Insights into Imaging最新文献

{"title":"CT-based quantification of intratumoral heterogeneity for predicting distant metastasis in retroperitoneal sarcoma.","authors":"Jun Xu, Jian-Guo Miao, Chen-Xi Wang, Yu-Peng Zhu, Ke Liu, Si-Yuan Qin, Hai-Song Chen, Ning Lang","doi":"10.1186/s13244-025-01977-9","DOIUrl":"https://doi.org/10.1186/s13244-025-01977-9","url":null,"abstract":"<p><strong>Objectives: </strong>Retroperitoneal sarcoma (RPS) is highly heterogeneous, leading to different risks of distant metastasis (DM) among patients with the same clinical stage. This study aims to develop a quantitative method for assessing intratumoral heterogeneity (ITH) using preoperative contrast-enhanced CT (CECT) scans and evaluate its ability to predict DM risk.</p><p><strong>Methods: </strong>We conducted a retrospective analysis of 274 PRS patients who underwent complete surgical resection and were monitored for ≥ 36 months at two centers. Conventional radiomics (C-radiomics), ITH radiomics, and deep-learning (DL) features were extracted from the preoperative CECT scans and developed single-modality models. Clinical indicators and high-throughput CECT features were integrated to develop a combined model for predicting DM. The performance of the models was evaluated by measuring the receiver operating characteristic curve and Harrell's concordance index (C-index). Distant metastasis-free survival (DMFS) was also predicted to further assess survival benefits.</p><p><strong>Results: </strong>The ITH model demonstrated satisfactory predictive capability for DM in internal and external validation cohorts (AUC: 0.735, 0.765; C-index: 0.691, 0.729). The combined model that combined clinicoradiological variables, ITH-score, and DL-score achieved the best predictive performance in internal and external validation cohorts (AUC: 0.864, 0.801; C-index: 0.770, 0.752), successfully stratified patients into high- and low-risk groups for DM (p < 0.05).</p><p><strong>Conclusions: </strong>The combined model demonstrated promising potential for accurately predicting the DM risk and stratifying the DMFS risk in RPS patients undergoing complete surgical resection, providing a valuable tool for guiding treatment decisions and follow-up strategies.</p><p><strong>Critical relevance statement: </strong>The intratumoral heterogeneity analysis facilitates the identification of high-risk retroperitoneal sarcoma patients prone to distant metastasis and poor prognoses, enabling the selection of candidates for more aggressive surgical and post-surgical interventions.</p><p><strong>Key points: </strong>Preoperative identification of retroperitoneal sarcoma (RPS) with a high potential for distant metastasis (DM) is crucial for targeted interventional strategies. Quantitative assessment of intratumoral heterogeneity achieved reasonable performance for predicting DM. The integrated model combining clinicoradiological variables, ITH radiomics, and deep-learning features effectively predicted distant metastasis-free survival.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"99"},"PeriodicalIF":4.1,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12064543/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144014296","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":"The interpretable CT-based vision transformer model for preoperative prediction of clear cell renal cell carcinoma SSIGN score and outcome.","authors":"Kaiyue Zhi, Yanmei Wang, Lei Yan, Feng Hou, Jie Wu, Shuo Zhang, He Zhu, Lianzi Zhao, Ning Wang, Xia Zhao, Xianjun Li, Yicong Wang, Chengcheng Chen, Nan Wang, Yuchao Xu, Guangjie Yang, Pei Nie","doi":"10.1186/s13244-025-01972-0","DOIUrl":"https://doi.org/10.1186/s13244-025-01972-0","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate an interpretable CT-based vision transformer (ViT) model for preoperative prediction of the stage, size, grade, and necrosis (SSIGN) and outcome in clear cell renal cell carcinoma (ccRCC) patients.</p><p><strong>Methods: </strong>Eight hundred forty-five ccRCC patients from multiple centers were retrospectively enrolled. For each patient, 768 ViT features were extracted in the cortical medullary phase (CMP) and renal parenchymal phase (RPP) images, respectively. The CMP ViT model (CVM), RPP ViT model (RVM), and CMP-RPP combined ViT model (CRVM) were constructed to predict the SSIGN in ccRCC patients. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of each model. Decision curve analysis (DCA) was used to evaluate the net clinical benefit. The endpoint was the progression-free survival (PFS). Kaplan-Meier survival analysis was used to assess the association between model-predicted SSIGN and PFS. The SHAP approach was applied to determine the prediction process of the CRVM.</p><p><strong>Results: </strong>The CVM, RVM, and CRVM demonstrated good performance in predicting SSIGN, with a high AUC of 0.859, 0.883, and 0.895, respectively, in the test cohort. DCA demonstrated the CRVM performed best in clinical net benefit. In predicting PFS, CRVM achieved a higher Harrell's concordance index (C-index, 0.840) than the CVM (0.719) and RVM (0.773) in the test cohort. The SHAP helped us understand the impact of ViT features on CRVM's SSIGN prediction from a global and individual perspective.</p><p><strong>Conclusion: </strong>The interpretable CT-based CRVM may serve as a non-invasive biomarker in predicting the SSIGN and outcome of ccRCC.</p><p><strong>Critical relevance statement: </strong>Our findings outline the potential of an interpretable CT-based ViT biomarker for predicting the SSIGN score and outcome of ccRCC, which might facilitate patient counseling and assist clinicians in therapy decision-making for individual cases.</p><p><strong>Key points: </strong>Current first-line imaging lacks preoperative prediction of the SSIGN score for ccRCC patients. The ViT model could predict the SSIGN score and outcome of ccRCC patients. This study can facilitate the development of personalized treatment for ccRCC patients.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"98"},"PeriodicalIF":4.1,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12064486/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143970392","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":"Acute arterial mesenteric ischaemia: comparison of partial and complete occlusion of the superior mesenteric artery.","authors":"Raphael Dufay, Lorenzo Garzelli, Iannis Ben Abdallah, Arnaud Tual, Dominique Cazals-Hatem, Olivier Corcos, Valérie Vilgrain, Emmanuel Weiss, Alexandre Nuzzo, Maxime Ronot","doi":"10.1186/s13244-025-01986-8","DOIUrl":"https://doi.org/10.1186/s13244-025-01986-8","url":null,"abstract":"<p><strong>Objectives: </strong>To describe the characteristics and outcomes of patients with an incomplete occlusion of the superior mesenteric artery (SMA) (persistence of contrast-enhanced vessel lumen) and compare them to those with a complete occlusion of the SMA (complete interruption of the contrast-enhanced vessel lumen) in arterial acute mesenteric ischaemia (AMI).</p><p><strong>Material and methods: </strong>Retrospective study of arterial AMI patients (2006-2022). Demographics, laboratory tests, clinical characteristics, CT, treatments and outcomes were compared between patients with complete or incomplete SMA obstruction after adjusting for aetiology (embolic or atherosclerotic). The primary outcome was 30-day mortality, and the secondary outcome was 6-month gastrointestinal disability-free survival (no short bowel syndrome or parenteral nutritional support or permanent stoma).</p><p><strong>Results: </strong>151 patients (65 women, mean age 69) were included, 62 (41%) with incomplete and 89 (59%) with occlusive SMA occlusion. After adjusting for aetiology, chronic kidney failure (p = 0.03) and normal bowel enhancement on CT (p < 0.01) were associated with incomplete SMA occlusion. Patients with incomplete SMA occlusion were more frequently treated by endovascular revascularisation (p < 0.01) and stenting (p < 0.01), while patients with complete SMA occlusion were treated by open revascularisation. The 30-day mortality rate was 13% with no difference between incomplete (11%) and complete SMA occlusion (15%; p = 0.89). Nevertheless, complete SMA occlusion patients had a lower 6-month gastrointestinal disability-free survival rate (p = 0.01), more transmural necrosis (p < 0.01) and a higher risk of gastrointestinal disability (p = 0.02).</p><p><strong>Conclusion: </strong>Incomplete SMA occlusion can cause AMI with a similar 30-day mortality rate to completely occlusive forms. However, it is associated with poorer gastrointestinal outcomes, regardless of aetiology.</p><p><strong>Critical relevance statement: </strong>Acute arterial mesenteric ischaemia caused by incomplete occlusion of the superior mesenteric artery demonstrates similar 30-day mortality to complete occlusion but distinctively better gastrointestinal outcomes, emphasising nuanced imaging evaluation for targeted management strategies in these patients.</p><p><strong>Key points: </strong>Occlusive acute mesenteric ischaemia can be caused by incomplete superior mesenteric artery (SMA) occlusion. Acute mesenteric ischaemia caused by incomplete SMA occlusion has a similar 30-day mortality rate to complete SMA occlusion. A complete occlusion of the SMA is associated with poorer gastrointestinal outcomes.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"97"},"PeriodicalIF":4.1,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12062469/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143998849","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":"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}