DOI: 10.1186/s13550-018-0411-7Pages: 1-14

A semi-automatic technique to quantify complex tuberculous lung lesions on 18F-fluorodeoxyglucose positron emission tomography/computerised tomography images

1. DDST-NRF Centre of Excellence for Biomedical Tuberculosis Research and South African Medical Research Council Centre for Tuberculosis Research

2. Stellenbosch University, Division of Molecular Biology and Human Genetics, Faculty of Medicine and Health Sciences

3. Laboratory for Cognitive Neurology, Department of Neurosciences

4. Stellenbosch University, Division of Nuclear Medicine, Department of Medical Imaging and Clinical Oncology, Faculty of Medicine and Health Sciences

5. National Institutes of Health, Tuberculosis Research Section, Laboratory of Clinical Infectious Diseases, Division of Intramural Research, National Institute of Allergy and Infectious Diseases

6. University of Cape Town, Wellcome Centre for Infectious Disease Research in Africa, Institute of Infectious Disease and Molecular Medicine, Faculty of Health Science

7. Groote Schuur Hospital, University of Cape Town, Department of Medicine, Faculty of Health Science

8. The Francis Crick Institute

9. Imperial College London, Department of Medicine

10. Stellenbosch University, Division of Radiodiagnosis, Department of Medical Imaging and Clinical Oncology, Faculty of Medicine and Health Sciences

11. Mater Research Institute – The University of Queensland, Translational Research Institute

12. Catalysis Foundation for Health

Correspondence to:
Stephanus T. Malherbe




There is a growing interest in the use of 18F-FDG PET-CT to monitor tuberculosis (TB) treatment response. However, TB causes complex and widespread pathology, which is challenging to segment and quantify in a reproducible manner.

To address this, we developed a technique to standardise uptake (Z-score), segment and quantify tuberculous lung lesions on PET and CT concurrently, in order to track changes over time. We used open source tools and created a MATLAB script. The technique was optimised on a training set of five pulmonary tuberculosis (PTB) cases after standard TB therapy and 15 control patients with lesion-free lungs.


We compared the proposed method to a fixed threshold (SUV > 1) and manual segmentation by two readers and piloted the technique successfully on scans of five control patients and five PTB cases (four cured and one failed treatment case), at diagnosis and after 1 and 6 months of treatment. There was a better correlation between the Z-score-based segmentation and manual segmentation than SUV > 1 and manual segmentation in terms of overall spatial overlap (measured in Dice similarity coefficient) and specificity (1 minus false positive volume fraction). However, SUV > 1 segmentation appeared more sensitive. Both the Z-score and SUV > 1 showed very low variability when measuring change over time. In addition, total glycolytic activity, calculated using segmentation by Z-score and lesion-to-background ratio, correlated well with traditional total glycolytic activity calculations. The technique quantified various PET and CT parameters, including the total glycolytic activity index, metabolic lesion volume, lesion volumes at different CT densities and combined PET and CT parameters. The quantified metrics showed a marked decrease in the cured cases, with changes already apparent at month one, but remained largely unchanged in the failed treatment case.


Our technique is promising to segment and quantify the lung scans of pulmonary tuberculosis patients in a semi-automatic manner, appropriate for measuring treatment response. Further validation is required in larger cohorts.

This article is freely available, click here to access the full text/PDF

  • Accepted: Jun 8, 2018
  • Online: Jun 25, 2018

Article Tools