Evaluation of Semiautomated Measurements of Mesothelioma Tumor Thickness on CT Scans

Academic Radiology. Volume 12, Issue 10, October 2005, Pages 1301-1309. Available online 20 September 2005. [Link]

Samuel G. Armato III^a, Geoffrey R. Oxnard^a, Masha Kocherginsky^b, Nicholas J. Vogelzang^d, Hedy L. Kindler^c and Heber MacMahon^a

^aDepartment of Radiology, The University of Chicago, 5841 South Maryland Avenue, Chicago, IL 60637
^bDepartment of Health Studies, The University of Chicago, 5841 South Maryland Avenue, Chicago, IL 60637
^cDepartment of Medicine, The University of Chicago, 5841 South Maryland Avenue, Chicago, IL 60637
^dNevada Cancer Institute, Las Vegas, NV

Abstract

Rationale and Objectives: To evaluate the clinical acceptability of semiautomated methods for the measurement of mesothelioma tumor thickness in computed tomography (CT) scans.

Materials and Methods: A computer interface was developed to allow the acquisition of semiautomated mesothelioma tumor thickness measurements, which require the manual selection of a point along the outer margin of the tumor in a CT section. After application of an automated lung segmentation method, the computer automatically identifies a corresponding point along the inner margin of the tumor (as represented by the lung boundary), constructs a line segment between the manually selected outer tumor margin point and the computer-determined inner tumor margin point, and computes tumor thickness as the length of this line segment. Three radiologists and oncologists independently reviewed line segments representing the semiautomated measurements generated by three different algorithms at 134 measurement sites in the CT scans of 22 mesothelioma patients. The observers either accepted a measurement line segment or modified it through the interface. Differences between the initial semiautomated measurements and the measurements as modified by the observers were analyzed.

Results: The frequency with which observers accepted the semiautomated measurements without modification was as high as 86%. Of all measurements across all observers and methods (1,206 measurements), 89% were changed by 2 mm or less.

Conclusion: We have developed semiautomated methods to measure mesothelioma tumor thickness. The potential of these methods has been demonstrated through an observer study. We expect these methods to become important tools for the efficient quantification of tumor extent.

Key Words: Computer-aided diagnosis (CAD); malignant pleural mesothelioma; tumor measurement; computed tomography; image processing