Non-invasive prediction of the secondary enucleation risk in uveal melanoma based on pretreatment CT and MRI prior to stereotactic radiotherapy.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiation Oncology, Faculty of Medicine, Hacettepe University, Sihhiye, 06100, Ankara, Turkey. [email protected].
- Division of Medical Quantum Science, Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 812-8582, Fukuoka, Japan. [email protected].
- Division of Medical Quantum Science, Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 812-8582, Fukuoka, Japan.
- Division of Medical Quantum Science, Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 812-8582, Fukuoka, Japan.
- Department of Radiation Oncology, Faculty of Medicine, Hacettepe University, Sihhiye, 06100, Ankara, Turkey.
Abstract
The aim of this study was to develop a radiomic model to non-invasively predict the risk of secondary enucleation (SE) in patients with uveal melanoma (UM) prior to stereotactic radiotherapy using pretreatment computed tomography (CT) and magnetic resonance (MR) images. This retrospective study encompasses a cohort of 308 patients diagnosed with UM who underwent stereotactic radiosurgery (SRS) or fractionated stereotactic radiotherapy (FSRT) using the CyberKnife system (Accuray, Sunnyvale, CA, USA) between 2007 and 2018. Each patient received comprehensive ophthalmologic evaluations, including assessment of visual acuity, anterior segment examination, fundus examination, and ultrasonography. All patients were followed up for a minimum of 5 years. The cohort was composed of 65 patients who underwent SE (SE+) and 243 who did not (SE-). Radiomic features were extracted from pretreatment CT and MR images. To develop a robust predictive model, four different machine learning algorithms were evaluated using these features. The stacking model utilizing CT + MR radiomic features achieved the highest predictive performance, with an area under the curve (AUC) of 0.90, accuracy of 0.86, sensitivity of 0.81, and specificity of 0.90. The feature of robust mean absolute deviation derived from the Laplacian-of-Gaussian-filtered MR images was identified as the most significant predictor, demonstrating a statistically significant difference between SE+ and SE- cases (p = 0.005). Radiomic analysis of pretreatment CT and MR images can non-invasively predict the risk of SE in UM patients undergoing SRS/FSRT. The combined CT + MR radiomic model may inform more personalized therapeutic decisions, thereby reducing unnecessary radiation exposure and potentially improving patient outcomes.