{"title":"Wide-Detector CT-Based optimized triple Rule-Out CT angiography for emergency chest pain: reducing contrast and radiation without compromising diagnostic quality.","authors":"Qiuhua Zhang, Kun Wang, Hong Ren","doi":"10.1007/s10140-025-02351-4","DOIUrl":"https://doi.org/10.1007/s10140-025-02351-4","url":null,"abstract":"<p><strong>Background: </strong>The triple rule-out computed tomography angiography (TRO-CTA) has recently emerged as a technique that noninvasively evaluates the coronary arteries (CAs), the pulmonary arteries (PAs) and the thoracic aorta (TA).</p><p><strong>Objective: </strong>To evaluate the feasibility of an optimized scanning protocol to reduce the volume of iodine contrast media (ICM), injection rate, and radiation dose in patients undergoing TRO-CTA.</p><p><strong>Methods: </strong>Patients undergoing TRO-CTA were assigned to either group A or group B using a 16 cm wide-detector CT. Patients in group A were imaged with a traditional triple scanning protocol with a sequence of the PA, CAs, and TA. Patients in group B were imaged using the modified protocol with scanning sequence of PA, TA, and CAs, ICM of 55 ml, and injection rate of 4.5 mL/s. The image quality and effective radiation dose (ED) were compared.</p><p><strong>Results: </strong>There were no significant differences in basic information between groups A and B. Other than the left PA, RA, and RV, there were no significant differences in the CT attenuation values of relevant vascular structures between groups A and B. There were no significant differences in CNR values between the two groups except the LAD-D and LCX. The image quality scores were comparable between groups A and B except the CAs. However, there were significant differences between the two groups in ICM (p < 0.05), scanning time (p < 0.001) and ED (p = 0. 023).</p><p><strong>Conclusions: </strong>The optimized TRO-CTA scanning protocol can achieve less ICM and lower ED while maintaining image quality.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hudson McKinney, Bryan A Kirk, Anuj J Jailwala, Aaron McFarlane, Jackson L Sullivan, Raghav Agarwal, Kevin D Hiatt
{"title":"Yield of MRI in patients with spontaneous deep intracerebral hemorrhage.","authors":"Hudson McKinney, Bryan A Kirk, Anuj J Jailwala, Aaron McFarlane, Jackson L Sullivan, Raghav Agarwal, Kevin D Hiatt","doi":"10.1007/s10140-025-02348-z","DOIUrl":"https://doi.org/10.1007/s10140-025-02348-z","url":null,"abstract":"<p><strong>Purpose: </strong>Hypertensive hemorrhage is the most common type of nontraumatic intracerebral hemorrhage (ICH), and it characteristically originates in deep structures, particularly the basal ganglia, internal capsules, thalami, brainstem, and cerebellum. While advanced imaging modalities like MRI can help uncover culprit lesions in cases of unexplained ICH, we hypothesized that the yield of brain MRI would be low in patients with spontaneous deep intracerebral hemorrhage.</p><p><strong>Methods: </strong>With IRB approval, we retrospectively reviewed cases of deep ICH at a single tertiary care academic center over a 5-year period and excluded cases with a known cause for hemorrhage. Patient history and demographics, initial blood pressure, and the results of the initial noncontrast head CT and subsequent imaging studies were recorded.</p><p><strong>Results: </strong>222 patients met study inclusion criteria, with a median age of 67 and 43.2% female sex. 188 patients (84.7%) had a history of hypertension, while 14 (6.3%) had a urine drug screen positive for cocaine or amphetamines during their hospital admission. The majority of hemorrhages were centered in the basal ganglia or internal capsules (116, 52.3%). Brain MRI was obtained for 120 (54.1%) of cases at a median interval of 0.97 days following the initial head CT, and of these studies, 85 (70.8%) included postcontrast imaging. Only 1 MRI study (0.8%) identified a culprit lesion adjacent to a cerebellar hematoma, which was later found to represent a pilocytic astrocytoma. 33.8% of patients overall met the modified Hong Kong Rule. Of the 77 MRIs performed in patients not meeting the modified Hong Kong Rule, 0 revealed a culprit lesion.</p><p><strong>Conclusion: </strong>Brain MRI obtained in the acute evaluation of patients with spontaneous deep intracerebral hemorrhage rarely uncovers a culprit lesion. Routine ordering of MRI in this cohort should be reconsidered, particularly in patients not meeting the modified Hong Kong Rule.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144110086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sneh Brahmbhatt, Jeremiah Daniel, Amit Agarwal, Vivek Gupta, Alok A Bhatt
{"title":"Sinonasal NK/T-cell lymphoma - imaging features overlap with non-neoplastic etiologies.","authors":"Sneh Brahmbhatt, Jeremiah Daniel, Amit Agarwal, Vivek Gupta, Alok A Bhatt","doi":"10.1007/s10140-025-02350-5","DOIUrl":"https://doi.org/10.1007/s10140-025-02350-5","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this retrospective study is to evaluate imaging features of sinonasal NK/T-cell lymphoma, potentially aiding early diagnosis and improving patient outcomes through timely biopsy evaluation and treatment.</p><p><strong>Materials & methods: </strong>This study was designed as a retrospective review. Imaging characteristics in a total of 28 patients with histology confirmed sinonasal NK/T-cell lymphoma were evaluated by two radiologists. Demographic data and clinical features were extracted from the electronic medical record.</p><p><strong>Results: </strong>Among 28 patients, 84.6% presented with nasal cavity involvement and 88.5% with an isoattenuating lesion on CT and 63.6% with T2 hypointensity on MRI. Notably, 57.7% showed osseous destruction and 27.3% had devascularized tissue, highlighting significant radiologic features that may overlap with non-neoplastic etiologies.</p><p><strong>Conclusion: </strong>Sinonasal NK/T-cell lymphoma should be in the differential diagnosis in patients presenting with chronic sinonasal symptoms and imaging findings of tissue necrosis, osseous destruction, and adjacent fat infiltration. Imaging features overlap with entities such as aggressive fungal sinusitis and granulomatosis with polyangiitis.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144093333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Igor M Kitanovski, Alec Buetow, Steven C Schoettler-Woll, Abdul M Zafar
{"title":"Value assessment of augmentative artificial intelligence for assessment of pulmonary emboli on CT - a meta-analysis comprising 15,963 CT scans.","authors":"Igor M Kitanovski, Alec Buetow, Steven C Schoettler-Woll, Abdul M Zafar","doi":"10.1007/s10140-025-02344-3","DOIUrl":"https://doi.org/10.1007/s10140-025-02344-3","url":null,"abstract":"<p><strong>Purpose: </strong>Artificial Intelligence (AI) algorithms in radiology are currently deployed as tools to augment radiologists rather than autonomous readers. An augmentative tool should improve performance above and beyond the baseline performance achieved by the user alone. We conducted a meta-analysis to elucidate the added value of augmentative AI to radiologists for detecting Pulmonary Embolism (PE) on CT scan.</p><p><strong>Methods: </strong>Using PRISMA guidelines, studies in which both AI and Human Interpreter (HI) assessed CT scans for pulmonary emboli were selected. Data extracted from these studies were used to compare diagnostic performance of AI and HI with an emphasis on the performance of AI above and beyond that of HI.</p><p><strong>Results: </strong>Both HI and AI performed similarly with no statistically significant difference in the pooled estimates of sensitivity, specificity, PPV, NPV and accuracy. Subsequent analysis focusing on the differences between performance of AI and HI within each study, followed by pooled estimate, also did not demonstrate any significant difference (p < 0.05).</p><p><strong>Conclusions: </strong>In a meta-analysis of nearly sixteen thousand CTs, AI and HI had similar performance for detection of pulmonary emboli. On one hand, this buttresses AI's use for triaging and for second reads. On the other hand, the outcomes may or may not be different when AI is added-on. The findings of this meta-analysis can be used to re-examine the use-scenarios of AI and to re-calibrate its value proposition.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143990555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emergency RadiologyPub Date : 2025-04-01Epub Date: 2025-02-10DOI: 10.1007/s10140-025-02316-7
Thomas Li, Piya Malhan, Mohadese Ahmadzade, Aaron Sahihi, Carleigh Klusman, David Wynne, David Leon, Ashkan Berenji, Mohammad Ghasemi-Rad
{"title":"Safety and efficacy of the Abre™ venous stent in treating thoracic venous stenosis/occlusion: a single-center experience.","authors":"Thomas Li, Piya Malhan, Mohadese Ahmadzade, Aaron Sahihi, Carleigh Klusman, David Wynne, David Leon, Ashkan Berenji, Mohammad Ghasemi-Rad","doi":"10.1007/s10140-025-02316-7","DOIUrl":"10.1007/s10140-025-02316-7","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to evaluate the clinical outcomes, technical success, and complications associated with the placement of Abre™ venous stents for central venous stenosis/occlusion (CVS/CVO).</p><p><strong>Materials and methods: </strong>A retrospective review was conducted, identifying 21 patients who underwent Abre™ venous stent placement for SVC syndrome at a single institution. Demographic and clinical data were collected, including stent configurations, procedural details, and follow-up outcomes. Primary stent patency, symptom resolution, and survival rates were analyzed. Survival curves were generated using Kaplan-Meier analysis, and complications were recorded.</p><p><strong>Results: </strong>Facial and/or upper extremity edema was present in all patients, and malignancy accounted for SVC syndrome in 71.4% of cases, with lung cancer as the predominant etiology (66.6%). The technical success rate was 100%. Clinical symptom resolution was achieved in all patients. The 30-day mortality rate was 23.8%, with all cases involving oncology patients. At six months, cross-sectional imaging showed a primary stent patency rate of 93%, and this remained stable through 12 months. The mean survival time for the cancer subgroup was 337.2 ± 343 days, while the overall cohort mean was 885.8 ± 453.7 days.</p><p><strong>Conclusion: </strong>The Abre™ venous stent demonstrates potential as an effective stent for SVC syndrome, achieving high symptom relief and patency rates. However, further long-term studies and randomized controlled trials are necessary to validate these findings.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":"139-145"},"PeriodicalIF":1.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143381890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Orbital compartment syndrome in orbital mucormycosis: spot the threat through radiologist's eye.","authors":"Reeta Kanaujiya, Charu Paruthi, Aravind M J, Komal Sood, Swarna Gupta, Anuradha Sharma","doi":"10.1007/s10140-025-02318-5","DOIUrl":"10.1007/s10140-025-02318-5","url":null,"abstract":"<p><strong>Purpose: </strong>To illustrate the imaging findings of orbital compartment syndrome (OCS) in patients with orbital mucormycosis and to identify the red flag signs on imaging for prompt diagnosis and timely intervention.</p><p><strong>Methods: </strong>We conducted a retrospective analysis of CT and MRI scans from patients diagnosed with sino-nasal mucormycosis within three months of a confirmed COVID-19 infection. Microbiologically proven cases of mucormycosis were included. Images were analysed for: Route of spread; proptosis; tenting of globe, Retro-orbital fat/extraocular muscle (EOM) nonenhancement; Intra-orbital abscess, superior ophthalmic vein (SOV) thrombosis, stretching/thickening/enhancement/diffusion restriction of optic nerve, orbital coat, and EOM. Descriptive statistics were elaborated in the form of mean/standard deviations for continuous variables and frequencies and percentages for categorical variables.</p><p><strong>Results: </strong>Out of 138 patients with mucormycosis, 49 had orbital involvement, OCS was present in 16 orbits. The mean age was 48.6 years with M: F of 2.75:1. Adjacent sinuses were involved in all patients. Spread along nerves and nasolacrimal duct was seen in 94% patients. Globe tenting was seen in all and thickening/coat enhancement in 53.3%. Optic nerve (ON) was thickened in 87.5%, diffusion restriction of ON and EOM in 78.5% cases. Non enhancement of retro-orbital fat was seen in 50% and intra-orbital abscess in 62.5% cases.</p><p><strong>Conclusions: </strong>OCS is a vision-threatening orbital emergency, leading to OIS and permanent blindness, if not managed promptly. Imaging features that warrant immediate clinical/ surgical intervention to avoid permanent loss of vision are distorted globe, posterior tenting of the globe, stretching of the optic nerve, non-enhancement of retro-bulbar fat and extra-ocular muscles (EOMs).</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":"217-224"},"PeriodicalIF":1.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143406516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emergency RadiologyPub Date : 2025-04-01Epub Date: 2025-02-26DOI: 10.1007/s10140-025-02321-w
Natalie Kozlowski, Matthew J Schmitz, Marco V Istasy, Luca Simonetto, Ivan R Diamond, Audra Smallfield
{"title":"Impact of a multi-modal intervention on CTA ordering rates in patients presenting with vertigo to the emergency department.","authors":"Natalie Kozlowski, Matthew J Schmitz, Marco V Istasy, Luca Simonetto, Ivan R Diamond, Audra Smallfield","doi":"10.1007/s10140-025-02321-w","DOIUrl":"10.1007/s10140-025-02321-w","url":null,"abstract":"<p><strong>Purpose: </strong>Vertigo and dizziness are common complaints at emergency departments (ED), often leading to computed tomography (CT) and CT angiography (CTA) studies, which when used non-selectively, have low clinical utility. The study assesses whether two quality improvement interventions (educational rounds and clinical decision making support tool) can better align CTA ordering rates with clinical practice guidelines in the ED workup of vertigo/dizziness at a large community hospital.</p><p><strong>Methods: </strong>CTA head and neck imaging rates were collected for patients presenting to the hospital's ED with dizziness/vertigo as the chief complaint during 6-month pre- and post-intervention periods and compared rates using the Chi-Square Test. The interventions were joint ED/Diagnostic Imaging/Stroke Neurology rounds discussing CTA head/neck indications and dissemination of a clinical decision making support tool.</p><p><strong>Results: </strong>The absolute reduction was 5.79% (N = 4,230, p < 0.001) in CTA rates for patients presenting with dizziness/vertigo between the pre- and post-intervention periods. For vertigo, the absolute reduction was 12.27% (N = 402, p < 0.005). For dizziness, the absolute reduction was 5.17% (N = 3828, p < 0.001). Despite the global decrease in CTA studies, there was no statistically significant decrease in CTA rates for the patients who were diagnosed with cerebrovascular accident or transient ischemic attack in the ED, indicating that the interventions were effective in limiting to the targeted CTA studies.</p><p><strong>Conclusions: </strong>This project was effective in improving patient safety and system efficiency, while providing a framework for low-burden, effective, practice-modifying quality improvement initiatives.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":"147-154"},"PeriodicalIF":1.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143499009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emergency RadiologyPub Date : 2025-04-01Epub Date: 2025-03-10DOI: 10.1007/s10140-025-02314-9
Saurabh Pallod, Rami Chatta, Ravanane Ramadosan, Hina Shah
{"title":"Assessing the utility of FDG PET/CT study in diagnosis of early acute appendicitis.","authors":"Saurabh Pallod, Rami Chatta, Ravanane Ramadosan, Hina Shah","doi":"10.1007/s10140-025-02314-9","DOIUrl":"10.1007/s10140-025-02314-9","url":null,"abstract":"<p><p>Acute appendicitis is a common surgical emergency that can be challenging to diagnose due to its varied clinical presentations. Standard imaging methods include ultrasonography, computed tomography (CT), and Magnetic resonance imaging (MRI), but fluorine-18-fluorodeoxyglucose positron emission tomography/computed tomography (18 F-FDG PET/CT), typically used for oncology, can incidentally detect appendicitis through increased radiotracer uptake associated with inflammation. The paper discusses two cases where acute appendicitis was identified during PET/CT scans conducted for cancer evaluations. In cancer patients, diagnosing appendicitis is difficult due to overlapping symptoms from chemotherapy, metastasis, or radiation effects. Clinicians and radiologists must remain vigilant for incidental appendicitis findings in PET/CT scans, as early diagnosis can prevent complications despite its rarity in oncology imaging.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":"291-295"},"PeriodicalIF":1.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emergency RadiologyPub Date : 2025-04-01Epub Date: 2024-12-23DOI: 10.1007/s10140-024-02306-1
David Dreizin, Garvit Khatri, Pedro V Staziaki, Karen Buch, Mathias Unberath, Mohammed Mohammed, Aaron Sodickson, Bharti Khurana, Anjali Agrawal, James Stephen Spann, Nicholas Beckmann, Zachary DelProposto, Christina A LeBedis, Melissa Davis, Gabrielle Dickerson, Michael Lev
{"title":"Artificial intelligence in emergency and trauma radiology: ASER AI/ML expert panel Delphi consensus statement on research guidelines, practices, and priorities.","authors":"David Dreizin, Garvit Khatri, Pedro V Staziaki, Karen Buch, Mathias Unberath, Mohammed Mohammed, Aaron Sodickson, Bharti Khurana, Anjali Agrawal, James Stephen Spann, Nicholas Beckmann, Zachary DelProposto, Christina A LeBedis, Melissa Davis, Gabrielle Dickerson, Michael Lev","doi":"10.1007/s10140-024-02306-1","DOIUrl":"10.1007/s10140-024-02306-1","url":null,"abstract":"<p><strong>Background: </strong>Emergency/trauma radiology artificial intelligence (AI) is maturing along all stages of technology readiness, with research and development (R&D) ranging from data curation and algorithm development to post-market monitoring and retraining.</p><p><strong>Purpose: </strong>To develop an expert consensus document on best research practices and methodological priorities for emergency/trauma radiology AI.</p><p><strong>Methods: </strong>A Delphi consensus exercise was conducted by the ASER AI/ML expert panel between 2022-2024. In phase 1, a steering committee (7 panelists) established key themes- curation; validity; human factors; workflow; barriers; future avenues; and ethics- and generated an edited, collated long-list of statements. In phase 2, two Delphi rounds using anonymous RAND/UCLA Likert grading were conducted with web-based data capture (round 1) and a bespoke excel document with literature hyperlinks (round 2). Between rounds, editing and knowledge synthesis helped maximize consensus. Statements reaching ≥80% agreement were included in the final document.</p><p><strong>Results: </strong>Delphi rounds 1 and 2 consisted of 81 and 78 items, respectively.18/21 expert panelists (86%) responded to round 1, and 15 to round 2 (17% drop-out). Consensus was reached for 65 statements. Observations were summarized and contextualized. Statements with unanimous consensus centered around transparent methodologic reporting; testing for generalizability and robustness with external data; and benchmarking performance with appropriate metrics and baselines. A manuscript draft was circulated to panelists for editing and final approval.</p><p><strong>Conclusions: </strong>The document is meant as a framework to foster best-practices and further discussion among researchers working on various aspects of emergency and trauma radiology AI.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":"155-172"},"PeriodicalIF":1.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142876674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emergency RadiologyPub Date : 2025-04-01Epub Date: 2025-01-17DOI: 10.1007/s10140-025-02311-y
Zhanye Lin, Jian Zheng, Yaohong Deng, Lingyue Du, Fan Liu, Zhengyi Li
{"title":"Deep learning-aided diagnosis of acute abdominal aortic dissection by ultrasound images.","authors":"Zhanye Lin, Jian Zheng, Yaohong Deng, Lingyue Du, Fan Liu, Zhengyi Li","doi":"10.1007/s10140-025-02311-y","DOIUrl":"10.1007/s10140-025-02311-y","url":null,"abstract":"<p><strong>Purpose: </strong>Acute abdominal aortic dissection (AD) is a serious disease. Early detection based on ultrasound (US) can improve the prognosis of AD, especially in emergency settings. We explored the ability of deep learning (DL) to diagnose abdominal AD in US images, which may help the diagnosis of AD by novice radiologists or non-professionals.</p><p><strong>Methods: </strong>There were 374 US images from patients treated before June 30, 2022. The images were classified as AD-positive and AD-negative images. Among them, 90% of images were used as the training set, and 10% of images were used as the test set. A Densenet-169 model and a VGG-16 model were used in this study and compared with two human readers.</p><p><strong>Results: </strong>DL models demonstrated high sensitivity and AUC for diagnosing abdominal AD in US images, and DL models showed generally better performance than human readers.</p><p><strong>Conclusion: </strong>Our findings demonstrated the efficacy of DL-aided diagnosis of abdominal AD in US images, which can be helpful in emergency settings.</p>","PeriodicalId":11623,"journal":{"name":"Emergency Radiology","volume":" ","pages":"233-239"},"PeriodicalIF":1.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143002265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}