Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910339014066176 |
|---|---|
| author | Pocius, Martynas Yan, Wen Barratt, Dean C. Emberton, Mark Clarkson, Matthew J. Hu, Yipeng Saeed, Shaheer U. |
| author_facet | Pocius, Martynas Yan, Wen Barratt, Dean C. Emberton, Mark Clarkson, Matthew J. Hu, Yipeng Saeed, Shaheer U. |
| contents | In this paper we propose a reinforcement learning based weakly supervised system for localisation. We train a controller function to localise regions of interest within an image by introducing a novel reward definition that utilises non-binarised classification probability, generated by a pre-trained binary classifier which classifies object presence in images or image crops. The object-presence classifier may then inform the controller of its localisation quality by quantifying the likelihood of the image containing an object. Such an approach allows us to minimize any potential labelling or human bias propagated via human labelling for fully supervised localisation. We evaluate our proposed approach for a task of cancerous lesion localisation on a large dataset of real clinical bi-parametric MR images of the prostate. Comparisons to the commonly used multiple-instance learning weakly supervised localisation and to a fully supervised baseline show that our proposed method outperforms the multi-instance learning and performs comparably to fully-supervised learning, using only image-level classification labels for training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13778 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images Pocius, Martynas Yan, Wen Barratt, Dean C. Emberton, Mark Clarkson, Matthew J. Hu, Yipeng Saeed, Shaheer U. Computer Vision and Pattern Recognition In this paper we propose a reinforcement learning based weakly supervised system for localisation. We train a controller function to localise regions of interest within an image by introducing a novel reward definition that utilises non-binarised classification probability, generated by a pre-trained binary classifier which classifies object presence in images or image crops. The object-presence classifier may then inform the controller of its localisation quality by quantifying the likelihood of the image containing an object. Such an approach allows us to minimize any potential labelling or human bias propagated via human labelling for fully supervised localisation. We evaluate our proposed approach for a task of cancerous lesion localisation on a large dataset of real clinical bi-parametric MR images of the prostate. Comparisons to the commonly used multiple-instance learning weakly supervised localisation and to a fully supervised baseline show that our proposed method outperforms the multi-instance learning and performs comparably to fully-supervised learning, using only image-level classification labels for training. |
| title | Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.13778 |