Radiology
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

Published online before print October 24, 2002, 10.1148/radiol.2253011582
This Article
Right arrow Abstract Freely available
Right arrow Full Text
Right arrow Full Text (PDF)
Right arrow Submit a response
Right arrow Alert me when this article is cited
Right arrow Alert me when eLetters are posted
Right arrow Alert me if a correction is posted
Right arrow Citation Map
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Gilhuijs, K. G. A.
Right arrow Articles by Schultze Kool, L. J.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Gilhuijs, K. G. A.
Right arrow Articles by Schultze Kool, L. J.

Breast MR Imaging in Women at Increased Lifetime Risk of Breast Cancer: Clinical System for Computerized Assessment of Breast Lesions—Initial Results1

Kenneth G. A. Gilhuijs, PhD, Eline E. Deurloo, MD, Sara H. Muller, PhD, Johannes L. Peterse, MD and Leo J. Schultze Kool, MD, PhD

1 From the Departments of Radiology (K.G.A.G., E.E.D., S.H.M., L.J.S.K.) and Pathology (J.L.P.), The Netherlands Cancer Institute, Antoni van Leeuwenhoek Hospital, Plesmanlaan 121, 1066 CX Amsterdam, the Netherlands. From the 2000 RSNA scientific assembly. Received September 25, 2001; revision requested December 10; revision received March 1, 2002; accepted April 2. Address correspondence to K.G.A.G.



View larger version (25K):

[in a new window]
  		Figure 1. Bar graph indicates the size of lesions included in this study. cc = cm3.

 


View larger version (137K):

[in a new window]
  		Figure 2. Processed contrast-enhanced MR images: interactive lesion detection. Top row: Uptake images. Bottom row: Washout images. From left to right: Sagittal, transverse, and coronal reconstructions of the processed MR images. A lesion (infiltrating ductal carcinoma) with uptake and corresponding washout is selected at the center of the crosshairs for further analysis. Movement of any of the six crosshairs results in instant updating of all reconstructed views to maintain correspondence in three directions and in two types of processing simultaneously.

 


View larger version (22K):

[in a new window]
  		Figure 3. Graph of the ROC curve shows the prospective estimate of the TPF of the system at various FPF values in the task of discriminating between benign and malignant lesions. The curve was derived from leave-one-out validation of the training set of suspicious lesions. The fitted binormal ROC parameters a and b are 2.02 and 0.66, respectively.

 


View larger version (28K):

[in a new window]
  		Figure 4. Graph shows estimates of the largest feasible PPV with the system at NPV of at least 98% for various values of prevalence of malignancy (PM) (top axis) in the total population (ie, including normal images) and (bottom axis) in the population of suspicious lesions only. The maximum (PPV = 87%) is at a prevalence of 1.2% (total population).

 


View larger version (29K):

[in a new window]
  		Figure 5. Graph shows the estimate of the predictive curve of the lesion analysis system at 2% prevalence of malignancy in the subset of suspicious lesions. Details at the operating point (arrow) are listed in Table 4.

 




HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
RADIOLOGY RADIOGRAPHICS RSNA JOURNALS ONLINE
Copyright © 2002 by the Radiological Society of North America.