Brain tumor grading diagnosis using transfer learning based on optical coherence tomography

• DOI: 10.1364/boe.513877
• Publication Date: 2024-02-20T09:00:07Z
• Authors: Sanford P. C. Hsu; Miao-Hui Lin; Chun-Fu Lin; Tien-Yu Hsiao; Yi-Min Wang; Chia-Wei Sun
• Keywords: Brain tumor; Grading (engineering)

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 tissues: normal tissue, primary central nervous system lymphoma (PCNSL), high-grade glioma (HGG), and low-grade (LGG) using transfer learning. Tumor specimens were measured with optical coherence tomography (OCT), MobileNetV2 pre-trained model was employed classification. Surgeons could optimize predictions based on experience. The showed robust promising clinical value. A dynamic t-SNE visualized its performance, offering new approach to neurosurgical decision-making regarding tumors.