Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2406.00672 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909214803230720 |
|---|---|
| author | Wang, Xuenian Shi, Shanshan Yan, Renao Sun, Qiehe Zhu, Lianghui Guan, Tian He, Yonghong |
| author_facet | Wang, Xuenian Shi, Shanshan Yan, Renao Sun, Qiehe Zhu, Lianghui Guan, Tian He, Yonghong |
| contents | In the field of whole slide image (WSI) classification, multiple instance learning (MIL) serves as a promising approach, commonly decoupled into feature extraction and aggregation. In this paradigm, our observation reveals that discriminative embeddings are crucial for aggregation to the final prediction. Among all feature updating strategies, task-oriented ones can capture characteristics specifically for certain tasks. However, they can be prone to overfitting and contaminated by samples assigned with noisy labels. To address this issue, we propose a heuristic clustering-driven feature fine-tuning method (HC-FT) to enhance the performance of multiple instance learning by providing purified positive and hard negative samples. Our method first employs a well-trained MIL model to evaluate the confidence of patches. Then, patches with high confidence are marked as positive samples, while the remaining patches are used to identify crucial negative samples. After two rounds of heuristic clustering and selection, purified positive and hard negative samples are obtained to facilitate feature fine-tuning. The proposed method is evaluated on both CAMELYON16 and BRACS datasets, achieving an AUC of 97.13% and 85.85%, respectively, consistently outperforming all compared methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00672 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification Wang, Xuenian Shi, Shanshan Yan, Renao Sun, Qiehe Zhu, Lianghui Guan, Tian He, Yonghong Computer Vision and Pattern Recognition In the field of whole slide image (WSI) classification, multiple instance learning (MIL) serves as a promising approach, commonly decoupled into feature extraction and aggregation. In this paradigm, our observation reveals that discriminative embeddings are crucial for aggregation to the final prediction. Among all feature updating strategies, task-oriented ones can capture characteristics specifically for certain tasks. However, they can be prone to overfitting and contaminated by samples assigned with noisy labels. To address this issue, we propose a heuristic clustering-driven feature fine-tuning method (HC-FT) to enhance the performance of multiple instance learning by providing purified positive and hard negative samples. Our method first employs a well-trained MIL model to evaluate the confidence of patches. Then, patches with high confidence are marked as positive samples, while the remaining patches are used to identify crucial negative samples. After two rounds of heuristic clustering and selection, purified positive and hard negative samples are obtained to facilitate feature fine-tuning. The proposed method is evaluated on both CAMELYON16 and BRACS datasets, achieving an AUC of 97.13% and 85.85%, respectively, consistently outperforming all compared methods. |
| title | Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.00672 |