Academic Radiology最新文献

{"title":"BMSMM-Net: A Bone Metastasis Segmentation Framework Based on Mamba and Multiperspective Extraction","authors":"Fudong Shang ,&nbsp;Shouguo Tang ,&nbsp;Xiaorong Wan ,&nbsp;Yingna Li ,&nbsp;Lulu Wang","doi":"10.1016/j.acra.2024.11.018","DOIUrl":"10.1016/j.acra.2024.11.018","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Metastatic bone tumors significantly reduce patients’ quality of life and expedite cancer spread. Traditional diagnostic methods rely on time-consuming manual annotations by radiologists, which are prone to subjectivity. Employing deep learning for rapid, precise segmentation of bone metastases can greatly improve patient outcomes and survival. However, accurate segmentation remains challenging due to the diverse and complex nature of osteoblastic, osteolytic, or mixed lesions.</div></div><div><h3>Materials and Methods</h3><div>In this study, we presented a novel segmentation framework, termed BMSMM-Net, tailored specifically for the detection of bone metastases. The framework integrates our newly proposed Bottleneck Gating Mamba layer (BGM) into the network backbone, enhancing the long-range dependencies in the depth feature maps. Additionally, we designed a Skip-Mamba (SKM) module on the skip connections to facilitate long-range modeling during multi-scale feature fusion. Furthermore, a Multi-Perspective Extraction (MPE) module was employed in the feature extraction phase, utilizing three different sizes of convolutional kernels to enhance sensitivity to bone metastases.</div></div><div><h3>Results</h3><div>Our framework was evaluated on the BM-Seg dataset through comparative and ablation studies. It achieved F1 scores of 91.07% and 95.17% for segmenting bone metastases and bone regions, respectively, along with mIoU scores of 83.60% and 90.78%, BMSMM-Net provides high-performance segmentation of bone metastases. Additionally, it maintains good computational efficiency compared to existing models.</div></div><div><h3>Conclusion</h3><div>The BMSMM-Net framework, integrating BGM, SKM, and MPE modules, effectively addresses the segmentation challenges of bone metastases. It significantly enhances accuracy, outperforms advanced existing methods, and maintains lower complexity, making it suitable for clinical application.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1204-1217"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142774367","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":"Abnormal Functional Attributes of Central Executive Network in Patients with Mild Cognitive Impairment Associated with End-Stage Renal Disease","authors":"Wenqing Li ,&nbsp;Wei Sun ,&nbsp;Di Wang ,&nbsp;Zhuqing Jiao ,&nbsp;Tongqiang Liu ,&nbsp;Wanchao Zhang ,&nbsp;Haifeng Shi","doi":"10.1016/j.acra.2024.07.030","DOIUrl":"10.1016/j.acra.2024.07.030","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To assess changes in the central executive network (CEN) of patients with mild cognitive impairment (MCI) associated with end-stage renal disease (ESRD).</div></div><div><h3>Methods</h3><div>A total of 121 patients with ESRD and 66 healthy controls (HCs) were enrolled. Patients were divided into an MCI group (<em>n</em> = 67) and a cognitively unimpaired group (<em>n</em> = 54). All participants underwent resting-state functional magnetic resonance imaging and were evaluated using the Montreal Cognitive Assessment (MoCA). The functional attributes of the CEN were calculated using three methods of functional connectivity (FC) analysis. Relationships among imaging features, cognitive scale scores, and clinical data were assessed, and a model was constructed to diagnose MCI in patients with ESRD.</div></div><div><h3>Results</h3><div>The comparison of the three groups showed that there were significant differences in the FC values of five connection pairs within the CEN, and the CEN demonstrated significant differences in connectivity to ten brain regions. In patients with MCI associated with ESRD, the information transmission efficiency of the CEN was reduced, which demonstrates the characteristics of a random network to some extent. Significant correlations were observed among imaging parameters, cognitive scale scores, and clinical data. The diagnostic model constructed based on these results demonstrated excellent discrimination and calibration.</div></div><div><h3>Conclusion</h3><div>Alterations in the function of the CEN provide relevant bases for revealing the neuropathological mechanism of MCI in patients with ESRD. The diagnostic model developed in this study may help to establish more reliable imaging markers for detecting early cognitive impairment in this patient population.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1586-1597"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141876647","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":"Radiological features on high-resolution MR imaging predicts successful recanalization in patients with symptomatic chronic intracranial large artery occlusion","authors":"Chun Zhou MD ,&nbsp;Yue-Zhou Cao MD ,&nbsp;Zhen-Yu Jia MD ,&nbsp;Lin-Bo Zhao MD ,&nbsp;Shan-Shan Lu MD ,&nbsp;Xiao-Quan Xu MD ,&nbsp;Hai-Bin Shi MD, PHD ,&nbsp;Sheng Liu MD, PHD","doi":"10.1016/j.acra.2024.10.020","DOIUrl":"10.1016/j.acra.2024.10.020","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Endovascular recanalization has been attempted in patients with symptomatic chronic intracranial large artery occlusion (CILAO), however, the heterogeneity of recanalization outcomes present challenges for the clinical application.</div></div><div><h3>Objective</h3><div>To determine the radiological features on high-resolution MR imaging (HR-MRI) for predicting successful recanalization of symptomatic CILAO.</div></div><div><h3>Methods</h3><div>Seventy-three patients with symptomatic CILAO who underwent endovascular recanalization at our center were retrospectively analyzed. Patients’ clinical information, HR-MRI characteristics, procedural results, and outcomes were recorded. Factors related to successful recanalization were analyzed by univariate and multivariate analyses.</div></div><div><h3>Results</h3><div>Technical success was achieved in 61 (83.6%) patients, with a complication rate of 13.7% (10/73). Based on multivariate analysis, responsible occluded artery (middle cerebral artery (MCA) trunk versus intracranial internal carotid artery (ICA), <em>P</em> = 0.004; MCA trunk versus intracranial vertebrobasilar artery (VBA), <em>P</em> = 0.010), occlusion with residual lumen (<em>P</em> = 0.036), occlusion with marked plaque enhancement (<em>P</em> = 0.011), and shorter occlusion length (≤10.2 mm versus &gt;10.2 mm, <em>P</em> = 0.008) were identified as independent positive predictors of successful recanalization. Patients were assigned score points according to the coefficients of the prediction model, and the technical success rates were 50.0%, 83.3%, 95.5%, and 100% in patients with score ≤ 2, 3, 4, and ≥ 5 points, respectively.</div></div><div><h3>Conclusions</h3><div>The HR-MRI modality may be valuable in identifying candidates for endovascular recanalization of symptomatic CILAO. MCA trunk occlusion, occlusion with residual lumen, occlusion with marked plaque enhancement and shorter occlusion length on HR-MRI appear to be significantly associated with the success of recanalization.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1621-1630"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142559322","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":"Dual-energy CT Radiomics Combined with Quantitative Parameters for Differentiating Lung Adenocarcinoma From Squamous Cell Carcinoma: A Dual-center Study","authors":"Ze Lin ,&nbsp;Ying Liu ,&nbsp;Chengcheng Xia ,&nbsp;Pei Huang ,&nbsp;Zhiwei Peng ,&nbsp;Li Yi ,&nbsp;Yu Wang ,&nbsp;Xiao Yu ,&nbsp;Bing Fan ,&nbsp;Minjing Zuo","doi":"10.1016/j.acra.2024.09.024","DOIUrl":"10.1016/j.acra.2024.09.024","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Rationale and Objectives&lt;/h3&gt;&lt;div&gt;To evaluate the ability of dual-energy CT(DECT)-based quantitative parameters and radiomics features to differentiate solid lung adenocarcinoma (ADC) from squamous cell carcinoma (SCC).&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Methods&lt;/h3&gt;&lt;div&gt;This study included 213 patients diagnosed with ADC and SCC who underwent DECT scans at two centers from November 2022 to December 2023. Patients at center 1 were randomly divided into training (&lt;em&gt;n&lt;/em&gt; = 114) and internal test set (&lt;em&gt;n&lt;/em&gt; = 50) in a 7:3 ratio, with center 2 serving as the external test set (&lt;em&gt;n&lt;/em&gt; = 49). Radiologic and clinical data were combined to establish a clinical-radiologic model. Ten types of DECT energy images including conventional images, iodine density (ID), effective atomic number (Z&lt;sub&gt;eff&lt;/sub&gt;), electron density, and virtual mono-energetic images (VMI) were reconstructed in both arterial phases (AP) and venous phases (VP). Quantitative parameters were measured at the uniform enhanced solid portion of the tumor and normalized to the aorta, used to develop a quantification model and calculate the quantitative score (quantscore). Radiologists manually delineated the tumor ROI at the largest level for extracting radiomics features in these 10 energy images. These features were used to establish 10 uni-energy models from which the best-performing features were selected to construct the final radiomics model and calculate a radiomics score (radscore). Then, a combined model was developed using the akaike information criterion(AIC) and compared to the clinical-radiological model to test its diagnostic validity.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Results&lt;/h3&gt;&lt;div&gt;The independent predictors of the clinical-radiological model included age, gender, and central or peripheral location, and the AUCs for the training set, internal test set, and external test set were 0.808, 0.837, and 0.802. The quantification model incorporated 40 keV CT values, Z&lt;sub&gt;eff&lt;/sub&gt;, normalized Z&lt;sub&gt;eff&lt;/sub&gt;, and the slope of the spectral attenuation curve (λHU) in the AP and normalized ID, Z&lt;sub&gt;eff&lt;/sub&gt;, and λHU in the VP. Uni-energy models based on AP ID maps, AP Z&lt;sub&gt;eff&lt;/sub&gt; maps, and VP VMI 65 keV significantly outperformed AUC&lt;!--&gt; &lt;!--&gt;= 0.5, and 11 radiomics features were selected from these three models to construct the final radiomics model. The combined model, incorporating age, gender, quantscore, and radscore, significantly outperformed the clinical-radiological model in the training set (AUC&lt;!--&gt; &lt;!--&gt;=&lt;!--&gt; &lt;!--&gt;0.952 vs 0.808, &lt;em&gt;P&lt;/em&gt; &lt; 0.001), and demonstrated higher performance in both the internal and external test sets, although these differences did not reach statistical significance (AUC&lt;!--&gt; &lt;!--&gt;=&lt;!--&gt; &lt;!--&gt;0.870 vs 0.837, for the internal test set [&lt;em&gt;P&lt;/em&gt; = 0.542], 0.888 vs 0.802 for the external test sets [&lt;em&gt;P&lt;/em&gt; = 0.128]). The evaluation of the combined model demonstrated good discriminative ability and potential for generalization.&lt;/div&gt;&lt;/div&gt;","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1675-1684"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331769","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":"Intra-individual Differences in Pericoronary Fat Attenuation Index Measurements Between Photon-counting and Energy-integrating Detector Computed Tomography","authors":"Giuseppe Tremamunno MD ,&nbsp;Milan Vecsey-Nagy MD, PhD ,&nbsp;Muhammad Taha Hagar MD ,&nbsp;U. Joseph Schoepf MD ,&nbsp;Jim O’Doherty PhD ,&nbsp;Julian A. Luetkens MD ,&nbsp;Daniel Kuetting MD ,&nbsp;Alexander Isaak MD ,&nbsp;Akos Varga-Szemes PhD, MD ,&nbsp;Tilman Emrich MD ,&nbsp;Dmitrij Kravchenko MD","doi":"10.1016/j.acra.2024.11.055","DOIUrl":"10.1016/j.acra.2024.11.055","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>The purpose of this study was to explore intra-individual differences in pericoronary adipose tissue (PCAT) fat attenuation index (FAI) between photon-counting detector (PCD)- and energy-integrating detector (EID)-CT.</div></div><div><h3>Material and Methods</h3><div>Patients were prospectively enrolled for a PCD-CT research scan within 30 days of EID-CT. Both acquisitions were reconstructed using a Qr36 kernel at 0.6 mm slice thickness (EID and PCD-down-sampled [DS]) and at 0.2 mm ultra-high resolution (UHR) for the PCD-CT. Iterative reconstruction was turned “off” (filter back projection used as alternative reconstruction method) or set to a recommended level in current literature. Coronary PCAT FAI was measured automatically using established thresholds of −190 to −30 HU at a set distance and radius. Statistical testing was performed using repeated-measures ANOVA and Bonferroni’s multiple comparison tests (<em>p</em> significance was determined to be &lt;0.003).</div></div><div><h3>Results</h3><div>In total, 40 patients (mean age 68±8 years, 32 males [80%]) were included for analysis. Absolute FAI measurements differed significantly for all vessels between all reconstructions in the ANOVA comparison (all p&lt;.001). The FAI decreased going from EID-CT to PCD-DS, to PCD-UHR with iterative reconstruction turned off (e.g. right coronary artery: EID-CT: −76.5±8.9 vs −80.9±7.0 vs −88.3±6.7 HU, respectively; <em>p</em> &lt; 0.001). The mean FAI of datasets using iterative reconstruction did not demonstrate significant differences on multiple comparisons (e.g. left circumflex artery: EID: −65.7±8.5; PCD-DS: −66.0±7.4; PCD-UHR: −67.8±7.0 HU, respectively; p&gt;0.06).</div></div><div><h3>Conclusion</h3><div>Intra-individual absolute PCAT FAI measurements differ significantly between EID- and PCD-CT when controlling for reconstruction kernel and slice thickness. However, the use of iterative reconstruction minimizes most differences in FAI, enabling inter-scanner comparability.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1333-1343"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142814979","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":"Differential Connectivity Patterns of Mild Cognitive Impairment in Alzheimer's and Parkinson's Disease: A Large-scale Brain Network Study","authors":"Juzhou Wang MD ,&nbsp;Xiaolu Li MD ,&nbsp;Huize Pang PhD ,&nbsp;Shuting Bu MD ,&nbsp;Mengwan Zhao MD ,&nbsp;Yu Liu MD ,&nbsp;Hongmei Yu PhD ,&nbsp;Yueluan Jiang ,&nbsp;Guoguang Fan PhD","doi":"10.1016/j.acra.2024.09.017","DOIUrl":"10.1016/j.acra.2024.09.017","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Cognitive disorders, such as Alzheimer's disease (AD) and Parkinson's disease (PD), significantly impact the quality of life in older adults. Mild cognitive impairment (MCI) is a critical stage for intervention and can predict the development of dementia. The causes of these two diseases are not fully understood, but there is an overlap in their neuropathology. There is a lack of direct comparison regarding the changes in functional connectivity within and between different brain networks during cognitive impairment in these two diseases.</div></div><div><h3>Objective</h3><div>This study aims to investigate changes in brain network connectivity of AD and PD with mild cognitive impairment, shedding light on the underlying neuropathological mechanisms and potential treatment options.</div></div><div><h3>Methods</h3><div>A total of 33 AD-MCI patients, 55 PD-MCI patients, and 34 healthy controls (HCs) underwent resting-state functional MRI and cognitive function assessment using Independent Components Analysis (ICA). We compared intra- and inter-network functional connectivity among the three groups and analyzed the correlation between changes in functional connectivity and cognitive domain performance.</div></div><div><h3>Results</h3><div>Using ICA, we identified eight functional networks. In the AD-MCI group, reductions in internetwork functional connectivity were mainly around the default mode network (DMN). Intra-network functional connectivity was widely reduced, especially in the DMN, while intra-network functional connectivity in the Salience Network (SN) increased. In contrast, in the PD-MCI group, reductions in internetwork functional connectivity were mainly around the SN. Intra-network functional connectivity in the SN decreased, while intra-network functional connectivity in other networks increased.</div></div><div><h3>Conclusion</h3><div>This study highlights distinct yet overlapping changes in brain network connectivity in AD and PD, providing new insights into the underlying mechanisms of cognitive impairment disorders.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1601-1610"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143015846","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":"Multiparameter and Ultrasound Radiomics Nomogram to Predict the Aggressiveness of Papillary Thyroid Carcinomas: A Multicenter, Retrospective Study","authors":"Fang Li ,&nbsp;Yu Du ,&nbsp;Long Liu ,&nbsp;Ji Ma ,&nbsp;Ziwei Qin ,&nbsp;Shuang Tao ,&nbsp;Minghua Yao ,&nbsp;Rong Wu ,&nbsp;Jinhua Zhao","doi":"10.1016/j.acra.2024.10.015","DOIUrl":"10.1016/j.acra.2024.10.015","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To construct a multiparameter radiomics nomogram based on ultrasound (US) to predict the aggressiveness of thyroid papillary carcinoma (PTC).</div></div><div><h3>Materials and Methods</h3><div>In total, 471 consecutive patients from three institutions were included in this study. Among them, patients from institution 1 were used for training (<em>n</em> = 294) and internal validation (<em>n</em> = 92), while 85 patients from institution 2 and institution 3 were used for external validation. Radiomics features were extracted from the conventional US. The least absolute shrinkage was employed to select the most relevant features for the aggressiveness of PTC, along with the maximum relevance minimum redundancy algorithm and selection operator. These features were then used to construct the radiomics signature (RS). Subsequently, relevant multiparameter ultrasound (MPUS) features from shear-wave elastic (SWE) and strain elastography (SE) will be extracted using multivariable logistic regression. The final radionics nomogram was conducted using the RS, clinical information, and conventional US and MPUS features. The receiver operating characteristic (ROC), calibration, and decision curves were used to evaluate the performance of the nomogram.</div></div><div><h3>Results</h3><div>Multivariable logistic regression analysis indicated that age, nodule size, capsule abutment, SWV tumor, and RS were independent predictors of the aggressiveness of PTC. The radiomics nomogram, utilizing these characteristics, displayed impressive performance with an AUC of 0.920 [95% CI, 0.889–0.950], 0.901 [95% CI, 0.839–0.963], and 0.896 [95% CI, 0.823–0.969] in the training, internal, and external validation cohort. It outperformed the clinical US, MPUS, and RS models (<em>p</em> &lt; 0.05). The decision curve analysis indicated that the nomogram offered valuable clinical utility.</div></div><div><h3>Conclusion</h3><div>The nomogram incorporated MPUS and radiomics have good diagnostic performance in predicting the aggressiveness of PTC which may help in the selection of the surgical modality.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1373-1384"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142569854","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":"Patient Engagement with Radiology Report Content: A Retrospective Analysis of 60,572 Radiology Report Views","authors":"Ryan G. Short MD ,&nbsp;Kenneth Weaver BS ,&nbsp;Estlin Haiss BA ,&nbsp;Nicholas T. Befera MD","doi":"10.1016/j.acra.2024.11.051","DOIUrl":"10.1016/j.acra.2024.11.051","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To evaluate patient use of plain language radiology report content.</div></div><div><h3>Methods</h3><div>Webpage-style radiology reports delivering patient-centered content were made available to patients via an online patient portal. Simple language explanations of terms and phrases in the reports were accessible to patients via a clickable hyperlink. For each viewed radiology report over a one-year study period, we recorded a count of the individual terms and phrases in the report that were annotated (i.e., had accessible patient-centered content), the annotated terms and phrases that the patient clicked, and the number of clicks of each term. The terms were categorized according to the hierarchical RadLex Tree Browser.</div></div><div><h3>Results</h3><div>In 60,572 unique viewed reports, there were 380,798 term clicks out of 4264,663 annotated terms (overall click rate 8.9%). 878 terms were annotated ≥ 1000 times. The click rate varied between these high-frequency terms from 0.1% to 63.2%. The average term click rate varied between RadLex categories from 16.7% for clinical findings to 7.9% for the property category.</div></div><div><h3>Discussion</h3><div>Modern web technologies can be used to gain insight into patient experience viewing online radiology reports. There is a significant variance in patient use of patient-centered radiology report content.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1656-1660"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142903960","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":"Ultrasound-based artificial intelligence model for prediction of Ki-67 proliferation index in soft tissue tumors","authors":"Xinpeng Dai Master's Degree ,&nbsp;Haiyong Lu Bachelor's Degree ,&nbsp;Xinying Wang Master's Degree ,&nbsp;Yujia Liu Master's Degree ,&nbsp;Jiangnan Zang Bachelor's Degree ,&nbsp;Zongjie Liu Master's Degree ,&nbsp;Tao Sun Doctoral degree ,&nbsp;Feng Gao Doctoral degree ,&nbsp;Xin Sui Doctoral degree","doi":"10.1016/j.acra.2024.09.067","DOIUrl":"10.1016/j.acra.2024.09.067","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To investigate the value of deep learning (DL) combined with radiomics and clinical and imaging features in predicting the Ki-67 proliferation index of soft tissue tumors (STTs).</div></div><div><h3>Materials and Methods</h3><div>In this retrospective study, a total of 394 patients with STTs admitted from January 2021 to December 2023 in two separate hospitals were collected. Hospital-1 was the training cohort (323 cases, of which 89 and 234 were high and low Ki-67, respectively) and Hospital-2 was the external validation cohort (71 cases, of which 23 and 48 were high and low Ki-67, respectively). Clinical and ultrasound characteristics including age, sex, tumor size, morphology, margins, internal echoes and blood flow were assessed. Risk factors with significant correlations were screened by univariate and multivariate logistic regression analyses. After extracting the radiomics and DL features, the feature fusion model is constructed by Support Vector Machine. The prediction results obtained from separate clinical features, radiomics features and DL features were combined to construct decision fusion models. Finally, the DeLong test was used to compare whether the AUCs between the models were significantly different.</div></div><div><h3>Results</h3><div>The three feature fusion models and three decision fusion models constructed demonstrated excellent diagnostic performance in predicting Ki-67 expression levels in STTs. Among them, the feature fusion model based on clinical, radiomics, and DL performed the best with an AUC of 0.911 (95% CI: 0.886–0.935) in the training cohort and 0.923 (95% CI: 0.873–0.972) in the validation cohort, and proved to be well-calibrated and clinically useful. The DeLong test showed that the decision fusion models based on clinical, radiomics and DL performed significantly worse than the three feature fusion models on the validation set. There was no statistical difference in diagnostic performance between the other models.</div></div><div><h3>Conclusion</h3><div>The ultrasound-based fusion model of clinical, radiomics, and DL features showed good performance in predicting Ki-67 expression levels in STTs.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1178-1188"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142479922","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":"Enhancing Radiologists’ Performance in Detecting Cerebral Aneurysms Using a Deep Learning Model: A Multicenter Study","authors":"Liyong Zhuo ,&nbsp;Yu Zhang ,&nbsp;Zijun Song ,&nbsp;Zhanhao Mo ,&nbsp;Lihong Xing ,&nbsp;Fengying Zhu ,&nbsp;Huan Meng ,&nbsp;Lei Chen ,&nbsp;Guoxiang Qu ,&nbsp;Pengbo Jiang ,&nbsp;Qian Wang ,&nbsp;Ruonan Cheng ,&nbsp;Xiaoming Mi ,&nbsp;Lin Liu ,&nbsp;Nan Hong ,&nbsp;Xiaohuan Cao ,&nbsp;Dijia Wu ,&nbsp;Jianing Wang PhD ,&nbsp;Xiaoping Yin","doi":"10.1016/j.acra.2024.09.038","DOIUrl":"10.1016/j.acra.2024.09.038","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>This study aimed to develop a deep learning (DL)-based model for detecting and diagnosing cerebral aneurysms in clinical settings, with and without human assistance.</div></div><div><h3>Materials and Methods</h3><div>The DL model was trained using data from 3829 patients across 11 clinical centers and tested on 484 patients from three institutions. Image interpretations were conducted by 10 radiologists (four junior, six senior), the DL model alone, and a combination of radiologists with the DL model. Time spent on post-processing and reading was recorded. The analysis of the area under the curve (AUC), sensitivity, and specificity for the above-mentioned three reading modes was performed at both the lesion and patient levels.</div></div><div><h3>Results</h3><div>Combining the DL model with radiologists reduced image interpretation time by 37.2% and post-processing time by 90.8%. With DL model assistance, the AUC increased from 0.842 to 0.881 (<em>P</em> = 0.008) for junior radiologists (JRs) and from 0.853 to 0.895 (<em>P</em> &lt; 0.001) for senior radiologists (SRs). With DL model assistance, sensitivity significantly improved at both lesion (JR: 68.9% to 81.6%, <em>P</em> = 0.011; SR: 72.4% to 83.5%, <em>P</em> &lt; 0.001) and patient levels (JR: 76.2% to 86.9%, <em>P</em> = 0.011; SR: 80.1% to 88.2%, <em>P</em> &lt; 0.001). Specificity at the patient level showed improvement (JR: 82.6% to 82.7%, P = 0.005; SR: 82.6% to 86.1%, <em>P</em> = 0.<em>021</em>).</div></div><div><h3>Conclusions</h3><div>The DL model enhanced radiologists’ diagnostic performance in detecting cerebral aneurysms, especially for JRs, and expedited the workflow.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1611-1620"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142480003","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}