Abstract
•A deep learning approach to automatically detect diagnostic CLE brain tumor images.•Ensemble modeling and fine-tuning effect on convolutional neural networks.•Unsupervised semantic localization of CLE histological features.•Interobserver study to compare human performance with the model.•Fine-tuning and ensemble modeling effect on convolutional neural networks.
Confocal laser endomicroscopy (CLE) is an advanced optical fluorescence technology undergoing assessment for applications in brain tumor surgery. Many of the CLE images can be distorted and interpreted as nondiagnostic. However, just one neat CLE image might suffice for intraoperative diagnosis of the tumor. While manual examination of thousands of nondiagnostic images during surgery would be impractical, this creates an opportunity for a model to select diagnostic images for the pathologists or surgeons review. In this study, we sought to develop a deep learning model to automatically detect the diagnostic images. We explored the effect of training regimes and ensemble modeling and localized histological features from diagnostic CLE images. The developed model could achieve promising agreement with the ground truth. With the speed and precision of the proposed method, it has potential to be integrated into the operative workflow in the brain tumor surgery.