| Literature DB >> 36221403 |
Hyeong Cheol Moon1, Young Seok Park1,2,3.
Abstract
The effectiveness of single-session gamma knife radiosurgery (GKRS) for small metastatic brain tumors has been proven, but hypofractionated GKRS (hfGKRS) for large brain metastases (BM) from the linear quadratic (LQ) model is uncertain. The purpose of this study was to investigate volume changes large BM after hfGKRS from the LQ model and predict volume changes using artificial neural network (ANN). We retrospectively investigated the clinical findings of 28 patients who underwent hfGKRS with large BM (diameter >3 cm or volume >10 cc). A total of 44 tumors were extracted from 28 patients with features. We randomly divided 30 large brain tumors as training set and 14 large brain tumors as test set. To predict the volume changes after hfGKRS, we used ANN models (single-layer perceptron (SLP) and multi-layer perceptron (MLP)). The volume reduction was 96% after hfGKRS for large BM from the LQ model. ANN model predicted volume changes with 70% and 80% accuracy for SLP and MLP, respectively. Even in large BM, hfGKRS from the LQ model could be a good treatment option. Additionally, the MLP model could predict volume changes with 80% accuracy after hfGKRS for large BM.Entities:
Mesh:
Year: 2022 PMID: 36221403 PMCID: PMC9542824 DOI: 10.1097/MD.0000000000030964
Source DB: PubMed Journal: Medicine (Baltimore) ISSN: 0025-7974 Impact factor: 1.817
Figure 1.The flowchart of artificial neural network modeling for predicting volume changes.
Clinical characteristics and planning parameters for gamma knife radiosurgery.
| Gender (male/female) | 18/10 | |
|---|---|---|
| Age (median) | 69.5 ± 15.7 | |
| KPS | >80 | 7 |
| ≦80 | 21 | |
| RPA | Class 1 | 13 |
| Class 2 | 15 | |
| Shots | 25 ± 7.8 | |
| Beam-on-time (min) | 25.3 ± 6.3 | |
| Coverage (%) | 0.9 ± 0.1 | |
| Selectivity (%) | 0.8 ± 0.1 | |
| Gradient index | 2.6 ± 0.1 | |
| Prescription dose (50% margin, Gy) | 5.8 ± 1.1 | |
| Number of fractionation | 4.0 ± 1.1 | |
| BED10 (Gy) | 3.9 ± 5.8 | |
| Diagnosis (lung/breast/others) | 22/5/1 | |
| Initial tumor volume (cc) | 14.0 ± 5.3 | |
| Tumor volume (cc) after hfGKRS | 9.0 ± 4.3 | |
| Volume reduction (%) | 96% | |
| Radiation response (complete/partial/progression) | 26/16/2 | |
BED = biologically effective dose, hfGKRS = hypofractionated gamma knife radiosurgery, KPS = Karnofsky performance scale, RPA = recursive partitioning analysis.
Figure 2.Follow-up MRI of case 1 after hypofractionated gamma knife radiosurgery. Pre (A) and post (B)-operative axial T1-weighted image. Contouring a tumor in red, margin in green. The tumor in blue was decreased at 3 months after hypofractionated gamma knife radiosurgery (follow-up MRI).
Figure 3.Illustration of biological effective dose10 according to the number of fractionated from the linear quadratic model.