Diagnostic and interventional radiology最新文献

{"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}

{"title":"New imaging techniques and trends in radiology.","authors":"Mecit Kantarcı, Sonay Aydın, Hayri Oğul, Volkan Kızılgöz","doi":"10.4274/dir.2024.242926","DOIUrl":"https://doi.org/10.4274/dir.2024.242926","url":null,"abstract":"<p><p>Radiography is a field of medicine inherently intertwined with technology. The dependency on technology is very high for obtaining images in ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI). Although the reduction in radiation dose is not applicable in US and MRI, advancements in technology have made it possible in CT, with ongoing studies aimed at further optimization. The resolution and diagnostic quality of images obtained through advancements in each modality are steadily improving. Additionally, technological progress has significantly shortened acquisition times for CT and MRI. The use of artificial intelligence (AI), which is becoming increasingly widespread worldwide, has also been incorporated into radiography. This technology can produce more accurate and reproducible results in US examinations. Machine learning offers great potential for improving image quality, creating more distinct and useful images, and even developing new US imaging modalities. Furthermore, AI technologies are increasingly prevalent in CT and MRI for image evaluation, image generation, and enhanced image quality.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143001886","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":"Reply: 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.2024.243123","DOIUrl":"https://doi.org/10.4274/dir.2024.243123","url":null,"abstract":"","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142970015","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":"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":" ","pages":"52-57"},"PeriodicalIF":1.4,"publicationDate":"2025-01-01","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":"Evaluating small coronary stents with dual-source photon-counting computed tomography: effect of different scan modes on image quality and performance in a phantom.","authors":"Thomas Stein, Constantin von Zur Muhlen, Niklas Verloh, Till Schürmann, Tobias Krauss, Martin Soschynski, Dirk Westermann, Jana Taron, Elif Can, Christopher L Schlett, Fabian Bamberg, Christopher Schuppert, Muhammad Taha Hagar","doi":"10.4274/dir.2024.242893","DOIUrl":"10.4274/dir.2024.242893","url":null,"abstract":"<p><strong>Purpose: </strong>The study aimed to assess the feasibility and image quality of dual-source photon-counting detector computed tomography (PCD-CT) in evaluating small-sized coronary artery stents with respect to different acquisition modes in a phantom model.</p><p><strong>Methods: </strong>Utilizing a phantom setup mimicking the average patient's water-equivalent diameter, we examined six distinct coronary stents inflated in a silicon tube, with stent sizes ranging from 2.0 to 3.5 mm, applying four different CT acquisition modes of a dual-source PCD-CT scanner: \"high-pitch,\" \"sequential,\" \"spiral\" (each with collimation of 144 × 0.4 mm and full spectral information), and \"ultra-high-resolution (UHR)\" (collimation of 120 × 0.2 mm and no spectral information). Image quality and diagnostic confidence were assessed using subjective measures, including a 4-point visual grading scale (4 = excellent; 1 = non-diagnostic) utilized by two independent radiologists, and objective measures, including the full width at half maximum (FWHM).</p><p><strong>Results: </strong>A total of 24 scans were acquired, and all were included in the analysis. Among all CT acquisition modes, the highest image quality was obtained for the UHR mode [median score: 4 (interquartile range (IQR): 3.67-4.00)] (<i>P</i> = 0.0015, with 37.5% rated as \"excellent\"), followed by the sequential mode [median score: 3.5 (IQR: 2.84-4.00)], <i>P</i> = 0.0326 and the spiral mode [median score: 3.0 (IQR: 2.53-3.47), <i>P</i> > 0.05]. The lowest image quality was observed for the high-pitch mode [median score: 2 (IQR: 1- 3), <i>P</i> = 0.028]. Similarly, diagnostic confidence for evaluating stent patency was highest for UHR and lowest for high-pitch (<i>P</i> < 0.001, respectively). Measurement of stent dimensions was accurate for all acquisition modes, with the UHR mode showing highest robustness (FWHM for sequential: 0.926 ± 0.061 vs. high-pitch: 0.990 ± 0.083 vs. spiral: 0.962 ± 0.085 vs. UHR: 0.941 ± 0.036, <i>P</i> = non-significant, respectively).</p><p><strong>Conclusion: </strong>Assessing small-sized coronary stents using PCD-CT technology is feasible. The UHR mode offers superior image quality and diagnostic confidence, while all modes show consistent and accurate measurements.</p><p><strong>Clinical significance: </strong>These findings highlight the potential of PCD-CT technology, particularly the UHR mode, to enhance non-invasive coronary stent evaluation. Confirmatory research is necessary to influence the guidelines, which recommend cardiac CT only for stents of 3 mm or larger.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"29-38"},"PeriodicalIF":1.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142497017","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":"Computed tomography-based contrast features for distinguishing extra-gastrointestinal stromal tumors from intra-abdominal fibromatosis.","authors":"Lijing Zhang, Yongbo Li, Xinxin Luo, Deqi Li, Linlin Yin, Jiayue Li, Li Zhang","doi":"10.4274/dir.2024.242800","DOIUrl":"10.4274/dir.2024.242800","url":null,"abstract":"<p><strong>Purpose: </strong>This study aims to define the computed tomography (CT) criteria that distinguish extra-gastrointestinal stromal tumors (eGISTs) from intra-abdominal fibromatosis (IAF).</p><p><strong>Methods: </strong>Retrospective analysis was conducted on CT images obtained from 31 pathologically confirmed cases, including 17 cases of eGISTs and 14 of IAF. Various parameters [e.g., lesion location, contour characteristics, border delineation, enhancement patterns, presence of intralesional necrosis, vessels, air, fat, and hemorrhage, the long diameter (LD), LD/short diameter (SD) ratio, and volume (LD × SD × height diameter)] were meticulously evaluated. In addition, the degree of enhancement during arterial and portal venous phases and the lesion-to-aorta CT attenuation ratio during both phases were quantified. Statistical analysis was performed using Fisher's exact test, the Student's t-test, and the receiver operating characteristic curve to identify significant CT criteria. Sensitivity and specificity assessments were conducted for single and combined CT criteria.</p><p><strong>Results: </strong>Significant differentiators between eGISTs and IAF include non-mesenteric localization, irregular contour, well-defined borders, heterogeneous enhancement, presence of intralesional necrosis and vessels, and absence of intralesional fat, with LD exceeding 9.6 cm, an LD/SD ratio >1.22, and volume surpassing 603.3 cm³ (<i>P</i> < 0.05). A combination of seven or more of these criteria yielded a specificity of 100%.</p><p><strong>Conclusion: </strong>Ten distinct CT criteria have been identified to distinguish eGISTs from IAF, notably encompassing non-mesenteric localization, irregular contour, well-defined borders, heterogeneous enhancement, presence of intralesional necrosis and vessels, absence of intralesional fat, LD >9.6 cm, an LD/SD ratio >1.22, and volume surpassing 603.3 cm³.</p><p><strong>Clinical significance: </strong>The current findings establish CT criteria to distinguish eGISTs from IAF in a clinical setting.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"10-16"},"PeriodicalIF":1.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141787557","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":"Endovascular recanalization of infra-popliteal TASC C and TASC D lesions in patients with critical limb-threatening ischemia: a single-center experience.","authors":"Mehmet Koray Akkan, Ali Can Yalçın, Zeydanlı Tolga, Fatih Öncü, Erhan Turgut Ilgıt, Ahmet Baran Önal, Mustafa Hakan Zor, Abdullah Özer","doi":"10.4274/dir.2024.232524","DOIUrl":"10.4274/dir.2024.232524","url":null,"abstract":"<p><strong>Purpose: </strong>The present study aims to (1) assess the technical success and limb salvage rates of endovascular therapy in patients with critical limb-threatening ischemia (CLTI) and infra-popliteal Trans-Atlantic Inter-Society Consensus (TASC) C/D lesions according to the updated 2015 TASC II classification and (2) to present our institutional experience.</p><p><strong>Methods: </strong>A single-center retrospective study was conducted on patients with TASC C/D CLTI who underwent endovascular treatment between 2012 and 2017. The follow-up protocol consisted of Doppler ultrasound conduction every 3 months for the first year unless patients showed symptoms of CLTI. Patients with at least 1 year of follow-up data were included in the study, and if applicable their 3-year results were evaluated in terms of primary patency, absence of amputation, amputation-free survival, and overall survival.</p><p><strong>Results: </strong>A total of 248 patients and 287 limbs (238 TASC D lesions and 49 TASC C lesions) were treated via infra-popliteal percutaneous transluminal angioplasty. The overall technical success was 87%, the primary patency rate was 41.5% in the first year, and the freedom from amputation rates were 80.8% in 1 year and 67.7% in 3 years.</p><p><strong>Conclusion: </strong>In patients with infra-popliteal arterial occlusive diseases, endovascular treatment methods demonstrate a high rate of technical success and favorable outcomes in limb preservation.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"39-44"},"PeriodicalIF":1.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139641831","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":"Preoperative prediction of lymphovascular invasion and T-staging of rectal cancer via a dual-energy computed tomography iodine map: a feasibility study.","authors":"Jinliang Zhang, Hui Qi, Chun Yang, Ling Liu, Yuxin Wang, Wei Li","doi":"10.4274/dir.2024.242755","DOIUrl":"10.4274/dir.2024.242755","url":null,"abstract":"<p><strong>Purpose: </strong>To investigate the value of dual-energy computed tomography (DECT) in predicting lymphovascular invasion (LVI) and the accuracy of preoperative T-staging of rectal cancer (RC).</p><p><strong>Methods: </strong>Forty-nine patients with RC who had not received radiotherapy were enrolled to undergo a DECT scan. All patients underwent surgical tumor resection within 3-5 days after the DECT scan. Preoperative T-staging of RC based on images was performed by experienced radiologists. The normalized iodine concentrations (NIC) of the tumor and the perirectal adipose tissue (PAT) from the arterial phase (AP) and venous phase (VP) were measured using DECT. The tumor LVI and T-staging confirmed by pathology were used as the gold standard for grouping (group A, LVI-; group B, LVI+; group C, T1-2; and group D, T3-4a). The NIC values between two groups were compared using the Mann-Whitney U test, with <i>P</i> < 0.05 indicating a statistically significant difference. The accuracy of NIC in predicting LVI and distinguishing T1-2 RC from T3-4a RC were determined via receiver operating characteristic curve analysis, and the optimal cut-off of NIC was determined using the area under the curve.</p><p><strong>Results: </strong>The tumor NIC values were significantly higher in the LV+ group than in the LVI- group in the VP (0.728 ± 0.031 vs. 0.669 ± 0.034, <i>P</i> < 0.001). The NIC values of PAT were significantly higher in the T3-4a group than in the T1-2 group in both the AP (4.034 ± 0.991 vs. 3.115 ± 0.581, <i>P</i> < 0.05) and the VP (5.481 ± 1.054 vs. 3.450 ± 0.980, <i>P</i> < 0.001). The accuracy of using NIC values to distinguish between the LVI+ group and the LVI- group and to diagnose the T3-4a group were 85.7% and 89.8%, respectively. However, there was no statistically significant difference between the NIC value in the LVI+ group and in the LVI- group in the AP. There was also no statistical difference in the tumor NIC value between the T1-2 group and the T3-4a group.</p><p><strong>Conclusion: </strong>The tumor and PAT NIC are valuable indicators in RC that can preoperatively predict LVI and improve the accuracy of preoperative RC T-staging.</p><p><strong>Clinical significance: </strong>The use of DECT improves the T-staging and LVI prediction of RC, which is helpful in guiding the clinical selection of appropriate treatment modalities and improving prognostic outcomes.</p>","PeriodicalId":11341,"journal":{"name":"Diagnostic and interventional radiology","volume":" ","pages":"1-9"},"PeriodicalIF":1.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141247561","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}