{"title":"Breast Cancer Risk Assessment in the AI Era: The Importance of Model Validation in Ethnically Diverse Cohorts.","authors":"Despina Kontos, Jayashree Kalpathy-Cramer","doi":"10.1148/ryai.230462","DOIUrl":"https://doi.org/10.1148/ryai.230462","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10698584/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138810442","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":"Chest Radiographs: A New Form of Identification?","authors":"Vineet K Raghu, Michael T Lu","doi":"10.1148/ryai.230397","DOIUrl":"https://doi.org/10.1148/ryai.230397","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10698601/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138810443","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}
Hui Ming Lin, Errol Colak, Tyler Richards, Felipe C Kitamura, Luciano M Prevedello, Jason Talbott, Robyn L Ball, Ekim Gumeler, Kristen W Yeom, Mohammad Hamghalam, Amber L Simpson, Jasna Strika, Deniz Bulja, Salita Angkurawaranon, Almudena Pérez-Lara, María Isabel Gómez-Alonso, Johanna Ortiz Jiménez, Jacob J Peoples, Meng Law, Hakan Dogan, Emre Altinmakas, Ayda Youssef, Yasser Mahfouz, Jayashree Kalpathy-Cramer, Adam E Flanders
{"title":"The RSNA Cervical Spine Fracture CT Dataset.","authors":"Hui Ming Lin, Errol Colak, Tyler Richards, Felipe C Kitamura, Luciano M Prevedello, Jason Talbott, Robyn L Ball, Ekim Gumeler, Kristen W Yeom, Mohammad Hamghalam, Amber L Simpson, Jasna Strika, Deniz Bulja, Salita Angkurawaranon, Almudena Pérez-Lara, María Isabel Gómez-Alonso, Johanna Ortiz Jiménez, Jacob J Peoples, Meng Law, Hakan Dogan, Emre Altinmakas, Ayda Youssef, Yasser Mahfouz, Jayashree Kalpathy-Cramer, Adam E Flanders","doi":"10.1148/ryai.230034","DOIUrl":"10.1148/ryai.230034","url":null,"abstract":"<p><p>This dataset is composed of cervical spine CT images with annotations related to fractures; it is available at https://www.kaggle.com/competitions/rsna-2022-cervical-spine-fracture-detection/.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10546361/pdf/ryai.230034.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41111242","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 AI Generalization Gap: One Size Does Not Fit All.","authors":"Merel Huisman, Gerjon Hannink","doi":"10.1148/ryai.230246","DOIUrl":"10.1148/ryai.230246","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10546357/pdf/ryai.230246.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41104173","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 Remark on Using Data Twice in Cross-Validation Schemes.","authors":"Aydin Demircioğlu","doi":"10.1148/ryai.230202","DOIUrl":"https://doi.org/10.1148/ryai.230202","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10546366/pdf/ryai.230202.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41158051","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":"On the Centrality of Data: Data Resources in Radiologic Artificial Intelligence.","authors":"John Mongan, Safwan S Halabi","doi":"10.1148/ryai.230231","DOIUrl":"10.1148/ryai.230231","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10546351/pdf/ryai.230231.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41151820","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}
Chika F Ezeana, Tiancheng He, Tejal A Patel, Virginia Kaklamani, Maryam Elmi, Erika Brigmon, Pamela M Otto, Kenneth A Kist, Heather Speck, Lin Wang, Joe Ensor, Ya-Chen T Shih, Bumyang Kim, I-Wen Pan, Adam L Cohen, Kristen Kelley, David Spak, Wei T Yang, Jenny C Chang, Stephen T C Wong
{"title":"A Deep Learning Decision Support Tool to Improve Risk Stratification and Reduce Unnecessary Biopsies in BI-RADS 4 Mammograms.","authors":"Chika F Ezeana, Tiancheng He, Tejal A Patel, Virginia Kaklamani, Maryam Elmi, Erika Brigmon, Pamela M Otto, Kenneth A Kist, Heather Speck, Lin Wang, Joe Ensor, Ya-Chen T Shih, Bumyang Kim, I-Wen Pan, Adam L Cohen, Kristen Kelley, David Spak, Wei T Yang, Jenny C Chang, Stephen T C Wong","doi":"10.1148/ryai.220259","DOIUrl":"10.1148/ryai.220259","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the performance of a biopsy decision support algorithmic model, the intelligent-augmented breast cancer risk calculator (iBRISK), on a multicenter patient dataset.</p><p><strong>Materials and methods: </strong>iBRISK was previously developed by applying deep learning to clinical risk factors and mammographic descriptors from 9700 patient records at the primary institution and validated using another 1078 patients. All patients were seen from March 2006 to December 2016. In this multicenter study, iBRISK was further assessed on an independent, retrospective dataset (January 2015-June 2019) from three major health care institutions in Texas, with Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions. Data were dichotomized and trichotomized to measure precision in risk stratification and probability of malignancy (POM) estimation. iBRISK score was also evaluated as a continuous predictor of malignancy, and cost savings analysis was performed.</p><p><strong>Results: </strong>The iBRISK model's accuracy was 89.5%, area under the receiver operating characteristic curve (AUC) was 0.93 (95% CI: 0.92, 0.95), sensitivity was 100%, and specificity was 81%. A total of 4209 women (median age, 56 years [IQR, 45-65 years]) were included in the multicenter dataset. Only two of 1228 patients (0.16%) in the \"low\" POM group had malignant lesions, while in the \"high\" POM group, the malignancy rate was 85.9%. iBRISK score as a continuous predictor of malignancy yielded an AUC of 0.97 (95% CI: 0.97, 0.98). Estimated potential cost savings were more than $420 million.</p><p><strong>Conclusion: </strong>iBRISK demonstrated high sensitivity in the malignancy prediction of BI-RADS 4 lesions. iBRISK may safely obviate biopsies in up to 50% of patients in low or moderate POM groups and reduce biopsy-associated costs.<b>Keywords:</b> Mammography, Breast, Oncology, Biopsy/Needle Aspiration, Radiomics, Precision Mammography, AI-augmented Biopsy Decision Support Tool, Breast Cancer Risk Calculator, BI-RADS 4 Mammography Risk Stratification, Overbiopsy Reduction, Probability of Malignancy (POM) Assessment, Biopsy-based Positive Predictive Value (PPV3) <i>Supplemental material is available for this article.</i> Published under a CC BY 4.0 license.See also the commentary by McDonald and Conant in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10698614/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47632038","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":"TotalSegmentator: A Gift to the Biomedical Imaging Community.","authors":"Ronnie Sebro, John Mongan","doi":"10.1148/ryai.230235","DOIUrl":"https://doi.org/10.1148/ryai.230235","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10546367/pdf/ryai.230235.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41167842","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}
Jacob A Macdonald, Zhe Zhu, Brandon Konkel, Maciej A Mazurowski, Walter F Wiggins, Mustafa R Bashir
{"title":"Duke Liver Dataset: A Publicly Available Liver MRI Dataset with Liver Segmentation Masks and Series Labels.","authors":"Jacob A Macdonald, Zhe Zhu, Brandon Konkel, Maciej A Mazurowski, Walter F Wiggins, Mustafa R Bashir","doi":"10.1148/ryai.220275","DOIUrl":"10.1148/ryai.220275","url":null,"abstract":"<p><p>The Duke Liver Dataset contains 2146 abdominal MRI series from 105 patients, including a majority with cirrhotic features, and 310 image series with corresponding manually segmented liver masks.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":9.8,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10546360/pdf/ryai.220275.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41150555","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}