Insights into Imaging最新文献

{"title":"Machine learning model for diagnosing salivary gland adenoid cystic carcinoma based on clinical and ultrasound features.","authors":"Huan-Zhong Su, Zhi-Yong Li, Long-Cheng Hong, Yu-Hui Wu, Feng Zhang, Zuo-Bing Zhang, Xiao-Dong Zhang","doi":"10.1186/s13244-025-01974-y","DOIUrl":"https://doi.org/10.1186/s13244-025-01974-y","url":null,"abstract":"<p><strong>Objective: </strong>To develop and validate machine learning (ML) models for diagnosing salivary gland adenoid cystic carcinoma (ACC) in the salivary glands based on clinical and ultrasound features.</p><p><strong>Methods: </strong>A total of 365 patients with ACC or non-ACC of the salivary glands treated at two centers were enrolled in training cohort, internal and external validation cohorts. Synthetic minority oversampling technique was used to address the class imbalance. The least absolute shrinkage and selection operator (LASSO) regression identified optimal features, which were subsequently utilized to construct predictive models employing five ML algorithms. The performance of the models was evaluated across a comprehensive array of learning metrics, prominently the area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>Through LASSO regression analysis, six key features-sex, pain symptoms, number, cystic areas, rat tail sign, and polar vessel-were identified and subsequently utilized to develop five ML models. Among these models, the support vector machine (SVM) model demonstrated superior performance, achieving the highest AUCs of 0.899 and 0.913, accuracy of 90.54% and 91.53%, and F1 scores of 0.774 and 0.783 in both the internal and external validation cohorts, respectively. Decision curve analysis further revealed that the SVM model offered enhanced clinical utility compared to the other models.</p><p><strong>Conclusions: </strong>The ML model based on clinical and US features provide an accurate and noninvasive method for distinguishing ACC from non-ACC.</p><p><strong>Critical relevance statement: </strong>This machine learning model, constructed based on clinical and ultrasound characteristics, serves as a valuable tool for the identification of salivary gland adenoid cystic carcinoma.</p><p><strong>Key points: </strong>Rat tail sign and polar vessel on US predict adenoid cystic carcinoma (ACC). Machine learning models based on clinical and US features can identify ACC. The support vector machine model performed robustly and accurately.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"96"},"PeriodicalIF":4.1,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12061827/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143999172","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":"CT of acute abdomen in the elderly.","authors":"Juliette Coutureau, Ingrid Millet, Patrice Taourel","doi":"10.1186/s13244-025-01955-1","DOIUrl":"https://doi.org/10.1186/s13244-025-01955-1","url":null,"abstract":"<p><p>Abdominal disorders represent 10 to 15% of all Emergency Department visits in elderly patients. This educational review focuses on acute abdomen pathologies specific to the elderly and on their imaging patterns and proposes a strategy for performing CT scans in this population. Bowel obstruction is the most common cause of emergency surgery in the elderly with a higher proportion of colonic obstructions, in particular obstructive colorectal cancer and sigmoid volvulus. Concerning abdominal inflammatory processes, such as cholecystitis, appendicitis, and diverticulitis, gangrenous cholecystitis and complicated appendicitis are relatively frequently encountered due to delayed diagnoses. Bowel ischemia, which includes acute mesenteric ischemia (AMI) and ischemic colitis (IC), is also much more common after the age of 80. Although ischemic colitis is mainly related to cardiovascular risk factors, it can also result from a persistent distension above a colonic cancer or from fecal impaction. Finally, extra-abdominal pathologies responsible for acute abdominal pain, such as inferior myocardial infarction, should not be overlooked. In clinical practice, when possible thanks to sufficient and appropriate radiological resources, we recommend a scan without injection of contrast and an injection depending on the results of the unenhanced scan, decided by the radiologist present at the CT scan room during the examination. CRITICAL RELEVANCE STATEMENT: CT is critical in the diagnosis and management of patients over 75 years old with an acute abdomen, given the difficulty of clinico-biological diagnosis, the frequency of complicated forms, and the morbidity induced by delayed diagnosis. KEY POINTS: The most common site and cause of bowel obstruction in the elderly is large bowel obstruction due to colon cancer. Discrepancy between a poor clinical examination and complicated forms on imaging, particularly for inflammation and infections, is responsible for late diagnosis and increased morbidity. Ischemia, including of the small bowel, colon, and gallbladder are common cause of acute abdomen in elderly. In patients with upper quadrant pain, consider extra-abdominal causes such as pneumonia or myocardial infarction.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"95"},"PeriodicalIF":4.1,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12058634/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143982243","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":"Radiological approach to metatarsalgia in current practice: an educational review.","authors":"Océane Palka, Raphaël Guillin, Romain Lecigne, Damien Combes","doi":"10.1186/s13244-025-01945-3","DOIUrl":"https://doi.org/10.1186/s13244-025-01945-3","url":null,"abstract":"<p><p>Metatarsalgia, characterized by forefoot pain, is frequent and is primarily due to foot static disorders. Initial evaluation with weight-bearing radiographs is essential, allowing precise analysis of the architecture of the foot. Ultrasound is useful for soft tissue and tendon examination and provides the best clinical correlation. Computed Tomography provides detailed bone assessment and is helpful for pre-operative planning. Magnetic Resonance Imaging is the gold standard modality, offering superior soft tissue contrast. The common causes of metatarsalgia include hallux pathologies (hallux valgus, hallux rigidus, and sesamoid issues), bursitis (intermetatarsal and subcapitellar), Morton's neuroma, second ray syndrome, stress fractures, and systemic pathologies affecting the foot. Combining clinical and imaging data is crucial for accurate diagnosis and effective management of metatarsalgia. Post-traumatic causes of metatarsalgia are beyond the scope of this article and will not be described. CRITICAL RELEVANCE STATEMENT: Metatarsalgia, the pain of the forefoot, necessitates accurate imaging for diagnosis and management. This review critically assesses imaging techniques and diagnostic approaches, aiming to enhance radiological practice and support effective therapeutic decision-making. KEY POINTS: Metatarsalgia commonly results from foot static disorders, requiring weight-bearing radiographs for assessment. MRI is often the gold standard examination, but ultrasound is complementary, allowing for a radioclinical approach with dynamic examinations. The radiologist is crucial in diagnosing metatarsalgia, providing essential imaging, and guiding treatment.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"94"},"PeriodicalIF":4.1,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12041408/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143998852","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":"Renal ectopic fat deposition and hemodynamics in type 2 diabetes mellitus assessment with magnetic resonance imaging.","authors":"Jian Liu, Hengzhi Chen, Chong Tian, Liwei Fu, Lisha Nie, Rongpin Wang, Xianchun Zeng","doi":"10.1186/s13244-025-01971-1","DOIUrl":"https://doi.org/10.1186/s13244-025-01971-1","url":null,"abstract":"<p><strong>Objectives: </strong>To assess renal perfusion and ectopic fat deposition in patients with type 2 diabetes mellitus (T2DM), and to evaluate the effects of ectopic fat deposition on renal hemodynamics.</p><p><strong>Methods: </strong>All participants underwent quantitative magnetic resonance imaging (MRI) to measure the cortical and medullary renal blood flow (RBF) and proton density fat fraction (PDFF). Patients with T2DM were classified into three groups according to the estimated glomerular filtration rate (mL/min/1.73 m²). One-way analysis of variance was used to assess differences among groups. Pearson's correlation coefficient was used to analyze correlations. Additionally, a receiver operating characteristic (ROC) curve was constructed to assess diagnostic performance.</p><p><strong>Results: </strong>Renal PDFF values of the renal cortex and medulla, as well as perirenal fat thickness, were significantly different among the four groups: healthy control < T2DM < diabetic kidney disease (DKD) I-II < DKD III-IV. Additionally, significant differences in cortical and medullary RBF values were observed among the four groups: healthy control > T2DM > DKD I-II > DKD III-IV. A significant negative correlation was observed between renal PDFF and RBF values. Medullary RBF values demonstrated the best performance in discriminating T2DM from DKD with the largest area under the ROC curve (AUC) of 0.971. The cortical PDFF achieved the largest AUC (0.961) for distinguishing DKD I-II from DKD III-IV.</p><p><strong>Conclusions: </strong>Quantitative MRI effectively evaluates renal perfusion and ectopic fat deposition in T2DM patients, aiding in assessing kidney function and disease progression. Additionally, renal ectopic fat deposition may be an important risk factor for renal hemodynamic injury.</p><p><strong>Critical relevance statement: </strong>Quantitative MRI could serve as a radiation-free imaging modality for assessing renal perfusion and ectopic fat deposition, which may be an important risk factor for DKD progression.</p><p><strong>Key points: </strong>Quantitative MRI can be used to assess kidney function and monitor disease progression in patients with T2DM. In patients with T2DM, decreased renal perfusion, increased renal ectopic fat deposition, and kidney damage were significantly correlated. Renal ectopic fat deposition may be an important risk factor for renal hemodynamic injury.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"93"},"PeriodicalIF":4.1,"publicationDate":"2025-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12034603/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144013269","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":"Harnessing routine MRI for the early screening of Parkinson's disease: a multicenter machine learning study using T2-weighted FLAIR imaging.","authors":"Junyan Fu, Hongyi Chen, Chengling Xu, Zhongzheng Jia, Qingqing Lu, Haiyan Zhang, Yue Hu, Kun Lv, Jun Zhang, Daoying Geng","doi":"10.1186/s13244-025-01961-3","DOIUrl":"https://doi.org/10.1186/s13244-025-01961-3","url":null,"abstract":"<p><strong>Objective: </strong>To explore the potential of radiomics features derived from T2-weighted fluid-attenuated inversion recovery (T2W FLAIR) images to distinguish idiopathic Parkinson's disease (PD) patients from healthy controls (HCs).</p><p><strong>Methods: </strong>T2W FLAIR images from 1727 subjects were retrospectively obtained from five cohorts and divided into a training set (395 PD/574 HC), an internal test set (99 PD/144 HC) and an external test set (295 PD/220 HC). Regions of interest (ROIs), including bilateral globus pallidus (GP), putamen (PU), substantia nigra (SN), and red nucleus (RN), were manually delineated. The radiomics features were extracted from ROIs. Six independent machine learning (ML) classifiers were trained on the training set, and validated on the internal and external test sets.</p><p><strong>Results: </strong>A selection of five, two, three, and ten highly correlated diagnostic features were identified from SN, RN, GP, and PU regions, respectively. Six ML classifiers were implemented based on the combined 20 radiomics features. In the internal test cohort, the six models achieved AUC of 0.96-0.98 with the accuracy ranging from 0.80 to 0.90. In the external test cohort, the multilayer perceptron model demonstrated the highest AUC of 0.85 (95% CI: 0.80-0.89) with an accuracy of 0.78.</p><p><strong>Conclusion: </strong>ML models based on the conventional T2W FLAIR images demonstrated promising diagnostic performance for PD and those models may serve as a basis for future investigations on PD diagnosis with the aid of ML methods.</p><p><strong>Critical relevance statement: </strong>Our study confirmed that early screening of Parkinson's Disease based on the conventional T2W FLAIR images was feasible with the aid of machine learning algorithms in a large multicenter cohort and those models had certain generalization.</p><p><strong>Key points: </strong>Conventional head MRI is routinely performed in Parkinson's disease (PD) but exhibits inadequate specificity for diagnosis. Machine learning (ML) models based on conventional T2W FLAIR images showed favorable accuracy for PD diagnosis. ML algorithm enables early screening of PD on routine T2W FLAIR sequence.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"92"},"PeriodicalIF":4.1,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12033128/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144063629","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":"Enhanced diagnosis of axial spondyloarthritis using machine learning with sacroiliac joint MRI: a multicenter study.","authors":"Zhuoyao Xie, Zefeiyun Chen, Qinmei Yang, Qiang Ye, Xin Li, Qiuxia Xie, Caolin Liu, Bomiao Lin, Xinai Han, Yi He, Xiaohong Wang, Wei Yang, Yinghua Zhao","doi":"10.1186/s13244-025-01967-x","DOIUrl":"https://doi.org/10.1186/s13244-025-01967-x","url":null,"abstract":"<p><strong>Objectives: </strong>To develop a machine learning (ML)-based model using MRI and clinical risk factors to enhance diagnostic accuracy for axial spondyloarthritis (axSpA).</p><p><strong>Methods: </strong>We retrospectively analyzed datasets from four centers (A-D), focusing on patients with chronic low back pain. A subset from center A was used for prospective validation. A deep learning (DL) model based on ResNet50 was constructed using sacroiliac joint MRI. Clinical variables were integrated with DL scores in ML algorithms to distinguish axSpA from non-axSpA patients. Model performance was assessed by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.</p><p><strong>Results: </strong>The study included 1294 patients (median age 31 years [interquartile range 24-42]; 35.5% females). Clinical risk factors identified were age, sex, and human leukocyte antigen-B27 status. The MRI-based DL model demonstrated an AUC of 0.837, 0.636, 0.724, 0.710, and 0.812 on the internal test set, three external test sets, and the prospective validation set, respectively. The combined model, particularly the K-nearest-neighbors-11 algorithm, demonstrated superior performance across multiple test sets with AUCs ranging from 0.853 to 0.912. It surpassed the Assessment of SpondyloArthritis International Society criteria with better AUC (0.858 vs. 0.650, p < 0.001), sensitivity (87.8% vs. 42.4%, p < 0.001), and accuracy (78.7% vs. 56.9%, p < 0.001).</p><p><strong>Conclusion: </strong>The ML method integrating MRI and clinical risk factors effectively identified axSpA, representing a promising tool for the diagnosis and management of axSpA.</p><p><strong>Clinical relevance statement: </strong>The machine learning model combining MRI and clinical risk factors potentially enables earlier diagnosis and intervention for axial spondyloarthritis patients, reducing the delays commonly associated with traditional diagnostic approaches.</p><p><strong>Key points: </strong>Axial spondyloarthritis (AxSpA) lacks definitive diagnostic criteria or markers, leading to diagnostic delay. MRI-based deep learning provided quantitative analysis of sacroiliac joint changes indicative of axSpA. A machine learning model combining sacroiliac joint MRI and clinical risk factors enhanced axSpA identification.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"91"},"PeriodicalIF":4.1,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12031678/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144013476","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":"Habitat radiomics assists radiologists in accurately diagnosing lymph node metastasis of adenocarcinoma of the esophagogastric junction.","authors":"Pingfan Jia, Yueying Li, Haonan Li, Yuan Li, Huijuan Qin, Anyu Xie, Yuru Li, Luyao Wang, Luqin Ke, Huijie Feng, Hongwei Yu, Juan Li, Ning Yuan, Xing Guo","doi":"10.1186/s13244-025-01969-9","DOIUrl":"https://doi.org/10.1186/s13244-025-01969-9","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to develop a habitat radiomics (HR) model capable of preoperatively predicting lymph node metastasis (LNM) in adenocarcinoma of the esophagogastric junction (AEG) and to implement its use in clinical practice.</p><p><strong>Methods: </strong>In this retrospective analysis, 337 patients from three centers were enrolled and divided into three cohorts: training, validation, and test (208, 52, and 77 patients, respectively). We constructed HR models, conventional radiomics models, and combined models to identify LNM in AEG. The area under the curve (AUC) was employed to identify the optimal model, which was then evaluated for assisting radiologists in the empirical and RADS groups in diagnosing LNM. Finally, the prediction process of the optimal model was visualized using SHAP plots.</p><p><strong>Results: </strong>The HR model demonstrated superior performance, achieving the highest AUC values of 0.876, 0.869, and 0.795 in the training, validation, and test cohorts, respectively. Regardless of seniority, the empirical group of radiologists showed a significant improvement in the AUC and accuracy when using the HR model, compared to working alone (p < 0.05). Furthermore, the RADS group radiologists exhibited strong reclassification ability, effectively reevaluating patients with false-negative LN initially classified as Node-RADS score 1 or 2 by themselves.</p><p><strong>Conclusion: </strong>The HR model facilitates the accurate prediction of LNM in AEG and holds potential as a valuable tool to augment radiologists' diagnostic capabilities in daily clinical practice.</p><p><strong>Critical relevance statement: </strong>The habitat radiomics model could accurately predict the lymph node status of adenocarcinoma in the esophagogastric junction and assist radiologists in improving diagnostic efficacy, which lays the foundation for accurate staging and effective treatment.</p><p><strong>Key points: </strong>Accurate lymph node diagnosis in esophagogastric junction adenocarcinoma is beneficial for prognosis. Habitat radiomics model accurately predicted and assisted physicians in diagnosing lymph nodes. The habitat model effectively reclassified false-negative lymph nodes at Node-RADS 1 and 2.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"90"},"PeriodicalIF":4.1,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021776/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143982246","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":"Radiology AI and sustainability paradox: environmental, economic, and social dimensions.","authors":"Burak Kocak, Andrea Ponsiglione, Valeria Romeo, Lorenzo Ugga, Merel Huisman, Renato Cuocolo","doi":"10.1186/s13244-025-01962-2","DOIUrl":"https://doi.org/10.1186/s13244-025-01962-2","url":null,"abstract":"<p><p>Artificial intelligence (AI) is transforming radiology by improving diagnostic accuracy, streamlining workflows, and enhancing operational efficiency. However, these advancements come with significant sustainability challenges across environmental, economic, and social dimensions. AI systems, particularly deep learning models, require substantial computational resources, leading to high energy consumption, increased carbon emissions, and hardware waste. Data storage and cloud computing further exacerbate the environmental impact. Economically, the high costs of implementing AI tools often outweigh the demonstrated clinical benefits, raising concerns about their long-term viability and equity in healthcare systems. Socially, AI risks perpetuating healthcare disparities through biases in algorithms and unequal access to technology. On the other hand, AI has the potential to improve sustainability in healthcare by reducing low-value imaging, optimizing resource allocation, and improving energy efficiency in radiology departments. This review addresses the sustainability paradox of AI from a radiological perspective, exploring its environmental footprint, economic feasibility, and social implications. Strategies to mitigate these challenges are also discussed, alongside a call for action and directions for future research. CRITICAL RELEVANCE STATEMENT: By adopting an informed and holistic approach, the radiology community can ensure that AI's benefits are realized responsibly, balancing innovation with sustainability. This effort is essential to align technological advancements with environmental preservation, economic sustainability, and social equity. KEY POINTS: AI has an ambivalent potential, capable of both exacerbating global sustainability issues and offering increased productivity and accessibility. Addressing AI sustainability requires a broad perspective accounting for environmental impact, economic feasibility, and social implications. By embracing the duality of AI, the radiology community can adopt informed strategies at individual, institutional, and collective levels to maximize its benefits while minimizing negative impacts.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"88"},"PeriodicalIF":4.1,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12006592/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144020711","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":"A deep learning model based on self-supervised learning for identifying subtypes of proliferative hepatocellular carcinoma from dynamic contrast-enhanced MRI.","authors":"Hui Qu, Shuairan Zhang, Xuedan Li, Yuan Miao, Yuxi Han, Ronghui Ju, Xiaoyu Cui, Yiling Li","doi":"10.1186/s13244-025-01968-w","DOIUrl":"https://doi.org/10.1186/s13244-025-01968-w","url":null,"abstract":"<p><strong>Objectives: </strong>This study employs dynamic contrast-enhanced MRI (DCE-MRI) to noninvasively predict the proliferative subtype of hepatocellular carcinoma (HCC). This subtype is marked by high tumor proliferation and aggressive clinical behavior. We developed a deep learning prediction model that employs a dynamic radiomics workflow and self-supervised learning (SSL). The model analyzes temporal and spatial patterns in DCE-MRI data to identify the proliferative subtype efficiently and accurately. Our goal is to improve diagnostic precision and guide personalized treatment planning.</p><p><strong>Methods: </strong>This retrospective study included 381 HCC patiephonnts who underwent curative resection at two medical centers. The cohort was divided into the training (n = 220), internal (n = 93), and external (n = 68) test sets. A DL model was developed using DCE-MRI of the primary tumor. Class activation mapping was used to interpret HCC proliferation in HCC.</p><p><strong>Results: </strong>The pHCC-SSL model performed well in predicting HCC proliferation, with a training set AUC) of 1.00, an internal test set AUC of 0.91, and an external test set AUC of 0.94. Without SSL pre-training, the AUC for internal and external testing decreased to 0.81 and 0.80, respectively. The predictive performance of the derived model was superior to that of the current single-sequence model.</p><p><strong>Conclusions: </strong>The pHCC-SSL model employs dynamic radiomics and a two-stage training approach to efficiently predict HCC proliferation from multi-sequence DCE-MRI, surpassing traditional single-stage models in accuracy and speed.</p><p><strong>Critical relevance statement: </strong>Our study introduces the pHCC-SSL model, a self-supervised deep learning approach using DCE-MRI that enhances the diagnostic accuracy of HCC subtypes, significantly advancing clinical radiology by enabling personalized treatment strategies.</p><p><strong>Key points: </strong>The proposed model enables noninvasive identification of HCC with high proliferation and aggressive behavior. SSL improves lesion differentiation by reducing redundancy and enhancing feature diversity. Dynamic feature extraction captures vascular infiltration, aiding preoperative metastasis risk assessment.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"89"},"PeriodicalIF":4.1,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12006648/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143984892","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":"Asclepius with contemporary glasses introduces 'Modern Radiology'-an open-access teaching resource.","authors":"Minerva Becker","doi":"10.1186/s13244-025-01953-3","DOIUrl":"https://doi.org/10.1186/s13244-025-01953-3","url":null,"abstract":"<p><p>The European Society of Radiology (ESR) initially developed the ESR e-Book as an open-access digital teaching resource aligned with the undergraduate European Training Curriculum for Radiology. Over time, this initiative evolved into Modern Radiology, a rebranded and expanded version that now serves not only medical students and educators but also residents and other healthcare professionals. Unlike traditional textbooks, Modern Radiology follows a visually engaging and succinct format, emphasising key concepts through annotated images, attention points, hyperlinks, and self-assessment sections. It complements case-based and interactive learning methods, providing a systematic foundation for radiology education. By continuously updating its content to reflect advancements in the field, Modern Radiology has been widely adopted by universities across Europe and beyond. Furthermore, several translations are in progress, ensuring its accessibility to a broader audience. KEY POINTS: Modern Radiology is an open-source, non-commercial teaching resource for undergraduate and postgraduate radiology teaching. It is a living document that follows the European Society of Radiology (ESR) Training Curriculum for Radiology. Its didactic and concise format facilitates the acquisition of basic knowledge and the preparation of interactive teaching and self-learning. It is widely used in universities across Europe and beyond, as well as by residents in training.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"87"},"PeriodicalIF":4.1,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12003229/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143963318","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}