Insights into Imaging最新文献

{"title":"The clinical implications and interpretability of computational medical imaging (radiomics) in brain tumors.","authors":"Yixin Wang, Zongtao Hu, Hongzhi Wang","doi":"10.1186/s13244-025-01950-6","DOIUrl":"https://doi.org/10.1186/s13244-025-01950-6","url":null,"abstract":"<p><p>Radiomics has widespread applications in the field of brain tumor research. However, radiomic analyses often function as a 'black box' due to their use of complex algorithms, which hinders the translation of brain tumor radiomics into clinical applications. In this review, we will elaborate extensively on the application of radiomics in brain tumors. Additionally, we will address the interpretability of handcrafted-feature radiomics and deep learning-based radiomics by integrating biological domain knowledge of brain tumors with interpretability methods. Furthermore, we will discuss the current challenges and prospects concerning the interpretability of brain tumor radiomics. Enhancing the interpretability of radiomics may make it more understandable for physicians, ultimately facilitating its translation into clinical practice. CRITICAL RELEVANCE STATEMENT: The interpretability of brain tumor radiomics empowers neuro-oncologists to make well-informed decisions from radiomic models. KEY POINTS: Radiomics makes a significant impact on the management of brain tumors in several key clinical areas. Transparent models, habitat analysis, and feature attribute explanations can enhance the interpretability of traditional handcrafted-feature radiomics in brain tumors. Various interpretability methods have been applied to explain deep learning-based models; however, there is a lack of biological mechanisms underlying these models.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"77"},"PeriodicalIF":4.1,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143752421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrast-enhanced MRI-based intratumoral heterogeneity assessment for predicting lymph node metastasis in resectable pancreatic ductal adenocarcinoma.","authors":"Junjian Shen, Qin Li, Lei Li, Tianyu Lu, Jun Han, Zongyu Xie, Peng Wang, Zirui Cao, Mengsu Zeng, Jianjun Zhou, Tianzhu Yu, Yaolin Xu, Haitao Sun","doi":"10.1186/s13244-025-01956-0","DOIUrl":"https://doi.org/10.1186/s13244-025-01956-0","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate a contrast-enhanced MRI-based intratumoral heterogeneity (ITH) model for predicting lymph node (LN) metastasis in resectable pancreatic ductal adenocarcinoma (PDAC).</p><p><strong>Methods: </strong>Lesions were encoded into different habitats based on enhancement ratios at arterial, venous, and delayed phases of contrast-enhanced MRI. Habitat models on enhanced ratio mapping and single sequences, radiomic models, and clinical models were developed for evaluating LN metastasis. The performance of the models was evaluated via different metrics. Additionally, patients were stratified into high-risk and low-risk groups based on an ensembled model to assess prognosis after adjuvant therapy.</p><p><strong>Results: </strong>We developed an ensembled radiomics-habitat-clinical (RHC) model that integrates radiomics, habitat, and clinical data for precise prediction of LN metastasis in PDAC. The RHC model showed strong predictive performance, with area under the curve (AUC) values of 0.805, 0.779, and 0.615 in the derivation, internal validation, and external validation cohorts, respectively. Using an optimal threshold of 0.46, the model effectively stratified patients, revealing significant differences in recurrence-free survival and overall survival (OS) (p = 0.004 and p < 0.001). Adjuvant therapy improved OS in the high-risk group (p = 0.004), but no significant benefit was observed in the low-risk group (p = 0.069).</p><p><strong>Conclusion: </strong>We developed an MRI-based ITH model that provides reliable estimates of LN metastasis for resectable PDAC and may offer additional value in guiding clinical decision-making.</p><p><strong>Critical relevance statement: </strong>This ensemble RHC model facilitates preoperative prediction of LN metastasis in resectable PDAC using contrast-enhanced MRI. This offers a foundation for enhanced prognostic assessment and supports the management of personalized adjuvant treatment strategies.</p><p><strong>Key points: </strong>MRI-based habitat models can predict LN metastasis in PDAC. Both the radiomics model and clinical characteristics were useful for predicting LN metastasis in PDAC. The RHC models have the potential to enhance predictive accuracy and inform personalized therapeutic decisions.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"76"},"PeriodicalIF":4.1,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143752418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel deep learning radiopathomics model for predicting carcinogenesis promotor cyclooxygenase-2 expression in common bile duct in children with pancreaticobiliary maljunction: a multicenter study.","authors":"Hui-Min Mao, Jian-Jun Zhang, Bin Zhu, Wan-Liang Guo","doi":"10.1186/s13244-025-01951-5","DOIUrl":"10.1186/s13244-025-01951-5","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate a deep learning radiopathomics model (DLRPM) integrating radiological and pathological imaging data to predict biliary cyclooxygenase-2 (COX-2) expression in children with pancreaticobiliary maljunction (PBM), and to compare its performance with single-modality radiomics, deep learning radiomics (DLR), and pathomics models.</p><p><strong>Methods: </strong>This retrospective study included 219 PBM patients, divided into a training set (n = 104; median age, 2.8 years, 75.0% females) and internal test set (n = 71; median age, 2.2 years, 83.1% females) from center I, and an external test set (n = 44; median age, 3.4 years, 65.9% females) from center II. Biliary COX-2 expression was detected using immunohistochemistry. Radiomics, DLR, and pathomics features were extracted from portal venous-phase CT images and H&E-stained histopathological slides, respectively, to build individual single-modality models. These were then integrated to develop the DLRPM, combining three predictive signatures. Model performance was evaluated using AUC, net reclassification index (NRI, for assessing improvement in correct classification) and integrated discrimination improvement (IDI).</p><p><strong>Results: </strong>The DLRPM demonstrated the highest performance, with AUCs of 0.851 (95% CI, 0.759-0.942) in internal test set and 0.841 (95% CI, 0.721-0.960) in external test set. In comparison, AUCs for the radiomics, DLR, and pathomics models were 0.532-0.602, 0.658-0.660, and 0.787-0.805, respectively. The DLRPM significantly outperformed three single-modality models, as demonstrated by the NRI and IDI tests (all p < 0.05).</p><p><strong>Conclusion: </strong>The multimodal DLRPM could accurately and robustly predict COX-2 expression, facilitating risk stratification and personalized postoperative management in PBM. However, prospective multicenter studies with larger cohorts are needed to further validate its generalizability.</p><p><strong>Critical relevance statement: </strong>Our proposed deep learning radiopathomics model, integrating CT and histopathological images, provides a novel and cost-effective approach to accurately predict biliary cyclooxygenase-2 expression, potentially advancing individualized risk stratification and improving long-term outcomes for pediatric patients with pancreaticobiliary maljunction.</p><p><strong>Key points: </strong>Predicting biliary COX-2 expression in pancreaticobiliary maljunction (PBM) is critical but challenging. A deep learning radiopathomics model achieved high predictive accuracy for COX-2. The model supports patient stratification and personalized postoperative management in PBM.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"74"},"PeriodicalIF":4.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11950503/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143718672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic sequence identification in multicentric prostate multiparametric MRI datasets for clinical machine-learning.","authors":"José Guilherme de Almeida, Ana Sofia Castro Verde, Carlos Bilreiro, Inês Santiago, Joana Ip, Manolis Tsiknakis, Kostas Marias, Daniele Regge, Celso Matos, Nickolas Papanikolaou","doi":"10.1186/s13244-025-01938-2","DOIUrl":"10.1186/s13244-025-01938-2","url":null,"abstract":"<p><strong>Objectives: </strong>To present an accurate machine-learning (ML) method and knowledge-based heuristics for automatic sequence-type identification in multi-centric multiparametric MRI (mpMRI) datasets for prostate cancer (PCa) ML.</p><p><strong>Methods: </strong>Retrospective prostate mpMRI studies were classified into 5 series types-T2-weighted (T2W), diffusion-weighted images (DWI), apparent diffusion coefficients (ADC), dynamic contrast-enhanced (DCE) and other series types (others). Metadata was processed for all series and two models were trained (XGBoost after custom categorical tokenization and CatBoost with raw categorical data) using 5-fold cross-validation (CV) with different data fractions for learning curve analyses. For validation, two test sets-hold-out test set and temporal split-were used. A leave-one-group-out (LOGO) CV analysis was performed with centres as groups to understand the effect of dataset-specific data.</p><p><strong>Results: </strong>4045 studies (31,053 series) and 1004 studies (7891 series) from 11 centres were used to train and test series identification models, respectively. Test F1-scores were consistently above 0.95 (CatBoost) and 0.97 (XGBoost). Learning curves demonstrate learning saturation, while temporal validation shows model remain capable of correctly identifying all T2W/DWI/ADC triplets. However, optimal performance requires centre-specific data-controlling for model and used feature sets when comparing CV with LOGOCV, F1-score dropped for T2W, DCE and others (-0.146, -0.181 and -0.179, respectively), with larger performance decreases for CatBoost (-0.265). Finally, we delineate heuristics to assist researchers in series classification for PCa mpMRI datasets.</p><p><strong>Conclusions: </strong>Automatic series-type identification is feasible and can enable automated data curation. However, dataset-specific data should be included to achieve optimal performance.</p><p><strong>Critical relevance statement: </strong>Organising large collections of data is time-consuming but necessary to train clinical machine-learning models. To address this, we outline and validate an automatic series identification method that can facilitate this process. Finally, we outline a set of metadata-based heuristics that can be used to further automate series-type identification.</p><p><strong>Key points: </strong>Multi-centric prostate MRI studies were used for sequence annotation model training. Automatic sequence annotation requires few instances and generalises temporally. Sequence annotation, necessary for clinical AI model training, can be performed automatically.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"75"},"PeriodicalIF":4.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143718676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT acquisition protocols for lung cancer screening-current landscape and the urgent need for consistency.","authors":"Mathis Franz Georg Konrad, Emily Nischwitz, Aad van der Lugt, Gudrun Zahlmann, Viktoria Palm, Joanna Chorostowska-Wynimko, Helmut Prosch, James L Mulshine, Hans-Ulrich Kauczor","doi":"10.1186/s13244-025-01949-z","DOIUrl":"10.1186/s13244-025-01949-z","url":null,"abstract":"<p><strong>Key points: </strong>Standardizing CT acquisition protocols reduces radiation exposure in lung cancer screening. Cross-continent collaboration will enhance understanding of diverse clinical practices. Survey results will inform future advancements in radiology sustainability efforts.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"72"},"PeriodicalIF":4.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11947330/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143729861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On-call or not on-call, what difference does it make in paediatric radiology?","authors":"Willemijn M Klein, Amaka C Offiah, Ola Kvist, Karen Rosendahl","doi":"10.1186/s13244-025-01948-0","DOIUrl":"10.1186/s13244-025-01948-0","url":null,"abstract":"<p><strong>Objectives: </strong>There is an ever-increasing demand for out-of-hours expert opinion in paediatric radiology, which cannot be delivered in all hospitals. This study was designed to ascertain whether paediatricians, paediatric surgeons and radiologists are satisfied with the current situation; and to investigate the extent to which diagnostic errors are made while on-call with either residents, general or paediatric radiologists reporting on paediatric examinations.</p><p><strong>Methods: </strong>Two surveys were compiled and dispatched. The first, is to paediatricians, paediatric surgeons and paediatric radiologists questioning their satisfaction with the current on-call paediatric radiology services in their hospitals. The second, is to paediatric radiologists inviting them to retrospectively score the accuracy of the reporting on consecutive paediatric radiology examinations performed during on-call hours in their hospitals.</p><p><strong>Results: </strong>The first survey revealed that 40/49 (82%) paediatric physicians were satisfied with the paediatric radiology service during office hours, decreasing to 33% during on-call hours. In the second survey, a total of 464 on-call paediatric radiology examinations were analysed, demonstrating 20.2% misdiagnoses. General radiologists had more misdiagnoses and were slower in providing a report than residents.</p><p><strong>Conclusion: </strong>The current service with a lack of on-call paediatric radiologists, is associated with increased misdiagnoses and dissatisfaction among physicians and requires improvement.</p><p><strong>Critical relevance statement: </strong>This study shows that it may be a struggle to organise the 24-h availability of an expert paediatric radiologist, yet this might avoid 20% of misdiagnoses, half of which have direct clinical consequences.</p><p><strong>Key points: </strong>The current organisation of paediatric radiology on-call rotas is unsatisfactory for many clinicians. A substantial amount of on-call paediatric radiology reports contain misdiagnoses, and these may have significant clinical consequences. Hospitals should reconfigure out-of-hours paediatric radiology covers.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"73"},"PeriodicalIF":4.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11947353/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143718708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bronchial wall T2w MRI signal as a new imaging biomarker of severe asthma.","authors":"Ilyes Benlala, Gaël Dournes, Pierre-Olivier Girodet, François Laurent, Wadie Ben Hassen, Fabien Baldacci, Baudouin Denis De Senneville, Patrick Berger","doi":"10.1186/s13244-025-01939-1","DOIUrl":"10.1186/s13244-025-01939-1","url":null,"abstract":"<p><strong>Objectives: </strong>Severe asthma patients are prone to severe exacerbations with a need of hospital admission increasing the economic burden on healthcare systems. T2w lung MRI was found to be useful in the assessment of bronchial inflammation. The main goal of this study is to compare quantitative MRI T2 signal bronchial intensity between patients with severe and non-severe asthma.</p><p><strong>Methods: </strong>This is an ancillary study of a prospective single-center study (NCT03089346). We assessed the mean T2 intensity MRI signal of the bronchial wall area (BrWall_T2-MIS) in 15 severe and 15 age and sex-matched non-severe asthmatic patients. They also have had pulmonary function tests (PFTs), fractional exhaled nitric oxide (FeNO) and blood eosinophils count (Eos). Comparisons between the two groups were performed using Student's t-test. Correlations were assessed using Pearson coefficients. Reproducibility was assessed using intraclass correlation coefficient and Bland-Altman analysis.</p><p><strong>Results: </strong>BrWall_T2-MIS was higher in severe than in non-severe asthma patients (74 ± 12 vs 49 ± 14; respectively p < 0.001). BrWall_T2-MIS showed a moderate inverse correlation with PFTs in the whole cohort (r = -0.54, r = -0.44 for FEV1(%pred) and FEV1/FVC respectively, p ≤ 0.01) and in the severe asthma group (r = -0.53, r = -0.44 for FEV1(%pred) and FEV1/FVC respectively, p ≤ 0.01). Eos was moderately correlated with BrWall_T2-MIS in severe asthma group (r = 0.52, p = 0.047). Reproducibility was almost perfect with ICC = 0.99 and mean difference in Bland-Altman analysis of -0.15 [95% CI = -0.48-0.16].</p><p><strong>Conclusion: </strong>Quantification of bronchial wall T2w signal intensity appears to be able to differentiate severe from non-severe asthma and correlates with obstructive PFTs' parameters and inflammatory markers in severe asthma.</p><p><strong>Critical relevance statement: </strong>The development of non-ionizing imaging biomarkers could play an essential role in the management of patients with severe asthma in the current era of biological therapies.</p><p><strong>Key points: </strong>Severe asthma exhibits severe exacerbations with a high burden on healthcare systems. T2w bronchial wall signal intensity is related to inflammatory biomarker in severe asthma. T2w MRI may represent a non-invasive tool to follow up severe asthma patients.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"71"},"PeriodicalIF":4.1,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11937477/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143709778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An update on multimodal imaging strategies for nipple discharge: from detection to decision.","authors":"Mireia Pitarch, Rodrigo Alcantara, Laura Comerma, Ivonne Vázquez de Las Heras, Javier Azcona, Antonia Wiedemann, Maja Prutki, Eva Maria Fallenberg","doi":"10.1186/s13244-025-01947-1","DOIUrl":"10.1186/s13244-025-01947-1","url":null,"abstract":"<p><p>Nipple discharge affects over 80% of women at some point in their lives, with malignancy detected in up to 23% of cases. This review highlights the shift from traditional surgical approaches to advanced imaging techniques, which enhance diagnostic accuracy and reduce unnecessary procedures. Diagnosis begins with a thorough medical history and physical examination to assess the need for imaging. Physiological nipple discharge, which is bilateral, multiductal, and non-spontaneous, typically requires no imaging. Conversely, pathological nipple discharge (PND), characteristically unilateral, uniductal, and spontaneous, requires imaging to rule out malignancy. Bloody PND is frequently associated with breast cancer, and up to 12% of non-bloody PND cases also involve malignancy. For women over 40 years, the first-line imaging modality is full-field digital mammography (FFDM) or digital breast tomosynthesis (DBT), usually combined with ultrasound (US). Men with PND undergo FFDM/DBT starting at age 25 years due to their higher risk of breast cancer. For women aged 30-39 years, US is the first assessment tool, with FFDM/DBT added, if necessary, while US is preferred for younger women and men. When initial imaging is negative or inconclusive, magnetic resonance imaging (MRI) is useful, often replacing galactography. With its high sensitivity and negative predictive value of almost 100%, a negative MRI can often obviate the need for surgery. Contrast-enhanced mammography (CEM) offers a viable alternative when MRI is not feasible. Although invasive, ductoscopy helps identify patients who may not require duct excision. This review consolidates the latest evidence and proposes an updated diagnostic algorithm for managing PND effectively. CRITICAL RELEVANCE STATEMENT: Effective management of nipple discharge requires recognising when imaging tests are needed and selecting the most appropriate diagnostic technique to rule out malignancy and avoid unnecessary interventions. KEY POINTS: First-line imaging for pathological nipple discharge (PND) assessment includes ultrasound and mammography. MRI is recommended for patients with PND and negative conventional imaging. A negative MRI is sufficient to justify surveillance rather than surgery. Contrast-enhanced mammography (CEM) is an alternative when MRI is unavailable or contraindicated.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"70"},"PeriodicalIF":4.1,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11933581/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143700386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prostate cancer detection with transrectal in-bore MRI biopsies: impact of prostate volume and lesion features.","authors":"Alexander Schaudinn, Harald Busse, Constantin Ehrengut, Nicolas Linder, Jonna Ludwig, Toni Franz, Lars-Christian Horn, Jens-Uwe Stolzenburg, Timm Denecke","doi":"10.1186/s13244-025-01942-6","DOIUrl":"10.1186/s13244-025-01942-6","url":null,"abstract":"<p><strong>Objectives: </strong>To systematically analyze the diagnostic outcome of transrectal in-bore MRI-guided biopsies as a function of prostate volume and lesion features.</p><p><strong>Methods: </strong>This single-center study retrospectively included 184 consecutive patients with transrectal in-bore MRI biopsies and histological analysis after multiparametric MRI diagnostics of at least one PI-RADS ≥ 3 lesion. Diagnostic and biopsy MRI data were analyzed for a number of patient and imaging features, specifically prostate volume, lesion size, lesion location (longitudinal, sagittal and segmental) and lesion depth. Features were then compared for statistically significant differences in the cancer detection rate (CDR) of clinically significant (cs-PCa) and any prostate cancer (any-PCa) using categorical and continuous variables.</p><p><strong>Results: </strong>A total of 201 lesions were biopsied detecting cs-PCa in 26% and any-PCa in 68%, respectively. In subgroup analyses of all features, the CDR of cs-PCa differed significantly between ranges of lesion size only (p < 0.001, largest for large lesions). In multivariable analysis, however, only PI-RADS score and PSA showed a significant association with a higher risk of cs-PCa.</p><p><strong>Conclusions: </strong>The cancer detection rates of transrectal in-bore MRI-guided biopsies did not vary significantly for prostate volume, lesion size or lesion location. This suggests that the diagnostic performance of such an approach is not necessarily compromised for challenging biopsy settings like large glands, small lesions or eccentric locations. A translation of these findings to other cohorts might be limited by the low detection rate for clinically significant cancer.</p><p><strong>Critical relevance statement: </strong>This systematic analysis indicates that the diagnostic performance of transrectal in-bore biopsies might not be substantially impaired by patient-specific factors like prostate volume, lesion size, and lesion location, making it a viable option for challenging biopsy cases as well.</p><p><strong>Key points: </strong>The impact of prostate and lesion features on in-bore MRI biopsy performance is controversial. Neither prostate volume, lesion size, nor location showed significant impact on cancer detection. In-bore biopsy does not seem to be limited by challenging sampling geometries.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"69"},"PeriodicalIF":4.1,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11930903/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143691874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Construction and validation of a risk stratification model based on Lung-RADS^® v2022 and CT features for predicting the invasive pure ground-glass pulmonary nodules in China.","authors":"Qingcheng Meng, Tong Liu, Hui Peng, Pengrui Gao, Wenda Chen, Mengjia Fang, Wentao Liu, Hong Ge, Renzhi Zhang, Xuejun Chen","doi":"10.1186/s13244-025-01937-3","DOIUrl":"10.1186/s13244-025-01937-3","url":null,"abstract":"<p><strong>Objectives: </strong>A novel risk stratification model based on Lung-RADS^® v2022 and CT features was constructed and validated for predicting invasive pure ground-glass nodules (pGGNs) in China.</p><p><strong>Methods: </strong>Five hundred and twenty-six patients with 572 pulmonary GGNs were prospectively enrolled and divided into training (n = 169) and validation (n = 403) sets. Utilising the Lung-RADS^® v2022 framework and the types of GGN-vessel relationships (GVR), a complementary Lung-RADS^® v2022 was established, and the pGGNs were reclassified from categories 2, 3 and 4x of Lung-RADS^® v2022 into 2, 3, 4a, 4b, and 4x of cLung-RADS^® v2022. The cutoff value of invasive pGGNs was defined as the cLung-RADS^® v2022 4a-4x. Evaluation metrics like recall rate, precision, F1 score, accuracy, Matthews correlation coefficient (MCC), and the area under the receiver operating characteristic curve (AUC) were employed to assess the utility of the cLung-RADS^® v2022.</p><p><strong>Results: </strong>In the training set, compared with the Lung-RADS 1.0, the AUC of Lung-RADS^® v2022 were decreased from 0.543 to 0.511 (p-value = 0.002), and compared to Lung-RADS 1.0 and Lung-RADS^® v2022, the cLung-RADS^® v2022 model exhibited the highest recall rate (94.9% vs 6.5%, 2.2%), MCC value (60.2% vs 5.4%, 6.3%), F1 score (92.5% vs 12.1%, 4.3%), accuracy (87.6% vs 23.1%, 19.5%), and AUC (0.718 vs 0.543, 0.511; p-value = 0.014, 0.0016) in diagnosing the invasiveness of pGGNs, and the similar performance was observed in the validation set.</p><p><strong>Conclusion: </strong>The cLung-RADS^® v2022 can effectively predict the invasiveness of pGGNs in real-world scenarios.</p><p><strong>Critical relevance statement: </strong>A complementary Lung-RADS^® v2022 based on the Lung-RADS^® v2022 and CT features can effectively predict the invasiveness of pulmonary pure ground-glass nodules and is applicable in clinical practice.</p><p><strong>Trial registration: </strong>Establishment and application of a multi-scale low-dose CT Lung cancer screening model based on modified lung-RADS1.1 and deep learning technology, 2022-KY-0137. Registered 24 January 2022. https://www.medicalresearch.org.cn/search/research/researchView?id=a97e67d8-1ee6-40fb-aab1-e6238dbd8f29 .</p><p><strong>Key points: </strong>Lung-RADS^® v2022 delayed lung cancer diagnosis for nodules appearing as pGGNs. Lung-RADS^® v2022 showed lower accuracy and AUC than Lung-RADS 1.0. cLung-RADS^® v2022 model effectively predicts the invasiveness of pulmonary pGGNs.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"68"},"PeriodicalIF":4.1,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11930897/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143691703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}