Introducing a secondary segmentation to construct a radiomics model for pulmonary tuberculosis cavities

Tamarisk du Plessis; Gopika Ramkilawon; William Ian Duncombe Rae; Tanita Botha; Neil Alexander Martinson; Sarah Alice Parry Dixon; Andre Kyme; Mike Michael Sathekge

doi:10.1007/s11547-023-01681-y

Introducing a secondary segmentation to construct a radiomics model for pulmonary tuberculosis cavities

Radiol Med. 2023 Sep;128(9):1093-1102. doi: 10.1007/s11547-023-01681-y. Epub 2023 Jul 20.

Authors

Tamarisk du Plessis¹, Gopika Ramkilawon², William Ian Duncombe Rae³, Tanita Botha², Neil Alexander Martinson^{4

5}, Sarah Alice Parry Dixon⁶, Andre Kyme⁶, Mike Michael Sathekge⁷

Affiliations

¹ Department of Nuclear Medicine, Faculty of Health Sciences, University of Pretoria, Pretoria, South Africa. tamarisk.duplessis@gmail.com.
² Department of Statistics, Faculty of Natural and Agricultural Sciences, University of Pretoria, Pretoria, South Africa.
³ Medical Imaging Department, Prince of Wales Hospital, Sydney, Australia.
⁴ Perinatal HIV Research Unit (PHRU), University of the Witwatersrand, Johannesburg, South Africa.
⁵ Johns Hopkins University Centre for TB Research, Baltimore, MD, USA.
⁶ School of Biomedical Engineering, University of Sydney, Sydney, Australia.
⁷ Department of Nuclear Medicine, Faculty of Health Sciences, University of Pretoria, Pretoria, South Africa.

Abstract

Purpose: Accurate segmentation (separating diseased portions of the lung from normal appearing lung) is a challenge in radiomic studies of non-neoplastic diseases, such as pulmonary tuberculosis (PTB). In this study, we developed a segmentation method, applicable to chest X-rays (CXR), that can eliminate the need for precise disease delineation, and that is effective for constructing radiomic models for automatic PTB cavity classification.

Methods: This retrospective study used a dataset of 266 posteroanterior CXR of patients diagnosed with laboratory confirmed PTB. The lungs were segmented using a U-net-based in-house automatic segmentation model. A secondary segmentation was developed using a sliding window, superimposed on the primary lung segmentation. Pyradiomics was used for feature extraction from every window which increased the dimensionality of the data, but this allowed us to accurately capture the spread of the features across the lung. Two separate measures (standard-deviation and variance) were used to consolidate the features. Pearson's correlation analysis (with a 0.8 cut-off value) was then applied for dimensionality reduction followed by the construction of Random Forest radiomic models.

Results: Two almost identical radiomic signatures consisting of 10 texture features each (9 were the same plus 1 other feature) were identified using the two separate consolidation measures. Two well performing random forest models were constructed from these signatures. The standard-deviation model (AUC = 0.9444 (95% CI, 0.8762; 0.9814)) performed marginally better than the variance model (AUC = 0.9288 (95% CI, 0.9046; 0.9843)).

Conclusion: The introduction of the secondary sliding window segmentation on CXR could eliminate the need for disease delineation in pulmonary radiomic studies, and it could improve the accuracy of CXR reporting currently regaining prominence as a high-volume screening tool as the developed radiomic models correctly classify cavities from normal CXR.

Keywords: Pulmonary tuberculosis; Radiomics; Segmentation; Sliding window.

MeSH terms

Humans
Lung / diagnostic imaging
Lung Diseases*
Radiography
Retrospective Studies
Tuberculosis, Pulmonary* / diagnostic imaging