HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Abstract Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Related articles in JNM Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Nie, Y. Articles by Doi, K. Search for Related Content PubMed PubMed Citation Articles by Nie, Y. Articles by Doi, K.

Integrating PET and CT Information to Improve Diagnostic Accuracy for Lung Nodules: A Semiautomatic Computer-Aided Method

¹ Kurt Rossmann Laboratories for Radiologic Image Research, Department of Radiology, University of Chicago, Chicago, Illinois; and ² Department of Radiology, General Hospital of PLA, Beijing, China

View larger version (12K): [in a new window]   FIGURE 1.  ROC curves for performance of computer outputs based on PET features alone, CT features alone, and both PET and CT features. Statistically significant difference exists between computer output based on both PET and CT and that based on PET alone (P = 0.037) or CT alone (P = 0.015).

View larger version (11K): [in a new window]   FIGURE 2.  Number of cases with potentially beneficial and detrimental effects resulting from use of CT features in addition to PET features. Number of cases with beneficial effect is larger than that with detrimental effect.

View larger version (21K): [in a new window]   FIGURE 3.  Number of cases with potentially beneficial and detrimental changes (>0.1) and with minor changes (<0.1) in computer output resulting from use of PET and additional CT features for 4 groups of nodules by SUV (A) and 3 groups of nodules by size (B). Number of cases with beneficial effects resulting from use of additional CT features was larger than that with detrimental effects, especially when nodule SUV was between 1 and 4 or nodule was smaller than 2 cm.

View larger version (52K): [in a new window]   FIGURE 4.  69-y-old woman with adenocarcinoma. (A) Axial CT scan shows 0.6-cm spiculated nodule in right upper lobe. (B) Nodule SUV was 1.2 on PET scan. Computer outputs based on CT features alone, PET features alone, and both PET and CT features were 0.96, 0.27, and 0.84, respectively. Use of CT features improved (increased) estimated likelihood of malignancy based on PET.

View larger version (59K): [in a new window]   FIGURE 5.  51-y-old man with benign nodule that resolved after antibiotic therapy. (A) Axial CT scan shows 2.0-cm nodule in right upper lobe. (B) Nodule SUV was 2.5 on PET scan. Computer outputs based on CT features alone, PET features alone, and both PET and CT features were 0.29, 0.78, and 0.41, respectively. Use of CT features improved (decreased) estimated likelihood of malignancy based on PET.