Radiology advances最新文献

{"title":"Improving radiologist detection of meniscal abnormality on undersampled, deep learning reconstructed knee MRI.","authors":"Natalia Konovalova, Aniket Tolpadi, Felix Liu, Zehra Akkaya, Johanna Luitjens, Felix Gassert, Paula Giesler, Rupsa Bhattacharjee, Misung Han, Emma Bahroos, Sharmila Majumdar, Valentina Pedoia","doi":"10.1093/radadv/umaf015","DOIUrl":"10.1093/radadv/umaf015","url":null,"abstract":"<p><strong>Background: </strong>Accurate interpretation of meniscal anomalies on knee MRI is critical for diagnosis and treatment planning, with artificial intelligence emerging as a promising tool to support and enhance this process through automated anomaly detection.</p><p><strong>Purpose: </strong>To evaluate the impact of an artificial intelligence (AI) anomaly detection assistant on radiologists' interpretation of meniscal anomalies in undersampled, deep learning (DL)-reconstructed knee MRI and assess the relationship between reconstruction quality metrics and anomaly detection performance.</p><p><strong>Materials and methods: </strong>This retrospective study included 947 knee MRI examinations; 51 were excluded for poor image quality, leaving 896 participants (mean age, 44.7 ± 15.3 years; 472 women). Using 8-fold undersampled data, DL-based reconstructed images were generated. An object detection model was trained on original, fully sampled images and evaluated on 1 original and 14 DL-reconstructed test sets to identify meniscal lesions. Standard reconstruction metrics (normalized root mean square error, peak signal-to-noise ratio, and structural similarity index) and anomaly detection metrics (mean average precision, F1 score) were quantified and compared. Two radiologists independently reviewed a stratified sample of 50 examinations unassisted and assisted with AI-predicted anomaly boxes. McNemar's test evaluated differences in diagnostic performance; Cohen's kappa assessed interrater agreement.</p><p><strong>Results: </strong>On the original images, the anomaly detection model achieved the following: 70.53% precision, 72.17% recall, 63.09% mAP, and a 71.34% F1 score. Comparing performance among the undersampled reconstruction datasets, box-based reconstruction metrics showed better correlation with detection performance than traditional image-based metrics (mAP to box-based SSIM, <i>r</i> = 0.81, <i>P</i> < .01; mAP to image-based SSIM, <i>r</i> = 0.64, <i>P</i> = .01). In 50 participants, AI assistance improved radiologists' accuracy on reconstructed images. Sensitivity increased from 77.27% (95% CI, 65.83-85.72; 51/66) to 80.30% (95% CI, 69.16-88.11; 53/66), and specificity improved from 88.46% (95% CI, 83.73-91.95; 207/234) to 90.60% (95% CI, 86.18-93.71; 212/234) (<i>P</i> < .05).</p><p><strong>Conclusion: </strong>AI-assisted meniscal anomaly detection enhanced radiologists' interpretation of undersampled, DL-reconstructed knee MRI. Anomaly detection may serve as a complementary tool alongside other reconstruction metrics to assess the preservation of clinically important features in reconstructed images, warranting further investigation.</p>","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 2","pages":"umaf015"},"PeriodicalIF":0.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021832/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144060178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of robotic versus manual needle insertion for CT-guided intervention: prospective randomized trial.","authors":"Takao Hiraki, Yusuke Matsui, Jun Sakurai, Koji Tomita, Mayu Uka, Soichiro Kajita, Noriyuki Umakoshi, Toshihiro Iguchi, Michihiro Yoshida, Kota Sakamoto, Takayuki Matsuno, Tetsushi Kamegawa","doi":"10.1093/radadv/umaf010","DOIUrl":"10.1093/radadv/umaf010","url":null,"abstract":"<p><strong>Background: </strong>Robotic needle insertion under CT guidance has been developed, but data on comparison with manual insertion are still lacking.</p><p><strong>Purpose: </strong>To compare robotic versus manual needle insertion for CT fluoroscopy-guided intervention, primarily in terms of insertion accuracy.</p><p><strong>Materials and methods: </strong>This was a prospective study between May 2020 and March 2023 at a single site. The cohort comprised 22 patients undergoing CT (Aquilion One or Aquilion CX; Canon Medical Systems) fluoroscopy-guided biopsy, who were randomly allocated to either the robotic or manual group. The robot used (Zerobot; Medicalnet Okayama) is not yet commercially available. A biopsy introducer needle was inserted by 1 of 3 physicians using a remote-control robot in the robotic group, versus by 1 of 3 different physicians by hand in the manual group. The primary endpoint was needle insertion accuracy, which was defined as the 3-dimensional Euclidean distance between a predetermined target point and the needle tip after insertion. The non-inferiority of robotic insertion to manual one was then tested. Adverse events were evaluated. Statistical comparisons were made between the 2 groups.</p><p><strong>Results: </strong>Technical success and pathological findings were confirmed in all patients of the 2 groups. The mean and SD of needle insertion were 4.8 mm ± 2.6 in the robotic group and 7.0 mm ± 3.1 in the manual group (<i>P</i> < .001). The mean difference in accuracy between the 2 groups (robotic minus manual group) was -2.1 mm (95% CI, -4.7 to 0.4). Effective dose to physicians was zero in all cases in the robotic group, while median dose was 1.0 µSv in the manual group (<i>P</i> < .001). Dose length product to patients was not significantly different between the 2 groups (<i>P</i> = .100). No major adverse events were observed.</p><p><strong>Conclusion: </strong>Robotic needle insertion was non-inferior to manual insertion in terms of accuracy, while it effectively eliminated radiation exposure to physicians.</p><p><strong>Trial registration number: </strong>jRCT2062200013.</p>","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 2","pages":"umaf010"},"PeriodicalIF":0.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429234/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Climate resilient and environmentally sustainable radiology: a framework for implementation.","authors":"Chloe DesRoche, Felipe Castillo, Sonali Sharma, Beth Zigmund, Julian Dobranowski, Myles Sergeant, Linda Varangu, Kate Hanneman","doi":"10.1093/radadv/umaf014","DOIUrl":"10.1093/radadv/umaf014","url":null,"abstract":"<p><p>Climate change adversely impacts human health and transformations in our approach to work are needed to build environmentally sustainable and climate resilient radiology systems. Radiology practices must reduce greenhouse gas emissions generated in the delivery of care while simultaneously building infrastructure and processes to anticipate, respond to, and recover from climate-related environmental events. The purpose of this review is to highlight the links between climate change, human health, and radiology; discuss mitigation, adaptation, and response approaches; describe opportunities to leverage existing knowledge such as pandemic planning and supply chain management; and develop a radiology resilience checklist to assess vulnerabilities and inform actions necessary to achieve environmentally sustainable and climate resilient practices. The proposed framework is based on 5 pillars of climate resilience capacity-threshold, coping, recovery, adaptive, and transformative. Key actions include increasing awareness of the health impacts of climate change, optimizing infrastructure, improving supply chain management, reducing energy use, and addressing health disparities through collaboration with stakeholders. These strategies are needed to reduce the environmental impact radiology service delivery, prepare for and minimize the effects of climate change on imaging departments, and build capacity to recover quickly from climate-related environmental impacts, ultimately improving planetary health and human well-being.</p>","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 2","pages":"umaf014"},"PeriodicalIF":0.0,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429196/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-institutional automated multilabel segmentation for acute intracerebral hemorrhage, intraventricular hemorrhage, and perihematomal edema on CT.","authors":"Jawed Nawabi, Georg Lukas Baumgaertner, Sophia Schulze-Weddige, Andrea Dell'Orco, Andrea Morotti, Federico Mazzacane, Helge Kniep, Frieder Schlunk, Maik Franz Hermann Boehmer, Burak Han Akkurt, Tobias Orth, Jana-Sofie Weissflog, Maik Schumann, Peter B Sporns, Michael Scheel, Uta Hanning, Jens Fiehler, Tobias Penzkofer","doi":"10.1093/radadv/umaf012","DOIUrl":"10.1093/radadv/umaf012","url":null,"abstract":"<p><strong>Background: </strong>Precise volume quantification of intracerebral hemorrhage (ICH), intraventricular hemorrhage (IVH), and perihematomal edema (PHE) is a critical parameter for guiding therapy decisions, monitoring therapeutic effects over time, and predicting patient outcomes.</p><p><strong>Purpose: </strong>To evaluate a nnU-Net-based deep learning model for automated, multilesion segmentation on non-contrast CT.</p><p><strong>Materials and methods: </strong>Retrospective data from acute spontaneous ICH patients admitted to 4 stroke centers (2015-2022) and controls (2022-2023) were analyzed. Manual segmentations served as ground truth with repeated segmentations as reference standard. nnU-Net was trained (<i>n</i> = 775) using 5-fold cross-validation and tested on a holdout set (<i>n</i> = 189). Lesion detection, segmentation, and volumetric accuracy were evaluated using the Dice similarity coefficient (DSC) and Pearson correlation coefficients (r), with subanalyses for anatomical location and impact of other hemorrhage types (subarachnoid, subdural, or epidural hematoma). The model was validated on internal (<i>n</i> = 121) and external (<i>n</i> = 169) datasets. Processing time was compared to manual segmentation.</p><p><strong>Results: </strong>Test set sensitivity was 99% for ICH and PHE and 97% for IVH. Segmentation achieved a DSC of 0.91 (ICH), 0.71 (PHE), and 0.76 (IVH), with <i>r</i> = 0.99 (ICH, IVH) and <i>r</i> = 0.92 (PHE). DSC for lobar and deep hemorrhages were 0.90 and 0.92, respectively, and 0.70 in the brainstem, with other hemorrhage types showing no significant impact on segmentation accuracy, <i>P</i> > .05. For internal validation, DSC was 0.88 (ICH), 0.66 (PHE), and 0.80 (IVH), with r of 0.98, 0.88, and 0.98, respectively. External validation yielded DSC values of 0.85 (ICH), 0.61 (PHE), and 0.80 (IVH), with <i>r</i> values of 0.97, 0.85, and 0.96. Mean processing time was 18.2 s (±5 SD), compared to 18.01 min (±20.47 SD) for manual segmentations.</p><p><strong>Conclusion: </strong>nnU-Net enables reliable, time-efficient segmentation of ICH, PHE, and IVH, validated across multicenter, multivendor datasets of spontaneous ICH, showing potential to enhance clinical workflows.</p>","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 2","pages":"umaf012"},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429176/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vincent's brain.","authors":"Graziana Agostinelli","doi":"10.1093/radadv/umaf002","DOIUrl":"https://doi.org/10.1093/radadv/umaf002","url":null,"abstract":"","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 2","pages":"umaf002"},"PeriodicalIF":0.0,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429250/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mitigation of T₁ impact for unbiased tumor magnetic resonance amide proton transfer imaging at 3T.","authors":"Zhou Liu, Qian Yang, Haizhou Liu, Honghong Luo, Yijia Zheng, Dehong Luo, Yin Wu","doi":"10.1093/radadv/umaf011","DOIUrl":"10.1093/radadv/umaf011","url":null,"abstract":"<p><strong>Background: </strong>Amide proton transfer (APT), a specific type of chemical exchange saturation transfer (CEST) MRI, has proved valuable in tumor diagnosis and characterization by detecting mobile protein/peptides in cancerous tissues. However, T₁ confounds CEST measurements, leading to reduced specificity to amides and potential misinterpretation of APT imaging.</p><p><strong>Purpose: </strong>The study aimed to investigate the feasibility of the quasi-steady-state (QUASS)-based apparent exchange-dependent relaxation (AREX) analysis in correcting T₁ for unbiased tumor APT MRI at 3T.</p><p><strong>Materials and methods: </strong>CEST MRI experiments were conducted on an egg white phantom and on prospectively enrolled brain tumor patients with T₁ values modulated by gadolinium (Gd). QUASS algorithm was employed to reconstruct steady-state Z spectra. Conventional T₁-uncorrected CEST effect was quantified with a multipool Lorentzian function from QUASS Z spectra. The non-QUASS AREX and QUASS-based AREX with T₁ correction were calculated from the inverse of non-QUASS and QUASS Z spectra, respectively. The student's <i>t</i>-test and Bland-Altman plots were performed to assess the statistical difference and consistency between pre- and post-Gd measurements.</p><p><strong>Results: </strong>In the phantom study, vials with different T₁ values showed conspicuous discrepancy on the conventional uncorrected APT and non-QUASS AREX maps, but comparable contrast on the QUASS-based AREX map. In the human study, 13 patients were enrolled. The contralateral normal-appearing white matter exhibited no substantial change in T₁ and similar CEST effect between uncorrected APT, non-QUASS AREX, and QUASS-based AREX pre- and post-Gd (all <i>P</i> > .05). However, the tumor regions showed significantly reduced T₁ post-Gd that altered the CEST measurements obtained from uncorrected APT and non-QUASS AREX (both <i>P</i> < .001). In comparison, QUASS-based AREX measurements were in excellent agreement between pre- and post-Gd (<i>P</i> = .19).</p><p><strong>Conclusion: </strong>QUASS-based AREX analysis can effectively correct T₁ contamination in CEST measurements, facilitating unbiased tumor APT MRI at 3T.</p>","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 2","pages":"umaf011"},"PeriodicalIF":0.0,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429276/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mentoring program: bridging gaps for international authors.","authors":"Luiz Celso Hygino da Cruz, Antonio Luna","doi":"10.1093/radadv/umae036","DOIUrl":"10.1093/radadv/umae036","url":null,"abstract":"","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 1","pages":"umae036"},"PeriodicalIF":1.8,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429170/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reply to the letter to editor titled \"mentoring program: bridging gaps for international authors\".","authors":"Haidara Almansour, Vivianne Aguilera Freitas, Niraj Nirmal Pandey","doi":"10.1093/radadv/umae037","DOIUrl":"10.1093/radadv/umae037","url":null,"abstract":"","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 1","pages":"umae037"},"PeriodicalIF":1.8,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mitigating overtreatment of ductal carcinoma in situ.","authors":"Hannah L Chung, Tanya W Moseley, Dulcy E Wolverton, Gary J Whitman","doi":"10.1093/radadv/umaf007","DOIUrl":"10.1093/radadv/umaf007","url":null,"abstract":"<p><p>Ductal carcinoma in situ (DCIS) represents a pathologic continuum between a high-risk lesion of the breast and an invasive cancer. Because death from breast cancer is linked to its metastatic spread, the major significance of DCIS is its potential to progress to an invasive cancer and the risk of an occult invasive cancer unrecognized until surgical excision is performed. The standard of care management for DCIS is a minimum of surgical excision, often coupled with adjuvant treatments. For approximately half of the DCIS cases that are at low risk for progression, standard-of-care treatment represents a potential overtreatment and the source of one of the main criticisms against screening. To minimize overtreatment, the tumor biology of any individual's DCIS should be considered in the context of the patient's age, medical comorbidities, and tolerance for risk to tailor personalized treatments. Just as the management of some high-risk lesions of the breast have evolved to include nonsurgical options, it makes sense to personalize the management offered to patients with DCIS. This article reviews the epidemiology, imaging, pathology, ongoing trials, current and possible future treatments of DCIS, comparing and contrasting it with classic high-risk breast lesions and invasive breast cancers.</p>","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 3","pages":"umaf007"},"PeriodicalIF":1.8,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12483188/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The inaugural year of <i>Radiology Advances</i>: A look back and a note of thanks.","authors":"Susanna I Lee","doi":"10.1093/radadv/umaf003","DOIUrl":"https://doi.org/10.1093/radadv/umaf003","url":null,"abstract":"","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 1","pages":"umaf003"},"PeriodicalIF":0.0,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12429198/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}