Zhibin Yue1, Xiaoyu Wang2, Yan Wang1, Hongbo Wang3, Wenyan Jiang4. 1. School of Intelligent Medicine, China Medical University, Liaoning, 110122, People's Republic of China. 2. Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Liaoning, 110042, People's Republic of China. 3. Department of Oncology, Shengjing Hospital of China Medical University, Shenyang, 110004, People's Republic of China. sj_wanghb@163.com. 4. Department of Scientific Research and Academic, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Liaoning, 110042, People's Republic of China. xiaoya83921@163.com.
Abstract
PURPOSE: To compare values of multiparametric magnetic resonance imaging (MRI) sequences and propose clinical-radiomics nomogram for diagnosis of soft-tissue sarcoma (STS). PROCEDURES: This study enrolled 148 patients from Dec. 2017 to Feb. 2021. All patients underwent T1-weighted (T1W), contrast-enhanced T1-weighted (T1CE), and T2-weighted fat-suppressed (T2FS) MRI scans. A total of 1967 radiomic features were extracted from the segmented regions of interest (ROIs) in each MRI sequence. Highly diagnostic radiomic features were selected with Mann-Whitney U test, elastic net, and Akaike's information criterion (AIC) based on MRI images. Logistical regression was used to build Rad scores. Clinical factors were analyzed using the chi-square test or Mann-Whitney U test. The performance of the Rad scores was judged using the area under the receiver operating characteristic area under the curve (ROC AUC), sensitivity, specificity, and accuracy. The nomogram was developed by integrating the Rad score and the most important clinical factor. RESULTS: By combining the three MRI sequences, the Rad-Com was developed consisting of twelve features selected by with Mann-Whitney U test, elastic net, and AIC: four from T1W, three from TICE, and five from T2FS MRI. The margin (P < 0.05) demonstrated a statistically significant difference between patients with benign and malignant soft-tissue tumors (STT). The nomogram was constructed by integrating the Rad-Com and margin, which yielded favorable diagnostic AUCs of 0.919 (sensitivity (Sen) = 0.784, specificity (Spe) = 0.936) and 0.913 (Sen = 0.923, Spe = 0.792) in the training and validation cohort. CONCLUSION: The proposed nomogram may have potential as a noninvasive marker for STS diagnosis.
PURPOSE: To compare values of multiparametric magnetic resonance imaging (MRI) sequences and propose clinical-radiomics nomogram for diagnosis of soft-tissue sarcoma (STS). PROCEDURES: This study enrolled 148 patients from Dec. 2017 to Feb. 2021. All patients underwent T1-weighted (T1W), contrast-enhanced T1-weighted (T1CE), and T2-weighted fat-suppressed (T2FS) MRI scans. A total of 1967 radiomic features were extracted from the segmented regions of interest (ROIs) in each MRI sequence. Highly diagnostic radiomic features were selected with Mann-Whitney U test, elastic net, and Akaike's information criterion (AIC) based on MRI images. Logistical regression was used to build Rad scores. Clinical factors were analyzed using the chi-square test or Mann-Whitney U test. The performance of the Rad scores was judged using the area under the receiver operating characteristic area under the curve (ROC AUC), sensitivity, specificity, and accuracy. The nomogram was developed by integrating the Rad score and the most important clinical factor. RESULTS: By combining the three MRI sequences, the Rad-Com was developed consisting of twelve features selected by with Mann-Whitney U test, elastic net, and AIC: four from T1W, three from TICE, and five from T2FS MRI. The margin (P < 0.05) demonstrated a statistically significant difference between patients with benign and malignant soft-tissue tumors (STT). The nomogram was constructed by integrating the Rad-Com and margin, which yielded favorable diagnostic AUCs of 0.919 (sensitivity (Sen) = 0.784, specificity (Spe) = 0.936) and 0.913 (Sen = 0.923, Spe = 0.792) in the training and validation cohort. CONCLUSION: The proposed nomogram may have potential as a noninvasive marker for STS diagnosis.
Authors: George D Demetri; Laurence H Baker; Derrick Beech; Robert Benjamin; Ephraim S Casper; Ernest U Conrad; Thomas F DeLaney; David S Ettinger; Martin J Heslin; Ray J Hutchinson; Krystyna Kiel; William G Kraybill; G Douglas Letson; James Neff; Richard J O'Donnell; I Benjamin Paz; Raphael E Pollock; R Lor Randall; Karen D Schupak; Douglas S Tyler; Margaret von Mehren; Jeffrey Wayne Journal: J Natl Compr Canc Netw Date: 2005-03 Impact factor: 11.908
Authors: Philippe Lambin; Ralph T H Leijenaar; Timo M Deist; Jurgen Peerlings; Evelyn E C de Jong; Janita van Timmeren; Sebastian Sanduleanu; Ruben T H M Larue; Aniek J G Even; Arthur Jochems; Yvonka van Wijk; Henry Woodruff; Johan van Soest; Tim Lustberg; Erik Roelofs; Wouter van Elmpt; Andre Dekker; Felix M Mottaghy; Joachim E Wildberger; Sean Walsh Journal: Nat Rev Clin Oncol Date: 2017-10-04 Impact factor: 66.675
Authors: Virendra Kumar; Yuhua Gu; Satrajit Basu; Anders Berglund; Steven A Eschrich; Matthew B Schabath; Kenneth Forster; Hugo J W L Aerts; Andre Dekker; David Fenstermacher; Dmitry B Goldgof; Lawrence O Hall; Philippe Lambin; Yoganand Balagurunathan; Robert A Gatenby; Robert J Gillies Journal: Magn Reson Imaging Date: 2012-08-13 Impact factor: 2.546
Authors: Nisreen S Ezuddin; Juan Pretell-Mazzini; Raphael L Yechieli; Darcy A Kerr; Breelyn A Wilky; Ty K Subhawong Journal: Skeletal Radiol Date: 2018-05-21 Impact factor: 2.199
Authors: Rolf D Issels; Lars H Lindner; Jaap Verweij; Rüdiger Wessalowski; Peter Reichardt; Peter Wust; Pirus Ghadjar; Peter Hohenberger; Martin Angele; Christoph Salat; Zeljko Vujaskovic; Soeren Daugaard; Olav Mella; Ulrich Mansmann; Hans Roland Dürr; Thomas Knösel; Sultan Abdel-Rahman; Michael Schmidt; Wolfgang Hiddemann; Karl-Walter Jauch; Claus Belka; Alessandro Gronchi Journal: JAMA Oncol Date: 2018-04-01 Impact factor: 31.777