Diagnostic and interventional radiology最新文献

{"title":"Automatic machine learning accurately predicts the efficacy of immunotherapy for patients with inoperable advanced non-small cell lung cancer using a computed tomography-based radiomics model.","authors":"Siyun Lin, Zhuangxuan Ma, Yuanshan Yao, Hou Huang, Wufei Chen, Dongfang Tang, Wen Gao","doi":"10.4274/dir.2024.242972","DOIUrl":"10.4274/dir.2024.242972","url":null,"abstract":"<p><strong>Purpose: </strong>Patients with advanced non-small cell lung cancer (NSCLC) have varying responses to immunotherapy, but there are no reliable, accepted biomarkers to accurately predict its therapeutic efficacy. The present study aimed to construct individualized models through automatic machine learning (autoML) to predict the efficacy of immunotherapy in patients with inoperable advanced NSCLC.</p><p><strong>Methods: </strong>A total of 63 eligible participants were included and randomized into training and validation groups. Radiomics features were extracted from the volumes of interest of the tumor circled in the preprocessed computed tomography (CT) images. Golden feature, clinical, radiomics, and fusion models were generated using a combination of various algorithms through autoML. The models were evaluated using a multi-class receiver operating characteristic curve.</p><p><strong>Results: </strong>In total, 1,219 radiomics features were extracted from regions of interest. The ensemble algorithm demonstrated superior performance in model construction. In the training cohort, the fusion model exhibited the highest accuracy at 0.84, with an area under the curve (AUC) of 0.89-0.98. In the validation cohort, the radiomics model had the highest accuracy at 0.89, with an AUC of 0.98-1.00; its prediction performance in the partial response subgroup outperformed that in both the clinical and radiomics models. Patients with low rad scores achieved improved progression-free survival (PFS); (median PFS 16.2 vs. 13.4, <i>P</i> = 0.009).</p><p><strong>Conclusion: </strong>autoML accurately and robustly predicted the short-term outcomes of patients with inoperable NSCLC treated with immune checkpoint inhibitor immunotherapy by constructing CT-based radiomics models, confirming it as a powerful tool to assist in the individualized management of patients with advanced NSCLC.</p><p><strong>Clinical significance: </strong>This article highlights that autoML promotes the accuracy and efficiency of feature selection and model construction. The radiomics model generated by autoML predicted the efficacy of immunotherapy in patients with advanced NSCLC effectively. This may provide a rapid and non-invasive method for making personalized clinical decisions.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"130-140"},"PeriodicalIF":1.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880869/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143001883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hepatic arterial infusion chemotherapy combined with toripalimab and surufatinib for the treatment of advanced intrahepatic cholangiocarcinoma.","authors":"Songlin Song, Yiming Liu, Yanqiao Ren, Chuansheng Zheng, Bin Liang","doi":"10.4274/dir.2024.242673","DOIUrl":"10.4274/dir.2024.242673","url":null,"abstract":"<p><strong>Purpose: </strong>The aim of the present study is to report the clinical results of patients with advanced intrahepatic cholangiocarcinoma (ICC) who received combination therapy of hepatic arterial infusion chemotherapy (HAIC), toripalimab and surufatinib.</p><p><strong>Methods: </strong>The study cohort consisted of 28 patients with advanced ICC who were treated with HAIC (mFOLFOX6 regimen, Q3W) in combination with intravenous toripalimab (240 mg, Q3W) and oral surufatinib (150 mg, once daily). The cohort had 14 male and 14 female patients. The baseline characteristics of the study cohort were obtained. The tumor response and drug-associated toxicity were assessed and reported.</p><p><strong>Results: </strong>During the follow-up period (median follow-up time: 11.3 months; range: 4-19 months), four patients died of tumor progression. The objective response rate and disease control rate were 58% and 79%, respectively. The mPFS was 9.5 months, and the overall survival rate was 83.3%. The most frequent adverse events were nausea and vomiting (100%) and abdominal pain (85.7%). Serious complications related to death were not observed.</p><p><strong>Conclusion: </strong>The combination treatment schedule for advanced ICC demonstrated positive efficacy and safety profiles.</p><p><strong>Clinical significance: </strong>This study provides promising clinical guidance for the treatment of advanced cholangiocarcinoma and is expected to modify the treatment strategy for this disease.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"145-151"},"PeriodicalIF":1.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880864/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141247614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Single-center 10-year retrospective analysis of Amplatzer Vascular Plug 4 embolization for pulmonary arteriovenous malformations with feeding arteries of <6 mm","authors":"Jung Guen Cha, Jongmin Park, Byunggeon Park, Seo Young Park, So Mi Lee, Jihoon Hong","doi":"10.4274/dir.2024.242732","DOIUrl":"10.4274/dir.2024.242732","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the efficacy and safety of Amplatzer Vascular Plug 4 (AVP4) embolization in pulmonary arteriovenous malformations (PAVMs) with small- to medium-sized feeding arteries (<6 mm) and to identify factors affecting persistence and the main persistence patterns after embolization.</p><p><strong>Methods: </strong>Between June 2013 and February 2023, we retrospectively reviewed 100 patients with 217 treated PAVMs. We included PAVMs with feeding arteries <6 mm, treated with AVP4 embolization, and followed adequately with computed tomography (CT). Technical success was defined as flow cessation observed on angiography. Persistence was defined as less than a 70% reduction of the venous sac on CT. We evaluated adverse events for each embolization session. Patterns of persistence were assessed using follow-up angiography. Univariate and multivariate analyses were performed to evaluate factors affecting persistence based on the 70% CT criteria.</p><p><strong>Results: </strong>Fifty-one patients (48 women, 3 men; mean age: 50.8 years; age range: 16-71 years) with 103 PAVMs met the inclusion criteria. The technical success rate was 100%. The persistence rate was 9.7% (10/103), and the overall adverse event rate was 2.9% (3/103) during a mean follow-up of 556 days (range: 181-3,542 days). In two cases, the persistence pattern confirmed by follow-up angiography involved reperfusion via adjacent pulmonary artery collaterals. The location of embolization relative to the last normal branch of the pulmonary artery was the only factor substantially affecting persistence.</p><p><strong>Conclusion: </strong>Embolization with AVP4 appears to be safe and effective for small- to medium-sized PAVMs. The location of the embolization relative to the last normal branch of the pulmonary artery was found to be the main determinant of persistence.</p><p><strong>Clinical significance: </strong>Given the increasing demand for the treatment of small PAVMs, AVP4 embolization could be considered a viable and effective option for managing PAVMs with feeding arteries <6 mm.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"152-160"},"PeriodicalIF":1.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880865/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141247684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects.","authors":"Burak Koçak, Andrea Ponsiglione, Arnaldo Stanzione, Christian Bluethgen, João Santinha, Lorenzo Ugga, Merel Huisman, Michail E Klontzas, Roberto Cannella, Renato Cuocolo","doi":"10.4274/dir.2024.242854","DOIUrl":"10.4274/dir.2024.242854","url":null,"abstract":"<p><p>Although artificial intelligence (AI) methods hold promise for medical imaging-based prediction tasks, their integration into medical practice may present a double-edged sword due to bias (i.e., systematic errors). AI algorithms have the potential to mitigate cognitive biases in human interpretation, but extensive research has highlighted the tendency of AI systems to internalize biases within their model. This fact, whether intentional or not, may ultimately lead to unintentional consequences in the clinical setting, potentially compromising patient outcomes. This concern is particularly important in medical imaging, where AI has been more progressively and widely embraced than any other medical field. A comprehensive understanding of bias at each stage of the AI pipeline is therefore essential to contribute to developing AI solutions that are not only less biased but also widely applicable. This international collaborative review effort aims to increase awareness within the medical imaging community about the importance of proactively identifying and addressing AI bias to prevent its negative consequences from being realized later. The authors began with the fundamentals of bias by explaining its different definitions and delineating various potential sources. Strategies for detecting and identifying bias were then outlined, followed by a review of techniques for its avoidance and mitigation. Moreover, ethical dimensions, challenges encountered, and prospects were discussed.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"75-88"},"PeriodicalIF":1.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880872/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141491311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unusual liver tumors: spectrum of imaging findings with pathologic correlation","authors":"Nir Stanietzky, Ahmed Ebada Salem, Khaled M Elsayes, Maryam Rezvani, Sarah Palmquist, Imran Ahmed, Ahmed Marey, Silvana Faria, Ayman H Gaballah, Christine O Menias, Akram M Shaaban","doi":"10.4274/dir.2024.242827","DOIUrl":"10.4274/dir.2024.242827","url":null,"abstract":"<p><p>The liver is a common location for both primary and secondary cancers of the abdomen. Radiologists become familiar with the typical imaging features of common benign and malignant liver tumors; however, many types of liver tumors are encountered infrequently. Due to the rarity of these lesions, their typical imaging patterns may not be easily recognized, meaning their underlying pathologic features may not be discovered or suggested until an invasive biopsy is performed. In this review article, we discuss multiple hepatic neoplasms that are both unusual and rare. Some have typical imaging patterns, whereas others are non-specific and can only be included in the differential diagnosis. The clinical history and serologic findings are often critical in suggesting these entities; therefore, these are also discussed to familiarize the radiologist with the appropriate clinical setting of each. The article includes an image-rich description of each entity with accompanying figures describing the ultrasonography, computed tomography, and magnetic resonance imaging features of each disease process. Novel therapies and prognosis of several of the diseases are also included in the discussion.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"58-67"},"PeriodicalIF":1.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880871/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141295738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence system for identification of overlooked lung metastasis in abdominopelvic computed tomography scans of patients with malignancy.","authors":"Hye Soo Cho, Eui Jin Hwang, Jaeyoun Yi, Boorym Choi, Chang Min Park","doi":"10.4274/dir.2024.242835","DOIUrl":"10.4274/dir.2024.242835","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to evaluate whether an artificial intelligence (AI) system can identify basal lung metastatic nodules examined using abdominopelvic computed tomography (CT) that were initially overlooked by radiologists.</p><p><strong>Methods: </strong>We retrospectively included abdominopelvic CT images with the following inclusion criteria: a) CT images from patients with solid organ malignancies between March 1 and March 31, 2019, in a single institution; and b) abdominal CT images interpreted as negative for basal lung metastases. Reference standards for diagnosis of lung metastases were confirmed by reviewing medical records and subsequent CT images. An AI system that could automatically detect lung nodules on CT images was applied retrospectively. A radiologist reviewed the AI detection results to classify them as lesions with the possibility of metastasis or clearly benign. The performance of the initial AI results and the radiologist's review of the AI results were evaluated using patient-level and lesion-level sensitivities, false-positive rates, and the number of false-positive lesions per patient.</p><p><strong>Results: </strong>A total of 878 patients (580 men; mean age, 63 years) were included, with overlooked basal lung metastases confirmed in 13 patients (1.5%). The AI exhibited an area under the receiver operating characteristic curve value of 0.911 for the identification of overlooked basal lung metastases. Patient- and lesion-level sensitivities of the AI system ranged from 69.2% to 92.3% and 46.2% to 92.3%, respectively. After a radiologist reviewed the AI results, the sensitivity remained unchanged. The false-positive rate and number of false-positive lesions per patient ranged from 5.8% to 27.6% and 0.1% to 0.5%, respectively. Radiologist reviews significantly reduced the false-positive rate (2.4%-12.6%; all <i>P</i> values < 0.001) and the number of false-positive lesions detected per patient (0.03-0.20, respectively).</p><p><strong>Conclusion: </strong>The AI system could accurately identify basal lung metastases detected in abdominopelvic CT images that were overlooked by radiologists, suggesting its potential as a tool for radiologist interpretation.</p><p><strong>Clinical significance: </strong>The AI system can identify missed basal lung lesions in abdominopelvic CT scans in patients with malignancy, providing feedback to radiologists, which can reduce the risk of missing basal lung metastasis.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"102-110"},"PeriodicalIF":1.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880870/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142153439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transperineal microwave thermoablation for benign prostatic hyperplasia-related lower urinary tract symptoms in an elderly patient.","authors":"Yaşar Türk, İsmail Devecioğlu, Nusret Can Çilesiz, Barış Nuhoğlu","doi":"10.4274/dir.2024.232639","DOIUrl":"10.4274/dir.2024.232639","url":null,"abstract":"<p><p>Transperineal prostate microwave thermoablation (TPMT) has been established as a safe means of treating benign prostatic hyperplasia (BPH); however, its effectiveness in addressing BPH-related lower urinary tract symptoms (LUTS) remains unexplored. This case study aims to evaluate the efficacy of TPMT in LUTS attributed to BPH. An 84-year-old man with LUTS due to BPH-induced bladder outlet obstruction, unresponsive to previous medical treatments, and failed prostate artery embolization, underwent TPMT. Three coaxial needles were positioned at the midline, right, and left sides of the hypertrophic transitional zone of the prostate. Microwave energy, with parameters determined using liver data and targeted ablation area, was applied at 2,450 MHz in continuous mode. The tissue temperature was monitored using bilateral thermocouple sensors. The patient exhibited no changes in defecation rhythm, abdominal discomfort, or anorectal pain. Temporary postoperative hematuria was promptly resolved through saline irrigation within 6 hours, and hematological evaluations showed normal results. Significant clinical improvements were observed (e.g., prostate volume, prostate-specific antigen levels) accompanied by an increase in peak flow rate. Thus, TPMT appears to be a promising intervention for bladder outlet stenosis and LUTS induced by BPH.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"141-145"},"PeriodicalIF":1.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880868/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139989598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning for named entity recognition in Turkish radiology reports.","authors":"Abubakar Ahmad Abdullahi, Murat Can Ganiz, Ural Koç, Muhammet Batuhan Gökhan, Ceren Aydın, Ali Bahadır Özdemir","doi":"10.4274/dir.2025.243100","DOIUrl":"https://doi.org/10.4274/dir.2025.243100","url":null,"abstract":"<p><strong>Purpose: </strong>The primary objective of this research is to enhance the accuracy and efficiency of information extraction from radiology reports. In addressing this objective, the study aims to develop and evaluate a deep learning framework for named entity recognition (NER).</p><p><strong>Methods: </strong>We used a synthetic dataset of 1,056 Turkish radiology reports created and labeled by the radiologists in our research team. Due to privacy concerns, actual patient data could not be used; however, the synthetic reports closely mimic genuine reports in structure and content. We employed the four-stage DYGIE++ model for the experiments. First, we performed token encoding using four bidirectional encoder representations from transformers (BERT) models: BERTurk, BioBERTurk, PubMedBERT, and XLM-RoBERTa. Second, we introduced adaptive span enumeration, considering the word count of a sentence in Turkish. Third, we adopted span graph propagation to generate a multidirectional graph crucial for coreference resolution. Finally, we used a two-layered feed-forward neural network to classify the named entity.</p><p><strong>Results: </strong>The experiments conducted on the labeled dataset showcase the approach's effectiveness. The study achieved an F1 score of 80.1 for the NER task, with the BioBERTurk model, which is pre-trained on Turkish Wikipedia, radiology reports, and biomedical texts, proving to be the most effective of the four BERT models used in the experiment.</p><p><strong>Conclusion: </strong>We show how different dataset labels affect the model's performance. The results demonstrate the model's ability to handle the intricacies of Turkish radiology reports, providing a detailed analysis of precision, recall, and F1 scores for each label. Additionally, this study compares its findings with related research in other languages.</p><p><strong>Clinical significance: </strong>Our approach provides clinicians with more precise and comprehensive insights to improve patient care by extracting relevant information from radiology reports. This innovation in information extraction streamlines the diagnostic process and helps expedite patient treatment decisions.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143523020","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":"Diagnostic accuracy of convolutional neural network algorithms to distinguish gastrointestinal obstruction on conventional radiographs in a pediatric population.","authors":"Ercan Ayaz, Hasan Güçlü, Ayşe Betül Oktay","doi":"10.4274/dir.2025.242950","DOIUrl":"https://doi.org/10.4274/dir.2025.242950","url":null,"abstract":"<p><strong>Purpose: </strong>Gastrointestinal (GI) dilatations are frequently observed in radiographs of pediatric patients who visit emergency departments with acute symptoms such as vomiting, pain, constipation, or diarrhea. Timely and accurate differentiation of whether there is an obstruction requiring surgery in these patients is crucial to prevent complications such as necrosis and perforation, which can lead to death. In this study, we aimed to use convolutional neural network (CNN) models to differentiate healthy children with normal intestinal gas distribution in abdominal radiographs from those with GI dilatation or obstruction. We also aimed to distinguish patients with obstruction requiring surgery and those with other GI dilatation or ileus.</p><p><strong>Methods: </strong>Abdominal radiographs of patients with a surgical, clinical, and/or laboratory diagnosis of GI diseases with GI dilatation were retrieved from our institution's Picture Archiving and Communication System archive. Additionally, abdominal radiographs performed to detect abnormalities other than GI disorders were collected to form a control group. The images were labeled with three tags according to their groups: surgically-corrected dilatation (SD), inflammatory/infectious dilatation (ID), and normal. To determine the impact of standardizing the imaging area on the model's performance, an additional dataset was created by applying an automated cropping process. Five CNN models with proven success in image analysis (ResNet50, InceptionResNetV2, Xception, EfficientNetV2L, and ConvNeXtXLarge) were trained, validated, and tested using transfer learning.</p><p><strong>Results: </strong>A total of 540 normal, 298 SD, and 314 ID were used in this study. In the differentiation between normal and abnormal images, the highest accuracy rates were achieved with ResNet50 (93.3%) and InceptionResNetV2 (90.6%) CNN models. Then, after using automated cropping preprocessing, the highest accuracy rates were achieved with ConvNeXtXLarge (96.9%), ResNet50 (95.5%), and InceptionResNetV2 (95.5%). The highest accuracy in the differentiation between SD and ID was achieved with EfficientNetV2L (94.6%).</p><p><strong>Conclusion: </strong>Deep learning models can be integrated into radiographs located in the emergency departments as a decision support system with high accuracy rates in pediatric GI obstructions by immediately alerting the physicians about abnormal radiographs and possible etiologies.</p><p><strong>Clinical significance: </strong>This paper describes a novel area of utilization of well-known deep learning algorithm models. Although some studies in the literature have shown the efficiency of CNN models in identifying small bowel obstruction with high accuracy for the adult population or some specific diseases, our study is unique for the pediatric population and for evaluating the requirement of surgical versus medical treatment.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143523022","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":"Adherence to the Checklist for Artificial Intelligence in Medical Imaging (CLAIM): an umbrella review with a comprehensive two-level analysis.","authors":"Burak Koçak, Fadime Köse, Ali Keleş, Abdurrezzak Şendur, İsmail Meşe, Mehmet Karagülle","doi":"10.4274/dir.2025.243182","DOIUrl":"https://doi.org/10.4274/dir.2025.243182","url":null,"abstract":"<p><strong>Purpose: </strong>To comprehensively assess Checklist for Artificial Intelligence in Medical Imaging (CLAIM) adherence in medical imaging artificial intelligence (AI) literature by aggregating data from previous systematic and non-systematic reviews.</p><p><strong>Methods: </strong>A systematic search of PubMed, Scopus, and Google Scholar identified reviews using the CLAIM to evaluate medical imaging AI studies. Reviews were analyzed at two levels: review level (33 reviews; 1,458 studies) and study level (421 unique studies from 15 reviews). The CLAIM adherence metrics (scores and compliance rates), baseline characteristics, factors influencing adherence, and critiques of the CLAIM were analyzed.</p><p><strong>Results: </strong>A review-level analysis of 26 reviews (874 studies) found a weighted mean CLAIM score of 25 [standard deviation (SD): 4] and a median of 26 [interquartile range (IQR): 8; 25^th-75^th percentiles: 20-28]. In a separate review-level analysis involving 18 reviews (993 studies), the weighted mean CLAIM compliance was 63% (SD: 11%), with a median of 66% (IQR: 4%; 25^th-75^th percentiles: 63%-67%). A study-level analysis of 421 unique studies published between 1997 and 2024 found a median CLAIM score of 26 (IQR: 6; 25^th-75^th percentiles: 23-29) and a median compliance of 68% (IQR: 16%; 25^th-75^th percentiles: 59%-75%). Adherence was independently associated with the journal impact factor quartile, publication year, and specific radiology subfields. After guideline publication, CLAIM compliance improved (<i>P</i> = 0.004). Multiple readers provided an evaluation in 85% (28/33) of reviews, but only 11% (3/28) included a reliability analysis. An item-wise evaluation identified 11 underreported items (missing in ≥50% of studies). Among the 10 identified critiques, the most common were item inapplicability to diverse study types and subjective interpretations of fulfillment.</p><p><strong>Conclusion: </strong>Our two-level analysis revealed considerable reporting gaps, underreported items, factors related to adherence, and common CLAIM critiques, providing actionable insights for researchers and journals to improve transparency, reproducibility, and reporting quality in AI studies.</p><p><strong>Clinical significance: </strong>By combining data from systematic and non-systematic reviews on CLAIM adherence, our comprehensive findings may serve as targets to help researchers and journals improve transparency, reproducibility, and reporting quality in AI studies.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143398672","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}