|
Towards the individual computer-assisted analysis of brain images| old_uid | 18133 |
|---|
| title | Towards the individual computer-assisted analysis of brain images |
|---|
| start_date | 2019/11/25 |
|---|
| schedule | 11h-12h |
|---|
| online | no |
|---|
| summary | Neuroimaging offers an unmatched description of the brain's structure and physiology, which explains its crucial role in the understanding, diagnosis and treatment of neurological disorders. In clinical practice, brain images are mostly analysed visually. The performance of this approach greatly depends on the observer's experience and is not in favour of centres where advanced expertise in image reading is limited. I will present two computer-aided approaches for the individual analysis of brain images. The first one is an anomaly detection framework that generates patient-specific maps summarising the patology's distribution in the brain. The second approach explores how visualisation techniques can improve the interpretability of neural networks used for computer-aided diagnosis. |
|---|
| responsibles | Tauber |
|---|
| |
|