Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Nov;66(11):1979-1992.
doi: 10.1007/s00234-024-03435-7. Epub 2024 Aug 5.

Radiomics features for the discrimination of tuberculomas from high grade gliomas and metastasis: a multimodal study

Abhilasha Indoria  1 , Karthik Kulanthaivelu  1 , Chandrajit Prasad  1 , Dwarakanath Srinivas  2 , Shilpa Rao  3 , Neelam Sinha  4 , Vivek Potluri  5 , M Netravathi  5 , Atchayaram Nalini  5 , Jitender Saini  6
Affiliations

Radiomics features for the discrimination of tuberculomas from high grade gliomas and metastasis: a multimodal study

Abhilasha Indoria et al. Neuroradiology. 2024 Nov.

Abstract

Background: Tuberculomas are prevalent in developing countries and demonstrate variable signals on MRI resulting in the overlap of the conventional imaging phenotype with other entities including glioma and brain metastasis. An accurate MRI diagnosis is important for the early institution of anti-tubercular therapy, decreased patient morbidity, mortality, and prevents unnecessary neurosurgical excision. This study aims to assess the potential of radiomics features of regular contrast images including T1W, T2W, T2W FLAIR, T1W post contrast images, and ADC maps, to differentiate between tuberculomas, high-grade-gliomas and metastasis, the commonest intra parenchymal mass lesions encountered in the clinical practice.

Methods: This retrospective study includes 185 subjects. Images were resampled, co-registered, skull-stripped, and zscore-normalized. Automated lesion segmentation was performed followed by radiomics feature extraction, train-test split, and features reduction. All machine learning algorithms that natively support multiclass classification were trained and assessed on features extracted from individual modalities as well as combined modalities. Model explainability of the best performing model was calculated using the summary plot obtained by SHAP values.

Results: Extra tree classifier trained on the features from ADC maps was the best classifier for the discrimination of tuberculoma from high-grade-glioma and metastasis with AUC-score of 0.96, accuracy-score of 0.923, Brier-score of 0.23.

Conclusion: This study demonstrates that radiomics features are effective in discriminating between tuberculoma, metastasis, and high-grade-glioma with notable accuracy and AUC scores. Features extracted from the ADC maps surfaced as the most robust predictors of the target variable.

Keywords: Explainable artificial intelligence; High-grade glioma; Machine learning; Metastasis; Multi-modality radiomics; Tuberculoma.

PubMed Disclaimer

References

    1. Erdem H, Inan A, Guven E, Hargreaves S, Larsen L, Shehata G, Pernicova E, Khan E, Bastakova L, Namani S, Harxhi A, Roganovic T, Lakatos B, Uysal S, Sipahi OR, Crisan A, Miftode E, Stebel R, Jegorovic B, Fehér Z, Jekkel C, Pandak N, Moravveji A, Yilmaz H, Khalifa A, Musabak U, Yilmaz S, Jouhar A, Oztoprak N, Argemi X, Baldeyrou M, Bellaud G, Moroti RV, Hasbun R, Salazar L, Tekin R, Canestri A, Čalkić L, Praticò L, Yilmaz-Karadag F, Santos L, Pinto A, Kaptan F, Bossi P, Aron J, Duissenova A, Shopayeva G, Utaganov B, Grgic S, Ersoz G, Wu AKL, Lung KC, Bruzsa A, Radic LB, Kahraman H, Momen-Heravi M, Kulzhanova S, Rigo F, Konkayeva M, Smagulova Z, Tang T, Chan P, Ahmetagic S, Porobic-Jahic H, Moradi F, Kaya S, Cag Y, Bohr A, Artuk C, Celik I, Amsilli M, Gul HC, Cascio A, Lanzafame M, Nassar M (2017) The burden and epidemiology of community-acquired central nervous system infections: a multinational study. Eur J Clin Microbiol Infect Dis 36:1595–1611. https://doi.org/10.1007/s10096-017-2973-0 - DOI - PubMed
    1. Ma H, Liu Y, Zhuang C, Shen Y, Wu R (2018) Clinical features and MRI findings of intracranial tuberculomas. Radiol Infect Dis 5:154–159. https://doi.org/10.1016/j.jrid.2018.10.001 - DOI
    1. Boruah D, Sarma K, Gogoi P, Singh B, Gogoi B, Hazarika K, Sharma B, Phukan P (2022) Magnetic resonance imaging appearance of Giant Intracerebral Tuberculoma: a retrospective analysis. Acta Med Lituanica 29:249–261. https://doi.org/10.15388/Amed.2022.29.2.19 - DOI
    1. Agrawal P, Phuyal S, Panth R, Shrestha P, Lamsal R (2020) Giant Cerebral Tuberculoma Masquerading as Malignant Brain Tumor - A Report of two cases. Cureus 12:e10546. https://doi.org/10.7759/cureus.10546 - DOI - PubMed - PMC
    1. Sahu C, Bhargava N, Singh V, Dwivedi P (2020) Giant Tuberculomas of Brain: rare neoplastic mimic. J Pediatr Neurosci 15:204–213. https://doi.org/10.4103/jpn.JPN_78_19 - DOI - PubMed - PMC

MeSH terms

LinkOut - more resources