Artificial intelligence prediction of nonenhancing brain tumor malignancy based on in vivo confocal laser endomicroscopic imaging

Authors

• Jiuxu Chen, School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, United States.
• Yuan Xu, The Loyal and Edith Davis Neurosurgical Research Laboratory, Barrow Neurological Institute, St. Joseph's Hospital and Medical Center, Phoenix, AZ, United States.Follow
• Irakliy Abramov, The Loyal and Edith Davis Neurosurgical Research Laboratory, Barrow Neurological Institute, St. Joseph's Hospital and Medical Center, Phoenix, AZ, United States.
• Carlos E. Calderón-Valero, The Loyal and Edith Davis Neurosurgical Research Laboratory, Barrow Neurological Institute, St. Joseph's Hospital and Medical Center, Phoenix, AZ, United States.
• Thomas J. On, The Loyal and Edith Davis Neurosurgical Research Laboratory, Barrow Neurological Institute, St. Joseph's Hospital and Medical Center, Phoenix, AZ, United States.
• Jennifer M. Eschbacher, Department of Neuropathology, Barrow Neurological Institute, St. Joseph's Hospital and Medical Center, Phoenix, AZ, United States.
• Baoxin Li, School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, United States.
• Mark C. Preul, The Loyal and Edith Davis Neurosurgical Research Laboratory, Barrow Neurological Institute, St. Joseph's Hospital and Medical Center, Phoenix, AZ, United States.

Document Type

Article

Abstract

BACKGROUND: Although nonenhancing tumors are often thought to be lower grade, malignant regions can be missed on conventional magnetic resonance imaging. Fluorescein-based confocal laser endomicroscopy (CLE) enables real-time, cellular-resolution imaging of brain tissue during tumor resection. It is particularly valuable for evaluating nonenhancing brain tumors. However, CLE interpretation remains subjective. Although CLE has high sensitivity, it is less specific than standard histology. Existing artificial intelligence (AI) models process CLE images as independent frames, neglecting the temporal context that human experts use during interpretation. METHODS: A novel sequence-based deep learning model was developed to classify tumor grade on the basis of CLE image sequences, mimicking the visual reasoning process of expert neuropathologists. CLE images were collected from 16 patients with nonenhancing brain tumors. Each sequence was labeled as high grade or low grade based on neuropathologist interpretation, blinded to final histopathology findings. Visual features were extracted using pretrained backbones (vision transformer, VGG16, ResNet50), followed by temporal modeling with a transformer encoder and temporal convolution. This model was compared with conventional frame-based classification across 3 random train-test splits. RESULTS: The dataset included 105 CLE sequences (3,173 images, 40 regions of interest). The sequence-based model achieved top-1 classification accuracies of 93% (vision transformer), 88% (VGG16), 74% (ResNet50), and 67% (Inception-ResNet-V2), outperforming corresponding frame-based models (78%, 74%, 55%, and 50%, respectively). Diagnostic performance was comparable to expert neuropathologist interpretation (87%). The model demonstrated robustness in artifact-affected sequences and improved interpretability by incorporating temporal progression. CONCLUSIONS: AI models that integrate both visual and temporal information from CLE digital imaging sequences can effectively classify brain tumor grade with accuracy comparable to that of expert neuropathologists, outperforming frame-based models. Such a system reduces interpretive subjectivity and holds promise as an intraoperative decision CLE support tool for nonenhancing brain tumor resection.

Publication Date

1-1-2025

Publication Title

Frontiers in surgery

ISSN

2296-875X

Volume

12

First Page

1655374

PubMed ID

41560935

Digital Object Identifier (DOI)

10.3389/fsurg.2025.1655374

Recommended Citation

Chen, Jiuxu; Xu, Yuan; Abramov, Irakliy; Calderón-Valero, Carlos E.; On, Thomas J.; Eschbacher, Jennifer M.; Li, Baoxin; and Preul, Mark C., "Artificial intelligence prediction of nonenhancing brain tumor malignancy based on in vivo confocal laser endomicroscopic imaging" (2025). Neurosurgery. 2325.
https://scholar.barrowneuro.org/neurosurgery/2325