Analyzing the Effect of $k$-Space Features in MRI Classification Models
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912037933678592 |
|---|---|
| author | Passigan, Pascal Ramkumar, Vayd |
| author_facet | Passigan, Pascal Ramkumar, Vayd |
| contents | The integration of Artificial Intelligence (AI) in medical diagnostics is often hindered by model opacity, where high-accuracy systems function as "black boxes" without transparent reasoning. This limitation is critical in clinical settings, where trust and reliability are paramount. To address this, we have developed an explainable AI methodology tailored for medical imaging. By employing a Convolutional Neural Network (CNN) that analyzes MRI scans across both image and frequency domains, we introduce a novel approach that incorporates Uniform Manifold Approximation and Projection UMAP] for the visualization of latent input embeddings. This approach not only enhances early training efficiency but also deepens our understanding of how additional features impact the model predictions, thereby increasing interpretability and supporting more accurate and intuitive diagnostic inferences |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13589 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Analyzing the Effect of $k$-Space Features in MRI Classification Models Passigan, Pascal Ramkumar, Vayd Image and Video Processing Computer Vision and Pattern Recognition The integration of Artificial Intelligence (AI) in medical diagnostics is often hindered by model opacity, where high-accuracy systems function as "black boxes" without transparent reasoning. This limitation is critical in clinical settings, where trust and reliability are paramount. To address this, we have developed an explainable AI methodology tailored for medical imaging. By employing a Convolutional Neural Network (CNN) that analyzes MRI scans across both image and frequency domains, we introduce a novel approach that incorporates Uniform Manifold Approximation and Projection UMAP] for the visualization of latent input embeddings. This approach not only enhances early training efficiency but also deepens our understanding of how additional features impact the model predictions, thereby increasing interpretability and supporting more accurate and intuitive diagnostic inferences |
| title | Analyzing the Effect of $k$-Space Features in MRI Classification Models |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.13589 |