| Paper ID | MLSP-43.6 |
| Paper Title |
HUMAN-EXPERT-LEVEL BRAIN TUMOR DETECTION USING DEEP LEARING WITH DATA DISTILLATION AND AUGMENTATION |
| Authors |
Diyuan Lu, Frankfurt Institute for Advanced Studies, Germany; Nenad Polomac, Iskra Gacheva, Elke Hattingen, Institute for Neuroradiology Frankfurt university hospital Frankfurt am Main, Germany; Jochen Triesch, Frankfurt Institute for Advanced Studies, Germany |
| Session | MLSP-43: Biomedical Applications |
| Location | Gather.Town |
| Session Time: | Friday, 11 June, 13:00 - 13:45 |
| Presentation Time: | Friday, 11 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-APPL] Applications of machine learning |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
The application of Deep Learning (DL) for medical diagnosis is often hampered by two problems. First, the amount of training data may be scarce, as it is limited by the number of patients who have acquired the condition. Second, the training data may be corrupted by various types of noise. Here, we study the problem of brain tumor detection from magnetic resonance spectroscopy (MRS) data, where both types of problems are prominent. To overcome these challenges, we propose a new method for training a deep neural network that distills particularly representative training examples and augments the training data by mixing these samples from one class with those from the same and other classes to create additional training samples. We demonstrate that this technique substantially improves performance, allowing our method to achieve human-expert-level accuracy with just a few thousand training examples. |
