Imperial College London
Portrait Picture

ProfessorTaraBarwick

Faculty of Medicine, Department of Surgery & Cancer

Professor of Practice (Cancer Imaging)
 
 
 
//

Contact

 

t.barwick

 
 
//

Location

 

Commonwealth BuildingHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Qaiser:2021:10.1007/978-3-030-87234-2_74,
author = {Qaiser, T and Winzeck, S and Barfoot, T and Barwick, T and Doran, SJ and Kaiser, MF and Wedlake, L and Tunariu, N and Koh, D-M and Messiou, C and Rockall, A and Glocker, B},
doi = {10.1007/978-3-030-87234-2_74},
pages = {786--796},
publisher = {Springer},
title = {Multiple instance learning with auxiliary task weighting for multiple myeloma classification},
url = {http://dx.doi.org/10.1007/978-3-030-87234-2_74},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Whole body magnetic resonance imaging (WB-MRI) is the recommended modality for diagnosis of multiple myeloma (MM). WB-MRI is used to detect sites of disease across the entire skeletal system, but it requires significant expertise and is time-consuming to report due to the great number of images. To aid radiological reading, we propose an auxiliary task-based multiple instance learning approach (ATMIL) for MM classification with the ability to localize sites of disease. This approach is appealing as it only requires patient-level annotations where an attention mechanism is used to identify local regions with active disease. We borrow ideas from multi-task learning and define an auxiliary task with adaptive reweighting to support and improve learning efficiency in the presence of data scarcity. We validate our approach on both synthetic and real multi-center clinical data. We show that the MIL attention module provides a mechanism to localize bone regions while the adaptive reweighting of the auxiliary task considerably improves the performance.
AU  - Qaiser,T
AU  - Winzeck,S
AU  - Barfoot,T
AU  - Barwick,T
AU  - Doran,SJ
AU  - Kaiser,MF
AU  - Wedlake,L
AU  - Tunariu,N
AU  - Koh,D-M
AU  - Messiou,C
AU  - Rockall,A
AU  - Glocker,B
DO  - 10.1007/978-3-030-87234-2_74
EP  - 796
PB  - Springer
PY  - 2021///
SN  - 0302-9743
SP  - 786
TI  - Multiple instance learning with auxiliary task weighting for multiple myeloma classification
UR  - http://dx.doi.org/10.1007/978-3-030-87234-2_74
UR  - http://arxiv.org/abs/2107.07805v1
UR  - http://hdl.handle.net/10044/1/90450
ER  -
Download