BJR artificial intelligence最新文献

{"title":"Auto-segmentation of neck nodal metastases using self-distilled masked image transformer on longitudinal MR images.","authors":"Ramesh Paudyal, Jue Jiang, James Han, Bill H Diplas, Nadeem Riaz, Vaios Hatzoglou, Nancy Lee, Joseph O Deasy, Harini Veeraraghavan, Amita Shukla-Dave","doi":"10.1093/bjrai/ubae004","DOIUrl":"10.1093/bjrai/ubae004","url":null,"abstract":"<p><strong>Objectives: </strong>Auto-segmentation promises greater speed and lower inter-reader variability than manual segmentations in radiation oncology clinical practice. This study aims to implement and evaluate the accuracy of the auto-segmentation algorithm, \"Masked Image modeling using the vision Transformers (SMIT),\" for neck nodal metastases on longitudinal T₂-weighted (T₂w) MR images in oropharyngeal squamous cell carcinoma (OPSCC) patients.</p><p><strong>Methods: </strong>This prospective clinical trial study included 123 human papillomaviruses (HPV-positive [+]) related OSPCC patients who received concurrent chemoradiotherapy. T₂w MR images were acquired on 3 T at pre-treatment (Tx), week 0, and intra-Tx weeks (1-3). Manual delineations of metastatic neck nodes from 123 OPSCC patients were used for the SMIT auto-segmentation, and total tumor volumes were calculated. Standard statistical analyses compared contour volumes from SMIT vs manual segmentation (Wilcoxon signed-rank test [WSRT]), and Spearman's rank correlation coefficients (<i>ρ</i>) were computed. Segmentation accuracy was evaluated on the test data set using the dice similarity coefficient (DSC) metric value. <i>P</i>-values <0.05 were considered significant.</p><p><strong>Results: </strong>No significant difference in manual and SMIT delineated tumor volume at pre-Tx (8.68 ± 7.15 vs 8.38 ± 7.01 cm³, <i>P</i> = 0.26 [WSRT]), and the Bland-Altman method established the limits of agreement as -1.71 to 2.31 cm³, with a mean difference of 0.30 cm³. SMIT model and manually delineated tumor volume estimates were highly correlated (<i>ρ</i> = 0.84-0.96, <i>P</i> < 0.001). The mean DSC metric values were 0.86, 0.85, 0.77, and 0.79 at the pre-Tx and intra-Tx weeks (1-3), respectively.</p><p><strong>Conclusions: </strong>The SMIT algorithm provides sufficient segmentation accuracy for oncological applications in HPV+ OPSCC.</p><p><strong>Advances in knowledge: </strong>First evaluation of auto-segmentation with SMIT using longitudinal T₂w MRI in HPV+ OPSCC.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"1 1","pages":"ubae004"},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10928808/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140112581","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":"Artificial intelligence in medicine: mitigating risks and maximizing benefits via quality assurance, quality control, and acceptance testing.","authors":"Usman Mahmood, Amita Shukla-Dave, Heang-Ping Chan, Karen Drukker, Ravi K Samala, Quan Chen, Daniel Vergara, Hayit Greenspan, Nicholas Petrick, Berkman Sahiner, Zhimin Huo, Ronald M Summers, Kenny H Cha, Georgia Tourassi, Thomas M Deserno, Kevin T Grizzard, Janne J Näppi, Hiroyuki Yoshida, Daniele Regge, Richard Mazurchuk, Kenji Suzuki, Lia Morra, Henkjan Huisman, Samuel G Armato, Lubomir Hadjiiski","doi":"10.1093/bjrai/ubae003","DOIUrl":"10.1093/bjrai/ubae003","url":null,"abstract":"<p><p>The adoption of artificial intelligence (AI) tools in medicine poses challenges to existing clinical workflows. This commentary discusses the necessity of context-specific quality assurance (QA), emphasizing the need for robust QA measures with quality control (QC) procedures that encompass (1) acceptance testing (AT) before clinical use, (2) continuous QC monitoring, and (3) adequate user training. The discussion also covers essential components of AT and QA, illustrated with real-world examples. We also highlight what we see as the shared responsibility of manufacturers or vendors, regulators, healthcare systems, medical physicists, and clinicians to enact appropriate testing and oversight to ensure a safe and equitable transformation of medicine through AI.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"1 1","pages":"ubae003"},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10928809/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140112580","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":"Launching <i>BJR</i>|<i>Artificial intelligence</i>: an editorial.","authors":"Heang-Ping Chan, Issam El Naqa","doi":"10.1093/bjrai/ubae002","DOIUrl":"10.1093/bjrai/ubae002","url":null,"abstract":"","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"1 1","pages":"ubae002"},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045697/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825218","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}