{"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}
Ali Tarighatnia, Masoud Amanzadeh, Mahnaz Hamedan, Alireza Mohammadnia, Nader D Nader
{"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}
Juan Hou, Simiao Zhang, Shouxian Li, Zicheng Zhao, Longfei Zhao, Tieliang Zhang, Wenya Liu
{"title":"CT-based radiomics models using intralesional and different perilesional signatures in predicting the microvascular density of hepatic alveolar echinococcosis.","authors":"Juan Hou, Simiao Zhang, Shouxian Li, Zicheng Zhao, Longfei Zhao, Tieliang Zhang, Wenya Liu","doi":"10.1186/s12880-025-01612-5","DOIUrl":"10.1186/s12880-025-01612-5","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the performance of CT-based intralesional combined with different perilesional radiomics models in predicting the microvascular density (MVD) of hepatic alveolar echinococcosis (HAE).</p><p><strong>Methods: </strong>This study retrospectively analyzed preoperative CT data from 303 patients with HAE confirmed by surgical pathology (MVD positive, n = 182; MVD negative, n = 121). The patients were randomly divided into the training cohort (n = 242) and test cohort (n = 61) at a ratio of 8:2. The radiomics features were extracted from CT images on the portal vein phase. Four radiomics models were constructed based on gross lesion volume (GLV), gross combined 10 mm perilesional volume (GPLV<sub>10mm</sub>), gross combined 15 mm perilesional volume (GPLV<sub>15mm</sub>) and gross combined 20 mm perilesional volume (GPLV<sub>20mm</sub>). The best radiomics signature model and clinical features were combined to establish a nomogram. Receiver operating characteristic curve (ROC) and decision curve analysis (DCA) were used to evaluate the predictive performance of models.</p><p><strong>Results: </strong>Among the four radiomics models, the GPLV<sub>20mm</sub> model performed the highest prediction performance with the area under the curves (AUCs) in training cohort and test cohort was 0.876 and 0.802, respectively. The AUC of the clinical model was 0.753 in the training cohort and 0.699 in the test cohort. The AUC of the nomogram model based clinical and GPLV<sub>20mm</sub> radiomic signatures was 0.922 in the training cohort and 0.849 in the test cohort. The DCA showed that the nomogram had greater benefits among the three models.</p><p><strong>Conclusion: </strong>CT-based GPLV<sub>20mm</sub> radiomics model can better predict MVD of HAE. The nomogram model showed the best predictive performance.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"84"},"PeriodicalIF":2.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11895365/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596146","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":"Stapes footplate's posterior border protrudes the vestibule in healthy ears: anatomical insights from ultra-high-resolution CT.","authors":"Ruowei Tang, Ning Xu, Zhengyu Zhang, Zhongrui Chen, Heyu Ding, Zhenghan Yang, Zhenchang Wang, Pengfei Zhao","doi":"10.1186/s12880-025-01622-3","DOIUrl":"10.1186/s12880-025-01622-3","url":null,"abstract":"<p><strong>Background: </strong>The stapes footplate (SF) and annular ligament (AL) in the oval window region are of paramount significances. This study aims to assess the visibility of AL and the relative positioning of the SF and vestibule using ultra-high-resolution computed tomography (U-HRCT).</p><p><strong>Methods: </strong>U-HRCT images between September 2020 and April 2023 were retrospectively reviewed, and 479 ears deemed healthy from both clinical and radiological perspectives were included. AL was considered visible when manifesting as linear low attenuation between the SF and oval window, and the visibility was assessed for its four borders (anterior, posterior, superior and inferior). Two neuroradiologists conducted measurements independently for the SF length, SF-oval window angle, and SF protrusion depth into the vestibule. The results were described on the entire cohort, and compared by age and by sex.</p><p><strong>Results: </strong>A cohort comprising 479 participants [median age 58 years (interquartile range 35-65); 269 females] with 479 healthy ears were included. The inferior border of the AL region demonstrated the highest visibility (476/479, 99.4%), whereas the posterior border exhibited the lowest visibility rate (394/479, 82.3%). The median protrusion depth of the SF posterior border into the vestibule was 0.4 mm (interquartile range 0.3-0.5 mm). Statistically significant differences were observed within age and sex groups for the SF length and the SF protrusion depth (all P < 0.05).</p><p><strong>Conclusions: </strong>This study established radiological features for the SF and AL in healthy ears through U-HRCT. The findings are essential for providing normative references, expediting disease diagnosis, and aiding in selection of surgical strategy.</p><p><strong>Trial registration: </strong>Retrospectively registered.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"82"},"PeriodicalIF":2.9,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11889849/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143584522","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}
Wenli Xie, Lixiu Cao, Jing Yu, Aijuan Tian, Jin Wang, Runlong Lin
{"title":"<sup>18</sup>F-FDG PET/CT metabolic parameter changes to assess vascular inflammatory response in patients with diffuse large B-cell lymphoma.","authors":"Wenli Xie, Lixiu Cao, Jing Yu, Aijuan Tian, Jin Wang, Runlong Lin","doi":"10.1186/s12880-025-01617-0","DOIUrl":"10.1186/s12880-025-01617-0","url":null,"abstract":"<p><strong>Objective: </strong>To study the changes in positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro-D-glucose integrated with computed tomography (<sup>18</sup>F-FDG PET/CT) aortic target-to-background ratio (TBR) and aortic calcification scores before and after 6 cycles of chemotherapy with the rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) regimen in patients with diffuse large B-cell lymphoma (DLBCL).</p><p><strong>Patients and methods: </strong>We selected 161 patients with DLBCL who received 6 cycles of R-CHOP standard chemotherapy and underwent baseline and 6-cycle efficacy evaluations using <sup>18</sup>F-FDG PET/CT examinations at the Second Hospital of Dalian Medical University from July 2017 to June 2023. Additionally, 125 patients who underwent <sup>18</sup>F-FDG PET/CT for physical examination during the same period, without active malignancy or systemic inflammatory disease, were chosen as the control group. We measured metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of systemic lymphoma lesions in tumor patients. Aortic wall FDG uptake was semi quantitatively analyzed as TBR (target-to-blood pool ratio) in five different vascular regions using oncological <sup>18</sup>F-FDG PET/CT. The aortic TBR difference (ΔTBR) was the difference between the post- and pre-chemotherapy TBR values. The degree of arterial segmental wall calcification was assessed using the CT semiquantitative method.</p><p><strong>Results: </strong>Comparison of the pre-treatment group of DLBCL with the control group showed that aortic TBR (1.28 ± 0.17 vs. 1.22 ± 0.18, P < 0.05) were higher in the former group. Additionally, comparing different stage groups of patients with DLBCL revealed that aortic TBR (1.30 ± 0.18 vs. 1.22 ± 0.15, P < 0.05) were higher in the Stage III/IV group compared to the Stage I/II group. Aortic TBR was positively correlated with TLG (P = 0.016, R = 0.19) and MTV (P = 0.032, R = 0.17). Analysis of changes in aortic <sup>18</sup>F-FDG uptake in patients with DLBCL after 6 cycles of treatment revealed that aortic TBR levels were significantly higher post-treatment compared to pre-treatment(P < 0.05). The aortic ΔTBR value was significantly higher in the progression group than in the complete remission group(P < 0.05).</p><p><strong>Conclusion: </strong>Aortic wall <sup>18</sup>F-FDG uptake is related to disease severity and prognosis, indicating a possible vascular effect of lymphoma and its therapeutic interventions. This work highlights an additional potential role of PET/CT in imaging oncology for evaluating disease severity and its consequences on the vasculature.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"81"},"PeriodicalIF":2.9,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11889901/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143584521","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":"Magnetic resonance diffusion-derived vessel density (DDVD) as a valuable tissue perfusion biomarker for isocitrate dehydrogenase genotyping in diffuse gliomas.","authors":"Chen-Xi Ni, Ruo-Lan Lin, Dian-Qi Yao, Fu-Zhao Ma, Yu-Ting Shi, Ying-Ying He, Yang Song, Guang Yang, Ri-Feng Jiang, Yì Xiáng J Wáng","doi":"10.1186/s12880-025-01605-4","DOIUrl":"10.1186/s12880-025-01605-4","url":null,"abstract":"<p><strong>Background: </strong>Determining isocitrate dehydrogenase (IDH) mutation is crucial for glioma clinical management. MR diffusion-derived 'vessel density' (DDVD) offers non-invasive tissue perfusion evaluation within the tumor microenvironment. The study attempts to distinguish IDH genotypes of diffuse gliomas using DDVD in whole tumor parenchyma and its habitats.</p><p><strong>Methods: </strong>This study enrolled 63 patients with diffuse gliomas (30 IDH-mutant and 33 IDH-wildtype) who underwent diffusion-weighted (DW) imaging at 3T. DDVD<sub>b0b10</sub> was the signal difference between the b = 0 and b = 10 s/mm<sup>2</sup> DW images. DDVD<sub>b0b10_b10b20</sub> is DDVD<sub>b0b10</sub> minus DDVD<sub>b10b20</sub>. nDDVD was DDVD divided by signal intensity at b = 0 s/mm<sup>2</sup> DW image. Correlations between DDVD metrics/intravoxel incoherent motion (IVIM) imaging metrics (D and f) and IDH genotypes/Ki-67 status were studied.</p><p><strong>Results: </strong>In tumor parenchyma, DDVD<sub>b0b10_b10b20</sub> and nDDVD<sub>b0b10_b10b20</sub> were lower, whereas D was higher in IDH-mutant gliomas [median (interquartile range): 12.76 (9.79-14.60); 15.14 (11.61-19.29); 1.31 (1.19-1.39)] compared to IDH-wildtype gliomas [14.48 (2.93-18.60), p = 0.008; 20.55 (15.89-24.02), p < 0.001; 1.16 (0.98-1.27), p = 0.003]. Habitat analysis improved the diagnostic performance for IDH genotyping, with the highest AUC of 0.823 found for the nDDVD<sub>b0b10_b10b20</sub> derived from the high DDVD<sub>b0b10</sub> value habitat. Diagnostic efficacy of the combined model of nDDVD<sub>b0b10_b10b20</sub> with D was superior to that of combined model of f with D. The habitat model incorporating age, sex, and Karnofsky Performance Status further significantly enhanced the diagnostic efficacy, with an AUC reaching 0.979. Additionally, DDVD and f showed a positive correlation with Ki-67, while D exhibited a negative correlation with Ki-67 (all p < 0.05).</p><p><strong>Conclusion: </strong>DDVD, as a novel biomarker of microvascular perfusion, effectively differentiates IDH genotypes in gliomas. The habitat analysis improves the diagnostic accuracy for IDH genotyping.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"79"},"PeriodicalIF":2.9,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11887403/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143571935","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":"LoG-staging: a rectal cancer staging method with LoG operator based on maximization of mutual information.","authors":"Ge Zhang, Hao Dang, Qian Zuo, Zhen Tian","doi":"10.1186/s12880-025-01610-7","DOIUrl":"10.1186/s12880-025-01610-7","url":null,"abstract":"<p><p>Deep learning methods have been migrated to rectal cancer staging as a classification process based on magnetic resonance images (MRIs). Typical approaches suffer from the imperceptible variation of images from different stage. The data augmentation also introduces scale invariance and rotation consistency problems after converting MRIs to 2D visible images. Moreover, the correctly labeled images are inadequate since T-staging requires pathological examination for confirmation. It is difficult for classification model to characterize the distinguishable features with limited labeled data. In this article, Laplace of Gaussian (LoG) filter is used to enhance the texture details of converted MRIs and we propose a new method named LoG-staging to predict the T stages of rectal cancer patients. We first use the LoG operator to clarify the fuzzy boundaries of rectal cancer cell proliferation. Then, we propose a new feature clustering method by leveraging the maximization of mutual information (MMI) mechanism which jointly learns the parameters of a neural network and the cluster assignments of features. The assignments are used as labels for the next round of training, which compensate the inadequacy of labeled training data. Finally, we experimentally verify that the LoG-staging is more accurate than the nonlinear dimensionality reduction in predicting the T stages of rectal cancer. We innovatively implement information bottleneck (IB) method in T-staging of rectal cancer based on image classification and impressive results are obtained.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"78"},"PeriodicalIF":2.9,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11887235/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143571854","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}
Bing Li, Nian Liu, Jianbin Bai, Jianfeng Xu, Yi Tang, Yan Liu
{"title":"MTMU: Multi-domain Transformation based Mamba-UNet designed for unruptured intracranial aneurysm segmentation.","authors":"Bing Li, Nian Liu, Jianbin Bai, Jianfeng Xu, Yi Tang, Yan Liu","doi":"10.1186/s12880-025-01611-6","DOIUrl":"10.1186/s12880-025-01611-6","url":null,"abstract":"<p><p>The management of Unruptured Intracranial aneurysm (UIA) depends on the shape parameters assessment of lesions, which requires target segmentation. However, the segmentation of UIA is a challenging task due to the small volume of the lesions and the indistinct boundary between the lesion and the parent arteries. To relieve these issues, this article proposes a multi-domain transformation-based Mamba-UNet (MTMU) for UIA segmentation. The model employs a U-shaped segmentation architecture, equipped with the feature encoder consisting of a set of Mamba and Flip (MF) blocks. It endows the model with the capability of long-range dependency perceiving while balancing computational cost. Fourier Transform (FT) based connection allows for the enhancement of edge information in feature maps, thereby mitigating the difficulties in feature extraction caused by the small size of the target and the limited number of foreground pixels. Additionally, a sub task providing target geometry constrain (GC) is utilized to constrain the model training, aiming at splitting aneurysm dome from its parent artery accurately. Extensive experiments have been conducted to demonstrate the superior performance of the proposed method compared to other competitive medical segmentation methods. The results prove that the proposed method have great clinical application prospects.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"80"},"PeriodicalIF":2.9,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11887374/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143571937","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}