Brain tumor grading diagnosis using transfer learning based on optical coherence tomography.
Sanford P C HsuMiao-Hui LinChun-Fu LinTien-Yu HsiaoYi-Min WangChia-Wei SunPublished in: Biomedical optics express (2024)
In neurosurgery, accurately identifying brain tumor tissue is vital for reducing recurrence. Current imaging techniques have limitations, prompting the exploration of alternative methods. This study validated a binary hierarchical classification of brain tissues: normal tissue, primary central nervous system lymphoma (PCNSL), high-grade glioma (HGG), and low-grade glioma (LGG) using transfer learning. Tumor specimens were measured with optical coherence tomography (OCT), and a MobileNetV2 pre-trained model was employed for classification. Surgeons could optimize predictions based on experience. The model showed robust classification and promising clinical value. A dynamic t-SNE visualized its performance, offering a new approach to neurosurgical decision-making regarding brain tumors.
Keyphrases
- low grade
- high grade
- optical coherence tomography
- deep learning
- machine learning
- diabetic retinopathy
- decision making
- high resolution
- optic nerve
- diffuse large b cell lymphoma
- gene expression
- white matter
- quality improvement
- brain injury
- fluorescence imaging
- ionic liquid
- cerebral ischemia
- high intensity
- subarachnoid hemorrhage