Machine Learning & Medical Imaging: The Future of Early Cancer Detection
summary
Applies machine learning and image‑processing to 4D ultrasound datasets to solve breathing motion that currently displaces liver lesions, using a pipeline of maximum intensity projection, windowed averaging, registration and a classifier that uses pixel intensity and texture to segment contrast‑enhanced tumors. Implements the pipeline inside MeVisLab and reviews results in ITK‑SNAP, showing the lesion stays centered across frames and enabling repeatable size quantification — a practical motion‑correction claim with working examples.
AI-written summary · about
related talks
55mDeep Learning in Medical Image Diagnostics
25mDeep Learning in Biomedicine: Challenges and Opportunities
29mCancer diagnostics enabled by machines: finding and classifying single tumor....
42mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics
43mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics
50mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics
18mCancer Screening using Deep Learning
49mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics