Radiology-Artificial Intelligence最新文献

{"title":"Stepwise Transfer Learning for Expert-level Pediatric Brain Tumor MRI Segmentation in a Limited Data Scenario.","authors":"Aidan Boyd, Zezhong Ye, Sanjay P Prabhu, Michael C Tjong, Yining Zha, Anna Zapaishchykova, Sridhar Vajapeyam, Paul J Catalano, Hasaan Hayat, Rishi Chopra, Kevin X Liu, Ali Nabavizadeh, Adam C Resnick, Sabine Mueller, Daphne A Haas-Kogan, Hugo J W L Aerts, Tina Y Poussaint, Benjamin H Kann","doi":"10.1148/ryai.230254","DOIUrl":"10.1148/ryai.230254","url":null,"abstract":"<p><p>Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001 through December 2015) from a national brain tumor consortium (<i>n</i> = 184; median age, 7 years [range, 1-23 years]; 94 male patients) and a pediatric cancer center (<i>n</i> = 100; median age, 8 years [range, 1-19 years]; 47 male patients) to develop and evaluate deep learning neural networks for pediatric low-grade glioma segmentation using a stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally tested on an independent test set and subjected to randomized blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain stepwise transfer learning (median Dice score coefficient, 0.88 [IQR, 0.72-0.91] vs 0.812 [IQR, 0.56-0.89] for baseline model; <i>P</i> = .049). With external testing, the AI model yielded excellent accuracy using reference standards from three clinical experts (median Dice similarity coefficients: expert 1, 0.83 [IQR, 0.75-0.90]; expert 2, 0.81 [IQR, 0.70-0.89]; expert 3, 0.81 [IQR, 0.68-0.88]; mean accuracy, 0.82). For clinical benchmarking (<i>n</i> = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score, 9 [IQR, 7-9] vs 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% vs 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level automated pediatric brain tumor autosegmentation and volumetric measurement with a high level of clinical acceptability. <b>Keywords:</b> Stepwise Transfer Learning, Pediatric Brain Tumors, MRI Segmentation, Deep Learning <i>Supplemental material is available for this article</i>. © RSNA, 2024.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294948/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141564667","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":"Navigating Clinical Variability: Transfer Learning's Impact on Imaging Model Performance.","authors":"Alexandre Cadrin-Chênevert","doi":"10.1148/ryai.240263","DOIUrl":"10.1148/ryai.240263","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294946/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141427772","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":"A New Era of Text Mining in Radiology with Privacy-Preserving LLMs.","authors":"Tugba Akinci D'Antonoli, Christian Bluethgen","doi":"10.1148/ryai.240261","DOIUrl":"10.1148/ryai.240261","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294969/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141427770","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":"Reproducibility Analysis of Radiomic Features on T2-weighted MR Images after Processing and Segmentation Alterations in Neuroblastoma Tumors.","authors":"Diana Veiga-Canuto, Matías Fernández-Patón, Leonor Cerdà Alberich, Ana Jiménez Pastor, Armando Gomis Maya, Jose Miguel Carot Sierra, Cinta Sangüesa Nebot, Blanca Martínez de Las Heras, Ulrike Pötschger, Sabine Taschner-Mandl, Emanuele Neri, Adela Cañete, Ruth Ladenstein, Barbara Hero, Ángel Alberich-Bayarri, Luis Martí-Bonmatí","doi":"10.1148/ryai.230208","DOIUrl":"10.1148/ryai.230208","url":null,"abstract":"<p><p>Purpose To evaluate the reproducibility of radiomics features extracted from T2-weighted MR images in patients with neuroblastoma. Materials and Methods A retrospective study included 419 patients (mean age, 29 months ± 34 [SD]; 220 male, 199 female) with neuroblastic tumors diagnosed between 2002 and 2023, within the scope of the PRedictive In-silico Multiscale Analytics to support cancer personalized diaGnosis and prognosis, Empowered by imaging biomarkers (ie, PRIMAGE) project, involving 746 T2/T2*-weighted MRI sequences at diagnosis and/or after initial chemotherapy. Images underwent processing steps (denoising, inhomogeneity bias field correction, normalization, and resampling). Tumors were automatically segmented, and 107 shape, first-order, and second-order radiomics features were extracted, considered as the reference standard. Subsequently, the previous image processing settings were modified, and volumetric masks were applied. New radiomics features were extracted and compared with the reference standard. Reproducibility was assessed using the concordance correlation coefficient (CCC); intrasubject repeatability was measured using the coefficient of variation (CoV). Results When normalization was omitted, only 5% of the radiomics features demonstrated high reproducibility. Statistical analysis revealed significant changes in the normalization and resampling processes (<i>P</i> < .001). Inhomogeneities removal had the least impact on radiomics (83% of parameters remained stable). Shape features remained stable after mask modifications, with a CCC greater than 0.90. Mask modifications were the most favorable changes for achieving high CCC values, with a radiomics features stability of 70%. Only 7% of second-order radiomics features showed an excellent CoV of less than 0.10. Conclusion Modifications in the T2-weighted MRI preparation process in patients with neuroblastoma resulted in changes in radiomics features, with normalization identified as the most influential factor for reproducibility. Inhomogeneities removal had the least impact on radiomics features. <b>Keywords:</b> Pediatrics, MR Imaging, Oncology, Radiomics, Reproducibility, Repeatability, Neuroblastic Tumors <i>Supplemental material is available for this article.</i> © RSNA, 2024 See also the commentary by Safdar and Galaria in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294951/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141307007","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":"Deep Learning Prostate MRI Segmentation Accuracy and Robustness: A Systematic Review.","authors":"Mohammad-Kasim Fassia, Adithya Balasubramanian, Sungmin Woo, Hebert Alberto Vargas, Hedvig Hricak, Ender Konukoglu, Anton S Becker","doi":"10.1148/ryai.230138","DOIUrl":"10.1148/ryai.230138","url":null,"abstract":"<p><p>Purpose To investigate the accuracy and robustness of prostate segmentation using deep learning across various training data sizes, MRI vendors, prostate zones, and testing methods relative to fellowship-trained diagnostic radiologists. Materials and Methods In this systematic review, Embase, PubMed, Scopus, and Web of Science databases were queried for English-language articles using keywords and related terms for prostate MRI segmentation and deep learning algorithms dated to July 31, 2022. A total of 691 articles from the search query were collected and subsequently filtered to 48 on the basis of predefined inclusion and exclusion criteria. Multiple characteristics were extracted from selected studies, such as deep learning algorithm performance, MRI vendor, and training dataset features. The primary outcome was comparison of mean Dice similarity coefficient (DSC) for prostate segmentation for deep learning algorithms versus diagnostic radiologists. Results Forty-eight studies were included. Most published deep learning algorithms for whole prostate gland segmentation (39 of 42 [93%]) had a DSC at or above expert level (DSC ≥ 0.86). The mean DSC was 0.79 ± 0.06 (SD) for peripheral zone, 0.87 ± 0.05 for transition zone, and 0.90 ± 0.04 for whole prostate gland segmentation. For selected studies that used one major MRI vendor, the mean DSCs of each were as follows: General Electric (three of 48 studies), 0.92 ± 0.03; Philips (four of 48 studies), 0.92 ± 0.02; and Siemens (six of 48 studies), 0.91 ± 0.03. Conclusion Deep learning algorithms for prostate MRI segmentation demonstrated accuracy similar to that of expert radiologists despite varying parameters; therefore, future research should shift toward evaluating segmentation robustness and patient outcomes across diverse clinical settings. <b>Keywords:</b> MRI, Genital/Reproductive, Prostate Segmentation, Deep Learning Systematic review registration link: osf.io/nxaev © RSNA, 2024.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294957/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140874810","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":"Improving Automated Hemorrhage Detection at Sparse-View CT via U-Net-based Artifact Reduction.","authors":"Johannes Thalhammer, Manuel Schultheiß, Tina Dorosti, Tobias Lasser, Franz Pfeiffer, Daniela Pfeiffer, Florian Schaff","doi":"10.1148/ryai.230275","DOIUrl":"10.1148/ryai.230275","url":null,"abstract":"<p><p>Purpose To explore the potential benefits of deep learning-based artifact reduction in sparse-view cranial CT scans and its impact on automated hemorrhage detection. Materials and Methods In this retrospective study, a U-Net was trained for artifact reduction on simulated sparse-view cranial CT scans in 3000 patients, obtained from a public dataset and reconstructed with varying sparse-view levels. Additionally, EfficientNet-B2 was trained on full-view CT data from 17 545 patients for automated hemorrhage detection. Detection performance was evaluated using the area under the receiver operating characteristic curve (AUC), with differences assessed using the DeLong test, along with confusion matrices. A total variation (TV) postprocessing approach, commonly applied to sparse-view CT, served as the basis for comparison. A Bonferroni-corrected significance level of .001/6 = .00017 was used to accommodate for multiple hypotheses testing. Results Images with U-Net postprocessing were better than unprocessed and TV-processed images with respect to image quality and automated hemorrhage detection. With U-Net postprocessing, the number of views could be reduced from 4096 (AUC: 0.97 [95% CI: 0.97, 0.98]) to 512 (0.97 [95% CI: 0.97, 0.98], <i>P</i> < .00017) and to 256 views (0.97 [95% CI: 0.96, 0.97], <i>P</i> < .00017) with a minimal decrease in hemorrhage detection performance. This was accompanied by mean structural similarity index measure increases of 0.0210 (95% CI: 0.0210, 0.0211) and 0.0560 (95% CI: 0.0559, 0.0560) relative to unprocessed images. Conclusion U-Net-based artifact reduction substantially enhanced automated hemorrhage detection in sparse-view cranial CT scans. <b>Keywords:</b> CT, Head/Neck, Hemorrhage, Diagnosis, Supervised Learning <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294955/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140877469","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":"Vision Transformer-based Deep Learning Models Accelerate Further Research for Predicting Neurosurgical Intervention.","authors":"Kengo Takahashi, Takuma Usuzaki, Ryusei Inamori","doi":"10.1148/ryai.240117","DOIUrl":"10.1148/ryai.240117","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294944/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141307009","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":"Bridging Pixels to Genes.","authors":"Mana Moassefi, Bradley J Erickson","doi":"10.1148/ryai.240262","DOIUrl":"10.1148/ryai.240262","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294947/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141427771","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":"From Nicki Minaj to Neuroblastoma: What Rigorous Approaches to Rhythms and Radiomics Have in Common.","authors":"Nabile M Safdar, Alina Galaria","doi":"10.1148/ryai.240350","DOIUrl":"10.1148/ryai.240350","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294945/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141627888","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":"Clinical, Cultural, Computational, and Regulatory Considerations to Deploy AI in Radiology: Perspectives of RSNA and MICCAI Experts.","authors":"Marius George Linguraru, Spyridon Bakas, Mariam Aboian, Peter D Chang, Adam E Flanders, Jayashree Kalpathy-Cramer, Felipe C Kitamura, Matthew P Lungren, John Mongan, Luciano M Prevedello, Ronald M Summers, Carol C Wu, Maruf Adewole, Charles E Kahn","doi":"10.1148/ryai.240225","DOIUrl":"10.1148/ryai.240225","url":null,"abstract":"<p><p>The Radiological Society of North of America (RSNA) and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society have led a series of joint panels and seminars focused on the present impact and future directions of artificial intelligence (AI) in radiology. These conversations have collected viewpoints from multidisciplinary experts in radiology, medical imaging, and machine learning on the current clinical penetration of AI technology in radiology and how it is impacted by trust, reproducibility, explainability, and accountability. The collective points-both practical and philosophical-define the cultural changes for radiologists and AI scientists working together and describe the challenges ahead for AI technologies to meet broad approval. This article presents the perspectives of experts from MICCAI and RSNA on the clinical, cultural, computational, and regulatory considerations-coupled with recommended reading materials-essential to adopt AI technology successfully in radiology and, more generally, in clinical practice. The report emphasizes the importance of collaboration to improve clinical deployment, highlights the need to integrate clinical and medical imaging data, and introduces strategies to ensure smooth and incentivized integration. <b>Keywords:</b> Adults and Pediatrics, Computer Applications-General (Informatics), Diagnosis, Prognosis © RSNA, 2024.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294958/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141564666","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}