# AI-Powered Histology for Molecular Profiling in Brain Tumors: Toward Smart Diagnostics from Tissue

## TL;DR

AI is being used to analyze brain tumor tissue for molecular profiling, offering accurate and accessible diagnostics for better treatment decisions.

## Contribution

AI models now predict molecular alterations in brain tumors directly from histology, improving diagnostic speed and global accessibility.

## Key findings

- Deep learning models on histopathology images predict glioma biomarkers with neuropathologist-level accuracy.
- AI enables real-time intraoperative diagnostics using techniques like stimulated Raman histology.
- Applications extend beyond gliomas to tumors like ependymomas and primary CNS lymphomas.

## Abstract

Artificial intelligence (AI) has rapidly entered the field of neuropathology, showing promise in the classification and molecular prediction of brain tumors. In particular, deep learning applied to digital histopathology has enabled accurate recognition of glioma subtypes, prediction of molecular alterations, and even intraoperative decision support. This review summarizes recent developments in both permanent and frozen section pathology, highlights innovations such as stimulated Raman histology, and explores applications beyond gliomas, including ependymomas and primary CNS lymphomas. We discuss opportunities, limitations, and future directions for integrating AI into routine clinical practice.

The integration of molecular features into histopathological diagnoses has become central to the World Health Organization (WHO) classification of central nervous system (CNS) tumors, improving prognostic accuracy and supporting precision medicine. However, unequal access to molecular testing limits the universal application of integrated diagnosis. To address this, artificial intelligence (AI) models are being developed to predict molecular alterations directly from histological data. In gliomas, deep learning applied to whole-slide images (WSIs) of permanent sections achieves neuropathologist-level accuracy in predicting biomarkers such as IDH mutation and 1p/19q co-deletion, as well as in molecular subtype classification and outcome prediction. Recent advances extend these approaches to intraoperative cryosections, enabling real-time glioma grading, molecular prediction, and label-free tissue analysis using modalities such as stimulated Raman histology and domain-adaptive image translation. Beyond gliomas, AI-powered histology is being explored in other brain tumors, including morphology-based molecular classification of spinal cord ependymomas and intraoperative discrimination of gliomas from primary CNS lymphomas. This review summarizes current progress in AI-assisted molecular profiling prediction of brain tumors from tissue, highlighting opportunities for rapid, accurate, and globally accessible diagnostics. The integration of histology and computational methods holds promise for the development of smart AI-assisted neuro-oncology.