Diagnostic and interventional radiology最新文献

{"title":"Burnout and the role of mentorship for radiology trainees and early career radiologists","authors":"Richard J Fagan, Dane Eskildsen, Tara Catanzano, Rachel Stanietzky, Serageldin Kamel, Mohamed Eltaher, Khaled M Elsayes","doi":"10.4274/dir.2024.242825","DOIUrl":"10.4274/dir.2024.242825","url":null,"abstract":"<p><p>Burnout is a widespread issue among physicians, including radiologists and radiology trainees. Long hours, isolation, and substantial stress levels contribute to healthcare workers experiencing a substantially higher rate of burnout compared with other professionals. Resident physicians, continuously exposed to stressors such as new clinical situations and performance feedback, are particularly susceptible. Mentorship has proven to be an effective strategy in mitigating burnout. Various mentorship delivery models exist, all aiming to have mentors serve as role models to mentees, thereby alleviating stress and anxiety. Physician groups and healthcare enterprises have actively implemented these programs, recognizing them as both successful and cost-effective. This article explores different mentorship models, their implementation processes, and the effectiveness of these programs as a standard component of academic departments.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141247644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparison of two artificial intelligence-based methods for assessing bone age in Turkish children: BoneXpert and VUNO Med-Bone Age.","authors":"Evrim Özmen, Hande Özen Atalay, Evren Uzer, Mert Veznikli","doi":"10.4274/dir.2024.242790","DOIUrl":"https://doi.org/10.4274/dir.2024.242790","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to evaluate the validity of two artificial intelligence (AI)-based bone age assessment programs, BoneXpert and VUNO Med-Bone Age (VUNO), compared with manual assessments using the Greulich-Pyle method in Turkish children.</p><p><strong>Methods: </strong>This study included a cohort of 292 pediatric cases, ranging in age from 1 to 15 years with an equal gender and number distribution in each age group. Two radiologists, who were unaware of the bone age determined by AI, independently evaluated the bone age. The statistical study involved using the intraclass correlation coefficient (ICC) to measure the level of agreement between the manual and AI-based assessments.</p><p><strong>Results: </strong>The ICC coefficients for the agreement between the manual measurements of two radiologists indicate almost perfect agreement. When all cases, regardless of gender and age group, were analyzed, a nearly perfect positive agreement was observed between the manual and software measurements. When bone age calculations were separated and analyzed separately for girls and boys, there was no statistically significant difference between the two AI-based methods for boys; however, ICC coefficients of 0.990 and 0.982 were calculated for VUNO and BoneXpert, respectively, and this difference of 0.008 was significant (<i>z</i> = 2.528, <i>P</i> = 0.012) for girls. Accordingly, VUNO showed higher agreement with manual measurements compared with BoneXpert. The difference between the agreements demonstrated by the two software packages with manual measurements in the prepubescent group was much more pronounced in girls compared with boys. After the age of 8 years for girls and 9 years for boys, the agreement between manual measurements and both AI software packages was equal.</p><p><strong>Conclusion: </strong>Both BoneXpert and VUNO showed high validity in assessing bone age. Furthermore, VUNO has a statistically higher correlation with manual assessment in prepubertal girls. These results suggest that VUNO may be slightly more effective in determining bone age, indicating its potential as a highly reliable tool for bone age assessment in Turkish children.</p><p><strong>Clinical significance: </strong>Investigating the most suitable AI program for the Turkish population could be clinically significant.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142105422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feasibility study of computed high b-value diffusion-weighted magnetic resonance imaging for pediatric posterior fossa tumors.","authors":"Semra Delibalta, Barış Genç, Meltem Ceyhan Bilgici, Kerim Aslan","doi":"10.4274/dir.2024.242720","DOIUrl":"https://doi.org/10.4274/dir.2024.242720","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the diagnostic efficacy of computed diffusion-weighted imaging (DWI) in pediatric posterior fossa tumors generated using high b-values.</p><p><strong>Methods: </strong>We retrospectively performed our study on 32 pediatric patients who had undergone brain magnetic resonance imaging for a posterior fossa tumor between January 2016 and January 2022. The DWIs were evaluated for each patient by two blinded radiologists. The computed DWI (cDWI) was mathematically derived using a mono-exponential model from images with b = 0 and 1,000 s/mm² and high b-values of 1,500, 2,000, 3,000, and 5,000 s/mm². The posterior fossa tumors were divided into two groups, low grade and high grade, and the tumor/thalamus signal intensity (SI) ratios were compared. The Mann-Whitney U test and receiver operating characteristic (ROC) curves were used to compare the diagnostic performance of the acquired DWI (DWI₁₀₀₀), apparent diffusion coefficient (ADC)₁₀₀₀ maps, and cDWI (cDWI1500, cDWI₂₀₀₀, cDWI₃₀₀₀, and cDWI₅₀₀₀).</p><p><strong>Results: </strong>The comparison of the two tumor groups revealed that the tumor/thalamus SI ratio on the DWI₁₀₀₀ and cDWI (cDWI1500, cDWI₂₀₀₀, cDWI₃₀₀₀, and cDWI₅₀₀₀) was statistically significantly higher in high-grade tumors (<i>P</i> < 0.001). In the ROC curve analysis, higher sensitivity and specificity were detected in the cDWI1500, cDWI₂₀₀₀, cDWI₃₀₀₀, and ADC₁₀₀₀ maps (100%, 90.90%) compared with the DWI₁₀₀₀ (80%, 81.80%). cDWI₃₀₀₀ had the highest area under the curve (AUC) value compared with other parameters (AUC: 0.976).</p><p><strong>Conclusion: </strong>cDWI generated using high b-values was successful in differentiating between low-grade and high-grade posterior fossa tumors without increasing imaging time.</p><p><strong>Clinical significance: </strong>cDWI created using high b-values can provide additional information about tumor grade in pediatric posterior fossa tumors without requiring additional imaging time.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142105425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A retrospective evaluation of the potential of ChatGPT in the accurate diagnosis of acute stroke.","authors":"Beyza Nur Kuzan, İsmail Meşe, Servan Yaşar, Taha Yusuf Kuzan","doi":"10.4274/dir.2024.242892","DOIUrl":"https://doi.org/10.4274/dir.2024.242892","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;Stroke is a neurological emergency requiring rapid, accurate diagnosis to prevent severe consequences. Early diagnosis is crucial for reducing morbidity and mortality. Artificial intelligence (AI) diagnosis support tools, such as Chat Generative Pre-trained Transformer (ChatGPT), offer rapid diagnostic advantages. This study assesses ChatGPT's accuracy in interpreting diffusion-weighted imaging (DWI) for acute stroke diagnosis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A retrospective analysis was conducted to identify the presence of stroke using DWI and apparent diffusion coefficient (ADC) map images. Patients aged &gt;18 years who exhibited diffusion restriction and had a clinically explainable condition were included in the study. Patients with artifacts that affected image homogeneity, accuracy, and clarity, as well as those who had undergone previous surgery or had a history of stroke, were excluded from the study. ChatGPT was asked four consecutive questions regarding the identification of the magnetic resonance imaging (MRI) sequence, the demonstration of diffusion restriction on the ADC map after sequence recognition, and the identification of hemispheres and specific lobes. Each question was repeated 10 times to ensure consistency. Senior radiologists subsequently verified the accuracy of ChatGPT's responses, classifying them as either correct or incorrect. We assumed a response to be incorrect if it was partially correct or suggested multiple answers. These responses were systematically recorded. We also recorded non-responses from ChatGPT-4V when it failed to provide an answer to a query. We assessed ChatGPT-4V's performance by calculating the number and percentage of correct responses, incorrect responses, and non-responses across all images and questions, a metric known as \"accuracy.\" ChatGPT-4V was considered successful if it answered ≥80% of the examples correctly.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 530 diffusion MRI, of which 266 were stroke images and 264 were normal, were evaluated in the study. For the initial query identifying MRI sequence type, ChatGPT-4V's accuracy was 88.3% for stroke and 90.1% for normal images. For detecting diffusion restriction, ChatGPT-4V had an accuracy of 79.5% for stroke images, with a 15% false positive rate for normal images. Regarding identifying the brain or cerebellar hemisphere involved, ChatGPT-4V correctly identified the hemisphere in 26.2% of stroke images. For identifying the specific brain lobe or cerebellar area affected, ChatGPT-4V had a 20.4% accuracy for stroke images. The diagnostic sensitivity of ChatGPT-4V in acute stroke was found to be 79.57%, with a specificity of 84.87%, a positive predictive value of 83.86%, a negative predictive value of 80.80%, and a diagnostic odds ratio of 21.86.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;Despite limitations, ChatGPT shows potential as a supportive tool for healthcare professionals in interpreting diffusion examinations in","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142105423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quadratus lumborum block for procedural and postprocedural analgesia in renal cell carcinoma percutaneous cryoablation.","authors":"Saman Fouladirad, Jasper Yoo, Behrang Homayoon, Jun Wang, Pedro Lourenço","doi":"10.4274/dir.2024.232100","DOIUrl":"https://doi.org/10.4274/dir.2024.232100","url":null,"abstract":"<p><p>This study assesses the efficacy of the quadratus lumborum block (QLB) in the management of procedural and periprocedural pain associated with small renal mass cryoablation. To the best of our knowledge, this is the first study that examines the use of QLB for pain management during percutaneous cryoablation of renal cell carcinoma (RCC). A single-center retrospective review was conducted for patients who underwent cryoablation for RCC with QLB between October 2020 and October 2021. The primary study endpoint included a total dose of procedural conscious sedation and administered, postprocedural analgesia. Technical success in cryoablation was achieved in every case. No patients required additional analgesic during or after the procedure, and no complications resulted from the use of the QLB. The QLB procedure appears to be an effective locoregional block for the management of procedural and periprocedural pain associated with renal mass cryoablation.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142105426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of guided reporting: quality and reading time of automatically generated radiology report in breast magnetic resonance imaging using a dedicated software solution.","authors":"Martin H Maurer, Daniel Lorenz, Maximilian Clemens Otterbach, Igor Toker, Alexander Huppertz","doi":"10.4274/dir.2024.242702","DOIUrl":"https://doi.org/10.4274/dir.2024.242702","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;Unstructured, free-text dictation (FT), the current standard in breast magnetic resonance imaging (MRI) reporting, is considered time-consuming and prone to error. The purpose of this study is to assess the usability and performance of a novel, software-based guided reporting (GR) strategy in breast MRI.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Eighty examinations previously evaluated for a clinical indication (e.g., mass and focus/non-mass enhancement) with FT were reevaluated by three specialized radiologists using GR. Each radiologist had a different number of cases (R1, n = 24; R2, n = 20; R3, n = 36). Usability was assessed by subjective feedback, and quality was assessed by comparing the completeness of automatically generated GR reports with that of their FT counterparts. Errors in GR were categorized and analyzed for debugging with a final software version. Combined reading and reporting times and learning curves were analyzed.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Usability was rated high by all readers. No non-sense, omission/commission, or translational errors were detected with the GR method. Spelling and grammar errors were observed in 3/80 patient reports (3.8%) with GR (exclusively in the discussion section) and in 36/80 patient reports (45%) with FT. Between FT and GR, 41 patient reports revealed no content differences, 33 revealed minor differences, and 6 revealed major differences that resulted in changes in treatment. The errors in all patient reports with major content differences were categorized as content omission errors caused by improper software operation (n = 2) or by missing content in software v. 0.8 displayable with v. 1.7 (n = 4). The mean combined reading and reporting time was 576 s (standard deviation: 327 s; min: 155 s; max: 1,517 s). The mean times for each reader were 485, 557, and 754 s, and the respective learning curves evaluated by regression models revealed statistically significant slopes (&lt;i&gt;P&lt;/i&gt; = 0.002; &lt;i&gt;P&lt;/i&gt; = 0.0002; &lt;i&gt;P&lt;/i&gt; &lt; 0.0001). Overall times were shorter compared with external references that used FT. The mean combined reading and reporting time of MRI examinations using FT was 1,043 s and decreased by 44.8% with GR.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;GR allows for complete reporting with minimized error rates and reduced combined reading and reporting times. The streamlining of the process (evidenced by lower reading times) for the readers in this study proves that GR can be learned quickly. Reducing reporting errors leads to fewer therapeutic faults and lawsuits against radiologists. It is known that delays in radiology reporting hinder early treatment and lead to poorer patient outcomes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Clinical significance: &lt;/strong&gt;While the number of scans and images per examination is continuously rising, staff shortages create a bottleneck in radiology departments. The IT-based GR method can be a major boon, improving radiologist efficiency, report quality, and the ","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142105424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Short-term outcomes of the iCover balloon-expandable covered stent for iliac artery lesions.","authors":"Murat Canyiğit, Muhammed Said Beşler","doi":"10.4274/dir.2024.242868","DOIUrl":"https://doi.org/10.4274/dir.2024.242868","url":null,"abstract":"<p><strong>Purpose: </strong>To describe the short-term follow-up results of the recently introduced iCover balloon-expandable covered stents for iliac artery lesions.</p><p><strong>Methods: </strong>All consecutive patients treated with iCover balloon-expandable covered stents between March 2022 and August 2023 were retrospectively reviewed. The primary endpoint was target lesion revascularization (TLR) at 6 months. Secondary endpoints included major adverse events, freedom from TLR throughout the follow-up period, primary and secondary patency, and clinical and technical success.</p><p><strong>Results: </strong>In the study population of 40 adult patients (87.5% men, mean age: 63.5 ± 11 years), the mean follow-up period was 6.2 ± 2.8 months. A total of 98 stents of various sizes were implanted. The technical success rate was 100%. Freedom from TLR was 95.8% [95%, confidence interval (CI): 95%- 96.6%], the primary patency rate was 91.7% (95%, CI: 89.8%-93.6%), and the secondary patency rate was 95.8% (95%, CI: 95%-96.6%) at 6 months. The all-cause mortality rate was 5%.</p><p><strong>Conclusion: </strong>These real-world data demonstrate a high technical and clinical success rate, a high 6-month primary patency rate, and a low requirement for TLR. These are promising indicators for the safety and efficacy of iCover stents.</p><p><strong>Clinical significance: </strong>Balloon-expandable covered stents are frequently used in iliac artery atherosclerotic disease. This study shows that the short-term follow-up results of the new iCover stent are satisfactory, indicating its safety and efficacy.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141999604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in musculoskeletal applications: a primer for radiologists.","authors":"Michelle W Tong, Jiamin Zhou, Zehra Akkaya, Sharmila Majumdar, Rupsa Bhattacharjee","doi":"10.4274/dir.2024.242830","DOIUrl":"https://doi.org/10.4274/dir.2024.242830","url":null,"abstract":"<p><p>As an umbrella term, artificial intelligence (AI) covers machine learning and deep learning. This review aimed to elaborate on these terms to act as a primer for radiologists to learn more about the algorithms commonly used in musculoskeletal radiology. It also aimed to familiarize them with the common practices and issues in the use of AI in this domain.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141999601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of synovial inflammation in the sacroiliac joint space through intravoxel incoherent motion imaging: an alternative to contrast agents.","authors":"Murat Ağırlar, Barış Genç, Aysu Başak Özbalcı","doi":"10.4274/dir.2024.242749","DOIUrl":"https://doi.org/10.4274/dir.2024.242749","url":null,"abstract":"<p><strong>Purpose: </strong>We investigated the diagnostic accuracy of simplified intravoxel incoherent motion (IVIM) imaging for detecting synovial inflammation in the sacroiliac joint (SIJ) in a population with active sacroiliitis.</p><p><strong>Methods: </strong>In accordance with the Assessment of Spondyloarthritis International Society criteria, 86 SIJs of 46 patients with active sacroiliitis were included in this retrospective study conducted between November 2020 and January 2022. Based on T1-weighted post-gadolinium images, the SIJs were divided into two groups: synovial inflammation positive (SIP) (n = 28) and synovial inflammation negative (SIN) (n = 58). Synovial areas in the SIJ space were independently and blindly reviewed for the presence of inflammation by two radiologists with differing levels of expertise in radiology. Using four b values, apparent diffusion coefficient (ADC)= ADC (0, 800) and the simplified 3T IVIM method parameters true diffusion coefficient (D₁)= ADC (50, 800), D= ADC (400, 800), f₁= f (0, 50, 800), f₂= f (0, 400, 800), pseudodiffusion coefficient (D*)= D* (0, 50, 400, 800), ADC_low = ADC (0, 50), and ADC_diff= ADC_low - D were generated voxel by voxel for each patient. The IVIM and ADC parameters at the SIN and SIP joints were compared.</p><p><strong>Results: </strong>The D parameter was significantly increased in SIP areas (1.23 ± 0.34 × 10^-3 mm²/s) compared with SIN areas (1.02 ± 0.16 × 10^-3 mm²/s) (<i>P</i> = 0.004). Conversely, the D* parameter was significantly decreased in SIP areas (21.78 ± 3.77 × 10^-3 mm²/s) compared with SIN areas (16.19 ± 4.58 × 10^-3 mm²/s) (<i>P</i> < 0.001). When the optimal cut-off value of 1.11 × 10^-3 mm²/s was selected, the sensitivity for the D value was 71% and the specificity was 72% [area under the curve (AUC): 0.716)]. When the optimal cut-off value of 21.06 × 10^-3 mm²/s was selected, the sensitivity for the D* value was 78.6%, and the specificity was 79.3% (AUC: 0.829). The interclass correlation coefficient was excellent for f₁, f₂ D*, D, and ADC_diff, good for ADC_low and D₁, but reasonable for ADC.</p><p><strong>Conclusion: </strong>The presence of synovial inflammation in the SIJ can be evaluated with high sensitivity and specificity using only four b values through the simplified IVIM method without the need for a contrast agent.</p><p><strong>Clinical significance: </strong>IVIM imaging is a technique that allows us to gain insights into tissue perfusion without the administration of contrast agents, utilizing diffusion-weighted images. In this study, for the first time, we demonstrated the potential of detecting synovial inflammation in the SIJ using IVIM, specifically through the pseudodiffusion (D*) parameter, without ","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141999602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images.","authors":"Alperen Elek, Duygu Doğa Ekizalioğlu, Ezgi Güler","doi":"10.4274/dir.2024.232680","DOIUrl":"https://doi.org/10.4274/dir.2024.232680","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the performance of Microsoft Bing with ChatGPT-4 technology in analyzing abdominal computed tomography (CT) and magnetic resonance images (MRI).</p><p><strong>Methods: </strong>A comparative and descriptive analysis was conducted using the institutional picture archiving and communication systems. A total of 80 abdominal images (44 CT, 36 MRI) that showed various entities affecting the abdominal structures were included. Microsoft Bing's interpretations were compared with the impressions of radiologists in terms of recognition of the imaging modality, identification of the imaging planes (axial, coronal, and sagittal), sequences (in the case of MRI), contrast media administration, correct identification of the anatomical region depicted in the image, and detection of abnormalities.</p><p><strong>Results: </strong>Microsoft Bing detected that the images were CT scans with 95.4% accuracy (42/44) and that the images were MRI scans with 86.1% accuracy (31/36). However, it failed to detect one CT image (2.3%) and misidentified another CT image as an MRI (2.3%). On the other hand, it also misidentified four MRI as CT images (11.1%) and one as an X-ray (2.7%). Bing achieved an 83.75% success rate in correctly identifying abdominal regions, with 90% accuracy for CT scans (40/44) and 77.7% for MRI scans (28/36). Concerning the identification of imaging planes, Bing achieved a success rate of 95.4% for CT images and 83.3% for MRI. Regarding the identification of MRI sequences (T1-weighted and T2-weighted), the success rate was 68.75%. In the identification of the use of contrast media for CT scans, the success rate was 64.2%. Bing detected abnormalities in 35% of the images but achieved a correct interpretation rate of 10.7% for the definite diagnosis.</p><p><strong>Conclusion: </strong>While Microsoft Bing, leveraging ChatGPT-4 technology, demonstrates proficiency in basic task identification on abdominal CT and MRI, its inability to reliably interpret abnormalities highlights the need for continued refinement to enhance its clinical applicability.</p><p><strong>Clinical significance: </strong>The contribution of large language models (LLMs) to the diagnostic process in radiology is still being explored. However, with a comprehensive understanding of their capabilities and limitations, LLMs can significantly support radiologists during diagnosis and improve the overall efficiency of abdominal radiology practices. Acknowledging the limitations of current studies related to ChatGPT in this field, our work provides a foundation for future clinical research, paving the way for more integrated and effective diagnostic tools.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141999603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}