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

Sanford P C Hsu; Miao-Hui Lin; Chun-Fu Lin; Tien-Yu Hsiao; Yi-Min Wang; Chia-Wei Sun

doi:10.1364/BOE.513877

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

Biomed Opt Express. 2024 Mar 13;15(4):2343-2357. doi: 10.1364/BOE.513877. eCollection 2024 Apr 1.

Authors

Sanford P C Hsu^{1

2

3}, Miao-Hui Lin⁴, Chun-Fu Lin^{2

3}, Tien-Yu Hsiao⁴, Yi-Min Wang⁴, Chia-Wei Sun^{4

5

6}

Affiliations

¹ Taipei Veterans General Hospital, Department of Rehabilitation and Technical Aid Center, Taipei, Taiwan.
² Taipei Veterans General Hospital, Neurological Institute, Department of Neurosurgery, Taipei, Taiwan.
³ School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
⁴ Biomedical Optical Imaging Lab, Department of Photonics, College of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.
⁵ Institute of Biomedical Engineering, College of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.
⁶ Medical Device Innovation and Translation Center, National Yang Ming Chiao Tung University, Taipei, Taiwan.

Abstract

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.