Related Experiment Video
Updated: Jul 11, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Brain metastasis tumor segmentation and detection using deep learning algorithms: A systematic review and
Ting-Wei Wang1, Ming-Sheng Hsu2, Wei-Kai Lee3
1Institute of Biophotonics, National Yang Ming Chiao Tung University, 155, Sec. 2, Li-Nong St. Beitou Dist., Taipei 112304, Taiwan; School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
Deep learning algorithms show promise in detecting brain metastases on MRI scans, with U-Net models excelling in segmentation. Further research with larger cohorts is needed for more generalizable diagnostic tools.
Area of Science:
- Radiology
- Artificial Intelligence
- Medical Imaging
Background:
- Manual detection of brain metastases from MRI is time-consuming and inconsistent.
- There is a critical need for automated and reliable solutions.
- Deep learning (DL) algorithms offer a potential avenue for improved detection and segmentation.
Conclusions:
- Deep learning holds significant potential for enhancing brain metastasis diagnostics and treatment planning.
- Further research with larger cohorts and meta-analyses is essential for developing practical and generalizable algorithms.
- The study highlights the impact of MRI hardware diversity and slice thickness on DL algorithm performance.
More Related Videos
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
09:53Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020