Non-Cochrane · DTA · PM42734878
Artificial intelligence in trigeminal neuralgia: trigeminal nerve segmentation and neurovascular conflict detection: a systematic review and meta-analysis.
Alvani Mohammadamin Sabbagh, Mohammadzadeh Ibrahim, Hajikarimloo Bardia, et al. · Neurosurgical review · 2026 · PubMed · doi:10.1007/s10143-026-04486-5
Findings
Population Patients with trigeminal neuralgia (TN) undergoing MRI; 5 studies, 577 patients
7 findings
| AI-based (machine learning or deep learning) models for trigeminal nerve segmentation and neurovascular conflict (NVC) detection on MRI | Reference standard (expert imaging annotation, clinical-radiological diagnosis, intraoperative confirmation where available) | Diagnostic odds ratio (DOR) MRI (T1, T2, MRA, CISS, rs-fMRI) | DOR 26.71 [16.38, 43.56] GRADE not reported 4 studies |
| AI-based (machine learning or deep learning) models for trigeminal nerve segmentation and neurovascular conflict (NVC) detection on MRI | Reference standard (expert imaging annotation, clinical-radiological diagnosis, intraoperative confirmation where available) | Pooled specificity MRI (T1, T2, MRA, CISS, rs-fMRI) | Specificity 0.92 [0.88, 0.94] GRADE not reported 4 studies |
| AI-based (machine learning or deep learning) models for trigeminal nerve segmentation and neurovascular conflict (NVC) detection on MRI | Reference standard (expert imaging annotation, clinical-radiological diagnosis, intraoperative confirmation where available) | Pooled sensitivity MRI (T1, T2, MRA, CISS, rs-fMRI) | Sensitivity 0.71 [0.65, 0.76] GRADE not reported 4 studies |
| AI-based (machine learning or deep learning) models for trigeminal nerve segmentation and neurovascular conflict (NVC) detection on MRI | Reference standard (expert imaging annotation, clinical-radiological diagnosis, intraoperative confirmation where available) | Area under the SROC curve (AUC) MRI (T1, T2, MRA, CISS, rs-fMRI) | AUC 0.91 [0.88, 0.93] GRADE not reported 4 studies |
| AI-based (machine learning or deep learning) models for trigeminal nerve segmentation and neurovascular conflict (NVC) detection on MRI | Reference standard (expert imaging annotation, clinical-radiological diagnosis, intraoperative confirmation where available) | Positive diagnostic likelihood ratio (DLR+) MRI (T1, T2, MRA, CISS, rs-fMRI) | Positive DLR 8.5 [5.75, 12.56] GRADE not reported 4 studies |
| AI-based (machine learning or deep learning) models for trigeminal nerve segmentation and neurovascular conflict (NVC) detection on MRI | Reference standard (expert imaging annotation, clinical-radiological diagnosis, intraoperative confirmation where available) | Diagnostic score MRI (T1, T2, MRA, CISS, rs-fMRI) | Diagnostic score 3.29 [2.8, 3.77] GRADE not reported 4 studies |
| AI-based (machine learning or deep learning) models for trigeminal nerve segmentation and neurovascular conflict (NVC) detection on MRI | Reference standard (expert imaging annotation, clinical-radiological diagnosis, intraoperative confirmation where available) | Negative diagnostic likelihood ratio (DLR-) MRI (T1, T2, MRA, CISS, rs-fMRI) | Negative DLR 0.32 [0.26, 0.38] GRADE not reported 4 studies |
Included primary studies 7
Open in Studies| Study | Year | Also included by | Outcomes it informs here | Trial data |
|---|---|---|---|---|
| Zhang 2023 matched by author and year (probable) | NR | 5 other reviews | not stated | not extracted yet |
| Halbert-Elliott 2025 matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Halbert-Elliott et al. 2025 Deep learning-based segmentation of the trigeminal nerve and surrounding vasculature in trigeminal neuralgia. PMID:40053933 | 2025 | this review only | not stated | not extracted yet |
| Hsu et al. 2025 Automatic Segmentation of the Cisternal Segment of Trigeminal Nerve on MRI Using Deep Learning. PMID:39989710 | 2025 | this review only | not stated | not extracted yet |
| Lin et al. 2021 Automated Segmentation of Trigeminal Nerve and Cerebrovasculature in MR-Angiography Images by Deep Learning. PMID:34955711 | 2021 | this review only | not stated | not extracted yet |
| Wu et al. 2025 Stratifying trigeminal neuralgia and characterizing an abnormal property of brain functional organization: a resting-state fMRI and… PMID:40153851 | 2025 | this review only | not stated | not extracted yet |
| Zhang et al. 2023 Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net. PMID:37920295 | 2023 | this review only | not stated | not extracted yet |
Overlap with other reviews
Reviews that include the same primary studies are not independent evidence. Shared counts match studies by PMID, DOI or NCT, and otherwise by author and year (a probable match). Only the non-Cochrane dental reviews have study lists, so overlap with Cochrane reviews is not counted yet.
Review question
| Element | Planned (methods) | Found (results) |
|---|---|---|
| Population | Patients with trigeminal neuralgia evaluated with MRI | Patients with TN (n=577 across 5 studies; mean age 53.86 years; 68.02% female) |
| Intervention | AI-based (ML or DL) methods for trigeminal nerve segmentation and/or NVC detection | 20 AI models (ML classifiers and DL architectures such as SEVB-Net, 3D U-Net, ResNet50) |
| Comparison | Reference standard: expert imaging annotation, neuroradiological identification of NVC, clinical-radiological diagnosis, symptom laterality, intraoperative confirmation | Clinical diagnosis plus MRI confirmation, manual segmentation, intraoperative confirmation where available |
| Outcomes | Sensitivity, specificity, accuracy, AUC, Dice similarity coefficient, Jaccard index, precision | Pooled sensitivity, specificity, DLR+, DLR-, DOR, diagnostic score, SROC AUC |
| Study designs | Original research: cohort studies, randomized trials, case series with at least 10 patients | 5 studies (4 retrospective, 1 prospective; China 3, USA 1, Taiwan/USA/China 1) |
| Timing | Not specified | Mean follow-up 34.5 months |