iRadiology最新文献

{"title":"Optimizing Contrast-Enhanced Magnetic Resonance Neurography of the Brachial Plexus With Delayed Scanning","authors":"Jun Xu,&nbsp;Xiaoli Hu,&nbsp;Xiaoyun Su,&nbsp;Shen Gui,&nbsp;Ziqiao Lei,&nbsp;Xiaoming Liu,&nbsp;Xiangzhi Zhou,&nbsp;Lixia Wang,&nbsp;Wenjun Wu,&nbsp;Xiangchuang Kong","doi":"10.1002/ird3.120","DOIUrl":"https://doi.org/10.1002/ird3.120","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Contrast-enhanced magnetic resonance neurography (ceMRN) can enhance brachial plexus visualization and quality of imaging. However, the interval between contrast injection and scanning that provides the highest-quality images is not known.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Fifteen patients underwent brachial plexus imaging using the 3D T2-NerveView sequence with a scanning duration of 5 min. A consecutive six-phase scan was initiated immediately at the start of contrast agent injection. Subsequently, all patients' images were classified into six groups according to the phases: group A (phase 1, delay 0 min), group B (phase 2, delay 5 min), group C (phase 3, delay 10 min), group D (phase 4, delay 15 min), group E (phase 5, delay 20 min), and group F (phase 6, delay 25 min). The image quality in each group was assessed based on nerve signal (signal_nerve), muscle signal (signal_muscle), lymph node signal (signal_{lymph node}), background noise (BN), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and subjective score.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Signal_nerve, signal_muscle, BN, and SNR did not significantly differ among the six groups (<i>p</i> &gt; 0.05). However, significant differences (<i>p</i> &lt; 0.05) were observed in signal_{lymph node} (<i>F</i> = 16.067), CNR (<i>F</i> = 9.495), and subjective score (<i>χ</i>² = 23.586). As the scanning delay increased, signal_{lymph node} intensity gradually increased whereas the CNR gradually decreased. The subjective score was significantly higher in groups B (4.83 ± 0.24), C (4.90 ± 0.21), D (4.87 ± 0.30), E (4.83 ± 0.31), and F (4.83 ± 0.31) than in group A (4.47 ± 0.30).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>We recommend performing brachial plexus ceMRN 5 min after contrast injection. With this delay, the brachial plexus can be visualized optimally with minimal interference from background signals.</p>\u0000 </section>\u0000 </div>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 2","pages":"168-175"},"PeriodicalIF":0.0,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.120","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143861667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Biphasic Synovial Sarcoma in the Abdominal Cavity","authors":"Yubo Wang,&nbsp;Jiageng Li,&nbsp;Yang Fu,&nbsp;Bin Yang","doi":"10.1002/ird3.118","DOIUrl":"https://doi.org/10.1002/ird3.118","url":null,"abstract":"<p>A 63-year-old man was admitted to the hospital with a &gt; 1-year history of repeated acid reflux and belching and a 1-month history of an abdominal mass. On admission, the patient was in good condition, and his vital signs were stable. Laboratory examinations revealed no significant abnormalities. Abdominal computed tomography (CT) revealed a soft tissue mass with uneven density, measuring approximately 13.3 cm × 9.0 cm and extending from the right abdomen into the pelvic cavity. Enhanced CT showed mild uneven enhancement of the mass during the arterial phase, with significant wall enhancement and visible septa. Significant enhancement of the solid components within the mass was observed during the venous and delayed phases with a CT value of approximately 50.3 HU, indicating “progressive enhancement.” Curved blood vessels were visible around the mass, and the surrounding structures were compressed and displaced (Figure 1). During the operation, a tumor measuring approximately 15 cm × 10 cm was observed in the lower right retroperitoneum. It was tightly adhered to the small intestine, ascending colon, and greater omentum, and showed invasive growth. No metastasis was found in the liver, gallbladder, or stomach during the surgical exploration. The pathological diagnosis was synovial sarcoma (SS) with extensive necrosis. Immunohistochemistry revealed epithelial–mesenchymal biphasic differentiation of the tumor cells.</p><p>SS is a rare malignant soft tissue tumor originating from primitive mesenchymal cells. It most commonly affects the limb joints, particularly those of the lower limbs. Cases of SS arising from the abdominal cavity, especially involving the ascending colon and small intestine, are rare and prone to preoperative misdiagnosis. This case exhibited unique imaging features, including significant arterial phase enhancement of the tumor wall, consistent with progressive enhancement. Magnetic resonance imaging further revealed characteristic signs, such as the “triple signal sign,” “liquid–liquid plane,” and “grape bowl sign,” which can help differentiate SS from other abdominal tumors.</p><p><b>Yubo Wang:</b> writing–original draft (lead), resources (equal). <b>Jiageng Li:</b> writing–original draft (equal). <b>Yang Fu:</b> writing–original draft (equal). <b>Bin Yang:</b> resources (equal), writing–review and editing (lead).</p><p>The authors have nothing to report.</p><p>The patient provided written informed consent at the time of entering this study.</p><p>The authors declare no conflicts of interest.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 2","pages":"178-179"},"PeriodicalIF":0.0,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.118","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143861447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Imaging Features of Rare Ovarian Adenomyoma","authors":"Haitao Liu,&nbsp;Weishun Lan","doi":"10.1002/ird3.117","DOIUrl":"https://doi.org/10.1002/ird3.117","url":null,"abstract":"<p>A 42-year-old single woman presented to the Department of Gynecology with irregular vaginal bleeding with blood clots for the previous 2 months. She had no abdominal pain. Since the onset of symptoms, she had remained cheerful, and her general physical condition had not changed significantly. She reported no history of sexual activity, surgical procedures, or trauma. Tumor markers, including alpha-fetoprotein, carcinoembryonic antigen, CA19-9, and CA15-3, were within normal limits, with the exception of a mildly elevated serum CA125 concentration of 37.34 U/mL. All other laboratory tests returned normal results. Magnetic resonance imaging revealed a mass with both cystic and solid components in the left adnexal area. The mass was Grade 3 according to the Ovarian-Adnexal Reporting and Data System. Its features are shown in Figure 1. There was no evidence of invasion of the surrounding organs or retroperitoneal lymphadenopathy. The final pathological diagnosis was ovarian adenomyoma as evidenced by tubal metaplasia of the endometrium with some edema (Figure 2). The patient was discharged from the hospital in good condition after surgery.</p><p>Ovarian adenomyoma, a rare benign tumor of the female reproductive system, was first reported in 1981. The mechanism of the development of extrauterine adenomyomas is unclear. The main symptom of ovarian adenomyomas is abdominal pain, which may be related to endometriosis. The imaging features of ovarian myomas vary considerably, the differential diagnosis being granulosa cell tumor, fibrothecoma, and cystadenoma. The following features support a diagnosis of ovarian adenomyoma. First, the presence of endometriosis or a history of pelvic surgery, including cesarean section. Second, the solid component of the mass shows marked enhancement. Finally, the diffusion sequence of the mass is not limited.</p><p><b>Haitao Liu:</b> writing–original draft (Lead). <b>Weishun Lan:</b> writing–review and editing.</p><p>Approval from our institutional ethics committee was not required because this was a retrospective observational study.</p><p>The patient provided written informed consent at the time of entering this study.</p><p>The authors declare no conflicts of interest.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 2","pages":"176-177"},"PeriodicalIF":0.0,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.117","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143861749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Rare Case of Primary Intraparenchymal Rosai-Dorfman Disease","authors":"Lin Chen,&nbsp;Rui Zhou","doi":"10.1002/ird3.116","DOIUrl":"https://doi.org/10.1002/ird3.116","url":null,"abstract":"<p>A 16-year-old male teenager with no prior medical history suddenly experienced right upper limb weakness. The weakness persisted for 2 weeks, followed by a headache and unstable walking. On physical examination, the patient exhibited decreased verbal fluency, a shallow right nasolabial fold, and tongue movement to the right side. Reduced muscle strength with normal muscle tension was observed in the right limb. On laboratory examination, lymphocytes were decreased, and neutrophils were slightly increased. The patient underwent brain CT, MRI, and whole-body ¹⁸F-fluorodeoxyglucose PET/CT. Intracranial biopsy was performed to confirm the pathology (Figure 1). The final pathological diagnosis was the Rosai–Dorfman disease, characterized by abnormal hyperplasia of the sinuses combined with an accumulation of histiocytes in the lymph nodes. Although extranodal involvement has been reported, primary infiltration of the central nervous system is extremely rare, particularly in the brain parenchyma.</p><p><b>Lin Chen:</b> writing–original draft (equal). <b>Rui Zhou:</b> supervision (equal).</p><p>All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.</p><p>Informed consent was obtained from the participant.</p><p>The authors declare no conflicts of interest.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"370-371"},"PeriodicalIF":0.0,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.116","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145385148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incidental Finding of Deep Vein Thrombosis on Routine Knee Magnetic Resonance Imaging","authors":"Karoline Kant,&nbsp;Michael Facek,&nbsp;Craig Buchan","doi":"10.1002/ird3.119","DOIUrl":"https://doi.org/10.1002/ird3.119","url":null,"abstract":"<p>A 53 year old male presented to his local doctor with an acute knee injury, limited knee movement and a haemoarthrosis. Patient did not have calf tenderness or clinical suspicion for deep vein thrombosis (DVT). He was referred for a routine acute knee magnetic resonance imaging (MRI) scan. This MRI demonstrated a full thickness anterior cruciate ligament tear with additional findings, of a probable incidental DVT. The relevant MRI findings suggestive of DVT in this case included perivascular edema and expanded caliber of the involved medial gastronomical veins on the axial proton density fat suppressed sequence (Figure 1), increased intraluminal T1 signal within the involved segment of vein and susceptibility within the vein related to haemosiderin deposition/blood products on the gradient echo sequence. DVTs are rarely reported on MRI scans. Awareness of suspicious imaging findings for both radiologists and surgeons may aid in recognition of incidental DVTs and improve management.</p><p><b>Karoline Kant:</b> writing–original draft (equal). <b>Michael Facek:</b> writing–review &amp; editing (equal). <b>Craig Buchan:</b> conceptualization (equal), writing–review &amp; editing (equal).</p><p>The authors have nothing to report.</p><p>The patient has provided consent for publication of this image.</p><p>The authors declare no conflicts of interest.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 1","pages":"88-89"},"PeriodicalIF":0.0,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.119","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physician Attitudes About Ultrasound-Guided Procedures","authors":"Emma Barry,&nbsp;Sanyukta Deshmukh,&nbsp;Vivian Zhang,&nbsp;Antoan Koshar,&nbsp;Haider Butt,&nbsp;Kenneth Rowe,&nbsp;Siamak Moayedi","doi":"10.1002/ird3.114","DOIUrl":"https://doi.org/10.1002/ird3.114","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>We aimed to study physician attitudes toward ultrasound-guided procedures and possible improvements. We hypothesized that the usage of ultrasound in procedures may be limited by a high barrier of entry and that most physicians would choose to adopt software that provides real-time image guidance if accessible.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A voluntary, cross-sectional survey of physicians at a single site was conducted using a five-point Likert scale. Data analysis included both descriptive and inferential statistical analyses and stratified by categorical descriptors, including variables of formal training, years of experience, and specialty of practice.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>One hundred sixteen physicians responded to the survey. The majority disagreed that there was a steep learning curve (57.5%) and that they need more time to identify structures under ultrasound (85.0%). Overall attitudes were mixed about the use of additional software to improve ease of use, but most (55.4%) had positive opinions toward the addition of real-time 3D reconstruction. Respondents without formal training were significantly more likely to agree that additional software would improve ease of ultrasound-guided procedures (<i>p</i> = 0.0389). Radiologists were significantly more likely to perceive a steeper learning curve and less likely to advocate for supplemental software compared to emergency medicine physicians, surgeons, or anesthesiologists.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Surveyed physicians demonstrated comfort with ultrasound-guided procedures and a mixed stance toward the use of additional software to assist with procedures. Those without formal training had significantly more positive attitudes toward the use of additional technology to augment ultrasound-guided procedures, suggesting a knowledge gap that may benefit from such technology.</p>\u0000 </section>\u0000 </div>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 1","pages":"72-78"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.114","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Natural Language Processing for Chest X-Ray Reports in the Transformer Era: BERT-Like Encoders for Comprehension and GPT-Like Decoders for Generation","authors":"Han Yuan","doi":"10.1002/ird3.115","DOIUrl":"https://doi.org/10.1002/ird3.115","url":null,"abstract":"<p>We conducted a comprehensive literature search in PubMed to illustrate the current landscape of transformer-based tools from the perspective of transformer's two integral components: encoder exemplified by BERT and decoder characterized by GPT. Also, we discussed adoption barriers and potential solutions in terms of computational burdens, interpretability concerns, ethical issues, hallucination problems, malpractice, and legal liabilities. We hope that this commentary will serve as a foundational introduction for radiologists seeking to explore the evolving technical landscape of chest X-ray report analysis in the transformer era.\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 4","pages":"295-301"},"PeriodicalIF":0.0,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.115","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144909910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic Review of Phase Aberration Correction Algorithms for Transcranial Focused Ultrasound","authors":"Mingyu Wang,&nbsp;Zhouyang Xu,&nbsp;Bingbing Cheng","doi":"10.1002/ird3.112","DOIUrl":"https://doi.org/10.1002/ird3.112","url":null,"abstract":"<p>Transcranial focused ultrasound (tFUS) is an emerging modality with strong potential for non-invasively treating brain disorders. However, the inhomogeneity and complex structure of the skull induce substantial phase aberrations and pressure attenuation; these can distort and shift the acoustic focus, thus hindering the efficiency of tFUS therapy. To achieve effective treatments, phased array transducers combined with aberration correction algorithms are commonly implemented. The present report aims to provide a comprehensive review of the current methods used for tFUS phase aberration correction. We first searched the PubMed and Web of Science databases for studies on phase aberration correction algorithms, identifying 54 articles for review. Relevant information, including the principles of algorithms and refocusing performances, were then extracted from the selected articles. The phase correction algorithms involved two main steps: acoustic field estimation and transmitted pulse adjustment. Our review identified key benchmarks for evaluating the effectiveness of these algorithms, each of which was used in at least three studies. These benchmarks included pressure and intensity, positioning error, focal region size, peak sidelobe ratio, and computational efficiency. Algorithm performances varied under different benchmarks, thus highlighting the importance of application-specific algorithm selection for achieving optimal tFUS therapy outcomes. The present review provides a thorough overview and comparison of various phase correction algorithms, and may offer valuable guidance to tFUS researchers when selecting appropriate phase correction algorithms for specific applications.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 1","pages":"26-46"},"PeriodicalIF":0.0,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.112","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Anatomic Boundary-Aware Explanation for Convolutional Neural Networks in Diagnostic Radiology","authors":"Han Yuan","doi":"10.1002/ird3.113","DOIUrl":"https://doi.org/10.1002/ird3.113","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Convolutional neural networks (CNN) have achieved remarkable success in medical image analysis. However, unlike some general-domain tasks where model accuracy is paramount, medical applications demand both accuracy and explainability due to the high stakes affecting patients' lives. Based on model explanations, clinicians can evaluate the diagnostic decisions suggested by CNN. Nevertheless, prior explainable artificial intelligence methods treat medical image tasks akin to general vision tasks, following end-to-end paradigms to generate explanations and frequently overlooking crucial clinical domain knowledge.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We propose a plug-and-play module that explicitly integrates anatomic boundary information into the explanation process for CNN-based thoracopathy classifiers. To generate the anatomic boundary of the lung parenchyma, we utilize a lung segmentation model developed on external public datasets and deploy it on the unseen target dataset to constrain model explanations within the lung parenchyma for the clinical task of thoracopathy classification.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Assessed by the intersection over union and dice similarity coefficient between model-extracted explanations and expert-annotated lesion areas, our method consistently outperformed the baseline devoid of clinical domain knowledge in 71 out of 72 scenarios, encompassing 3 CNN architectures (VGG-11, ResNet-18, and AlexNet), 2 classification settings (binary and multi-label), 3 explanation methods (Saliency Map, Grad-CAM, and Integrated Gradients), and 4 co-occurred thoracic diseases (Atelectasis, Fracture, Mass, and Pneumothorax).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>We underscore the effectiveness of leveraging radiology knowledge in improving model explanations for CNN and envisage that it could inspire future efforts to integrate clinical domain knowledge into medical image analysis.</p>\u0000 </section>\u0000 </div>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 1","pages":"47-60"},"PeriodicalIF":0.0,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.113","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in medical imaging","authors":"Bin Huang,&nbsp;Bo Gao","doi":"10.1002/ird3.111","DOIUrl":"https://doi.org/10.1002/ird3.111","url":null,"abstract":"<p>With the rapid development of science and technology, the application of artificial intelligence (AI) in various fields is constantly expanding, especially in the field of medical imaging [<span>1</span>]. AI technology is suitable to be applied to standardized digital medical image big data based on digital imaging and communications in medicine protocol and picture archiving and communication system. With the integration of AI technology, this field is undergoing profound transformation, not only improving the accuracy and efficiency of diagnosis, but also significantly reducing the workload of doctors [<span>2</span>]. At present, AI is widely used in medical imaging, including risk modeling and stratification, personalized screening, diagnosis (including classification of molecular pathologic subtypes), treatment response prediction, prognosis prediction, image segmentation, and image quality control. AI can help doctors identify and analyze lesions in various medical images, especially in diseases such as lung, breast, and prostate cancer. The research mainly focuses on the identification of benign and malignant, the measurement of risk factors, prognosis judgment and treatment guidance, and it is increasingly being used in the field of psychoradiology [<span>3</span>]. In addition, AI is also focused on reducing image acquisition time and improving data quality. Through deep learning algorithms, AI can optimize imaging parameters, improve imaging quality, and reduce noise and artifacts.</p><p>This special issue of AI includes seven latest studies, which covers artificial intelligence of disease diagnosis and prediction, imaging technology model construction, image segmentation and quality control. Wang et al. [<span>4</span>] used systematic review to summarize the technical methods, clinical applications and existing problems of artificial intelligence in cerebrovascular diseases, they found that the availability of algorithms, reliability of validation, and consistency of evaluation metrics may facilitate better clinical applicability and acceptance. Zhu et al. [<span>5</span>] proposed a diffusion magnetic diffusion magnetic (dMRI) index reconstruction model based on deep learning methods-qIRR-Net and a training framework based on data enhancement and consistency loss, The reconstruction of dMRI index is realized without the influence of signal inhomogeneity, and the model validity is verified on simulated inhomogeneity data and real ultra-high field data, thus promoting the application of ultra-high field dMRI technology in medicine and clinic. Artificial intelligence-assisted compressed sensing is a deep learning technology based on convolutional neural networks which can reconstruct images with ultra-high resolution and reduce noise. On the premise of ensuring the quality of the image, the collection time of the sequence is greatly shortened. In this special issue, The application of assisted compressed sensing technology in 5T MRI","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"2 6","pages":"525-526"},"PeriodicalIF":0.0,"publicationDate":"2024-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.111","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143252565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}