L) shear strain parameters were computed from radiofrequency data, and TLF thickness was measured on reconstructed B-mode images. Statistical analysis included linear mixed-effects regression.</p><p><strong>Results: </strong>Thirty-two NSLBP participants (mean age, 57 ± 9 years [standard deviation]; 21 women) and 32 controls (51 ± 10 years; 22 women) (p = 0.02) were enrolled. The mean shear strain was higher in NSLBP participants (C|ShS|_L: 327.1% ± 106.0 vs 290.2% ± 99.8, p < 0.0001; Max|ShS|_L: 8.1% ± 2.8 vs 7.0% ± 2.4, p < 0.0001) than controls, while mean TLF thickness (1.6 mm ± 1.0 vs 1.5 mm ± 0.9; p = 0.43) was comparable. Elastography parameters correlated with pain [C|ShS|_L estimate [β], 0.01 [95% CI: 0.002, 0.02]; p = 0.02); Max|ShS|_L [β]_, 0.003 [95% CI: 0.001, 0.005]; p < 0.001)] and disability [C|ShS|_L [β] 0.02 [95% CI: 0.005, 0.03]; p = 0.009); Max|ShS|_L [β] 0.003 [95% CI: 0.001, 0.006]; p = 0.002)] scores. Neither C|ShS|_L (β, 0.13 [-0.27, 0.53]; p = 0.53) nor Max|ShS|_L (β, -0.02 [-0.10, 0.05]; p = 0.59) changed post-intervention.</p><p><strong>Conclusion: </strong>Individuals with NSLBP demonstrated elevated TLF shear strain compared to controls, with similar TLF thickness. The shear strain correlated with pain and disability scores, yet a brief massage did not influence shear strain.</p><p><strong>Trial registration: </strong>Clinicaltrials.gov, NCT04716101. Registered 14 January 2021, https://clinicaltrials.gov/study/NCT04716101 .</p><p><strong>Critical relevance statement: </strong>Ultrasound shows elevated TLF shear strain in lower back pain sufferers compared to controls. This correlates with symptoms, suggesting a role as a pain generator. Further investigation into its anatomy, mechanical characteristics, and pathophysiology is crucial for better understanding.</p><p><strong>Key points: </strong>Structural and mechanical alterations of the TLF may contribute to low back pain. Elevated TLF lateral shear strain was found in patients with NSLBP. A brief standardized massage therapy technique did not influence elastography parameters.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"18"},"PeriodicalIF":4.1,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11735703/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142983508","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":"Characterization of adrenal glands on computed tomography with a 3D V-Net-based model.","authors":"Yuanchong Chen, Yaofeng Zhang, Xiaodong Zhang, Xiaoying Wang","doi":"10.1186/s13244-025-01898-7","DOIUrl":"10.1186/s13244-025-01898-7","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the performance of a 3D V-Net-based segmentation model of adrenal lesions in characterizing adrenal glands as normal or abnormal.</p><p><strong>Methods: </strong>A total of 1086 CT image series with focal adrenal lesions were retrospectively collected, annotated, and used for the training of the adrenal lesion segmentation model. The dice similarity coefficient (DSC) of the test set was used to evaluate the segmentation performance. The other cohort, consisting of 959 patients with pathologically confirmed adrenal lesions (external validation dataset 1), was included for validation of the classification performance of this model. Then, another consecutive cohort of patients with a history of malignancy (N = 479) was used for validation in the screening population (external validation dataset 2). Parameters of sensitivity, accuracy, etc., were used, and the performance of the model was compared to the radiology report in these validation scenes.</p><p><strong>Results: </strong>The DSC of the test set of the segmentation model was 0.900 (0.810-0.965) (median (interquartile range)). The model showed sensitivities and accuracies of 99.7%, 98.3% and 87.2%, 62.2% in external validation datasets 1 and 2, respectively. It showed no significant difference comparing to radiology reports in external validation datasets 1 and lesion-containing groups of external validation datasets 2 (p = 1.000 and p > 0.05, respectively).</p><p><strong>Conclusion: </strong>The 3D V-Net-based segmentation model of adrenal lesions can be used for the binary classification of adrenal glands.</p><p><strong>Critical relevance statement: </strong>A 3D V-Net-based segmentation model of adrenal lesions can be used for the detection of abnormalities of adrenal glands, with a high accuracy in the pre-surgical scene as well as a high sensitivity in the screening scene.</p><p><strong>Key points: </strong>Adrenal lesions may be prone to inter-observer variability in routine diagnostic workflow. The study developed a 3D V-Net-based segmentation model of adrenal lesions with DSC 0.900 in the test set. The model showed high sensitivity and accuracy of abnormalities detection in different scenes.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"17"},"PeriodicalIF":4.1,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11732807/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142978370","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":"Enhancing safety in CT-guided lung biopsies: correlation of MinIP imaging with pneumothorax risk prediction.","authors":"Michael P Brönnimann, Leonie Manser, Bernhard Gebauer, Timo A Auer, Dirk Schnapauff, Federico Collettini, Alexander Pöllinger, Alois Komarek, Miltiadis E Krokidis, Johannes T Heverhagen","doi":"10.1186/s13244-024-01890-7","DOIUrl":"10.1186/s13244-024-01890-7","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to evaluate whether minimum-intensity projection (MinIP) images could predict complications in CT-guided lung biopsies.</p><p><strong>Methods: </strong>We retrospectively analyzed 72 procedures from January 2019 to December 2023, categorizing patients by pneumothorax and the severity of hemorrhage (grade 2 or higher). Radiodensity measurements were performed using lung window (LW) and MinIP (10-mm slab) images. Regions of interest (ROIs) were placed at sites of the lowest density along the biopsy pathway. Absolute values were recorded, categorized by a radiodensity level of -850 HU, and assessed using our bridged radiological observations with measurement-optimized model (BROM-OLB) model with validation from three additional ROIs. Emphysema was visually scored. Statistical analysis included univariate analysis (Fisher's exact and Mann-Whitney U-tests) and binomial logistic regression to identify confounders.</p><p><strong>Results: </strong>Lower radiodensity values in MinIP images in the access route, particularly with the BROM-OLB MinIP method, were significantly associated with a higher risk of pneumothorax (5/39, 13% vs 27/33, 82%, p < 0.01; Sensitivity 81.8% and Specificity 87.2%). Pneumothorax was more common with longer procedures (p < 0.05). Lower LW density values correlated with higher pulmonary hemorrhage rates (p < 0.01). Binomial logistic regression identified positive BROM-OLB MinIP results (OR 28.244, 95% CI: 7.675-103.9, p < 0.01) and lower LW density (OR 0.992, 95% CI: 0.985-0.999, p = 0.025) as independent risk factors. The optimal threshold values to predict pneumothorax were -868 HU in MinIP images and -769 HU in LW.</p><p><strong>Conclusion: </strong>The assessment of MinIP images is superior, and in combination with relative quantitative measurement of radiodensity for access route planning, it can reduce the risk of pneumothorax in CT-guided lung biopsies.</p><p><strong>Critical relevance statement: </strong>This article critically evaluates the risk factors for complications in CT-guided lung biopsies, highlighting the potential of MinIP images for predicting pneumothorax risk, thereby advancing clinical radiology practices to improve patient safety and reduce healthcare costs.</p><p><strong>Key points: </strong>This work investigates if MinIP images efficiently predict CT-guided lung biopsy complications. MinIP imaging identified higher pneumothorax risk post-CT lung biopsy with superior accuracy. Our method detects high-risk lung changes linked to pneumothorax without additional software.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"16"},"PeriodicalIF":4.1,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730046/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142969801","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":"Critical reflection on the indication for computed tomography: an interdisciplinary survey of risk and benefit management in patients with sepsis.","authors":"Maria Isabel Opper Hernando, Denis Witham, Ann-Christine Stahl, Peter Richard Steinhagen, Stefan Angermair, Wolfgang Bauer, Friederike Compton, Andreas Edel, Jan Matthias Kruse, York Kühnle, Gunnar Lachmann, Susanne Marz, Holger Müller-Redetzky, Jens Nee, Oliver Paul, Damaris Praeger, Carsten Skurk, Miriam Stegemann, Alexander Uhrig, Stefan Wolf, Myrto Bolanaki, Kerstin Rubarth, Joachim Seybold, Elke Zimmermann, Marc Dewey, Julian Pohlan","doi":"10.1186/s13244-024-01894-3","DOIUrl":"10.1186/s13244-024-01894-3","url":null,"abstract":"<p><strong>Objectives: </strong>To survey physicians' views on the risks and benefits of computed tomography (CT) in the management of septic patients and indications for and contraindications to contrast media use in searching for septic foci.</p><p><strong>Methods: </strong>A web-based questionnaire was administered to physicians at a large European university medical center in January 2022. A total of 371 questionnaires met the inclusion criteria and were analyzed with physicians' work experience, workplace, and medical specialty as independent variables. Chi-square tests were used for exploratory analysis.</p><p><strong>Results: </strong>While physicians with all levels of work experience were included, the largest group (35.0%, n = 130/371) had 3-7 years of experience. Most physicians agreed that the benefits of CT outweigh its potential adverse effects in septic patients (90.5%, n = 336/371). Responders saw the strongest indication for contrast media administration in septic patients for (1) CT examinations of the abdomen (92.7%, n = 333/359) and (2) combined CT examinations of the chest, abdomen, and pelvis (94.1%, n = 337/358). While radiologists were most likely to consider manifest hyperthyroidism an absolute contraindication to contrast media administration (43.8%, n = 14/32), most other groups of physicians opted for appropriate preparation before contrast media administration in this subset of septic patients.</p><p><strong>Conclusion: </strong>In this survey, most participating physicians considered CT an essential diagnostic modality to detect an infectious focus in septic patients. Whereas the risk of ionizing radiation was regarded as justifiable by most physicians, different specialties varied in their assessment of the risks of contrast media administration.</p><p><strong>Key points: </strong>Physicians recognize CT as a relevant imaging modality in the diagnostic management of patients with sepsis. There is an interdisciplinary consensus that the use of ionizing radiation is justified in septic patients. There is disagreement about indications for and contraindications to contrast media administration among physicians from different medical specialties.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"15"},"PeriodicalIF":4.1,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730041/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142970623","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":"Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses.","authors":"Lu Liu, Wenjun Cai, Feibo Zheng, Hongyan Tian, Yanping Li, Ting Wang, Xiaonan Chen, Wenjing Zhu","doi":"10.1186/s13244-024-01874-7","DOIUrl":"10.1186/s13244-024-01874-7","url":null,"abstract":"<p><strong>Objective: </strong>To develop an automatic segmentation model to delineate the adnexal masses and construct a machine learning model to differentiate between low malignant risk and intermediate-high malignant risk of adnexal masses based on ovarian-adnexal reporting and data system (O-RADS).</p><p><strong>Methods: </strong>A total of 663 ultrasound images of adnexal mass were collected and divided into two sets according to experienced radiologists: a low malignant risk set (n = 446) and an intermediate-high malignant risk set (n = 217). Deep learning segmentation models were trained and selected to automatically segment adnexal masses. Radiomics features were extracted utilizing a feature analysis system in Pyradiomics. Feature selection was conducted using the Spearman correlation analysis, Mann-Whitney U-test, and least absolute shrinkage and selection operator (LASSO) regression. A nomogram integrating radiomic and clinical features using a machine learning model was established and evaluated. The SHapley Additive exPlanations were used for model interpretability and visualization.</p><p><strong>Results: </strong>The FCN ResNet101 demonstrated the highest segmentation performance for adnexal masses (Dice similarity coefficient: 89.1%). Support vector machine achieved the best AUC (0.961, 95% CI: 0.925-0.996). The nomogram using the LightGBM algorithm reached the best AUC (0.966, 95% CI: 0.927-1.000). The diagnostic performance of the nomogram was comparable to that of experienced radiologists (p > 0.05) and outperformed that of less-experienced radiologists (p < 0.05). The model significantly improved the diagnostic accuracy of less-experienced radiologists.</p><p><strong>Conclusions: </strong>The segmentation model serves as a valuable tool for the automated delineation of adnexal lesions. The machine learning model exhibited commendable classification capability and outperformed the diagnostic performance of less-experienced radiologists.</p><p><strong>Critical relevance statement: </strong>The ultrasound radiomics-based machine learning model holds the potential to elevate the professional ability of less-experienced radiologists and can be used to assist in the clinical screening of ovarian cancer.</p><p><strong>Key points: </strong>We developed an image segmentation model to automatically delineate adnexal masses. We developed a model to classify adnexal masses based on O-RADS. The machine learning model has achieved commendable classification performance. The machine learning model possesses the capability to enhance the proficiency of less-experienced radiologists. We used SHapley Additive exPlanations to interpret and visualize the model.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"14"},"PeriodicalIF":4.1,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11729609/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142970615","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":"Ultra-low dose dual-layer detector spectral CT for pulmonary nodule screening: image quality and diagnostic performance.","authors":"Li Ding, Mingwang Chen, Xiaomei Li, Yuting Wu, Jingxu Li, Shuting Deng, Yikai Xu, Zhao Chen, Chenggong Yan","doi":"10.1186/s13244-024-01888-1","DOIUrl":"10.1186/s13244-024-01888-1","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate the image quality and diagnostic performance with ultra-low dose dual-layer detector spectral CT (DLSCT) by various reconstruction techniques for evaluation of pulmonary nodules.</p><p><strong>Materials and methods: </strong>Between April 2023 and December 2023, patients with suspected pulmonary nodules were prospectively enrolled and underwent regular-dose chest CT (RDCT; 120 kVp/automatic tube current) and ultra-low dose CT (ULDCT; 100 kVp/10 mAs) on a DLSCT scanner. ULDCT was reconstructed with hybrid iterative reconstruction (HIR), electron density map (EDM), and virtual monoenergetic images at 40 keV and 70 keV. Quantitative and qualitative image analysis, nodule detectability, and Lung-RADS evaluation were compared using repeated one-way analysis of variance, Friedman test, and weighted kappa coefficient.</p><p><strong>Results: </strong>A total of 249 participants (mean age ± standard deviation, 50.0 years ± 12.9; 126 male) with 637 lung nodules were included. ULDCT resulted in a significantly lower mean radiation dose than RDCT (0.3 mSv ± 0.0 vs. 3.6 mSv ± 0.8; p < 0.001). Compared with RDCT, ULDCT EDM showed significantly higher signal-noise-ratio (44.0 ± 77.2 vs. 4.6 ± 6.6; p < 0.001) and contrast-noise-ratio (26.7 ± 17.7 vs. 5.0 ± 4.4; p < 0.001) with qualitative scores ranked higher or equal to the average. Using the regular-dose images as a reference, ULDCT EDM images had a satisfactory nodule detection rate (84.6%) and good inter-observer agreements compared with RDCT (κw > 0.60).</p><p><strong>Conclusion: </strong>Ultra-low dose dual-layer detector CT with 91.2% radiation dose reduction achieves sufficient image quality and diagnostic performance of pulmonary nodules.</p><p><strong>Critical relevance statement: </strong>Dual-layer detector spectral CT enables substantial radiation dose reduction without impairing image quality for the follow-up of pulmonary nodules or lung cancer screening.</p><p><strong>Key points: </strong>Radiation dose is a major concern for patients requiring pulmonary nodules CT screening. Ultra-low dose dual-layer detector spectral CT with 91.2% dose reduction demonstrated satisfactory performance. Dual-layer detector spectral CT has the potential for lung cancer screening and management.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"11"},"PeriodicalIF":4.1,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11723867/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142947949","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}