Araştırma Makalesi

Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm

Cilt: 36 Sayı: 2026 16 Ekim 2026
Habip Eser Akkaya *, Önder Polat , Dorukan İnanç Akpınar , Zeynep Ziroglu , Muhammet Uzun , Hafize Nalan Güneş
PDF İndir
Genel Tıp Dergisi Kapak Genel Tıp Dergisi
EN TR

Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm

Öz

Aim: To investigate whether MRI-derived texture (radiomic) features combined with machine learning can provide objective diagnostic discrimination between patients with hemifacial spasm (HFS) and healthy controls, and to evaluate the added value of high-resolution 3D T2-SPACE imaging.
Materials and Methods: This retrospective study included 35 patients with clinically diagnosed HFS and 36 age- and sex-matched controls. All subjects underwent 3-Tesla MRI with axial T2-weighted imaging (T2WI), and a subgroup of 21 HFS patients and their matched controls also underwent 3D T2-SPACE imaging. Segmentation was performed across axial slices encompassing the brainstem, the entire posterior fossa, and the inner ear, middle ear, and mastoid portions, with the anterior boundary extending to the clivus, using a single manually drawn region of interest (ROI) to capture comprehensive radiomic features. 137 radiomic texture features were extracted using the PyRadiomics platform. Multiple machine learning classifiers, including k-nearest neighbors, Naive Bayes, discriminant analysis, decision trees, and ensemble learning methods, were evaluated. Data were split into 80% training and 20% testing sets, and performance was assessed using accuracy, sensitivity, specificity, and ROC-AUC over 20 randomized repetitions.
Results: Among all tested models, the Ensemble Bagged Trees classifier demonstrated the highest overall performance among the tested models. Using T2WI, the model achieved a mean accuracy of 0.71 ± 0.10, sensitivity of 0.72 ± 0.15, specificity of 0.70 ± 0.18, and ROC-AUC of 0.76 ± 0.16. In the subgroup analyzed with high-resolution 3D T2-SPACE imaging, performance further improved, yielding a mean accuracy of 0.80 ± 0.12, sensitivity of 0.67 ± 0.23, specificity of 0.95 ± 0.12, and ROC-AUC of 0.85 ± 0.11. High-resolution T2-SPACE images provided an improvement in specificity compared with conventional T2WI.
Conclusions: Radiomic texture features extracted from conventional and high-resolution MRI, when combined with ensemble machine learning methods, show potential for facilitating discrimination between patients with hemifacial spasm and healthy controls. The particularly high specificity achieved with 3D T2-SPACE imaging suggests that this approach may serve as a promising complementary diagnostic tool, supporting conventional imaging and clinical assessment and offering a step toward objective, image-based biomarkers for HFS.

Anahtar Kelimeler

Hemifacial spasm, Machine learning, Magnetic Resonance Imaging, Radiomics

Destekleyen Kurum

None.

Etik Beyan

Ethical approval was obtained from the ethics committee of Ankara Training and Research Hospital (Date: September 6, 2023, number: E-93471371-514.99-223932257, E-23-1359).

Kaynakça

  1. 1. Haller S, Etienne L, Kövari E, Varoquaux AD, Urbach H, Becker M. Imaging of Neurovascular Compression Syndromes: Trigeminal Neuralgia, Hemifacial Spasm, Vestibular Paroxysmia, and Glossopharyngeal Neuralgia. AJNR Am J Neuroradiol 2016;3 7(8):1384–1392.
  2. 2.Sringean J, Dressler D, Bhidayasiri R. More than hemifacial spasm? A case of unilateral facial spasms with systematic review of red flags. J Neurol Sci 2019; 407:116532.
  3. 3.Hermier M. Imaging of hemifacial spasm. Neurochirurgie 2018; 64(2):117–123.
  4. 4. Aktan D, Depierreux F. How to face the hemifacial spasm: challenges and misconceptions. Acta Neurol Belg 2024; 124(1):17–23.
  5. 5. Raslan AM, DeJesus R, Berk C, Zacest A, Anderson JC, Burchiel KJ. Sensitivity of high-resolution three-dimensional magnetic resonance angiography and three-dimensional spoiled-gradient recalled imaging in the prediction of neurovascular compression in patients with hemifacial spasm. J Neurosurg 2009; 111(4):733–736.
  6. 6. Sindgi RP, Jamiyen B. Neuroimaging Markers for Diagnosis and Management of Hemifacial Spasm: A Systematic Review. Vascular and Endovascular Review 2025; 8(16s):21-27.
  7. 7. Port JD. Advanced magnetic resonance imaging techniques for patients with hemifacial spasm. Ophthalmic Plast Reconstr Surg, 2002;18(1). 72–74.
  8. 8. Liang C, Yang L, Reichardt W, Zhang B, Li R. Different MRI-based methods for the diagnosis of neurovascular compression in trigeminal neuralgia or hemifacial spasm: A network meta-analysis. J Clin Neurosci 2023; 108:19–24.
  9. 9. Mulford KL, Moen SL, Grande AW, Nixdorf DR, Van de Moortele PF. Identifying symptomatic trigeminal nerves from MRI in a cohort of trigeminal neuralgia patients using radiomics. Neuroradiology. 2022; 64(3):603-609.
  10. 10. Zhang F, Ni Y, Luo G, Zhang Y, Lin J. Independent association of the Meckel’s cave with trigeminal neuralgia and development of a screening tool. Eur J Radiol. 2024; 171:111272.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Radyoloji ve Organ Görüntüleme

Bölüm

Araştırma Makalesi

Yazarlar

Yayımlanma Tarihi

16 Ekim 2026

Gönderilme Tarihi

25 Ocak 2026

Kabul Tarihi

1 Haziran 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 36 Sayı: 2026

DOI

https://doi.org/10.54005/geneltip.1866460

IZ

https://izlik.org/JA84HR89JZ

Kaynak Göster

RIS / Bibtex
APA
Akkaya, H. E., Polat, Ö., Akpınar, D. İ., Ziroglu, Z., Uzun, M., & Güneş, H. N. (2026). Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm. Genel Tıp Dergisi, 36(2026), 1-8. https://doi.org/10.54005/geneltip.1866460
AMA
1.Akkaya HE, Polat Ö, Akpınar Dİ, Ziroglu Z, Uzun M, Güneş HN. Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm. Genel Tıp Derg. 2026;36(2026):1-8. doi:10.54005/geneltip.1866460
Chicago
Akkaya, Habip Eser, Önder Polat, Dorukan İnanç Akpınar, Zeynep Ziroglu, Muhammet Uzun, ve Hafize Nalan Güneş. 2026. “Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm”. Genel Tıp Dergisi 36 (2026): 1-8. https://doi.org/10.54005/geneltip.1866460.
EndNote
Akkaya HE, Polat Ö, Akpınar Dİ, Ziroglu Z, Uzun M, Güneş HN (01 Ekim 2026) Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm. Genel Tıp Dergisi 36 2026 1–8.
IEEE
[1]H. E. Akkaya, Ö. Polat, D. İ. Akpınar, Z. Ziroglu, M. Uzun, ve H. N. Güneş, “Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm”, Genel Tıp Derg, c. 36, sy 2026, ss. 1–8, Eki. 2026, doi: 10.54005/geneltip.1866460.
ISNAD
Akkaya, Habip Eser - Polat, Önder - Akpınar, Dorukan İnanç - Ziroglu, Zeynep - Uzun, Muhammet - Güneş, Hafize Nalan. “Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm”. Genel Tıp Dergisi 36/2026 (01 Ekim 2026): 1-8. https://doi.org/10.54005/geneltip.1866460.
JAMA
1.Akkaya HE, Polat Ö, Akpınar Dİ, Ziroglu Z, Uzun M, Güneş HN. Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm. Genel Tıp Derg. 2026;36:1–8.
MLA
Akkaya, Habip Eser, vd. “Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm”. Genel Tıp Dergisi, c. 36, sy 2026, Ekim 2026, ss. 1-8, doi:10.54005/geneltip.1866460.
Vancouver
1.Habip Eser Akkaya, Önder Polat, Dorukan İnanç Akpınar, Zeynep Ziroglu, Muhammet Uzun, Hafize Nalan Güneş. Evaluation of MRI-Based Radiomic Texture Analysis and Ensemble Machine Learning Models in the Diagnosis of Hemifacial Spasm. Genel Tıp Derg. 01 Ekim 2026;36(2026):1-8. doi:10.54005/geneltip.1866460


Genel Tıp Dergisi Creative Commons Atıf-GayriTicari 4.0 Uluslararası Lisansı (CC BY NC) ile lisanslanmıştır.