David V Schacht1, Karen Drukker2, Iris Pak3, Hiroyuki Abe4, Maryellen L Giger5. 1. Department of Radiology, The University of Chicago, Section of Breast Imaging, 5841 S. Maryland Avenue, MC 2026, Chicago, IL 60637, United States. Electronic address: dschacht@radiology.bsd.uchicago.edu. 2. Department of Radiology, The University of Chicago, Section of Breast Imaging, 5841 S. Maryland Avenue, MC 2026, Chicago, IL 60637, United States. Electronic address: kdrukker@uchicago.edu. 3. Department of Radiology, The University of Chicago, Section of Breast Imaging, 5841 S. Maryland Avenue, MC 2026, Chicago, IL 60637, United States. Electronic address: irisgpak@gmail.com. 4. Department of Radiology, The University of Chicago, Section of Breast Imaging, 5841 S. Maryland Avenue, MC 2026, Chicago, IL 60637, United States. Electronic address: habe@radiology.bsd.uchicago.edu. 5. Department of Radiology, The University of Chicago, Section of Breast Imaging, 5841 S. Maryland Avenue, MC 2026, Chicago, IL 60637, United States. Electronic address: m-giger@uchicago.edu.
Abstract
PURPOSE: To assess the performance of computer extracted feature analysis of dynamic contrast enhanced (DCE) magnetic resonance images (MRI) of axillary lymph nodes. To determine which quantitative features best predict nodal metastasis. METHODS: This institutional board-approved HIPAA compliant study, in which informed patient consent was waived, collected enhanced T1 images of the axilla from patients with breast cancer. Lesion segmentation and feature analysis were performed on 192 nodes using a laboratory-developed quantitative image analysis (QIA) workstation. The importance of 28 features were assessed. Classification used the features as input to a neural net classifier in a leave-one-case-out cross-validation and evaluated with receiver operating characteristic (ROC) analysis. RESULTS: The area under the ROC curve (AUC) values for features in the task of distinguishing between positive and negative nodes ranged from just over 0.50 to 0.70. Five features yielded AUCs greater than 0.65: two morphological and three textural features. In cross-validation, the neural net classifier obtained an AUC of 0.88 (SE 0.03) for the task of distinguishing between positive and negative nodes. CONCLUSION: QIA of DCE MRI demonstrated promising performance in discriminating between positive and negative axillary nodes.
PURPOSE: To assess the performance of computer extracted feature analysis of dynamic contrast enhanced (DCE) magnetic resonance images (MRI) of axillary lymph nodes. To determine which quantitative features best predict nodal metastasis. METHODS: This institutional board-approved HIPAA compliant study, in which informed patient consent was waived, collected enhanced T1 images of the axilla from patients with breast cancer. Lesion segmentation and feature analysis were performed on 192 nodes using a laboratory-developed quantitative image analysis (QIA) workstation. The importance of 28 features were assessed. Classification used the features as input to a neural net classifier in a leave-one-case-out cross-validation and evaluated with receiver operating characteristic (ROC) analysis. RESULTS: The area under the ROC curve (AUC) values for features in the task of distinguishing between positive and negative nodes ranged from just over 0.50 to 0.70. Five features yielded AUCs greater than 0.65: two morphological and three textural features. In cross-validation, the neural net classifier obtained an AUC of 0.88 (SE 0.03) for the task of distinguishing between positive and negative nodes. CONCLUSION: QIA of DCE MRI demonstrated promising performance in discriminating between positive and negative axillary nodes.
Authors: Nola M Hylton; Jeffrey D Blume; Wanda K Bernreuter; Etta D Pisano; Mark A Rosen; Elizabeth A Morris; Paul T Weatherall; Constance D Lehman; Gillian M Newstead; Sandra Polin; Helga S Marques; Laura J Esserman; Mitchell D Schnall Journal: Radiology Date: 2012-06 Impact factor: 11.105
Authors: Armando E Giuliano; Kelly K Hunt; Karla V Ballman; Peter D Beitsch; Pat W Whitworth; Peter W Blumencranz; A Marilyn Leitch; Sukamal Saha; Linda M McCall; Monica Morrow Journal: JAMA Date: 2011-02-09 Impact factor: 56.272
Authors: Constance D Lehman; Constantine Gatsonis; Christiane K Kuhl; R Edward Hendrick; Etta D Pisano; Lucy Hanna; Sue Peacock; Stanley F Smazal; Daniel D Maki; Thomas B Julian; Elizabeth R DePeri; David A Bluemke; Mitchell D Schnall Journal: N Engl J Med Date: 2007-03-28 Impact factor: 91.245
Authors: Tristan C F van Heijst; Bram van Asselen; Ruud M Pijnappel; Marissa Cloos-van Balen; Jan J W Lagendijk; Desirée van den Bongard; Mariëlle E P Philippens Journal: Br J Radiol Date: 2016-05-10 Impact factor: 3.039
Authors: Pietro Bontempi; Alice Busato; Giamaica Conti; Sabino Walter Della Sala; Pasquina Marzola; Paolo Farace Journal: Contrast Media Mol Imaging Date: 2019-04-04 Impact factor: 3.161
Authors: Roberta Fusco; Mario Sansone; Vincenza Granata; Maurizio Di Bonito; Franca Avino; Orlando Catalano; Gerardo Botti; Antonella Petrillo Journal: Biomed Res Int Date: 2018-05-30 Impact factor: 3.411