Eastwood, Mark, Marc, Silviu Tudor, Gao, Xiaohong, Sailem, Heba, Offman, Judith, Karteris, Emmanouil, Fernandez, Angeles Montero, Jonigk, Danny, Cookson, William, Moffatt, Miriam, Popat, Sanjay, Minhas, Fayyaz and Robertus, Jan Lukas (2022) Malignant mesothelioma subtyping of tissue images via sampling driven multiple instance prediction. In: 20th International Conference on Artificial Intelligence in Medicine, AIME 202, Halifax; Canada, 14-17 Jun 2022. Published in: Lecture Notes in Computer Science, 13263 pp. 263-272. doi:10.1007/978-3-031-09342-5_25 ISSN 0302-9743.
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Abstract
Malignant Mesothelioma is a difficult to diagnose and highly lethal cancer usually associated with asbestos exposure. It can be broadly classified into three subtypes: Epitheliod, Sarcomatoid, and Biphasic. Early diagnosis and identification of the subtype informs treatment and can help improve patient outcome. However, the subtyping of malignant mesothelioma, and specifically the recognition of transitional features from routine histology slides has a high level of inter-observer variablity. In this work, we propose the first end-to-end multiple instance learning (MIL) approach for malignant mesothelioma subtyping. This uses an instance-based sampling scheme for training deep convolutional neural networks on this task that allows learning on a wider range of relevant instances compared to max or top-N based MIL approaches. The proposed MIL approach enables identification of malignant mesothelial subtypes of specific tissue regions. From this a continuous characterization of a sample according to predominance of sarcomatoid vs epithelioid regions is possible, thus avoiding the arbitrary and highly subjective categorisation by currently used subtypes. Instance scoring also enables studying tumor heterogeneity and identifying patterns associated with different subtypes. We have evaluated the proposed method on a dataset of 243 tissue micro-array cores with an AUROC of 0.87±0.04 for this task. The dataset and developed methodology is available for the community at: https://github.com/measty/PINS. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
| Item Type: | Conference Item (Paper) |
|---|---|
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science |
| Journal or Publication Title: | Lecture Notes in Computer Science |
| Publisher: | Springer |
| ISSN: | 0302-9743 |
| Book Title: | Artificial Intelligence in Medicine |
| Official Date: | 9 July 2022 |
| Dates: | Date Event 9 July 2022 Published |
| Volume: | 13263 |
| Page Range: | pp. 263-272 |
| DOI: | 10.1007/978-3-031-09342-5_25 |
| Status: | Peer Reviewed |
| Publication Status: | Published |
| Access rights to Published version: | Restricted or Subscription Access |
| Copyright Holders: | © 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG |
| Conference Paper Type: | Paper |
| Title of Event: | 20th International Conference on Artificial Intelligence in Medicine, AIME 202 |
| Type of Event: | Conference |
| Location of Event: | Halifax; Canada |
| Date(s) of Event: | 14-17 Jun 2022 |
| URI: | https://wrap.warwick.ac.uk/168519/ |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |