Laser Interstitial Thermal Therapy for High-Grade Gliomas: Current Evidence, Clinical Applications and Emerging Role of Artificial Intelligence

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Background: High-grade gliomas pose formidable challenges in neuro-oncology, with a median overall survival (OS) of 12–18 months. Laser interstitial thermal therapy (LITT) offers a minimally invasive cytoreductive option for deep-seated or recurrent tumors, achieving ablation rates of 85–98%. In parallel, artificial intelligence and machine learning are increasingly being applied to neuro-oncology to improve diagnosis, treatment planning, and outcome prediction, although these applications remain largely investigational. Methods: A literature search was conducted using the PubMed, MEDLINE, Embase, and ClinicalTrials.gov databases. The search terms included “laser interstitial thermotherapy,” “glioblastoma,” and “high-grade glioma”, “machine learning”, “artificial intelligence”. A total of 196 articles were identified. Inclusion criteria comprised primary studies, meta-analyses, and systematic reviews involving human data, with LITT used as a primary or secondary treatment modality. Sixty-nine studies were included in this review, while case reports and animal studies were excluded. Results: LITT represents a precision therapy for inoperable gliomas, achieving ablation rates of 85–98%. For primary glioblastoma, median overall survival (mOS) ranges from 11–16 months, and median progression-free survival (mPFS) from 4–9.5 months. In recurrent glioblastoma, LITT demonstrates a median overall survival ranging from 8.5 to 14.1 months and a median progression-free survival of 3–3.5 months with lower complication rates (5.7% vs. 13.8%) and shorter hospital stays (2.2 vs. 7 days). Overall complication rates range from 20–35%, predominantly due to cerebral edema, which is generally responsive to steroid therapy. Its value may be expanded by machine learning tools that integrate clinical, molecular, and imaging features to support patient selection and predict outcomes, though these remain at the proof-of-concept stage. In addition, LITT may serve as a platform for combination therapies, including immunotherapy, chemotherapy, targeted agents, and radiotherapy. Conclusions: Based on current evidence, LITT demonstrates outcomes that appear favorable in selected patient populations with high-grade gliomas and may be considered as a treatment option for primary tumors with challenging localization, near-spherical geometry, and volumes of approximately 30 cm3. It has a particularly important role in recurrent glioblastomas with similar characteristics, offering efficacy comparable to resection but with an improved safety profile in retrospective comparisons. LITT is evolving from a technically focused ablation method into a data-driven therapeutic platform. Integration with artificial intelligence may improve precision, safety, and personalization, helping define the role of LITT within modern neuro-oncology as higher-quality clinical evidence continues to accumulate.
Funding Information
  • Technische Universität München

This publication has 65 references indexed in Scilit: