BMC Medical Imaging最新文献

{"title":"Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis.","authors":"Suo Yu Yan, Fang Ming Chen, Bang Jun Guo, Su Hu, Li Lin, Yi Wen Yang, Xin Yu Jiang, Hui Yao, Chun Hong Hu, Yun Yan Su","doi":"10.1186/s12880-025-01773-3","DOIUrl":"10.1186/s12880-025-01773-3","url":null,"abstract":"<p><strong>Background: </strong>The role of radiomics and abdominal fat analysis in the survival prediction of pancreatic ductal adenocarcinoma (PDAC) has attracted attention. This study aims to develop a preoperative model for predicting early recurrence (ER) in patients pathologically confirmed PDAC, combining radiomic and abdominal fat analysis.</p><p><strong>Methods: </strong>A total of 177 patients (Hospital A) were retrospectively analyzed and allocated to the training cohort (n = 124) and internal validation cohort (n = 53). Another 71 patients (Hospital B) group formed the geographic external validation cohort. The threshold of ER was set at 6 months after surgery, and the primary endpoint was to determine the best model to predict ER of PDAC patients. A radiomics model for predicting ER was constructed by the least absolute shrinkage and selection operator Cox regression. Univariate and multivariate Cox regression analyses were used to build a combined model based on radiomics, fat quantitation, and clinical features. The combined model's performance was assessed using the Harrell concordance index (C-index). Based on the nomogram score, patients were stratified into high-risk and low-risk groups, and survival analysis of different risk groups was performed using the Kaplan-Meier (KM) method. All patients were divided into four subgroups according to recurrence patterns: local recurrence subgroup, distant recurrence subgroup, \"local + distant\" recurrence subgroup, and \"multiple\" recurrence subgroup. The predictive efficacy of the combined model was calculated in different subgroups.</p><p><strong>Results: </strong>Radiomics scores (P < 0.001), CA19-9 (P = 0.009), and visceral to subcutaneous fat volume ratio(P = 0.009) were selected for the combined model. Compared to clinical and radiomics models, the combined model exhibited the best prediction performance. C indexes of the training cohort, internal validation cohort, and external validation cohort were 0.778 (0.711,0.845), 0.746 (0.632,0.860), and 0.712 (0.612,0.812) respectively, showing the improvement over the clinical model (without radiomics and fat quantitation features) in the internal validation and external validation sets (DeLong test: P = 0.027, P = 0.079). KM analysis showed significant differences between risk groups (all P < 0.05). The combined model also achieved robust performance in different subgroups of recurrence patterns.</p><p><strong>Conclusion: </strong>The combined model effectively predicted the probability of ER in PDAC patients and may provide an emerging tool to preoperatively guide personalized treatment.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"251"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MCAUnet: a deep learning framework for automated quantification of body composition in liver cirrhosis patients.","authors":"Jiening Wang, Shuqi Xia, Jie Zhang, Xinyi Wang, Cai Zhao, Wen Zheng","doi":"10.1186/s12880-025-01756-4","DOIUrl":"https://doi.org/10.1186/s12880-025-01756-4","url":null,"abstract":"<p><p>Traditional methods for measuring body composition in CT scans rely on labor-intensive manual delineation, which is time-consuming and imprecise. This study proposes a deep learning-driven framework, MCAUnet, for accurate and automated quantification of body composition and comprehensive survival analysis in cirrhotic patients. A total of 11,362 L3-level lumbar CT slices were collected to train and validate the segmentation model. The proposed model incorporates an attention mechanism from the channel perspective, enabling adaptive fusion of critical channel features. Experimental results demonstrate that our approach achieves an average Dice coefficient of 0.952 for visceral fat segmentation, significantly outperforming existing segmentation models. Based on the quantified body composition, sarcopenic visceral obesity (SVO) was defined, and an association model was developed to analyze the relationship between SVO and survival rates in cirrhotic patients. The study revealed that 3-year and 5-year survival rates of SVO patients were significantly lower than those of non-SVO patients. Regression analysis further validated the strong correlation between SVO and mortality in cirrhotic patients. In summary, the MCAUnet framework provides a novel, precise, and automated tool for body composition quantification and survival analysis in cirrhotic patients, offering potential support for clinical decision-making and personalized treatment strategies.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"215"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computed tomography imaging analysis of hematogenous disseminated pulmonary tuberculosis cases combined with prostate tuberculosis.","authors":"Xu-Wen Fu, Yan Bi, Min Qi, Jing-Liang Liu, Jia-Lu Wei, Wei Gan, Jin-Tang He, Xiang Li","doi":"10.1186/s12880-025-01753-7","DOIUrl":"https://doi.org/10.1186/s12880-025-01753-7","url":null,"abstract":"<p><strong>Objective: </strong>The aim of this study is to enhance the understanding of prostate tuberculosis by analyzing clinical data and prostate computed tomography (CT) imaging of patients with hematogenous disseminated pulmonary tuberculosis and prostate tuberculosis.</p><p><strong>Methods: </strong>Patients with hematogenous disseminated pulmonary tuberculosis and prostate tuberculosis admitted to Kunming Third People's Hospital between January 2018 and December 2024 were enrolled in the study. Their clinical and imaging characteristics were retrospectively analyzed.</p><p><strong>Results: </strong>A cohort of 11 male patients were included in the study, with only 4 (36.4%) experiencing scrotal swelling and pain. All 11 patients (100.0%) had positive γ-interferon release assay results. More than 90% exhibited a decreased absolute value and percentage of peripheral blood lymphocytes, lower serum albumin and prealbumin levels, elevated C-reactive protein, and an increased erythrocyte sedimentation rate. CT images of prostate tuberculosis predominantly revealed multiple hypodense shadows in the prostate, while contrast-enhanced scans demonstrated annular enhancement or significant enhancement of prostate tissue outside the lesion. Following effective anti-tuberculosis treatment, follow-up CT scans showed lesion size reduction, decreased enhancement around the hypodense lesion, and the emergence of punctate and sand-like calcifications. If tuberculosis involved other organs of the male reproductive system, corresponding CT findings were also observed.</p><p><strong>Conclusion: </strong>Hematogenous disseminated pulmonary tuberculosis with concurrent prostate tuberculosis is often associated with other extrapulmonary tuberculosis and tuberculosis affecting organs of the reproductive system. Clinical symptoms are generally mild. CT imaging plays a significant role in diagnosing and monitoring this condition.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"212"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preoperative MRI-based deep learning reconstruction and classification model for assessing rectal cancer.","authors":"Yuan Yuan, Shengnan Ren, Haidi Lu, Fangying Chen, Lei Xiang, Ryan Chamberlain, Chengwei Shao, Jianping Lu, Fu Shen, Luguang Chen","doi":"10.1186/s12880-025-01775-1","DOIUrl":"10.1186/s12880-025-01775-1","url":null,"abstract":"<p><strong>Background: </strong>To determine whether deep learning reconstruction (DLR) could improve the image quality of rectal MR images, and to explore the discrimination of the TN stage of rectal cancer by different readers and deep learning classification models, compared with conventional MR images without DLR.</p><p><strong>Methods: </strong>Images of high-resolution T2-weighted, diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted imaging (CE-T1WI) from patients with pathologically diagnosed rectal cancer were retrospectively processed with and without DLR and assessed by five readers. The first two readers measured the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the lesions. The overall image quality and lesion display performance for each sequence with and without DLR were independently scored using a five-point scale, and the TN stage of rectal cancer lesions was evaluated by the other three readers. Fifty of the patients were randomly selected to further make a comparison between DLR and traditional denoising filter. Deep learning classification models were developed and compared for the TN stage. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were used to evaluate the diagnostic performance of the proposed model.</p><p><strong>Results: </strong>Overall, 178 patients were evaluated. The SNR and CNR of the lesion on images with DLR were significantly higher than those without DLR, for T2WI, DWI and CE-T1WI, respectively (p < 0.0001). A significant difference was observed in overall image quality and lesion display performance between images with and without DLR (p < 0.0001). The image quality scores, SNR, and CNR values of DLR image set were significantly larger than those of original and filter enhancement image sets (all p values < 0.05) for all the three sequences, respectively. The deep learning classification models with DLR achieved good discrimination of the TN stage, with area under the curve (AUC) values of 0.937 (95% CI 0.839-0.977) and 0.824 (95% CI 0.684-0.913) in the test sets, respectively.</p><p><strong>Conclusion: </strong>Deep learning reconstruction and classification models could improve the image quality of rectal MRI images and enhance the diagnostic performance for determining the TN stage of patients with rectal cancer.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"259"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a machine learning model for central compartmental lymph node metastasis in solitary papillary thyroid microcarcinoma via ultrasound imaging features and clinical parameters.","authors":"Haiyang Han, Heng Sun, Chang Zhou, Li Wei, Liang Xu, Dian Shen, Wenshu Hu","doi":"10.1186/s12880-025-01757-3","DOIUrl":"https://doi.org/10.1186/s12880-025-01757-3","url":null,"abstract":"<p><strong>Background: </strong>Papillary thyroid microcarcinoma (PTMC) is the most common malignant subtype of thyroid cancer. Preoperative assessment of the risk of central compartment lymph node metastasis (CCLNM) can provide scientific support for personalized treatment decisions prior to microwave ablation of thyroid nodules. The objective of this study was to develop a predictive model for CCLNM in patients with solitary PTMC on the basis of a combination of ultrasound radiomics and clinical parameters.</p><p><strong>Methods: </strong>We retrospectively analyzed data from 480 patients diagnosed with PTMC via postoperative pathological examination. The patients were randomly divided into a training set (n = 336) and a validation set (n = 144) at a 7:3 ratio. The cohort was stratified into a metastasis group and a nonmetastasis group on the basis of postoperative pathological results. Ultrasound radiomic features were extracted from routine thyroid ultrasound images, and multiple feature selection methods were applied to construct radiomic models for each group. Independent risk factors, along with radiomics features identified through multivariate logistic regression analysis, were subsequently refined through additional feature selection techniques to develop combined predictive models. The performance of each model was then evaluated.</p><p><strong>Results: </strong>The combined model, which incorporates age, the presence of Hashimoto's thyroiditis (HT), and radiomics features selected via an optimal feature selection approach (percentage-based), exhibited superior predictive efficacy, with AUC values of 0.767 (95% CI: 0.716-0.818) in the training set and 0.729 (95% CI: 0.648-0.810) in the validation set.</p><p><strong>Conclusion: </strong>A machine learning-based model combining ultrasound radiomics and clinical variables shows promise for the preoperative risk stratification of CCLNM in patients with PTMC. However, further validation in larger, more diverse cohorts is needed before clinical application.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"228"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusion weighted imaging-based differentiation of arteritic and non-arteritic anterior ischemic optic neuropathy.","authors":"Charlotte Pietrock, Theresia Knoche, Sophia Meidinger, Victor Wenzel, Konrad Neumann, Eberhard Siebert, Leon Alexander Danyel","doi":"10.1186/s12880-025-01780-4","DOIUrl":"10.1186/s12880-025-01780-4","url":null,"abstract":"<p><strong>Purpose: </strong>To assess the utility of DWI-MRI to differentiate arteritic (A-AION) from non-arteritic (NA-AION) ischemic optic neuropathy.</p><p><strong>Methods: </strong>This bicentric cohort-study evaluated 3T DWI-MRI scans performed within 10 days after onset of AION in patients treated between 2014 and 2024 at two tertiary care centers. DWI was first assessed for the presence of restricted diffusion within the optic nerve. Quantitative apparent diffusion coefficient (ADC) evaluation was performed by placing a region of interest (ROI) within the affected optic nerve. Qualitative and quantitative DWI assessments were compared between A-AION and NA-AION patients.</p><p><strong>Results: </strong>Twenty A-AION patients (75.7 ± 6.8 years; 16 [80.0%] female) and 59 NA-AION patients (64.6 ± 10.7 years; 22 [37.3%] female) with a total of 82 (A-AION: 23; NA-AION: 59) DWI-MRI scans were included in the study. Restricted diffusion on ADC was significantly more frequent in A-AION, when compared to NA-AION (82.6% vs. 42.4%; p = 0.001). Corresponding sensitivity, specificity, positive and negative predictive value of qualitative ADC assessment for the identification of A-AION were 0.83, 0.58, 0.43 and 0.89. Quantitative ADC analysis revealed significantly lower values in optic nerves affected by A-AION (ADC: 448.0 ± 256.2 × 10^- 6 mm²/s vs. 671.5 ± 174.9 × 10^- 6 mm²/s, p = 0.002).</p><p><strong>Conclusion: </strong>Restricted diffusion of the optic nerve is more frequent in A-AION and associated with lower optic nerve ADC values, when compared to NA-AION. Prospective studies are required to further explore the potential of DWI in discerning arteritic from non-arteritic AION.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"208"},"PeriodicalIF":2.9,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12180212/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144332423","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":"Association between age and lung cancer risk: evidence from lung lobar radiomics.","authors":"Yuwei Li, Chengting Lin, Lei Cui, Chao Huang, Liting Shi, Shiyang Huang, Yue Yu, Xianglan Zhou, Qian Zhou, Kun Chen, Lei Shi","doi":"10.1186/s12880-025-01747-5","DOIUrl":"10.1186/s12880-025-01747-5","url":null,"abstract":"<p><strong>Background: </strong>Previous studies have highlighted the prominent role of age in lung cancer risk, with signs of lung aging visible in computed tomography (CT) imaging. This study aims to characterize lung aging using quantitative radiomic features extracted from five delineated lung lobes and explore how age contributes to lung cancer development through these features.</p><p><strong>Methods: </strong>We analyzed baseline CT scans from the Wenling lung cancer screening cohort, consisting of 29,810 participants. Deep learning-based segmentation method was used to delineate lung lobes. A total of 1,470 features were extracted from each lobe. The minimum redundancy maximum relevance algorithm was applied to identify the top 10 age-related radiomic features among 13,137 never smokers. Multiple regression analyses were used to adjust for confounders in the association of age, lung lobar radiomic features, and lung cancer. Linear, Cox proportional hazards, and parametric accelerated failure time models were applied as appropriate. Mediation analyses were conducted to evaluate whether lobar radiomic features mediate the relationship between age and lung cancer risk.</p><p><strong>Results: </strong>Age was significantly associated with an increased lung cancer risk, particularly among current smokers (hazard ratio = 1.07, P = 2.81 × 10^- 13). Age-related radiomic features exhibited distinct effects across lung lobes. Specifically, the first order mean (mean attenuation value) filtered by wavelet in the right upper lobe increased with age (β = 0.019, P = 2.41 × 10^- 276), whereas it decreased in the right lower lobe (β = -0.028, P = 7.83 × 10^- 277). Three features, namely wavelet_HL_firstorder_Mean of the right upper lobe, wavelet_LH_firstorder_Mean of the right lower lobe, and original_shape_MinorAxisLength of the left upper lobe, were independently associated with lung cancer risk at Bonferroni-adjusted P value. Mediation analyses revealed that density and shape features partially mediated the relationship between age and lung cancer risk while a suppression effect was observed in the wavelet first order mean of right upper lobe.</p><p><strong>Conclusions: </strong>The study reveals lobe-specific heterogeneity in lung aging patterns through radiomics and their associations with lung cancer risk. These findings may contribute to identify new approaches for early intervention in lung cancer related to aging.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"204"},"PeriodicalIF":2.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12143070/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144233088","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":"Investigation of the correlation between radiomorphometric indices in cone-beam computed tomography images and dual X-ray absorptiometry bone density test results in postmenopausal women.","authors":"Sara Rafieizadeh, Sima Lari, Mohammad Mahdi Maleki, Abbas Shokri, Leili Tapak","doi":"10.1186/s12880-025-01739-5","DOIUrl":"10.1186/s12880-025-01739-5","url":null,"abstract":"<p><strong>Objective: </strong>Osteoporosis is a prevalent skeletal disorder characterized by reduced bone mineral density (BMD) and structural deterioration, resulting in increased fracture risk. Early diagnosis is crucial to prevent fractures and improve patient outcomes. This study investigates the diagnostic utility of morphometric and cortical indices derived from cone-beam computed tomography (CBCT) for identifying osteoporotic postmenopausal women who were candidates for dental implant therapy, with dual-energy X-ray absorptiometry (DXA) used as the reference standard.</p><p><strong>Materials and methods: </strong>This cross-sectional study included 71 postmenopausal women, aged 50-79 years, who underwent CBCT imaging at the Oral and Maxillofacial Radiology Department of Hamadan University of Medical Sciences between 2022 and 2024. Participants with systemic conditions affecting bone metabolism were excluded. The morphometric indices-Computed Tomography Mandibular Index (CTMI), Computed Tomography Index Superior (CTI(S)), Computed Tomography Index Inferior (CTI(I)), and Computed Tomography Cortical Index (CTCI)-were measured at the mental foramen and antegonial regions using OnDemand3D Dental software. Bone mineral density (BMD) was assessed by DXA scans of the lumbar spine and femoral neck. In addition to traditional statistical analyses (Pearson's correlation and one-way ANOVA with LSD test), a multilayer perceptron (MLP) neural network model was employed to evaluate the diagnostic power of CBCT indices.</p><p><strong>Results: </strong>DXA results based on the femoral neck T-scores categorized 38 patients as normal, 32 as osteopenic, and one as osteoporotic, while lumbar spine T-scores identified 38 normal, 22 osteopenic, and 11 osteoporotic patients. Significant differences (p < 0.05) were observed in most CBCT-derived indices, with the CTMI index demonstrating the most marked variation, especially between normal and osteoporotic groups (p < 0.001). Moreover, significant positive correlations were found between the CBCT indices and DXA T-scores across the lumbar spine, femoral neck, and total hip regions. The neural network model achieved an overall diagnostic accuracy of 75%, with the highest predictive importance attributed to antegonial CTCI and CTMI indices.</p><p><strong>Conclusion: </strong>This study highlights the significant correlation between CBCT-derived radiomorphometric indices such as CTMI, CTI(S), CTI(I), and CTCI at the mental foramen and antegonial regions and bone mineral density (BMD) in postmenopausal women. CBCT, particularly the CTMI index in the antegonial region, offers a cost-effective, non-invasive method for early osteoporosis detection, providing a valuable alternative to traditional screening methods.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"203"},"PeriodicalIF":2.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12139361/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144233090","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":"StrokeNeXt: an automated stroke classification model using computed tomography and magnetic resonance images.","authors":"Evren Ekingen, Ferhat Yildirim, Ozgur Bayar, Erhan Akbal, Ilknur Sercek, Abdul Hafeez-Baig, Sengul Dogan, Turker Tuncer","doi":"10.1186/s12880-025-01721-1","DOIUrl":"10.1186/s12880-025-01721-1","url":null,"abstract":"<p><strong>Background and objective: </strong>Stroke ranks among the leading causes of disability and death worldwide. Timely detection can reduce its impact. Machine learning delivers powerful tools for image‑based diagnosis. This study introduces StrokeNeXt, a lightweight convolutional neural network (CNN) for computed tomography (CT) and magnetic resonance (MR) scans, and couples it with deep feature engineering (DFE) to improve accuracy and facilitate clinical deployment.</p><p><strong>Materials and methods: </strong>We assembled a multimodal dataset of CT and MR images, each labeled as stroke or control. StrokeNeXt employs a ConvNeXt‑inspired block and a squeeze‑and‑excitation (SE) unit across four stages: stem, StrokeNeXt block, downsampling, and output. In the DFE pipeline, StrokeNeXt extracts features from fixed‑size patches, iterative neighborhood component analysis (INCA) selects the top features, and a t algorithm-based k-nearest neighbors (tkNN) classifier has been utilized for classification.</p><p><strong>Results: </strong>StrokeNeXt achieved 93.67% test accuracy on the assembled dataset. Integrating DFE raised accuracy to 97.06%. This combined approach outperformed StrokeNeXt alone and reduced classification time.</p><p><strong>Conclusion: </strong>StrokeNeXt paired with DFE offers an effective solution for stroke detection on CT and MR images. Its high accuracy and fewer learnable parameters make it lightweight and it is suitable for integration into clinical workflows. This research lays a foundation for real‑time decision support in emergency and radiology settings.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"205"},"PeriodicalIF":2.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12142900/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144233100","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":"Development and validation of a CT algorithm based on intratumoral necrosis and tumor morphology to predict the nuclear grade of small (2-4 cm) solid clear cell renal cell carcinoma.","authors":"Jianyi Qu, Pingyi Zhu, Xianli Zhu, Xinyan Li, Wenjie Zhang, Xinhong Song, Xiaofei Wang, Chenchen Dai, Qianqian Zhang, Jianjun Zhou","doi":"10.1186/s12880-025-01741-x","DOIUrl":"10.1186/s12880-025-01741-x","url":null,"abstract":"<p><strong>Background: </strong>Preoperative non-invasive prediction of the World Health Organization/International Society of Urological Pathology (WHO/ISUP) nuclear grade of small clear cell renal cell carcinoma (ccRCC) can aid in decision making for active surveillance. The study aimed to develop and validate a CT algorithm for the prediction of the WHO/ISUP nuclear grade of small (2-4 cm) solid ccRCC.</p><p><strong>Methods: </strong>A total of 233 patients with 233 ccRCCs (50 high-grade [WHO/ISUP grades 3-4] and 183 low-grade [WHO/ISUP grades 1-2]) in the initial cohort were enrolled in this study. The tumor necrosis (presence of necrosis, proportion of necrosis, and tumor necrosis score [TNS]) and tumor morphology (five grades) were retrospectively evaluated using contrast-enhanced CT. A four-tiered CT score based on TNS and shape irregularity score (SIS) was constructed using logistic regression and receiver operating characteristic (ROC) curve analyses. The effectiveness of the four-tiered CT score was confirmed through an external validation cohort (218 ccRCCs from 218 patients, including 42 high-grade and 176 low-grade).</p><p><strong>Results: </strong>The TNS and tumor morphologies significantly differed between high-grade and low-grade ccRCCs (both P < 0.001). For diagnosis of high-grade ccRCC, the TNS and SIS achieved the area under the ROC curve (AUC) values of 0.697 and 0.731, respectively. The four-tiered CT score had an interobserver agreement of 0.677 (Cohen kappa), and achieved the AUC values of 0.793 and 0.781 in the initial and validation cohorts, respectively. The CT score of ≥ 3 exhibited a sensitivity of 54.00% and 54.76% in the initial and validation cohorts, respectively, with corresponding specificity of 90.16% and 88.07%, accuracy of 82.40% and 81.65%, positive predictive value of 60.00% and 52.27%, and negative predictive value (NPV) of 87.77% and 89.08%.</p><p><strong>Conclusions: </strong>The TNS based on the number and size of necrotic foci could help diagnose high-grade ccRCC. The developed CT score algorithm achieved moderate AUC and high NPV for the diagnosis of high-grade ccRCC, which might facilitate active surveillance for ccRCC with a diameter of 2-4 cm.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"207"},"PeriodicalIF":2.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12143066/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144233089","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}