Academic Radiology最新文献

{"title":"A Novel Visual Model for Predicting Prognosis of Resected Hepatoblastoma: A Multicenter Study.","authors":"Ying He, Chaohui An, Kuiran Dong, Zhibao Lyu, Shanlu Qin, Kezhe Tan, Xiwei Hao, Chengzhan Zhu, Wenli Xiu, Bin Hu, Nan Xia, Chaojin Wang, Qian Dong","doi":"10.1016/j.acra.2025.03.004","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.004","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>This study aimed to evaluate the application of a contrast-enhanced CT-based visual model in predicting postoperative prognosis in patients with hepatoblastoma (HB).</p><p><strong>Materials and methods: </strong>We analyzed data from 224 patients across three centers (178 in the training cohort, 46 in the validation cohort). Visual features were extracted from contrast-enhanced CT images, and key features, along with clinicopathological data, were identified using LASSO Cox regression. Visual (DINOv2_score) and clinical (Clinical_score) models were developed, and a combined model integrating DINOv2_score and clinical risk factors was constructed. Nomograms were created for personalized risk assessment, with calibration curves and decision curve analysis (DCA) used to evaluate model performance.</p><p><strong>Results: </strong>The DINOv2_score was recognized as a key prognostic indicator for HB. In both the training and validation cohorts, the combined model demonstrated superior performance in predicting disease-free survival (DFS) [C-index (95% CI): 0.886 (0.879-0.895) and 0.873 (0.837-0.909), respectively] and overall survival (OS) [C-index (95% CI): 0.887 (0.877-0.897) and 0.882 (0.858-0.906), respectively]. Calibration curves showed strong alignment between predicted and observed outcomes, while DCA demonstrated that the combined model provided greater clinical net benefit than the clinical or visual models alone across a range of threshold probabilities.</p><p><strong>Conclusion: </strong>The contrast-enhanced CT-based visual model serves as an effective tool for predicting postoperative prognosis in HB patients. The combined model, integrating the DINOv2_score and clinical risk factors, demonstrated superior performance in survival prediction, offering more precise guidance for personalized treatment strategies.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large Language Models with Image Processing Capabilities: An Inevitable yet Undetermined Presence in Radiology Practice and Education.","authors":"Erin Gomez","doi":"10.1016/j.acra.2025.03.027","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.027","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using Optimal Feature Selection and Continuous Learning to Implement Efficient Model Arrays for Predicting Daily Clinical Radiology Workload.","authors":"Leslie K Lee, Melissa Viator, Catherine S Giess, Michael Gee, Ray Huang, Fionnuala McPeake, Oleg S Pianykh","doi":"10.1016/j.acra.2025.02.051","DOIUrl":"https://doi.org/10.1016/j.acra.2025.02.051","url":null,"abstract":"<p><strong>Rationale and objective: </strong>Clinical workload can fluctuate daily in radiology practice. We sought to design, validate, and implement an efficient and sustainable machine learning model to forecast daily clinical image interpretation workload.</p><p><strong>Materials and methods: </strong>A year of radiology exam volume data at two academic medical centers was analyzed with an optimal feature selection algorithm and several machine learning models, to produce the most accurate and explainable prediction of the next weekday's clinical workload. Continuous learning was used to maintain high model quality over time.</p><p><strong>Results: </strong>After evaluating several AI models of differing complexity on a large set of 707 workflow features, a continuously learning linear regression model array was selected based on three optimal features: the current number of unread exams, the number of exams scheduled to be performed after 5 pm, and the number of exams scheduled to be performed the next day. The model array had an average R² of 0.83 (IQR 0.13) across the tested radiology divisions; it significantly outperformed trivial estimates and provided an accurate daily prediction pattern. The solution was successfully implemented into an online dashboard, displaying the forecasted clinical volume as a percentile in reference to the past year's daily clinical volume. Retraining the model on a weekly basis using live data resulted in high, and sometimes increased, model quality.</p><p><strong>Conclusion: </strong>An AI model can be developed and implemented to forecast daily clinical radiology workload, as a practice management tool.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knowledge Graph-Based Few-Shot Learning for Label of Medical Imaging Reports.","authors":"Tiancheng Li, Yuxuan Zhang, Deyu Su, Ming Liu, Mingxin Ge, Linyu Chen, Chuanfu Li, Jin Tang","doi":"10.1016/j.acra.2025.02.045","DOIUrl":"https://doi.org/10.1016/j.acra.2025.02.045","url":null,"abstract":"<p><strong>Background: </strong>The application of artificial intelligence (AI) in the field of automatic imaging report labeling faces the challenge of manually labeling large datasets.</p><p><strong>Purpose: </strong>To propose a data augmentation method by using knowledge graph (KG) and few-shot learning.</p><p><strong>Methods: </strong>A KG of lumbar spine X-ray images was constructed, and 2000 data were annotated based on the KG, which were divided into training, validation, and test sets in a ratio of 7:2:1. The training dataset was augmented based on the synonym/replacement attributes of the KG and was the augmented data was input into the BERT (Bidirectional Encoder Representations from Transformers) model for automatic annotation training. The performance of the model under different augmentation ratios (1:10, 1:100, 1:1000) and augmentation methods (synonyms only, replacements only, combination of synonyms and replacements) was evaluated using the precision and F1 scores. In addition, with the augmentation ratio was fixed, iterative experiments were performed by supplementing the data of nodes that perform poorly in the validation set to further improve model's performance.</p><p><strong>Results: </strong>Prior to data augmentation, the precision was 0.728 and the F1 score was 0.666. By adjusting the augmentation ratio, the precision increased from 0.912 at a 1:10 augmentation ratio to 0.932 at a 1:100 augmentation ratio (P<.05), while F1 score improved from 0.853 at a 1:10 augmentation ratio to 0.881 at a 1:100 augmentation ratio (P<.05). Additionally, the effectiveness of various augmentation methods was compared at a 1:100 augmentation ratio. The augmentation method that combined synonyms and replacements (F1=0.881) was superior to the methods that only used synonyms (F1=0.815) and only used replacements (F1=0.753) (P<.05). For nodes that exhibited suboptimal performance on the validation set, supplementing the training set with target data improved model performance, increasing the average F1 score to 0.979 (P<.05).</p><p><strong>Conclusion: </strong>Based on the KG, this study trained an automatic labeling model of radiology reports using a few-shot data set. This method effectively reduces the workload of manual labeling, improves the efficiency and accuracy of image data labeling, and provides an important research strategy for the application of AI in the domain of automatic labeling of image reports.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bridging Gaps in Radiology Education: Insights From Clinical-year Medical Students and the Risk of Diminishing the Radiologist's Role in Patient Care.","authors":"Omar R Vayani, Senthooran Kalidoss, Dima K Halabi, Christopher M Straus","doi":"10.1016/j.acra.2025.02.050","DOIUrl":"https://doi.org/10.1016/j.acra.2025.02.050","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>This study investigates clinical-year medical student perceptions of the role of radiologists and medical imaging in patient care, assessing their exposure to and experiences with radiology during clinical rotations. Given radiology's critical function in modern healthcare, this study aims to highlight educational gaps and propose improvements for integrating radiology more effectively within medical curricula.</p><p><strong>Materials and methods: </strong>A mixed-methods approach was employed, combining a validated survey and semi-structured interviews to collect quantitative and qualitative data. The survey focused on students' familiarity with the radiologist's role, confidence in interpreting imaging findings, and experiences with radiology across different clinical rotations. Ten students were randomly selected for in-depth interviews to provide deeper insights. Quantitative data were analyzed using descriptive statistics, while qualitative data using thematic analysis.</p><p><strong>Results: </strong>Out of 90 surveyed students, 50% responded, revealing varied experiences across clinical rotations and limited exposure to diagnostic and interventional radiology. Radiologists were widely viewed as ancillary service providers, with many students reporting no direct communication with them regarding image interpretation. While radiology reports were noted to influence patient treatment, few students reported patient awareness of the radiologist's contributions. The study also highlighted a moderate understanding of radiation risks and the selection of appropriate diagnostic imaging.</p><p><strong>Conclusion: </strong>The findings underscore the necessity for an integrated radiology curriculum, including practical exposure and enhanced interprofessional collaboration. These insights advocate for an educational framework that aligns radiology's educational presence with its clinical significance, thus preparing students for the multifaceted demands of modern medical practice.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Distress to Growth: Promoting Moral Resilience in Radiology.","authors":"Jose Nicolas Duarte, Gonzalo Andrés Montaño Rozo, David Fernando Torres Cortes, Alejandra Duarte","doi":"10.1016/j.acra.2025.02.037","DOIUrl":"https://doi.org/10.1016/j.acra.2025.02.037","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preoperative Prediction of STAS Risk in Primary Lung Adenocarcinoma Using Machine Learning: An Interpretable Model with SHAP Analysis.","authors":"Ping Wang, Jianing Cui, Haoyuan Du, Zhanhua Qian, Huili Zhan, Heng Zhang, Wei Ye, Wei Meng, Rongjie Bai","doi":"10.1016/j.acra.2025.03.005","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.005","url":null,"abstract":"<p><strong>Background: </strong>Accurate preoperative prediction of spread through air spaces (STAS) in primary lung adenocarcinoma (LUAD) is critical for optimizing surgical strategies and improving patient outcomes.</p><p><strong>Objective: </strong>To develop a machine learning (ML) based model to predict STAS using preoperative CT imaging features and clinicopathological data, while enhancing interpretability through shapley additive explanations (SHAP) analysis.</p><p><strong>Materials and methods: </strong>This multicenter retrospective study included 1237 patients with pathologically confirmed primary LUAD from three hospitals. Patients from Center 1 (n=932) were divided into a training set (n=652) and an internal test set (n=280). Patients from Centers 2 (n=165) and 3 (n=140) formed external validation sets. CT imaging features and clinical variables were selected using Boruta and least absolute shrinkage and selection operator regression. Seven ML models were developed and evaluated using five-fold cross-validation. Performance was assessed using F1 score, recall, precision, specificity, sensitivity, and area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>The Extreme Gradient Boosting (XGB) model achieved AUCs of 0.973 (training set), 0.862 (internal test set), and 0.842/0.810 (external validation sets). SHAP analysis identified nodule type, carcinoembryonic antigen, maximum nodule diameter, and lobulated sign as key features for predicting STAS. Logistic regression analysis confirmed these as independent risk factors.</p><p><strong>Conclusion: </strong>The XGB model demonstrated high predictive accuracy and interpretability for STAS. By integrating widely available clinical and imaging features, this model offers a practical and effective tool for preoperative risk stratification, supporting personalized surgical planning in primary LUAD management.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The CHANOA Score: Will Collateral Circulation Help Determine Candidacy for Endovascular Stroke Treatment?","authors":"Franklin G Moser","doi":"10.1016/j.acra.2025.03.021","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.021","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Foundation Model and Radiomics-Based Quantitative Characterization of Perirenal Fat in Renal Cell Carcinoma Surgery.","authors":"Haonan Mei, Hui Chen, Qingyuan Zheng, Rui Yang, Nanxi Wang, Panpan Jiao, Xiao Wang, Zhiyuan Chen, Xiuheng Liu","doi":"10.1016/j.acra.2025.03.002","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.002","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To quantitatively characterize the degree of perirenal fat adhesion using artificial intelligence in renal cell carcinoma.</p><p><strong>Materials and methods: </strong>This retrospective study analyzed a total of 596 patients from three cohorts, utilizing corticomedullary phase computed tomography urography (CTU) images. The nnUNet v2 network combined with numerical computation was employed to segment the perirenal fat region. Pyradiomics algorithms and a computed tomography foundation model were used to extract features from CTU images separately, creating single-modality predictive models for identifying perirenal fat adhesion. By concatenating the Pyradiomics and foundation model features, an early fusion multimodal predictive signature was developed. The prognostic performance of the single-modality and multimodality models was further validated in two independent cohorts.</p><p><strong>Results: </strong>The nnUNet v2 segmentation model accurately segmented both kidneys. The neural network and thresholding approach effectively delineated the perirenal fat region. Single-modality models based on radiomic and computed tomography foundation features demonstrated a certain degree of accuracy in diagnosing and identifying perirenal fat adhesion, while the early feature fusion diagnostic model outperformed the single-modality models. Also, the perirenal fat adhesion score showed a positive correlation with surgical time and intraoperative blood loss.</p><p><strong>Conclusion: </strong>AI-based radiomics and foundation models can accurately identify the degree of perirenal fat adhesion and have the potential to be used for surgical risk assessment.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Size and Contrast Thresholds for Liver Lesion Detection in Regular and Low-dose CT Examinations: A Reader Study of 2300 Synthetic Lesions Across 100 Patients.","authors":"Li Yan, Ulrich Genske, Yang Peng, Angelo Laudani, Katharina Beller, Thula Walter-Rittel, Moritz Wagner, Bernd Hamm, Paul Jahnke","doi":"10.1016/j.acra.2025.03.001","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.001","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To determine the size and contrast required for liver lesion detection in regular and low-dose computed tomography (CT) examinations.</p><p><strong>Materials and methods: </strong>100 abdominal CT datasets were retrospectively collected, with 50 originating from vendor A and 50 from vendor B. Half the datasets from each scanner were regular-dose oncologic examinations, the other half were acquired using a low-dose kidney stone protocol. Cylindrical liver lesions with 23 different combinations of diameter and contrast to the surrounding liver were digitally inserted. Seven radiologists assessed lesion detectability in a four-alternative forced choice reading experiment, and image noise was measured within the liver.</p><p><strong>Results: </strong>Lesion detection thresholds at regular dose were at -30, -35, and -70 Hounsfield unit (HU) lesion contrast (vendor A) and -25, -35, and -65 HU (vendor B) for lesions with 15-, 10-, and 5-mm diameter, respectively. At low dose, thresholds were -40 and -45 HU (vendor A) and -40 and -50 HU (vendor B) for 15- and 10-mm lesions, while 5-mm lesions did not reach the detection threshold. Noise levels were 21.5±2.3 HU at regular dose vs 22.2±2.0 HU at low dose for vendor A (P=.06) and 25.9±4.9 HU vs 30.9±3.1 HU for vendor B (P<.001).</p><p><strong>Conclusion: </strong>In oncologic CT examinations, liver lesions with diameters of 15-, 10-, and 5-mm require contrasts of -30, -35, and -70 HU, respectively for reliable detection. In low-dose examinations, greater contrasts of -40 and -50 HU are required for lesions measuring 15- and 10-mm, while readers do not reliably detect 5-mm lesions.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143694314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}