Insights into Imaging最新文献

{"title":"Diagnosis of adult midgut malrotation in CT: sign of absent retromesenteric duodenum reliable.","authors":"Min Yang, Shaokun Zheng, Jian Shu, Zhenwei Yao","doi":"10.1186/s13244-025-01921-x","DOIUrl":"10.1186/s13244-025-01921-x","url":null,"abstract":"<p><strong>Objectives: </strong>To compare the incidence of absent retromesenteric duodenum with other radiological signs and to assess its diagnostic significance for midgut malrotation in adults.</p><p><strong>Methods: </strong>This IRB-approved retrospective single-center study involved adult patients who underwent abdominal CT scans. Patients were screened for the presence of the absent retromesenteric duodenum sign. Signs observed included the position of the duodenal-jejunal junction (DJJ) and jejunum within the abdomen, the relationship between the superior mesenteric artery (SMA) and superior mesenteric vein (SMV), the locations of the ascending colon, cecum, and appendix, and the presence of intestinal volvulus.</p><p><strong>Results: </strong>A total of 5594 patients were included. Seven patients exhibited the sign of absent retromesenteric duodenum. Four of these patients were identified as those diagnosed with midgut malrotation in the past five years. The common features observed in all 11 patients were: the horizontal segment of the duodenum did not traverse behind the SMA but instead curved rightwards and forwards adjacent to it; the DJJ and jejunum were positioned in the right abdomen; the SMV was anterior to the SMA. In 7 patients (7/11), the ascending colon, cecum, and appendix were located in the left abdomen. 5 patients (5/11) showed a high cecum position, and 2 patients (2/11) exhibited a pelvic appendix.</p><p><strong>Conclusion: </strong>The absent retromesenteric duodenum sign in CT diagnosis of adult midgut malrotation has proven to be more reliable.</p><p><strong>Critical relevance statement: </strong>Radiologists should routinely identify the course of the duodenum horizontal segment in CT images, to prevent misdiagnosis of adult midgut malrotation.</p><p><strong>Key points: </strong>CT is suitable for the diagnosis of adult midgut malrotation. Absent retromesenteric duodenum for diagnosing adult midgut malrotation is more reliable than other signs. Diagnostic CT criteria for adult midgut malrotation need updating.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"35"},"PeriodicalIF":4.1,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143440707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Guiding AI in radiology: ESR's recommendations for effective implementation of the European AI Act.","authors":"Elmar Kotter, Tugba Akinci D'Antonoli, Renato Cuocolo, Monika Hierath, Merel Huisman, Michail E Klontzas, Luis Martí-Bonmatí, Matthias Stefan May, Emanuele Neri, Konstantin Nikolaou, Daniel Pinto Dos Santos, Maija Radzina, Susan Cheng Shelmerdine, Arianna Bellemo","doi":"10.1186/s13244-025-01905-x","DOIUrl":"10.1186/s13244-025-01905-x","url":null,"abstract":"<p><p>This statement has been produced within the European Society of Radiology AI Working Group and identifies the key policies of the EU AI Act as they pertain to medical imaging. It offers specific recommendations to policymakers and the professional community for the effective implementation of the legislation, addressing potential gaps and uncertainties. Key areas include AI literacy, classification rules for high-risk AI systems, data governance, transparency, human oversight, quality management, deployer obligations, regulatory sandboxes, post-market monitoring, information sharing, and market surveillance. By proposing actionable solutions, the statement highlights ESR's readiness in supporting appropriate application of the AI Act in the field, promoting clarity and the effective integration of AI technologies to ensure their impactful and safe use for the benefit of Europe's patients. CRITICAL RELEVANCE STATEMENT: With the impending arrival of the EU AI Act, it is critical for stakeholders to provide timely input on its key areas. This statement offers expert feedback on the aspects of the EU AI Act that will affect medical imaging. KEY POINTS: The AI Act will significantly impact the field of medical imaging, shaping how AI technologies are used and regulated. The ESR is committed to develop guidelines and best practices, collaborating on the implementation process. This statement offers expert feedback on the aspects of the framework that will affect medical imaging.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"33"},"PeriodicalIF":4.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11825415/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143414044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multiparameter body composition analysis on chest CT predicts clinical outcomes in resectable non-small cell lung cancer.","authors":"Yilong Huang, Hanxue Cun, Zhanglin Mou, Zhonghang Yu, Chunmei Du, Lan Luo, Yuanming Jiang, Yancui Zhu, Zhenguang Zhang, Xin Chen, Bo He, Zaiyi Liu","doi":"10.1186/s13244-025-01910-0","DOIUrl":"10.1186/s13244-025-01910-0","url":null,"abstract":"<p><strong>Objectives: </strong>This study investigates the association between baseline CT body composition parameters and clinical outcomes in patients with resectable non-small cell lung cancer (NSCLC).</p><p><strong>Methods: </strong>Patients who underwent surgical resection for NSCLC between January 2006 and December 2017 were retrospectively enrolled in this multicenter study. Body composition metrics, including the area of skeletal muscle, intermuscular adipose tissue, subcutaneous adipose tissue, visceral adipose tissue, muscle radiodensity, and derivative parameters from five basic metrics mentioned before, were calculated based on preoperative non-contrast-enhanced chest CT images at L1 level. The Cox proportional hazards regression analysis was used to evaluate the association between body composition metrics and survival outcomes including overall survival (OS) and disease-free survival (DFS).</p><p><strong>Results: </strong>A total of 2712 patients (mean age, 61.53 years; 1146 females) were evaluated. A total of 635 patients (23.41%) died. 465 patients (19.51%) experienced recurrence and/or distant metastasis. After multivariable adjustment, skeletal muscle index (SMI, HR = 0.86), intermuscular adipose index (IMAI, HR = 1.49), and subcutaneous adipose index (SAI, HR = 0.96) were associated with OS. Similar results were found after stratification by gender, TNM stage, and center. There was no significant association between all body composition metrics and DFS (all p > 0.05). The body composition metrics significantly enhance the model including clinicopathological factors, resulting in an improved AUC for predicting 1-year and 3-year OS, with AUC values of 0.707 and 0.733, respectively.</p><p><strong>Conclusions: </strong>SMI, IMAI, and SAI body composition metrics have been identified as independent prognostic factors and may indicate mortality risk for resectable NSCLC patients.</p><p><strong>Critical relevance statement: </strong>Our findings emphasize the significance of muscle mass, quality, and fat energy storage in clinical decision-making for patients with non-small cell lung cancer (NSCLC). Nutritional and exercise interventions targeting muscle quality and energy storage could be considered for patients with NSCLC.</p><p><strong>Key points: </strong>Multiparameter body composition analysis is associated with the clinical outcome in NSCLC patients. Assessing muscle mass, quality, and adipose tissue helps predict overall survival in NSCLC. The quantity and distribution of body composition can contribute to unraveling the adiposity paradox.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"32"},"PeriodicalIF":4.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11803022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Students' perspective on new teaching concepts for medical studies: case- and competency-based learning in radiology.","authors":"Max Masthoff, Friedrich Pawelka, Gisela Zak, Bas de Leng, Dogus Darici, Philipp Schindler, Walter Heindel, Anne Helfen","doi":"10.1186/s13244-025-01909-7","DOIUrl":"10.1186/s13244-025-01909-7","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to evaluate medical students' perception of a new radiology teaching format for abdominal diagnostics. The format transitioned traditional lectures and seminars to a case- and competency-based course that incorporates technology-enhanced individual case-work, small group discussions, and concise lectures.</p><p><strong>Materials and methods: </strong>235 students (23.5 ± 2.6 years, 72.3% female, 93.3% response rate, November 2023-June 2024) completed a questionnaire before (12 items) and after (20 items) the course, assessing perceived importance of course content, competency gains in abdominal imaging, enjoyment of learning, interest in a radiology career, and pedagogical perception of the teaching concept. Responses were recorded on a 1-10 scale (no agreement to strong agreement) or dichotomously (yes/no). The new course format was compared with a cohort of students who had previously (May 2022-June 2023) attended traditional lectures (n = 169) and/or seminars (n = 234).</p><p><strong>Results: </strong>Students strongly agreed before the course that radiology content in abdominal diagnostics is important, and they found the content highly relevant and applicable to their work as doctors following the course. Significant improvement was observed in perceived competency in modality selection and description and interpretation of common pathologies, with the strongest effect for CT and MRI data. The new format was rated more motivating and significantly better in pedagogical and content quality than traditional lectures and seminars, although it did not influence students' interest in pursuing a radiology career.</p><p><strong>Conclusion: </strong>From the students' perspective, case- and competency-based teaching enhances skill acquisition, learning success, and enjoyment in radiology.</p><p><strong>Clinical relevance statement: </strong>From a student perspective, case- and competency-based teaching in radiology may enhance imaging competency, contributing to the development of more skilled healthcare providers.</p><p><strong>Key points: </strong>Case- and competency-based teaching concepts may improve students' learning. Students reported improved perceived competency in decision-making and image interpretation with the new teaching method. Case- and competency-based teaching was perceived as more engaging, motivating, and pedagogically superior to traditional lectures.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"31"},"PeriodicalIF":4.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11803062/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attitudes of radiologists and interns toward the adoption of GPT-like technologies: a National Survey Study in China.","authors":"Tianyi Xia, Shijun Zhang, Ben Zhao, Ying Lei, Zebin Xiao, Bingwei Chen, Junhao Zha, Yaoyao Yu, Zhijun Wu, Chunqiang Lu, Tianyu Tang, Yang Song, Yuancheng Wang, Shenghong Ju","doi":"10.1186/s13244-025-01908-8","DOIUrl":"10.1186/s13244-025-01908-8","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate the attitudes of Chinese radiologists or interns towards generative pre-trained (GPT)-like technologies.</p><p><strong>Methods: </strong>A prospective survey was distributed to 1339 Chinese radiologists or interns via an online platform from October 2023 to May 2024. The questionnaire covered respondent characteristics, opinions on using GPT-like technologies (in clinical practice, training and education, environment and regulation, and development trends), and their attitudes toward these technologies. Logistic regression was conducted to identify underlying factors associated with the attitude.</p><p><strong>Results: </strong>After quality control, 1289 respondents (median age, 37.0 years [IQR, 31.0-44.0 years]; 813 males) were surveyed. Most of the respondents (n = 1223, 94.9%) supported adoption of GPT-like technologies. Based on the acceptance level of GPT-like technologies, the respondents were 3 (0.2%), 29 (2.2%), 352 (27.3%), 677 (52.5%), and 228 (17.7%) from low to high acceptance degrees. Multivariable analysis revealed significant associations between positive attitudes towards GPT-like technologies and their acceptance: writing papers and language polishing (odds ratio [OR] = 1.99; p < 0.001), influence of colleagues using such technologies (OR = 1.77; p = 0.007), government regulation introduction (OR = 2.25; p < 0.001), and enhancement of decision support capabilities (OR = 2.67; p < 0.001). Sensitivity analyses confirmed these results for different acceptance thresholds (all p < 0.001).</p><p><strong>Conclusions: </strong>Chinese radiologists or interns generally support GPT-like technologies due to their potential capabilities in clinical practice, medical education, and scientific research. They also emphasize the need for regulatory oversight and remain optimistic about their future medical applications.</p><p><strong>Critical relevance statement: </strong>This study highlights the broad support among Chinese radiologists for GPT-like technologies, emphasizing their potential to enhance clinical decision-making, streamline medical education, and improve research efficiency, while underscoring the need for regulatory oversight.</p><p><strong>Key points: </strong>The impact of GPT-like technologies on the radiology field is unclear. Most Chinese radiologists express the supportive adoption of GPT-like technologies. GPT-like technologies' capabilities at research and clinic prompt the attitude.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"30"},"PeriodicalIF":4.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11785863/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143074223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The value of MRI in differentiating ovarian clear cell carcinoma from other adnexal masses with O-RADS MRI scores of 4-5.","authors":"Lingling Lin, Le Fu, Huawei Wu, Saiming Cheng, Guangquan Chen, Lei Chen, Jun Zhu, Yu Wang, Jiejun Cheng","doi":"10.1186/s13244-024-01860-z","DOIUrl":"10.1186/s13244-024-01860-z","url":null,"abstract":"<p><strong>Objective: </strong>To assess the utility of clinical and MRI features in distinguishing ovarian clear cell carcinoma (CCC) from adnexal masses with ovarian-adnexal reporting and data system (O-RADS) MRI scores of 4-5.</p><p><strong>Methods: </strong>This retrospective study included 850 patients with indeterminate adnexal masses on ultrasound. Two radiologists evaluated all preoperative MRIs using the O-RADS MRI risk stratification system. Patients with O-RADS MRI scores of 4-5 were divided into a training set (n = 135, hospital A) and a test set (n = 86, hospital B). Clinical and MRI features were compared between CCC and non-CCC patients. Analysis of variance and support vector machine were used to develop four CCC prediction models. Tenfold cross-validation was applied to determine the hyperparameters. Model performance was evaluated by the area under the curve (AUC) and decision curve.</p><p><strong>Results: </strong>221 patients were included (30 CCCs, 191 non-CCCs). CA125, HE4, CEA, ROMA, endometriosis, shape, parity, unilocular, component, the growth pattern of mural nodules, high signal on T1WI, number of nodules, the ratio of signal intensity, and the ADC value were significantly different between CCCs and non-CCCs. The kappa and interobserver correlation coefficient of each MRI feature exceeded 0.85. The comprehensive model combining clinical and MRI features had a greater AUC than the clinical model and tumour maker model (0.92 vs 0.66 and 0.78 in the test set; both p < 0.05), displaying improved net benefit.</p><p><strong>Conclusions: </strong>The comprehensive model combining clinical and MRI features can effectively differentiate CCC from adnexal masses with O-RADS MRI scores of 4-5.</p><p><strong>Critical relevance statement: </strong>CCC has a high incidence rate in Asians and has limited sensitivity to platinum chemotherapy. This comprehensive model improves CCC prediction ability and clinical applicability for facilitating individualised clinical decision-making.</p><p><strong>Key points: </strong>Identifying ovarian CCC preoperatively is beneficial for treatment planning. Ovarian CCC tends to be high-signal on T1WI, unilocular, big size, with endometriosis and low CEA. This model, integrating clinical and MRI features, can differentiate ovarian CCC from adnexal masses with O-RADS MRI scores 4-5.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"22"},"PeriodicalIF":4.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780052/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D-AttenNet model can predict clinically significant prostate cancer in PI-RADS category 3 patients: a retrospective multicenter study.","authors":"Jie Bao, Litao Zhao, Xiaomeng Qiao, Zhenkai Li, Yanting Ji, Yueting Su, Libiao Ji, Junkang Shen, Jiangang Liu, Jie Tian, Ximing Wang, Hailin Shen, Chunhong Hu","doi":"10.1186/s13244-024-01896-1","DOIUrl":"10.1186/s13244-024-01896-1","url":null,"abstract":"<p><strong>Purposes: </strong>The presence of clinically significant prostate cancer (csPCa) is equivocal for patients with prostate imaging reporting and data system (PI-RADS) category 3. We aim to develop deep learning models for re-stratify risks in PI-RADS category 3 patients.</p><p><strong>Methods: </strong>This retrospective study included a bi-parametric MRI of 1567 consecutive male patients from six centers (Centers 1-6) between Jan 2015 and Dec 2020. Deep learning models with double channel attention modules based on MRI (AttenNet) for predicting PCa and csPCa were constructed separately. Each model was first pretrained using 1144 PI-RADS 1-2 and 4-5 images and then retrained using 238 PI-RADS 3 images from three training centers (centers 1-3), and tested using 185 PI-RADS 3 images from the other three testing centers (centers 4-6).</p><p><strong>Results: </strong>Our AttenNet models achieved excellent prediction performances in testing cohort of center 4-6 with the area under the receiver operating characteristic curves (AUC) of 0.795 (95% CI: [0.700, 0.891]), 0.963 (95% CI: [0.915, 1]) and 0.922 (95% CI: [0.810, 1]) in predicting PCa, and the corresponding AUCs were 0.827 (95% CI: [0.703, 0.952]) and 0.926 (95% CI: [0.846, 1]) in predicting csPCa in testing cohort of center 4 and center 5. In particular, 71.1% to 92.2% of non-csPCa patients were identified by our model in three testing cohorts, who can spare from invasive biopsy or RP procedure.</p><p><strong>Conclusions: </strong>Our model offers a noninvasive screening clinical tool to re-stratify risks in PI-RADS 3 patients, thereby reducing unnecessary invasive biopsies and improving the effectiveness of biopsies.</p><p><strong>Critical relevance statement: </strong>The deep learning model with MRI can help to screen out csPCa in PI-RADS category 3.</p><p><strong>Key points: </strong>AttenNet models included channel attention and soft attention modules. 71.1-92.2% of non-csPCa patients were identified by the AttenNet model. The AttenNet models can be a screen clinical tool to re-stratify risks in PI-RADS 3 patients.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"25"},"PeriodicalIF":4.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780012/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study.","authors":"Qian Wu, Tao Zhang, Fan Xu, Lixiu Cao, Wenhao Gu, Wenjing Zhu, Yanfen Fan, Ximing Wang, Chunhong Hu, Yixing Yu","doi":"10.1186/s13244-025-01904-y","DOIUrl":"10.1186/s13244-025-01904-y","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate radiomics and deep learning models based on contrast-enhanced MRI (CE-MRI) for differentiating dual-phenotype hepatocellular carcinoma (DPHCC) from HCC and intrahepatic cholangiocarcinoma (ICC).</p><p><strong>Methods: </strong>Our study consisted of 381 patients from four centers with 138 HCCs, 122 DPHCCs, and 121 ICCs (244 for training and 62 for internal tests, centers 1 and 2; 75 for external tests, centers 3 and 4). Radiomics, deep transfer learning (DTL), and fusion models based on CE-MRI were established for differential diagnosis, respectively, and their diagnostic performances were compared using the confusion matrix and area under the receiver operating characteristic (ROC) curve (AUC).</p><p><strong>Results: </strong>The radiomics model demonstrated competent diagnostic performance, with a macro-AUC exceeding 0.9, and both accuracy and F1-score above 0.75 in the internal and external validation sets. Notably, the vgg19-combined model outperformed the radiomics and other DTL models. The fusion model based on vgg19 further improved diagnostic performance, achieving a macro-AUC of 0.990 (95% CI: 0.965-1.000), an accuracy of 0.935, and an F1-score of 0.937 in the internal test set. In the external test set, it similarly performed well, with a macro-AUC of 0.988 (95% CI: 0.964-1.000), accuracy of 0.875, and an F1-score of 0.885.</p><p><strong>Conclusions: </strong>Both the radiomics and the DTL models were able to differentiate DPHCC from HCC and ICC before surgery. The fusion models showed better diagnostic accuracy, which has important value in clinical application.</p><p><strong>Critical relevance statement: </strong>MRI-based deep learning radiomics were able to differentiate DPHCC from HCC and ICC preoperatively, aiding clinicians in the identification and targeted treatment of these malignant hepatic tumors.</p><p><strong>Key points: </strong>Fusion models may yield an incremental value over radiomics models in differential diagnosis. Radiomics and deep learning effectively differentiate the three types of malignant hepatic tumors. The fusion models may enhance clinical decision-making for malignant hepatic tumors.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"27"},"PeriodicalIF":4.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780023/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Upskilling or deskilling? Measurable role of an AI-supported training for radiology residents: a lesson from the pandemic.","authors":"Mattia Savardi, Alberto Signoroni, Sergio Benini, Filippo Vaccher, Matteo Alberti, Pietro Ciolli, Nunzia Di Meo, Teresa Falcone, Marco Ramanzin, Barbara Romano, Federica Sozzi, Davide Farina","doi":"10.1186/s13244-024-01893-4","DOIUrl":"10.1186/s13244-024-01893-4","url":null,"abstract":"<p><strong>Objectives: </strong>This article aims to evaluate the use and effects of an artificial intelligence system supporting a critical diagnostic task during radiology resident training, addressing a research gap in this field.</p><p><strong>Materials and methods: </strong>We involved eight residents evaluating 150 CXRs in three scenarios: no AI, on-demand AI, and integrated-AI. The considered task was the assessment of a multi-regional severity score of lung compromise in patients affected by COVID-19. The chosen artificial intelligence tool, fully integrated in the RIS/PACS, demonstrated superior performance in scoring compared to the average radiologist. Using quantitative metrics and questionnaires, we measured the 'upskilling' effects of using AI support and residents' resilience to 'deskilling,' i.e., their ability to overcome AI errors.</p><p><strong>Results: </strong>Residents required AI in 70% of cases when left free to choose. AI support significantly reduced severity score errors and increased inter-rater agreement by 22%. Residents were resilient to AI errors above an acceptability threshold. Questionnaires indicated high tool usefulness, reliability, and explainability, with a preference for collaborative AI scenarios.</p><p><strong>Conclusion: </strong>With this work, we gathered quantitative and qualitative evidence of the beneficial use of a high-performance AI tool that is well integrated into the diagnostic workflow as a training aid for radiology residents.</p><p><strong>Critical relevance statement: </strong>Balancing educational benefits and deskilling risks is essential to exploit AI systems as effective learning tools in radiology residency programs. Our work highlights metrics for evaluating these aspects.</p><p><strong>Key points: </strong>Insights into AI tools' effects in radiology resident training are lacking. Metrics were defined to observe residents using an AI tool in different settings. This approach is advisable for evaluating AI tools in radiology training.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"23"},"PeriodicalIF":4.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780016/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Determining the status of tertiary lymphoid structures in invasive pulmonary adenocarcinoma based on chest CT radiomic features.","authors":"Ye Yu, Tianshu Yang, Pengfei Ma, Yan Zeng, Yongming Dai, Yicheng Fu, Aie Liu, Ying Zhang, Guanglei Zhuang, Yan Zhou, Huawei Wu","doi":"10.1186/s13244-025-01906-w","DOIUrl":"10.1186/s13244-025-01906-w","url":null,"abstract":"<p><strong>Objectives: </strong>The aim of this study was to determine the status of tertiary lymphoid structures (TLSs) using radiomic features in patients with invasive pulmonary adenocarcinoma (IA).</p><p><strong>Methods: </strong>In this retrospective study, patients with IA from November 2015 to March 2024 were recruited from two independent centers (center 1, training and internal test data set; center 2, external test data set). TLS was divided into two groups according to hematoxylin-eosin staining. Radiomic features were extracted, and support vector machine (SVM) were implemented to predict the status of TLSs. Receiver operating characteristic (ROC) curves were used to analyze diagnostic performance. Furthermore, visual assessments of the test set were also conducted by two thoracic radiologists and compared with the radiomics results.</p><p><strong>Results: </strong>A total of 456 patients were included (training data set, n = 278; internal test data set, n = 115; external test data set, n = 63). The area under the curve (AUC) of the radiomics model on the validation set, the internal test set, and the external test set were 0.781 (95% confidence interval (CI): 0.659-0.905;), 0.804 (95% CI: 0.723-0.884;) and 0.747 (95% CI: 0.621-0.874;), respectively. In the visual assessments, the mean CT value and air bronchogram were important indicators of TLS, the AUC was 0.683. In the external test set, the AUC of the clinical model was 0.632.</p><p><strong>Conclusions: </strong>The radiomics model has a higher AUC than the clinical model and effectively discriminates TLSs in patients with IA.</p><p><strong>Critical relevance statement: </strong>This study demonstrates that the radiomics-based model can differentiate TLSs in patients with IA. As a non-invasive biomarker, it enhances our understanding of tumor prognosis and management.</p><p><strong>Key points: </strong>TLSs are closely related to favorable clinical outcomes in non-small cell lung cancer. Radiomics from Chest CT predicted TLSs in patients with IA. This study supports individualized clinical decision-making for patients with IA.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"28"},"PeriodicalIF":4.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}