Evaluation of Semiautomated Measurements of Mesothelioma Tumor Thickness on CT Scans1

Department of Radiology, The University of Chicago, 5841 South Maryland Avenue, Chicago, IL 60637, USA.
Academic Radiology (Impact Factor: 2.08). 11/2005; 12(10):1301-9. DOI: 10.1016/j.acra.2005.05.021
Source: PubMed

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

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Aufbauend auf früheren Arbeiten wurde ein Bildverarbeitungssystem entwickelt, welches pleurale Verdickungen automatisch lokalisiert und visualisiert. Es liefert reproduzierbare, quantitative Daten, die eine genauere Beobachtung der Verdickungen ermöglichen als die konventionelle Befundungsmethode, und reduziert den für die Befundung nötigen Zeitaufwand. Die automatische Detektion findet innerhalb eines zweistufigen Algorithmus statt, der zuerst aus allen Schichten des Datensatzes die Pleurakonturen extrahiert und darauf aufbauend die Verdickungen in den Pleurakonturen detektiert. Da die Änderung der Form einer Verdickung ein wichtiges Kriterium bei der Entscheidung ist, ob eine Verdickung entartet, wurde eine Möglichkeit zur Visualisierung der Verdickungen und der Lungenflügel implementiert. Diese können nun aus allen Perspektiven betrachtet werden. Unterschiede in den Verdickungen zweier aufeinanderfolgender Scans können so erkannt werden.
    Bildverarbeitung für die Medizin 2006, Algorithmen, Systeme, Anwendungen, Proceedings des Workshops vom 19. - 21. März 2006 in Hamburg; 01/2006
  • [Show abstract] [Hide abstract]
    ABSTRACT: : The purpose of this study was to investigate the continuous changes in three distinct response assessment methods during treatment as a marker of response for patients with mesothelioma. Linear tumor thickness measurements, disease volume measurements, and lung volume measurements (a physiological correlate of disease volumes) were investigated in this study. : Serial computed tomography scans were obtained during the course of clinically standard chemotherapy for 61 patients. For each of the 216 computed tomography scans, the aerated lung volumes were segmented using a fully automated method, and the pleural disease volume was segmented using a semiautomated method. Modified Response Evaluation Criteria in Solid Tumors linear-thickness measurements were acquired clinically. Diseased (ipsilateral) lung volumes were normalized by the respective contralateral lung volumes to account for the differences in inspiration between scans for each patient. Relative changes in each metric from baseline were tracked over the course of follow-up imaging. Survival modeling was performed using Cox proportional hazards models with time-varying covariates. : Median survival from pretreatment baseline imaging was 12.7 months. A negative correlation was observed between measurements of lung volume and disease volume, and a positive correlation was observed between linear-thickness measurements and disease volume. As continuous numerical parameters, all three response assessment methods were significant imaging biomarkers of patient prognosis in independent survival models. : Analysis of trajectories of linear-thickness measurements, disease volume measurements, and lung volume measurements during chemotherapy for patients with mesothelioma indicates that increasing linear thickness, increasing disease volume, and decreasing lung volume are all significantly and independently associated with poor patient prognosis.
    Journal of thoracic oncology: official publication of the International Association for the Study of Lung Cancer 04/2013; 8(4):478-86. DOI:10.1097/JTO.0b013e31828354c8 · 5.80 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: title = {Computer-Assisted Diagnosis for Early Stage Pleural Mesothelioma: Automated Extraction of Pleura to Detect Pleural Thickenings from Thoracic {CT} Images}, booktitle = {Proc. International Workshop on Advanced Image Technology}, address = {Bangkok}, pages = {229--234}, month = {January 8--9,}, year = {2007}, } © Agreement on the Copyright Transfer. The authors agree to transfer all copyright right in and to the above work to the IWAIT 2007 Steering Board so that the IWAIT 2007 Steering Board shall have the right to publish the work for non-profit use in any media or form. In return, authors retain (1) all proprietary right other than copyright (2) re-use of all or part of the above paper in their other work, and (3) right to reproduce or authorize others to reproduce the above paper for authors's personal use or for company use if the source and IWAIT 2007 copyright notice is indicated and if the reproduction is not made for the purpose or sale. ABSTRACT Malignant pleuramesothelioma is an occupational disease, which is caused by asbestos exposure. After its diagnosis, a survival time lasting between 4 to 18 months was reported. However, the earlier a pleural mesothelioma is found, the higher the survival time expected due to appropriate ther-apy methods. To date, diagnosis was done by subjective investigation of thoracic CT images of patients on a work-station, which turned out to be a very time consuming pro-cedure. In this work, a method is described to implement a software system with a graphical user interface to auto-matically detect pleural thickenings, including the 3D visu-alization feature of the pleura. Accurate and reliable docu-mentation of diagnostic findings is helpful for therapy, thus reducing the morbidity and delaying the mortality.