Computer-assisted diagnosis for early stage pleural mesothelioma: towards automated detection and quantitative assessment of pleural thickening from thoracic CT images

Our plain-English summary of Computer-assisted diagnosis for early stage pleural mesothelioma: towards automated detection and quantitative assessment of pleural thickening from thoracic CT images, by K. Chaisaowong, T. Aach, P. Jäger, et al (Methods of Information in Medicine, 2007).

The study

• Authors: K. Chaisaowong, T. Aach, P. Jäger, S. Vogel, A. Knepper, T. Kraus
• Journal: Methods of Information in Medicine
• Published: 2007;46(3):324-31
• Cited by: 11 articles, as counted by NIH iCite
• Read it: PubMed · Publisher

Abstract

Objectives: Pleural thickenings as biomarker of exposure to asbestos may evolve into malignant pleural mesothelioma. For its early stage, pleurectomy with perioperative treatment can reduce morbidity and mortality. The diagnosis is based on a visual investigation of CT images, which is a time-consuming and subjective procedure. Our aim is to develop an automatic image processing approach to detect and quantitatively assess pleural thickenings.

Methods: We first segment the lung areas, and identify the pleural contours. A convexity model is then used together with a Hounsfield unit threshold to detect pleural thickenings. The assessment of the detected pleural thickenings is based on a spline-based model of the healthy pleura.

Results: Tests were carried out on 14 data sets from three patients. In all cases, pleural contours were reliably identified, and pleural thickenings detected. PC-based Computation times were 85 min for a data set of 716 slices, 35 min for 401 slices, and 4 min for 75 slices, resulting in an average computation time of about 5.2 s per slice. Visualizations of pleurae and detected thickenings were provided.

Conclusion: Results obtained so far indicate that our approach is able to assist physicians in the tedious task of finding and quantifying pleural thickenings in CT data. In the next step, our system will undergo an evaluation in a clinical test setting using routine CT data to quantify its performance.

In plain English

This article described a computer program the authors developed to find and measure pleural thickenings automatically on chest CT scans. The authors described pleural thickenings as a marker of asbestos exposure that may develop into malignant pleural mesothelioma. The program first outlined the lungs and pleura on each scan slice. It then flagged areas that broke the normally smooth outline of the pleura and kept those that spanned at least three slices and were dense enough. Finally, it estimated each thickening's size and volume. It was tested on 14 CT data sets from three male patients described as asbestos-exposed. In all cases the pleural outlines were identified and pleural thickenings were detected. Processing took 4 minutes for a 75-slice data set, 35 minutes for 401 slices and 85 minutes for 716 slices, about 5.2 seconds per slice on average. In one example, an area near the spinal cord was wrongly classified as a thickening. The authors concluded the approach could help physicians find and measure pleural thickenings. They said it still had to be evaluated in a clinical setting.

We wrote this plain-English summary from the full article with the help of AI, and a second AI model checked each sentence against the article. It is not the authors' wording; the abstract and the article are their own account.

What the study did and found

• Design: Technical development study of an automated image analysis system for CT scans, with a small preliminary test on patient data
• Who was studied: 14 thoracic CT data sets from three patients, all male, whose scans were taken within a preventive medical assessment program in Germany
• Exposure: The patients were described as asbestos-exposed. No fiber types, jobs or doses were given for them.
• Main results:
  • In all 14 data sets, pleural contours were identified and pleural thickenings were detected
  • Computing times on a PC were 85 minutes for a 716-slice data set, 35 minutes for 401 slices and 4 minutes for 75 slices, an average of about 5.2 seconds per slice
  • Per-slice times were 3.20 seconds for the 75-slice data set, 5.2 seconds for the 401-slice data set and 7.1 seconds for the 716-slice data set
  • In one example slice, a concave area near the spinal cord was wrongly classified as a pleural thickening
  • For one example thickening, the program measured an area of 8.23 square millimetres in one slice, a maximum thickness of 1.77 mm and a total volume of 6.60 cubic millimetres
• The authors' conclusion: The authors concluded that, based on results so far, their approach is able to assist physicians in finding and quantifying pleural thickenings in CT data
• Limitations the authors state:
  • The classification step does not yet use the position of detected thickenings, which led to a misclassification
  • Tissue (histopathological) findings from living patients were not available to check the results. The authors planned instead to compare the program with experienced physicians.
  • The system had not yet been evaluated in a clinical setting using routine CT data

Topics

Medical terms in this study, explained in our Lexicon: Pleural Mesothelioma, Pleural Thickening, Biomarker, Pleura.

Related studies

• Computer-assisted differential diagnosis of malignant mesothelioma based on syntactic structure analysis — B. Weyn, G. van de Wouwer, et al. (1999)
• Computer-assisted classification system for chest X-ray and computed tomography findings in occupational lung disease — T. Kraus, H.J. Raithel, et al. (1997)
• Can semi-automated image cytometry on induced sputum become a screening tool for lung cancer? Evaluation of quantitative semi-automated sputum cytometry on radon- and uranium-exposed workers — W. Marek, N. Kotschy-Lang, et al. (2001)
• Use of antimesothelial cell antibody and computer assisted quantitative analysis for distinguishing between reactive and neoplastic serosal tissues — A. Donna, P.G. Betta, et al. (1987)
• Computer-aided volumetric assessment of malignant pleural mesothelioma on CT using a random walk-based method — M. Chen, E. Helm, et al. (2017)
• Pitfalls in diagnosis of early stage malignant peritoneal mesothelioma: a case report — P.S. Lee, K.M. Auyeung, et al. (2002)

Browse return to medical research.