BMC Medical Imaging最新文献

{"title":"Intra-discal vacuum phenomenon with advanced lumbar spine disc degeneration: complementary findings from both MRI and CT.","authors":"Derek T Cawley, Aoibhín McDonnell, Andrew Simpkin, Thomas Doyle, Mohammed Habash, Conor McNamee, Cliona Nic Gabhann, Padraig O'Reilly, David O'Sullivan, Robert Woods, Aiden Devitt","doi":"10.1186/s12880-025-01635-y","DOIUrl":"10.1186/s12880-025-01635-y","url":null,"abstract":"<p><strong>Objective: </strong>Intra-Discal Vacuum phenomenon (IDVP) is associated with advanced disc degeneration, representing persistent intra-segmental movement. Our objective is to further characterise IDVP patterns from both MRI and CT thus informing on an otherwise poorly understood phenomenon.</p><p><strong>Methods: </strong>An observational analysis was performed, including an over-60s population sample of 325 lumbar discs in 65 subjects (29 M, 36 F) with low back pain +/- leg symptoms, with MRI of the lumbar spine and concomitant CT abdomen. Exclusion criteria were those with insufficient quality, non-degenerative or destructive spinal pathology, previous neuromodulation or spine instrumentation.</p><p><strong>Results: </strong>49 subjects (94 levels) displayed IDVP, including 11/184 Pfirrmann grade 3/IVDP positive, 49/79 grade 4/IVDP positive and 34/39 grade 5/IVDP positive discs. Increased severity of IDVP significantly correlated with increased Pfirrmann grade and decreased disc height (p <.05). Affected IDVP levels within the L1L2 & L2L3 region when compared to the L4L5 & L5S1 region, displayed similar Pfirrmann grade (4.1 v 4.3) and disc height (0.52 v 0.51) but with greater severity of IDVP in the latter (1.5 v 1.98, p <.002). While 83/105 (81%) of levels with Pfirrmann 4/5 with reduced disc height, displayed IDVP, a small minority did not, where instead they displayed a significantly higher risk of adjacent IDVP (p <.05).</p><p><strong>Conclusion: </strong>CT and MRI complement each other through the identification of IDVP, allowing the diagnostician further insight on disc degeneration. Worsening severity of IDVP on CT correlates with increased disc degeneration and reduced disc height on MRI, particularly in the lower lumbar spine. A small minority of advanced degenerate discs do not display IDVP and quiesce, mostly where there is presence of an adjacent IDVP.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"94"},"PeriodicalIF":2.9,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927346/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143668861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic review and meta-analysis of magnetic resonance imaging in the diagnosis of pulmonary embolism.","authors":"Chuan-Hua Yang, Miao Yu, Deng-Chao Wang","doi":"10.1186/s12880-025-01629-w","DOIUrl":"10.1186/s12880-025-01629-w","url":null,"abstract":"<p><strong>Background: </strong>Pulmonary embolism is a significant clinical challenge with high mortality risk. Computed Tomography Pulmonary Angiography (CTPA) is the gold standard for diagnosis but involves radiation risks. Magnetic Resonance Imaging (MRI) offers a radiation-free alternative, yet its adoption is hindered by inconsistent validation of its diagnostic accuracy. This study systematically assesses MRI's efficacy in diagnosing pulmonary embolism, incorporating a broad range of literature to ensure comprehensive analysis.</p><p><strong>Methods: </strong>Relevant studies on the diagnostic use of MRI for pulmonary embolism were collected through computer searches of PubMed, Embase, Cochrane Library, Web of Science, China National Knowledge Infrastructure (CNKI), Wanfang Database, VIP Database, and China Biology Medicine disc (CBM) databases up to May 12, 2024. Literature was screened based on inclusion and exclusion criteria, data extracted, and study quality assessed according to Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) standards. Data analysis was performed using Stata (versions 17.0 and 14.0) and Meta-Disc 1.4 software. Stata software was used to calculate pooled sensitivity, pooled specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio, and to plot forest plots, hierarchical summary receiver operating characteristic (HSROC) curves, and summary receiver operating characteristic (SROC) curves. The area under the SROC curve (AUC) was calculated, and publication bias was assessed through Deek's funnel plot, Egger's test, and Begg's test.</p><p><strong>Results: </strong>Eighteen articles involving 1,264 participants were included. The meta-analysis showed that MRI for the diagnosis of pulmonary embolism had a pooled sensitivity of 0.89 (95% CI: 0.79-0.94) and a specificity of 0.94 (95% CI: 0.89-0.97). The pooled positive likelihood ratio was 14.6 (95% CI: 8.0-26.7) and the negative likelihood ratio was 0.12 (95% CI: 0.06-0.23). The diagnostic odds ratio was 121 (95% CI: 49-299). The AUC of the SROC was 0.97. Deek's funnel plot suggested potential publication bias in the studies included.</p><p><strong>Conclusion: </strong>MRI exhibits high sensitivity and specificity in the diagnosis of pulmonary embolism, demonstrating excellent diagnostic efficacy. Despite potential publication bias, MRI continues to show strong potential for clinical application.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"92"},"PeriodicalIF":2.9,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924644/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143668865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning prediction model for functional prognosis of acute ischemic stroke based on MRI radiomics of white matter hyperintensities.","authors":"Yayuan Xia, Linhui Li, Peipei Liu, Tianxu Zhai, Yibing Shi","doi":"10.1186/s12880-025-01632-1","DOIUrl":"10.1186/s12880-025-01632-1","url":null,"abstract":"<p><strong>Objective: </strong>The purpose of the current study is to explore the value of a nomogram that integrates clinical factors and MRI white matter hyperintensities (WMH) radiomics features in predicting the prognosis at 90 days for patients with acute ischemic stroke (AIS).</p><p><strong>Methods: </strong>A total of 202 inpatients with acute anterior circulation ischemic stroke from the Department of Neurology, Xuzhou Central Hospital between September 2023 and March 2024 were retrospectively enrolled. Inpatient clinical data and cranial MRI images were acquired. In this study, the sample was randomly divided into a training cohort comprising 141 cases and a validation cohort of 61 cases in a 7:3 ratio. WMH lesions on fluid-attenuated inversion recovery (FLAIR) sequences were automatically segmented and manually adjusted using Matlab and ITK-SNAP software. The segmentation led to the identification of total white matter hyperintensity (TWMH), periventricular white matter hyperintensity (PWMH), and deep white matter hyperintensity (DWMH). Subsequently, radiomics features were meticulously extracted from these three distinct regions of interest (ROIs). Radiomic models for the three ROIs were developed using six machine learning algorithms. The clinical model was built by identifying clinical risk factors through univariate and multivariate logistic regression analyses. A combined model was subsequently developed incorporating the best radiomics model with significant clinical factors. To illustrate these risk factors, a graphical representation known as a nomogram was devised.</p><p><strong>Results: </strong>Age, previous stroke history, coronary artery disease, admission blood glucose levels, homocysteine levels, and infarct volume were identified as independent clinical predictors of AIS prognosis. A total of 16, 21, and 22 radiomics features were selected from TWMH, PWMH, and DWMH, respectively. The TWMH radiomics model using the SVM classifier exhibited the best predictive performance for AIS prognosis, achieving a sensitivity of 90.0%, a specificity of 81.3%, an accuracy of 85.3%, and an AUC of 0.916 in the validation set. The combined model outperformed both the clinical and radiomics models, exhibiting exceptional predictive capabilities with a validation cohort sensitivity of 89.3%, specificity of 84.8%, accuracy of 86.9%, and AUC of 0.939.</p><p><strong>Conclusion: </strong>The FLAIR sequence-based WMH radiomics approach demonstrates effective prediction of the 90-day functional prognosis in patients with AIS. The integration of TWMH radiomics and clinical factors in a combined model exhibits superior performance. This innovative model shows potential in aiding clinicians to enhance their assessment of patient prognosis and tailor personalized treatment strategies.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"91"},"PeriodicalIF":2.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924691/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143662022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combining artificial intelligence assisted image segmentation and ultrasound based radiomics for the prediction of carotid plaque stability.","authors":"Jiajia Song, Liwen Zou, Yu Li, Xiaoyin Wang, Junlan Qiu, Kailin Gong","doi":"10.1186/s12880-025-01621-4","DOIUrl":"10.1186/s12880-025-01621-4","url":null,"abstract":"<p><strong>Purpose: </strong>Utilizing artificial intelligence (AI) technology for the segmentation of plaques on ultrasound images to evaluate the stability of carotid artery plaques and analyze its diagnostic accuracy in differentiating vulnerable plaques from stable ones.</p><p><strong>Methods: </strong>A retrospective study was conducted on 202 patients with ischemic stroke, who were divided into vulnerable plaque group (85 cases) and stable plaque group (117 cases) based on the results of carotid color Doppler ultrasound examination. From the vulnerable plaque group, 63 cases were randomly selected as the modeling group and 22 cases as the validation group; similarly, from the stable plaque group, 87 cases were randomly selected as the modeling group and 30 cases as the validation group. Based on the ultrasound images of the modeling group, plaques were segmented using artificial intelligence technology, and 1414 radiomics features were extracted. These features were then subjected to dimensionality reduction and feature selection using the least absolute shrinkage and selection operator (LASSO) method. Subsequently, a Support Vector Machine (SVM) model was constructed and validated using the selected features. The sensitivity, specificity, and Area Under the Curve (AUC) of the model were evaluated through the analysis of the receiver operating characteristic (ROC) curve.</p><p><strong>Results: </strong>A total of 43 radiomics feature parameters were selected by the LASSO method. The training group for the SVM model had an AUC of 89.42% (95% CI: 80.74-98.10%), sensitivity of 79.84%, and specificity of 93.10%, while the validation group had an AUC of 82.73% (95% CI: 71.64-93.81%), sensitivity of 81.82%, and specificity of 80.00%.</p><p><strong>Conclusion: </strong>The use of artificial intelligence technology for the segmentation of plaques in ultrasound images, coupled with the analysis of radiomics models, can efficiently distinguish the stability of carotid artery plaques, providing a diagnostic basis for the clinical prediction of ischemic stroke.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"89"},"PeriodicalIF":2.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11917087/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Stepwise decision tree model for differential diagnosis of Kimura's disease in the head and neck.","authors":"Rui Luo, Gongxin Yang, Huimin Shi, Yining He, Yongshun Han, Zhen Tian, Yingwei Wu","doi":"10.1186/s12880-025-01618-z","DOIUrl":"10.1186/s12880-025-01618-z","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to differentiate Kimura's disease (KD) from Sjogren's syndrome with mucosa-associated lymphoid tissue lymphoma (SS&MALT), neurofibromatosis (NF), and lymphoma in the head and neck by using a stepwise decision tree approach.</p><p><strong>Materials and methods: </strong>A retrospective analysis of 202 patients with pathologically confirmed KD, SS&MALT, NF, or lymphoma was conducted. Demographic and magnetic resonance imaging (MRI) data were collected, with qualitative features (e.g., skin thickening, lesion morphology, lymphadenopathy, MRI signal intensity) and quantitative variables (e.g., age, lesion size, apparent diffusion coefficients (ADCs), wash-in rate, time to peak (TTP), time-signal intensity curve (TIC) patterns) examined. A stepwise decision-tree model using the classification and regression trees (CART) algorithm was developed to aid in the differential diagnosis of KD in the head and neck. The model's diagnostic accuracy and misclassification risk were assessed to evaluate its reliability and effectiveness.</p><p><strong>Results: </strong>Key characteristics for KD included male predominance (91.7%), frequent lymphadenopathy (86.1%), and skin thickening (72.2%). Primary lesions of NF typically exhibited higher ADCs compared to those of KD, SS&MALT, and lymphoma. In lymphadenopathy, however, unique ADC patterns were observed: in KD, the ADCs of lymphadenopathy were lower than those of primary lesions, whereas in lymphoma, the ADCs of lymphadenopathy were comparable to those of primary lesions. Predictors for distinguishing KD included lesion's location, ADCs, lymphadenopathy, and sizes (all p < 0.001). The decision-tree model achieved an impressive 99.0% accuracy in the differential diagnosis across the overall cohort, with a 10-fold cross-validated misclassification risk of 0.079 ± 0.024.</p><p><strong>Conclusion: </strong>The stepwise decision tree model, based on MRI features, showed high accuracy in differentiating KD from other head and neck diseases, offering a reliable diagnostic tool in clinical practice.</p><p><strong>Clinical relevance: </strong>KD is characterized by male predominance, skin thickening, and high incidence of lymphadenopathy. ADCs and TIC patterns are distinguishable in differentiating KD from SS&MALT, NF, and lymphoma in the head and neck. The decision tree model enhances the understanding of KD imaging features and facilitates accurate KD diagnosis, offering an easily accessible and convenient diagnostic tool for radiologists and physicians in daily practice and guiding tailored clinical management plans for affected patients.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"90"},"PeriodicalIF":2.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11916975/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143646974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-ready rectal cancer MR imaging: a workflow for tumor detection and segmentation.","authors":"Heather M Selby, Yewon A Son, Vipul R Sheth, Todd H Wagner, Erqi L Pollom, Arden M Morris","doi":"10.1186/s12880-025-01614-3","DOIUrl":"10.1186/s12880-025-01614-3","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Magnetic Resonance (MR) imaging is the preferred modality for staging in rectal cancer; however, despite its exceptional soft tissue contrast, segmenting rectal tumors on MR images remains challenging due to the overlapping appearance of tumor and normal tissues, variability in imaging parameters, and the inherent subjectivity of reader interpretation. For studies requiring accurate segmentation, reviews by multiple independent radiologists remain the gold standard, albeit at a substantial cost. The emergence of Artificial Intelligence (AI) offers promising solutions to semi- or fully-automatic segmentation, but the lack of publicly available, high-quality MR imaging datasets for rectal cancer remains a significant barrier to developing robust AI models.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to foster collaboration between a radiologist and two data scientists in the detection and segmentation of rectal tumors on T2- and diffusion-weighted MR images. By combining the radiologist's clinical expertise with the data scientists' imaging analysis skills, we sought to establish a foundation for future AI-driven approaches that streamline rectal tumor detection and segmentation, and optimize workflow efficiency.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A total of 37 patients with rectal cancer were included in this study. Through radiologist-led training, attendance at Stanford's weekly Colorectal Cancer Multidisciplinary Tumor Board (CRC MDTB), and the use of radiologist annotations and clinical notes in Epic Electronic Health Records (EHR), data scientists learned how to detect and manually segment tumors on T2- and diffusion-weighted pre-treatment MR images. These segmentations were then reviewed and edited by a radiologist. The accuracy of the segmentations was evaluated using the Dice Similarity Coefficient (DSC) and Jaccard Index (JI), quantifying the overlap between the segmentations delineated by the data scientists and those edited by the radiologist.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;With the help of radiologist annotations and radiology notes in Epic EHR, the data scientists successfully identified rectal tumors in Slicer v5.7.0 across all evaluated T2- and diffusion-weighted MR images. Through radiologist-led training and participation at Stanford's weekly CRC MDTB, the data scientists' rectal tumor segmentations exhibited strong agreement with the radiologist's edits, achieving a mean DSC [95% CI] of 0.965 [0.939-0.992] and a mean JI [95% CI] of 0.943 [0.900, 0.985]. Discrepancies in segmentations were attributed to over- or under-segmentation, often incorporating surrounding structures such as the rectal wall and lumen.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;This study demonstrates the feasibility of generating high-quality labeled MR datasets through collaboration between a radiologist and two data scientists, which is essential for training AI models to automate tumor detection and segmentation in rectal can","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"88"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11909848/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Morphological characterization of atypical pancreatic ductal adenocarcinoma with cystic lesion on DCE-CT: a comprehensive retrospective study.","authors":"Jing Chen, Qi Wu, Ling Liu, Yuan Yuan, Shengsheng Lai, Zhe Wu, Ruimeng Yang","doi":"10.1186/s12880-025-01586-4","DOIUrl":"10.1186/s12880-025-01586-4","url":null,"abstract":"<p><strong>Background: </strong>Pancreatic ductal adenocarcinoma (PDAC) with cystic features presents significant challenges in achieving an accurate preoperative diagnosis and in implementing appropriate clinical management. The aim of this study was to analyze the dynamic contrast-enhanced computed tomography (DCE-CT) findings of PDACs with cystic lesions and correlate them with histopathological findings.</p><p><strong>Methods: </strong>We retrospectively reviewed 40 patients with pathology-proven PDACs exhibiting cystic lesions who underwent preoperative DCE-CT imaging. The CT manifestations were classified into three subtypes based on the morphological characteristics of the cystic lesions: Type 1, small proportion (< 50%) of intratumoral cystic lesions, with or without associated peritumoral cystic lesions; Type 2, large proportion (≥ 50%) of intratumoral cystic lesions, with or without associated peritumoral cystic lesions; Type 3, a solid pancreatic mass with accompanying peritumoral cystic lesions. The DCE-CT findings were analyzed based on location, size, contour, enhancement patterns, and secondary findings, and compared with the corresponding pathological diagnoses.</p><p><strong>Results: </strong>Among the 40 patients, 23 (57.5%) tumors were located in the pancreatic body or tail. Type 1 was identified in 21 cases, Type 2 in 6 cases, and Type 3 in 13 cases. All masses exhibited a bulging pancreatic contour, with 4 cases showing isoattenuating enhancement on DCE-CT. Secondary signs were present in 87.5% (35/40) of cases. Notably, 15 cases (37.5%) were misdiagnosed or missed. Surgical resection specimens demonstrated common pathological features, including large duct-like cysts and coagulative necrosis.</p><p><strong>Conclusion: </strong>Atypical PDAC with cystic lesions is a relatively uncommon variant that exhibits a range of DCE-CT features, along with distinct pathological characteristics. Familiarity with these imaging features is essential for radiologists in order to minimize the risk of misdiagnosis and guide appropriate clinical management of these challenging cases.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"87"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11909956/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based evaluation of panoramic radiographs for osteoporosis screening: a systematic review and meta-analysis.","authors":"Ali Tarighatnia, Masoud Amanzadeh, Mahnaz Hamedan, Alireza Mohammadnia, Nader D Nader","doi":"10.1186/s12880-025-01626-z","DOIUrl":"10.1186/s12880-025-01626-z","url":null,"abstract":"<p><strong>Background: </strong>Osteoporosis is a complex condition that drives research into its causes, diagnosis, treatment, and prevention, significantly affecting patients and healthcare providers in various aspects of life. Research is exploring orthopantomogram (OPG) radiography for osteoporosis screening instead of bone mineral density (BMD) assessments. Although this method uses various indicators, manual analysis can be challenging. Machine learning and deep learning techniques have been developed to address this. This systematic review and meta-analysis is the first to evaluate the accuracy of deep learning models in predicting osteoporosis from OPG radiographs, providing evidence for their performance and clinical use.</p><p><strong>Methods: </strong>A literature search was conducted in MEDLINE, Scopus, and Web of Science up to February 10, 2025, using the keywords related to deep learning, osteoporosis, and panoramic radiography. We conducted title, abstract, and full-text screening based on inclusion/exclusion criteria. Meta-analysis was performed using a bivariate random-effects model to pool diagnostic accuracy measures, and subgroup analyses explored sources of heterogeneity.</p><p><strong>Results: </strong>We found 204 articles, removed 189 duplicates and irrelevant studies, assessed 15articles, and ultimately, seven studies were selected. The DL models showed AUC values of 66.8-99.8%, with sensitivity and specificity ranging from 59 to 97% and 64.9-100%, respectively. No significant differences in diagnostic accuracy were found among subgroups. AlexNet had the highest performance, achieving a sensitivity of 0.89 and a specificity of 0.99. Sensitivity analysis revealed that excluding outliers had little impact on the results. Deeks' funnel plot indicated no significant publication bias (P = 0.54).</p><p><strong>Conclusions: </strong>This systematic review indicates that deep learning models for osteoporosis diagnosis achieved 80% sensitivity, 92% specificity, and 93% AUC. Models like AlexNet and ResNet demonstrate effectiveness. These findings suggest that DL models are promising for noninvasive early detection, but more extensive multicenter studies are necessary to validate their efficacy in at-risk groups.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"86"},"PeriodicalIF":2.9,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905531/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143612784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantifying anterior segment vascular changes in thyroid eye disease using optical coherence tomography angiography.","authors":"Ahmad Masoumi, Pedram Afshar, Hanieh Fakhredin, Hamidreza Ghanbari, Fateme Montazeri, Amirhossein Aghajani, Zahra Montazeriani, Pezhman Pasyar, Haniyeh Zeidabadinejad, Faezeh Moghimpour Bijani, Seyed Mohsen Rafizadeh","doi":"10.1186/s12880-025-01627-y","DOIUrl":"10.1186/s12880-025-01627-y","url":null,"abstract":"<p><strong>Purpose: </strong>Thyroid eye disease (TED) presents challenges in the accurate assessment of disease activity, especially concerning ocular surface manifestations. This study aims to evaluate the potential of anterior segment optical coherence tomography angiography (AS-OCTA) in quantifying vascular changes associated with TED, thereby enhancing understanding of its pathophysiology and aiding in diagnosis and management.</p><p><strong>Methods: </strong>We conducted a cross-sectional study involving 29 TED patients and 21 healthy controls. Participants underwent comprehensive ophthalmic examination and AS-OCTA imaging of predefined regions of interest (ROI) in the nasal and temporal quadrants. Vascular metrics including vessel density (VD), vessel length density (VLD), vessel diameter index (VDI) and fractal dimension (FD) were analyzed using AS-OCTA software. Disease activity was assessed using clinical activity scores (CAS).</p><p><strong>Results: </strong>TED patients exhibited increased VD and VLD, particularly in the temporal quadrant, compared to healthy controls. Additionally, TED patients in active disease phases demonstrated larger VDI in the nasal quadrant. Negative correlations were observed between superficial VD and disease activity scores, while positive correlations were found between deep VDI and disease activity.</p><p><strong>Conclusion: </strong>AS-OCTA demonstrates potential in quantitatively assessing vascular changes in TED, providing valuable insights into its pathophysiology and potential implications for clinical management. Conjunctival vascular parameters might be valuable in grading the TED disease activity in the future.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"85"},"PeriodicalIF":2.9,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11899867/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143603650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Convolutional block attention gate-based Unet framework for microaneurysm segmentation using retinal fundus images.","authors":"C B Vanaja, P Prakasam","doi":"10.1186/s12880-025-01625-0","DOIUrl":"10.1186/s12880-025-01625-0","url":null,"abstract":"<p><strong>Background: </strong>Diabetic retinopathy is a major cause of vision loss worldwide. This emphasizes the need for early identification and treatment to reduce blindness in a significant proportion of individuals. Microaneurysms, extremely small, circular red spots that appear in retinal fundus images, are one of the very first indications of diabetic retinopathy. Due to their small size and weak nature, microaneurysms are tough to identify manually. However, because of the complex background and varied lighting factors, it is challenging to recognize microaneurysms in fundus images automatically.</p><p><strong>Methods: </strong>To address the aforementioned issues, a unique approach for MA segmentation is proposed based on the CBAM-AG U-Net model, which incorporates Convolutional Block Attention Module (CBAM) and Attention Gate (AG) processes into the U-Net architecture to boost the extraction of features and segmentation accuracy. The proposed architecture takes advantage of the U-Net's encoder-decoder structure, which allows for perfect segmentation by gathering both high- and low-level information. The addition of CBAM introduces channel and spatial attention mechanisms, allowing the network to concentrate on the most useful elements while reducing the less relevant ones. Furthermore, the AGs enhance this process by selecting and displaying significant locations in the feature maps, which improves a model's capability to identify and segment the MAs.</p><p><strong>Results: </strong>The CBAM-AG-UNet model is trained on the IDRiD dataset. It achieved an Intersection over Union (IoU) of 0.758, a Dice Coefficient of 0.865, and an AUC-ROC of 0.996, outperforming existing approaches in segmentation accuracy. These findings illustrate the model's ability to effectively segment the MAs, which is critical for the timely detection and treatment of DR.</p><p><strong>Conclusion: </strong>The proposed deep learning-based technique for automatic segmentation of micro-aneurysms in fundus photographs produces promising results for improving DR diagnosis and treatment. Furthermore, our method has the potential to simplify the process of delivering immediate and precise diagnoses.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"83"},"PeriodicalIF":2.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11895248/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}