Share Email Print
cover

Proceedings Paper

Measuring tumor burden: comparison of automatic and manual techniques
Author(s): Binsheng Zhao; Lawrence H. Schwartz; Robert A. Lefkowitz; Liang Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The reproducible measurement of tumors is critical to assess therapy response in oncology patients. Our purpose was to develop an automated technique of measuring tumor burden and compare the results with radiologists. 15 patients with pulmonary metastases were evaluated by 3 independent, blinded radiologists. Each radiologist identified and measured the 5 largest pulmonary metastases for each patient. A computerized method for automated detection and measurement of pulmonary nodules was developed. This included automatic detection of lung nodules using a local density maximum algorithm and accurate delineation of the nodules with a multi-criterion automated algorithm. Five largest nodules from each patient were determined using this method. The cross-product measurement was calculated as the greatest diameter and greatest perpendicular for each of the nodules automatically and by each radiologist. The mean cross-product size of the pulmonary metastases was 3.6 cm2 (range 0.6 to 12.2 cm2). All 3 Radiologists identified the identical 5 metastases as "largest" in only 5 (33%) of cases. They identified the same metastases 54/75 (72%) and at least 2 Radiologists identified the same metastases 66/75 (88%) of the time. Of the 54 metastases identified by all 3 Radiologists, the computer calculated 52 of these to be the largest. The difference in cross-product measurement was significant for 2 (p=.006, p= .003) of the 3 Radiologists. There was no significant difference in cross-product measurement for the automatic measurement as compared to any of the Radiologists. Automated measurement of tumor burden generates more reproducible measurements especially compared with the manual techniques used by one or more Radiologists.

Paper Details

Date Published: 12 May 2004
PDF: 6 pages
Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); doi: 10.1117/12.534342
Show Author Affiliations
Binsheng Zhao, Memorial Sloan-Kettering Cancer Ctr. (United States)
Lawrence H. Schwartz, Memorial Sloan-Kettering Cancer Ctr. (United States)
Robert A. Lefkowitz, Memorial Sloan-Kettering Cancer Ctr. (United States)
Liang Wang, Memorial Sloan-Kettering Cancer Ctr. (United States)


Published in SPIE Proceedings Vol. 5370:
Medical Imaging 2004: Image Processing
J. Michael Fitzpatrick; Milan Sonka, Editor(s)

© SPIE. Terms of Use
Back to Top