GazeLT: Visual attention-guided long-tailed disease classification in chest radiographs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909735701184512 |
|---|---|
| author | Bhattacharya, Moinak Singh, Gagandeep Jain, Shubham Prasanna, Prateek |
| author_facet | Bhattacharya, Moinak Singh, Gagandeep Jain, Shubham Prasanna, Prateek |
| contents | In this work, we present GazeLT, a human visual attention integration-disintegration approach for long-tailed disease classification. A radiologist's eye gaze has distinct patterns that capture both fine-grained and coarser level disease related information. While interpreting an image, a radiologist's attention varies throughout the duration; it is critical to incorporate this into a deep learning framework to improve automated image interpretation. Another important aspect of visual attention is that apart from looking at major/obvious disease patterns, experts also look at minor/incidental findings (few of these constituting long-tailed classes) during the course of image interpretation. GazeLT harnesses the temporal aspect of the visual search process, via an integration and disintegration mechanism, to improve long-tailed disease classification. We show the efficacy of GazeLT on two publicly available datasets for long-tailed disease classification, namely the NIH-CXR-LT (n=89237) and the MIMIC-CXR-LT (n=111898) datasets. GazeLT outperforms the best long-tailed loss by 4.1% and the visual attention-based baseline by 21.7% in average accuracy metrics for these datasets. Our code is available at https://github.com/lordmoinak1/gazelt. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09478 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GazeLT: Visual attention-guided long-tailed disease classification in chest radiographs Bhattacharya, Moinak Singh, Gagandeep Jain, Shubham Prasanna, Prateek Computer Vision and Pattern Recognition In this work, we present GazeLT, a human visual attention integration-disintegration approach for long-tailed disease classification. A radiologist's eye gaze has distinct patterns that capture both fine-grained and coarser level disease related information. While interpreting an image, a radiologist's attention varies throughout the duration; it is critical to incorporate this into a deep learning framework to improve automated image interpretation. Another important aspect of visual attention is that apart from looking at major/obvious disease patterns, experts also look at minor/incidental findings (few of these constituting long-tailed classes) during the course of image interpretation. GazeLT harnesses the temporal aspect of the visual search process, via an integration and disintegration mechanism, to improve long-tailed disease classification. We show the efficacy of GazeLT on two publicly available datasets for long-tailed disease classification, namely the NIH-CXR-LT (n=89237) and the MIMIC-CXR-LT (n=111898) datasets. GazeLT outperforms the best long-tailed loss by 4.1% and the visual attention-based baseline by 21.7% in average accuracy metrics for these datasets. Our code is available at https://github.com/lordmoinak1/gazelt. |
| title | GazeLT: Visual attention-guided long-tailed disease classification in chest radiographs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.09478 |