DeepGlioma: AI-Based Rapid Molecular Classification of Brain Tumours in Under 90 Seconds
DeepGlioma combines stimulated Raman histology with deep learning to classify diffuse gliomas by their WHO-defining molecular alterations -- IDH mutation, 1p19q co-deletion, and ATRX mutation -- in under 90 seconds. In a prospective multicenter cohort of 153 patients, the system achieved 93.3% mean classification accuracy. This represents a significant advance toward real-time intraoperative molecular diagnostics that could eliminate delays associated with conventional wet-lab testing.
The original study
Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging.
- Authors
- Hollon T, Jiang C, Chowdury A, Nasir-Moin M, Kondepudi A, Aabedi A, et al.
- Journal
- Nature medicine
- Type
- Multicenter Study, Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't
- PMID
- 36959422
Original abstract
Molecular classification has transformed the management of brain tumors by enabling more accurate prognostication and personalized treatment. However, timely molecular diagnostic testing for patients with brain tumors is limited, complicating surgical and adjuvant treatment and obstructing clinical trial enrollment. In this study, we developed DeepGlioma, a rapid (<90 seconds), artificial-intelligence-based diagnostic screening system to streamline the molecular diagnosis of diffuse gliomas. DeepGlioma is trained using a multimodal dataset that includes stimulated Raman histology (SRH); a rapid, label-free, non-consumptive, optical imaging method; and large-scale, public genomic data. In a prospective, multicenter, international testing cohort of patients with diffuse glioma (n = 153) who underwent real-time SRH imaging, we demonstrate that DeepGlioma can predict the molecular alterations used by the World Health Organization to define the adult-type diffuse glioma taxonomy (IDH mutation, 1p19q co-deletion and ATRX mutation), achieving a mean molecular classification accuracy of 93.3 ± 1.6%. Our results represent how artificial intelligence and optical histology can be used to provide a rapid and scalable adjunct to wet lab methods for the molecular screening of patients with diffuse glioma.