Insights into Imaging最新文献

{"title":"Dental magnetic resonance imaging for bone loss assessment and disease activity classification in severe periodontitis.","authors":"Arne Lauer, Luisa Schulte, Artid Skenderi, Nouha Tekiki, Alexander Juerchott, Meysam Sohani, Maurice Ruetters, Franz Sebastian Schwindling, Peter Rammelsberg, Mathias Nittka, Sabine Heiland, Martin Bendszus, Tim Hilgenfeld","doi":"10.1186/s13244-025-02004-7","DOIUrl":"10.1186/s13244-025-02004-7","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the reliability and accuracy of dental MRI (dMRI) for volumetric infrabony and furcation bone loss compared to cone-beam computed tomography (CBCT) and to correlate to clinical signs of inflammation in patients with severe periodontitis.</p><p><strong>Methods: </strong>In this cross-sectional study nineteen patients with severe periodontitis underwent standardized clinical examination as well as pre-treatment CBCT and 3T-dMRI. Bone lesion volumetry was performed in CBCT, contrast-enhanced-T1-weighting (T1W + C) and T2-weighting (T2W) dMRI. Lesions whose T2W signal significantly exceeded T1W/CBCT margins (indicating excessive edema) were classified as T2W-mismatch. Volumetric data were compared to clinical findings.</p><p><strong>Results: </strong>Ten female and nine male patients with 253 bony lesions were examined. Reliability for bone lesions was highest in CBCT (ICC [95% CI] T1W + C/T2W/CBCT: 0.78 [0.74-0.83]/0.82 [0.77-0.85]/0.87 [0.94-0.89]). Overall, T1W + C and T2W dMRI strongly correlated with CBCT (r_s = 0.86 [95% CI: 0.82-0.89], p < 0.001 and r_s = 0.91 [95% CI: 0.88-0.93], p < 0.001 respectively) but volume was significantly overestimated by dMRI (median percentage error of T1W + C-T2W: 19-55%). A T2W-mismatch was found in 44.1% and correlated with bleeding (85.8% vs. 70.9%, p = 0.005), giving 47.5% sensitivity and 71.2% specificity.</p><p><strong>Conclusions: </strong>While dMRI offers good reliability, T2W- and to a lesser extent T1W + C imaging overestimate infrabony and interradicular periodontal bone lesion volumetry compared to CBCT. While this could increase the risk of overtreatment, dMRI detects periodontal inflammation beyond areas of bone loss, and T2W-mismatch is closely related but not identical to signs of active inflammation in clinical examination. This may provide additional diagnostic information and could serve as a supplemental tool for higher-risk patients.</p><p><strong>Critical relevance statement: </strong>Dental MRI excels in detecting inflammation beyond bone loss, identifying high-risk tissue. This study assesses reliability in evaluating periodontitis-related bone loss, highlighting its tendency to overestimate lesion volume. A novel \"mismatch lesion pattern\" was observed, potentially linked to disease activity.</p><p><strong>Key points: </strong>Dental MRI (dMRI) reliably assesses bone loss in periodontitis but overestimates volume vs. cone-beam computed tomography (CBCT). dMRI detects excess bone marrow edema, indicating inflammation beyond visible bone loss. dMRI could aid periodontal diagnosis and guide targeted therapeutic interventions.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"134"},"PeriodicalIF":4.1,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12202246/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144505606","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":"Feedback in radiology: Essential tool for improving user experience and providing value-based care.","authors":"Andrea Rockall, Jacob J Visser, Cristina Garcia-Villar, Naama Lev-Cohain, Patrick Omoumi, Marie-Pierre Revel, Ruth Mary Strudwick","doi":"10.1186/s13244-025-02002-9","DOIUrl":"10.1186/s13244-025-02002-9","url":null,"abstract":"<p><p>Measuring the value that radiology brings to patient care can be challenging. A positive patient experience is consistently associated with patient safety, clinical effectiveness, and outcome measures and is therefore a tool for measuring value-based care. Monitoring the experience of users of radiology services is an indispensable component of quality improvement programmes for radiology departments. The integration of comprehensive feedback mechanisms brings numerous benefits, including enhanced care, strengthened trust, and greater engagement with our stakeholders and service users. Feedback should be collected from a variety of stakeholders through a 360-degree approach, combining both systematically performed structured methods, such as formal surveys, and unstructured methods, such as informal and opportunistic information gathering during multidisciplinary rounds. To maximise the impact of feedback, it should be frequent and diverse, ensuring that all perspectives are considered. Leaders in radiology must prioritise embedding a culture of feedback within their institutions, recognising its crucial role in continuous improvement. It is essential to ensure that our departments consistently provide value to our most important stakeholders-the patients-but also to our referrers and trainees. In this article, we consider methods for collecting feedback and provide some of the key findings from the literature. By fostering an environment that values and acts upon feedback, we can achieve significant advancements in patient care and overall service quality in radiology. CRITICAL RELEVANCE STATEMENT: Regular feedback from patients, peers, radiographers, referrers, trainees and other users of imaging services is an essential tool for continuous quality improvement, patient safety and value-based care, enhancing trust and greater engagement with our stakeholders and service users. KEY POINTS: Feedback from patients and referrers, radiographers and radiology trainees, helps radiology departments to identify weaknesses and strengths, and should be fully incorporated into daily practice. Many methods are available for collecting user and stakeholder experience, and these should be implemented as a priority. Acting on stakeholder feedback can improve patient safety and patient experience ratings, leading to a culture of continuous improvement in value-based care.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"132"},"PeriodicalIF":4.1,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12202251/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144496141","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":"Association between ultrasound-based biliary and parenchymal intrahepatic mass-forming cholangiocarcinoma subtypes and clinicopathological features and survival.","authors":"Cong-Jian Wen, Hui Liu, Li-Ping Sun, Chong-Ke Zhao, Hao-Hao Yin, Li-Fan Wang, Ming-Rui Zhu, Yi-Kang Sun, Ya-Qin Zhang, Zi-Tong Chen, Xi Wang, Han-Sheng Xia, Hong Han, Hui-Xiong Xu, Bo-Yang Zhou","doi":"10.1186/s13244-025-02019-0","DOIUrl":"10.1186/s13244-025-02019-0","url":null,"abstract":"<p><strong>Objective: </strong>Mass-forming intrahepatic cholangiocarcinomas (MF-ICCs) can be classified into ductal and parenchymal types using magnetic resonance imaging (MRI). We aimed to subclassify MF-ICC into biliary and parenchymal types based on ultrasound (US) findings and to investigate the differences in their contrast-enhanced ultrasound (CEUS) patterns, clinicopathologic features, and prognosis.</p><p><strong>Methods: </strong>In this study, 141 patients who underwent US with pathologically proven MF-ICC from two hospitals were retrospectively enrolled. MF-ICCs were divided into biliary (bMF-ICCs) and parenchymal MF-ICC (pMF-ICCs) based on the signs of bile duct dilation in US images. Clinicopathological, imaging, and short-term survival data were collected from medical records and compared.</p><p><strong>Results: </strong>Among 141 patients (61.96 ± 10.15 years, 83 men), bMF-ICCs (33/141, 23.4%) showed significantly more CEA ≥ 5 µg/L (42.4% vs 20.2%, p = 0.01), microvascular invasion (54.5% vs 10.2%, p < 0.001), lymph node metastasis (48.5% vs 5.6%, p < 0.001), bile duct invasion (48.5% vs 5.6%, p < 0.001), and high Ki-67 expression (63.6% vs 38.9%, p = 0.01) than pMF-ICCs. Pathologically, bMF-ICCs were more inclined toward the large duct type (78.1% vs 11.7%, p < 0.001). In addition, the bMF-ICCs were usually located in the left lobe of the liver (63.6% vs 41.7%, p = 0.03). pMF-ICCs showed better overall survival than bMF-ICCs (p = 0.04).</p><p><strong>Conclusions: </strong>Subclassification of MF-ICCs into biliary and parenchymal types based on US is useful for discriminating clinicopathological characteristics.</p><p><strong>Critical relevance statement: </strong>The subclassification of mass-forming intrahepatic cholangiocarcinoma (MF-ICC) into biliary (bMF-ICC) and parenchymal (pMF-ICC) subtypes using ultrasound can provide clinicopathological and prognostic information before surgery.</p><p><strong>Key points: </strong>We subclassified mass-forming intrahepatic cholangiocarcinomas into biliary and parenchymal types using ultrasound. Biliary and parenchymal types have different clinicopathological features and postsurgical outcomes. Biliary type above and below 50 mm exhibits different unfavorable clinicopathological characteristics. Our classification has certain similarities with MRI classification in clinicopathological characteristics.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"130"},"PeriodicalIF":4.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12179021/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144325594","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":"Pelvic nerve endometriosis: MRI features and key findings for surgical decision.","authors":"Justine Bourg, Edouard Ruaux, Pierre Adrien Bolze, Marie Gavrel, Mathilde Charlot, François Golfier, Isabelle Thomassin-Naggara, Pascal Rousset","doi":"10.1186/s13244-025-02005-6","DOIUrl":"10.1186/s13244-025-02005-6","url":null,"abstract":"<p><p>Endometriosis is a prevalent gynecological disorder in women of reproductive age. It is the leading cause of chronic pelvic pain. While the mechanisms underlying this pain remain elusive, rare cases of pelvic nerve involvement can result in severe, debilitating symptoms, adding complexity to the clinical landscape. Nerve involvement typically results from the direct extension of deep infiltrating endometriosis, though it may also occur in isolation. The nerves most commonly affected include the inferior hypogastric and lumbosacral plexuses, as well as the sciatic, pudendal, obturator, and femoral nerves. Early and accurate diagnosis is essential for the effective management of the pain and the prevention of irreversible nerve damage. Given the limitations of transvaginal ultrasonography in visualizing the lateral compartment, MRI is considered the gold standard for detecting and evaluating pelvic nerve involvement. Through the use of optimized protocols to enhance the visualization of nerves and their anatomical landmarks, radiologists play a key role in the identification of endometriotic lesions. A comprehensive and structured radiology report is essential for surgical planning, as nerve involvement often requires precise interventions to alleviate symptoms and restore quality of life. CRITICAL RELEVANCE STATEMENT: Accurate identification and a structured reporting of pelvic nerve endometriosis in the lateral compartment are pivotal to guide surgical decision-making and optimize patient outcomes. KEY POINTS: Pelvic nerve endometriosis is often overlooked, underestimated by clinicians, and underdiagnosed on imaging. Timely nerve involvement diagnosis prevents permanent damage in pelvic pain with neurological symptoms. Deep endometriosis in the lateral compartment may extend to the pelvic nerves. The inferior hypogastric plexus, sacral plexus, sciatic, and pudendal nerves are commonly affected. A dedicated MRI protocol with 3D T2-weighted sequence ensures accurate pelvic nerve assessment.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"131"},"PeriodicalIF":4.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12179019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144333067","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":"Differentiation of benign and malignant breast lesions by ultrasound localization microscopy.","authors":"Jia Li, Cong Wei, Tao Ying, Yan Liu, Ronghui Wang, Maoyao Li, Chao Feng, Di Sun, Yuanyi Zheng","doi":"10.1186/s13244-025-02013-6","DOIUrl":"10.1186/s13244-025-02013-6","url":null,"abstract":"<p><strong>Objective: </strong>We investigated the role of ultrasound localization microscopy (ULM) qualitative and quantitative parameters in distinguishing benign from malignant breast lesions.</p><p><strong>Methods: </strong>The ULM qualitative and quantitative parameters of breast lesions were recorded. A receiver operating characteristic (ROC) curve was applied to assess the diagnostic performance of ULM. Intra- and inter-operator reliabilities of quantitative parameters were assessed.</p><p><strong>Results: </strong>Thirty-one breast lesions were verified by pathologic results, 14 of which were benign and 17 were malignant. Benign lesions were associated with dot-like, line-like, or branch-like patterns (93% vs 6%), whereas malignant lesions were associated with chaotic patterns (94% vs 7%) (p < 0.001). The microvasculature morphology had an area under the curve (AUC) of 0.935, a sensitivity of 94.1%, and a specificity of 92.9%. The microvasculature density, mean diameter, largest diameter, and max tortuosity of malignant lesions were significantly greater than those of benign lesions (p < 0.05, p < 0.001, p < 0.001, p < 0.05). The microvasculature mean flow velocity of benign lesions was significantly greater than that of malignant lesions (p < 0.05). For the quantitative parameters, the AUC was highest for the microvasculature's largest diameter (0.962), with a sensitivity of 88.2% and a specificity of 92.9%. The intra- and inter-operator reliabilities of quantitative parameters were excellent (ICC greater than 0.90).</p><p><strong>Conclusions: </strong>ULM is useful for distinguishing benign from malignant breast lesions. ULM can offer a new diagnostic method for breast lesions, which deserves further research.</p><p><strong>Critical relevance statement: </strong>This study suggests that ULM is a new technology with super-resolution that is helpful for distinguishing benign from malignant breast lesions.</p><p><strong>Trial registration: </strong>ChiCTR, ChiCTR2100048361. Registered 6 July 2021, https://www.chictr.org.cn/ .</p><p><strong>Key points: </strong>ULM is an emerging technology that can detect highly detailed networks of microvasculature. Microvasculature morphology based on ULM can be a good indicator for the differential diagnosis of breast lesions. Among quantitative parameters extracted from ULM, microvasculature largest diameter was the best for the classification of breast lesions.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"128"},"PeriodicalIF":4.1,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12176706/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144325595","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":"Quality appraisal of radiomics-based studies on chondrosarcoma using METhodological RadiomICs Score (METRICS) and Radiomics Quality Score (RQS).","authors":"Salvatore Gitto, Renato Cuocolo, Michail E Klontzas, Domenico Albano, Carmelo Messina, Luca Maria Sconfienza","doi":"10.1186/s13244-025-02016-3","DOIUrl":"10.1186/s13244-025-02016-3","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the methodological quality of radiomics-based studies on bone chondrosarcoma using METhodological RadiomICs Score (METRICS) and Radiomics Quality Score (RQS).</p><p><strong>Methods: </strong>A literature search was conducted on EMBASE and PubMed databases for research papers published up to July 2024 and focused on radiomics in bone chondrosarcoma, with no restrictions regarding the study aim. Three readers independently evaluated the study quality using METRICS and RQS. Baseline study characteristics were extracted. Inter-reader reliability was calculated using intraclass correlation coefficient (ICC).</p><p><strong>Results: </strong>Out of 68 identified papers, 18 were finally included in the analysis. Radiomics research was aimed at lesion classification (n = 15), outcome prediction (n = 2) or both (n = 1). Study design was retrospective in all papers. Most studies employed MRI (n = 12), CT (n = 3) or both (n = 1). METRICS and RQS adherence rates ranged between 37.3-94.8% and 2.8-44.4%, respectively. Excellent inter-reader reliability was found for both METRICS (ICC = 0.961) and RQS (ICC = 0.975). Among the limitations of the evaluated studies, the absence of prospective studies and deep learning-based analyses was highlighted, along with the limited adherence to radiomics guidelines, use of external testing datasets and open science data.</p><p><strong>Conclusions: </strong>METRICS and RQS are reproducible quality assessment tools, with the former showing higher adherence rates in studies on chondrosarcoma. METRICS is better suited for assessing papers with retrospective design, which is often chosen in musculoskeletal oncology due to the low prevalence of bone sarcomas. Employing quality scoring systems should be promoted in radiomics-based studies to improve methodological quality and facilitate clinical translation.</p><p><strong>Critical relevance statement: </strong>Employing reproducible quality scoring systems, especially METRICS (which shows higher adherence rates than RQS and is better suited for assessing retrospective investigations), is highly recommended to design radiomics-based studies on chondrosarcoma, improve methodological quality and facilitate clinical translation.</p><p><strong>Key points: </strong>The low scientific and reporting quality of radiomics studies on chondrosarcoma is the main reason preventing clinical translation. Quality appraisal using METRICS and RQS showed 37.3-94.8% and 2.8-44.4% adherence rates, respectively. Room for improvement was noted in study design, deep learning methods, external testing and open science. Employing reproducible quality scoring systems is recommended to design radiomics studies on bone chondrosarcoma and facilitate clinical translation.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"129"},"PeriodicalIF":4.1,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12177113/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144325596","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":"Colour map displays.","authors":"Nandita M deSouza, Miha Fuderer, Nico Sollmann, Barbara Daria Wichtmann, Xavier Golay","doi":"10.1186/s13244-025-01970-2","DOIUrl":"10.1186/s13244-025-01970-2","url":null,"abstract":"","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"127"},"PeriodicalIF":4.1,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12173982/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144316846","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":"Solitary rectal ulcer syndrome: MRI findings and differentiation from rectal cancer.","authors":"Peiyi Xie, Xiaoying Lou, Shuai Fu, Xiaohui Di, Qitong Huang, Zhiming Zeng, Kexin Niu, Junying Zhu, Meiyu Hu, Xiaochun Meng","doi":"10.1186/s13244-025-01979-7","DOIUrl":"10.1186/s13244-025-01979-7","url":null,"abstract":"<p><strong>Background: </strong>Systematic MRI findings of solitary rectal ulcer syndrome (SRUS) are lacking. We aimed to evaluate the MRI findings of SRUS and to identify the MRI features that differentiate SRUS from rectal cancer.</p><p><strong>Methods: </strong>This retrospective study consecutively included 30 patients diagnosed with SRUS from January 2015 to December 2021. The clinical and MRI findings of SRUS patients were summarized. We randomly selected 120 rectal cancer patients with ≤ T2N0 pathological staging in a 1:4 ratio of SRUS to rectal cancer cases to perform differential diagnosis analysis.</p><p><strong>Results: </strong>SRUS patients were significantly younger (mean age ± standard deviation [SD], 37 years ± 17; 22 men) than rectal cancer patients (mean age ± SD, 62 years ± 12; 67 men; p < 0.001). Compared to rectal cancer patients, SRUS patients had a significantly higher incidence of ulceration (63.33%), submucosal edema (36.67%), unrestricted diffusion (76.67%), hypo- or high-low mixed intensity on T2-weighted imaging (T2WI, 76.67%), and layer enhancement (40%) (all p < 0.001). Interestingly, in the combinations of MRI features including unrestricted diffusion, hypo- or high-low mixed intensity on T2WI, and layer enhancement or submucosal edema showed an excellent diagnostic performance with area under the curve, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 0.97 (95% CI: 0.92, 1.00), 93%, 100%, 100%, 98%, and 99%, respectively, in differentiating SRUS from rectal cancer.</p><p><strong>Conclusion: </strong>The combinations of three MRI features are simple and show excellent diagnostic performance. These may be useful tools for differentiating SRUS from rectal cancer.</p><p><strong>Critical relevance statement: </strong>The combinations of three MRI features including unrestricted diffusion, hypo- or high-low mixed intensity on T2WI, and layer enhancement or submucosal edema show excellent diagnostic performance, which have potential to serve as useful tools for differentiating SRUS from rectal cancer.</p><p><strong>Key points: </strong>MRI could differentiate solitary rectal ulcer syndrome (SRUS) from rectal cancer. SRUS patients had a significantly higher incidence of several MRI features. The combinations have potential for differentiating SRUS from rectal cancer.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"126"},"PeriodicalIF":4.1,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12170985/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301999","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":"Predicting mucosal healing in Crohn's disease: development of a deep-learning model based on intestinal ultrasound images.","authors":"Li Ma, Yuepeng Chen, Xiangling Fu, Jing Qin, Yanwen Luo, Yuanjing Gao, Wenbo Li, Mengsu Xiao, Zheng Cao, Jialin Shi, Qingli Zhu, Chenyi Guo, Ji Wu","doi":"10.1186/s13244-025-02014-5","DOIUrl":"10.1186/s13244-025-02014-5","url":null,"abstract":"<p><strong>Objective: </strong>Predicting treatment response in Crohn's disease (CD) is essential for making an optimal therapeutic regimen, but relevant models are lacking. This study aimed to develop a deep learning model based on baseline intestinal ultrasound (IUS) images and clinical information to predict mucosal healing.</p><p><strong>Methods: </strong>Consecutive CD patients who underwent pretreatment IUS were retrospectively recruited at a tertiary hospital. A total of 1548 IUS images of longitudinal diseased bowel segments were collected and divided into a training cohort and a test cohort. A convolutional neural network model was developed to predict mucosal healing after one year of standardized treatment. The model's efficacy was validated using the five-fold internal cross-validation and further tested in the test cohort.</p><p><strong>Results: </strong>A total of 190 patients (68.9% men, mean age 32.3 ± 14.1 years) were enrolled, consisting of 1038 IUS images of mucosal healing and 510 images of no mucosal healing. The mean area under the curve in the test cohort was 0.73 (95% CI: 0.68-0.78), with the mean sensitivity of 68.1% (95% CI: 60.5-77.4%), specificity of 69.5% (95% CI: 60.1-77.2%), positive prediction value of 80.0% (95% CI: 74.5-84.9%), negative prediction value of 54.8% (95% CI: 48.0-63.7%). Heat maps showing the deep-learning decision-making process revealed that information from the bowel wall, serous surface, and surrounding mesentery was mainly considered by the model.</p><p><strong>Conclusions: </strong>We developed a deep learning model based on IUS images to predict mucosal healing in CD with notable accuracy. Further validation and improvement of this model with more multi-center, real-world data are needed.</p><p><strong>Critical relevance statement: </strong>Predicting treatment response in CD is essential to making an optimal therapeutic regimen. In this study, a deep-learning model using pretreatment ultrasound images and clinical information was generated to predict mucosal healing with an AUC of 0.73.</p><p><strong>Key points: </strong>Response to medication treatment is highly variable among patients with CD. High-resolution IUS images of the intestinal wall may hide significant characteristics for treatment response. A deep-learning model capable of predicting treatment response was generated using pretreatment IUS images.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"125"},"PeriodicalIF":4.1,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12170472/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic work-up of lipomatous tumors: a decision-making analysis among European sarcoma centers.","authors":"Ali Naimi, Paul Martin Putora, Christian Rothermundt, Antonia Digklia, Jose Manuel Asencio, Sylvie Bonvalot, Florian Bösch, Anant Desai, Amer James Durrani, Haim Gutman, Daphne Hompes, Jens Jakob, Wolfram Trudo Knoefel, Elisabetta Pennacchioli, Piotr Rutkowski, Winan J van Houdt, Barbara L van Leeuwen, Stephan Waelti, Tim Steffen Fischer, Stefan Markart, Simon Wildermuth, Tobias Johannes Dietrich","doi":"10.1186/s13244-025-02012-7","DOIUrl":"10.1186/s13244-025-02012-7","url":null,"abstract":"<p><strong>Objectives: </strong>Lipomatous soft-tissue tumors present a diagnostic burden. The aim of this work was to compare standard operating procedures (SOPs) for the diagnostic management of lipomatous soft-tissue tumors among European academic centers.</p><p><strong>Methods: </strong>Experts of the Soft Tissue and Bone Sarcoma Group of the European Organization for Research and Treatment of Cancer were asked for their SOPs in the diagnosis of adipocytic soft-tissue tumors in an otherwise healthy patient. The answers were converted to decision trees and subsequently compared using the objective consensus methodology. Mediastinal and retroperitoneal lipomatous tumors were excluded from the analysis.</p><p><strong>Results: </strong>The highest consensus (93%) among fourteen institutions was noted for evaluation with core needle biopsy (CNB) as SOP for lipomatous tumors located deep in tissue exceeding 7 cm and tumor-associated symptoms. Evaluation of heterogeneous features on imaging by CNB usually showed a consensus rate of at least 75%. Consensus was less likely for lipomatous tumors without symptoms or heterogeneous features. In these settings, CNB and follow-up were almost equally recommended. For lipomatous tumors smaller than 3 cm, without growth or symptoms, no localization in the trunk, and homogeneous imaging features, a consensus rate of 71% was achieved for follow-up.</p><p><strong>Conclusions: </strong>SOPs for diagnostic work-up of lipomatous tumors varied despite their geographical proximity. The highest consensus for biopsy was for deep large tumors with associated symptoms. For follow-up, consensus was shown for small homogenous tumors outside the trunk, without growth or symptoms. Consensus on resection involved homogeneous deeply located small tumors outside the trunk with growth and symptoms.</p><p><strong>Critical relevance statement: </strong>This study identifies the decision-making criteria with the highest consensus rate among participating academic sarcoma centers in diagnosing lipomatous tumors: tumors located deep in the tissue, a tumor size exceeding 7 cm, and associated symptoms emerge as pivotal criteria.</p><p><strong>Key points: </strong>Standard operating procedures for diagnostic work-up of lipomatous tumors among fourteen sarcoma centers were analyzed. Identified diagnostic criteria are: imaging features, size, growth, symptoms, superficial and trunk location. The highest consensus concerned recommending biopsies for deep tumors > 7 cm with associated symptoms.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"123"},"PeriodicalIF":4.1,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12167213/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144293694","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}