Klasifikace mitotických obrazů u gliomu pomocí konvolučních neuronových sítí s přidanou pozorností
| Thesis title in Czech: | Klasifikace mitotických obrazů u gliomu pomocí konvolučních neuronových sítí s přidanou pozorností |
|---|---|
| Thesis title in English: | Mitotic Image Classification in Glioma Using Attention-Enhanced Convolutional Neural Networks |
| Key words: | CNNs|Hluboké učení|Pozornost|Gliom |
| English key words: | CNNs|Deep Learning|Attention|Glioma |
| Academic year of topic announcement: | 2024/2025 |
| Thesis type: | Bachelor's thesis |
| Thesis language: | |
| Department: | Department of Software and Computer Science Education (32-KSVI) |
| Supervisor: | Kassem Anis Bouali, M.Sc. |
| Author: | Martin Dostál - assigned and confirmed by the Study Dept. |
| Date of registration: | 08.04.2025 |
| Date of assignment: | 30.05.2025 |
| Confirmed by Study dept. on: | 30.05.2025 |
| Guidelines |
|
This project focuses on classifying mitotic images in glioma using convolutional neural networks enhanced with attention mechanisms. Specifically, the student will compare CNN attention blocks such as Squeeze-and-Excitation (SE) and Convolutional Block Attention Module (CBAM) blocks...etc. The goal is to achieve better predictions to support medical diagnostics in glioma analysis. |
| References |
| LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539
Guo, MH., Xu, TX., Liu, JJ. et al. Attention mechanisms in computer vision: A survey. Comp. Visual Media 8, 331–368 (2022). https://doi.org/10.1007/s41095-022-0271-y |