Mask-Free Neuron Concept Annotation for Interpreting Neural Networks in Medical Domain
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_ | 1866917723075772416 |
|---|---|
| author | Kim, Hyeon Bae Ahn, Yong Hyun Kim, Seong Tae |
| author_facet | Kim, Hyeon Bae Ahn, Yong Hyun Kim, Seong Tae |
| contents | Recent advancements in deep neural networks have shown promise in aiding disease diagnosis and medical decision-making. However, ensuring transparent decision-making processes of AI models in compliance with regulations requires a comprehensive understanding of the model's internal workings. However, previous methods heavily rely on expensive pixel-wise annotated datasets for interpreting the model, presenting a significant drawback in medical domains. In this paper, we propose a novel medical neuron concept annotation method, named Mask-free Medical Model Interpretation (MAMMI), addresses these challenges. By using a vision-language model, our method relaxes the need for pixel-level masks for neuron concept annotation. MAMMI achieves superior performance compared to other interpretation methods, demonstrating its efficacy in providing rich representations for neurons in medical image analysis. Our experiments on a model trained on NIH chest X-rays validate the effectiveness of MAMMI, showcasing its potential for transparent clinical decision-making in the medical domain. The code is available at https://github.com/ailab-kyunghee/MAMMI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11375 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mask-Free Neuron Concept Annotation for Interpreting Neural Networks in Medical Domain Kim, Hyeon Bae Ahn, Yong Hyun Kim, Seong Tae Computer Vision and Pattern Recognition Recent advancements in deep neural networks have shown promise in aiding disease diagnosis and medical decision-making. However, ensuring transparent decision-making processes of AI models in compliance with regulations requires a comprehensive understanding of the model's internal workings. However, previous methods heavily rely on expensive pixel-wise annotated datasets for interpreting the model, presenting a significant drawback in medical domains. In this paper, we propose a novel medical neuron concept annotation method, named Mask-free Medical Model Interpretation (MAMMI), addresses these challenges. By using a vision-language model, our method relaxes the need for pixel-level masks for neuron concept annotation. MAMMI achieves superior performance compared to other interpretation methods, demonstrating its efficacy in providing rich representations for neurons in medical image analysis. Our experiments on a model trained on NIH chest X-rays validate the effectiveness of MAMMI, showcasing its potential for transparent clinical decision-making in the medical domain. The code is available at https://github.com/ailab-kyunghee/MAMMI. |
| title | Mask-Free Neuron Concept Annotation for Interpreting Neural Networks in Medical Domain |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.11375 |