Supporting Mitosis Detection AI Training with Inter-Observer Eye-Gaze Consistencies
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_ | 1866913295563227136 |
|---|---|
| author | Gu, Hongyan Yan, Zihan Alvi, Ayesha Day, Brandon Yang, Chunxu Wu, Zida Magaki, Shino Haeri, Mohammad Chen, Xiang 'Anthony' |
| author_facet | Gu, Hongyan Yan, Zihan Alvi, Ayesha Day, Brandon Yang, Chunxu Wu, Zida Magaki, Shino Haeri, Mohammad Chen, Xiang 'Anthony' |
| contents | The expansion of artificial intelligence (AI) in pathology tasks has intensified the demand for doctors' annotations in AI development. However, collecting high-quality annotations from doctors is costly and time-consuming, creating a bottleneck in AI progress. This study investigates eye-tracking as a cost-effective technology to collect doctors' behavioral data for AI training with a focus on the pathology task of mitosis detection. One major challenge in using eye-gaze data is the low signal-to-noise ratio, which hinders the extraction of meaningful information. We tackled this by levering the properties of inter-observer eye-gaze consistencies and creating eye-gaze labels from consistent eye-fixations shared by a group of observers. Our study involved 14 non-medical participants, from whom we collected eye-gaze data and generated eye-gaze labels based on varying group sizes. We assessed the efficacy of such eye-gaze labels by training Convolutional Neural Networks (CNNs) and comparing their performance to those trained with ground truth annotations and a heuristic-based baseline. Results indicated that CNNs trained with our eye-gaze labels closely followed the performance of ground-truth-based CNNs, and significantly outperformed the baseline. Although primarily focused on mitosis, we envision that insights from this study can be generalized to other medical imaging tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01656 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Supporting Mitosis Detection AI Training with Inter-Observer Eye-Gaze Consistencies Gu, Hongyan Yan, Zihan Alvi, Ayesha Day, Brandon Yang, Chunxu Wu, Zida Magaki, Shino Haeri, Mohammad Chen, Xiang 'Anthony' Computer Vision and Pattern Recognition The expansion of artificial intelligence (AI) in pathology tasks has intensified the demand for doctors' annotations in AI development. However, collecting high-quality annotations from doctors is costly and time-consuming, creating a bottleneck in AI progress. This study investigates eye-tracking as a cost-effective technology to collect doctors' behavioral data for AI training with a focus on the pathology task of mitosis detection. One major challenge in using eye-gaze data is the low signal-to-noise ratio, which hinders the extraction of meaningful information. We tackled this by levering the properties of inter-observer eye-gaze consistencies and creating eye-gaze labels from consistent eye-fixations shared by a group of observers. Our study involved 14 non-medical participants, from whom we collected eye-gaze data and generated eye-gaze labels based on varying group sizes. We assessed the efficacy of such eye-gaze labels by training Convolutional Neural Networks (CNNs) and comparing their performance to those trained with ground truth annotations and a heuristic-based baseline. Results indicated that CNNs trained with our eye-gaze labels closely followed the performance of ground-truth-based CNNs, and significantly outperformed the baseline. Although primarily focused on mitosis, we envision that insights from this study can be generalized to other medical imaging tasks. |
| title | Supporting Mitosis Detection AI Training with Inter-Observer Eye-Gaze Consistencies |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.01656 |