TY - JOUR
T1 - Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images
AU - Denholm, J
AU - Scheiber, B.A.
AU - Crook, O.M.
AU - Evans, S.C.
AU - Sharma, A.
AU - Watson, J.L.
AU - Bancroft, H
AU - Langman, G.
AU - Gilbey, J.D.
AU - Schönlieb, C.-B
AU - Arends, Mark J
AU - Soilleux, E.J.
N1 - Funding Information:
This work was supported by a Coeliac UK and Innovate UK grant (INOV03-19) awarded to E.J.S. and a Pump Priming Grant (to E.J.S.) from the Pathological Society of Great Britain and Ireland (Path Soc). B.A.S. gratefully acknowledges financial support from a PhD studentship awarded by Path Soc. O.M.C. was supported by an EPSRC grant EP/N510129/1. J.L.W. and A.S. acknowledge financial support from undergraduate bursaries awarded by Path Soc. All authors gratefully acknowledge and thank: Yossef Molchanov (Sheba Medical Centre), Chen Mayer (Department of Pathology, Sheba Medical Centre) and Iris Barshack (Sackler Faculty of Medicine, Tel Aviv University), for facilitating the transfer of a small batch of whole-slide images to test our model on; Rosie Telford Spencer, for a careful proofreading of this manuscript; Graham Snudden for organisational and financial support.
Funding Information:
This work was supported by a Coeliac UK and Innovate UK grant ( INOV03-19 ) awarded to E.J.S., and a Pump Priming Grant (to E.J.S.) from the Pathological Society of Great Britain and Ireland (Path Soc). B.A.S. gratefully acknowledges financial support from a PhD studentship awarded by Path Soc . O.M.C. was supported by an EPSRC grant EP/N510129/1 . J.L.W. and A.S. acknowledge financial support from undergraduate bursaries awarded by Path Soc .
Publisher Copyright:
© 2022 The Authors
PY - 2022/10/28
Y1 - 2022/10/28
N2 - We present a multiple-instance-learning-based scheme for detecting coeliac disease, an autoimmune disorder affecting the intestine, in histological whole-slide images (WSIs) of duodenal biopsies. We train our model to detect 2 distinct classes, normal tissue and coeliac disease, on the patch-level, and in turn leverage slide-level classifications. Using 5-fold cross-validation in a training set of 1841 (1163 normal; 680 coeliac disease) WSIs, our model classifies slides as normal with accuracy (96.7±0.6)%, precision (98.0±1.7)%, and recall (96.8±2.5)%, and as coeliac disease with accuracy (96.7±0.5)%, precision (94.9±3.7)%, and recall (96.5±2.9)% where the error bars are the cross-validation standard deviation. We apply our model to 2 test sets: one containing 191 WSIs (126 normal; 65 coeliac) from the same sources as the training data, and another from a completely independent source, containing 34 WSIs (17 normal; 17 coeliac), obtained with a scanner model not represented in the training data. Using the same-source test data, our model classifies slides as normal with accuracy 96.5%, precision 98.4% and recall 96.1%, and positive for coeliac disease with accuracy 96.5%, precision 93.5%, and recall 97.3%. Using the different-source test data the model classifies slides as normal with accuracy 94.1% (32/34), precision 89.5%, and recall 100%, and as positive for coeliac disease with accuracy 94.1%, precision 100%, and recall 88.2%. We discuss generalising our approach to screen for a range of pathologies.
AB - We present a multiple-instance-learning-based scheme for detecting coeliac disease, an autoimmune disorder affecting the intestine, in histological whole-slide images (WSIs) of duodenal biopsies. We train our model to detect 2 distinct classes, normal tissue and coeliac disease, on the patch-level, and in turn leverage slide-level classifications. Using 5-fold cross-validation in a training set of 1841 (1163 normal; 680 coeliac disease) WSIs, our model classifies slides as normal with accuracy (96.7±0.6)%, precision (98.0±1.7)%, and recall (96.8±2.5)%, and as coeliac disease with accuracy (96.7±0.5)%, precision (94.9±3.7)%, and recall (96.5±2.9)% where the error bars are the cross-validation standard deviation. We apply our model to 2 test sets: one containing 191 WSIs (126 normal; 65 coeliac) from the same sources as the training data, and another from a completely independent source, containing 34 WSIs (17 normal; 17 coeliac), obtained with a scanner model not represented in the training data. Using the same-source test data, our model classifies slides as normal with accuracy 96.5%, precision 98.4% and recall 96.1%, and positive for coeliac disease with accuracy 96.5%, precision 93.5%, and recall 97.3%. Using the different-source test data the model classifies slides as normal with accuracy 94.1% (32/34), precision 89.5%, and recall 100%, and as positive for coeliac disease with accuracy 94.1%, precision 100%, and recall 88.2%. We discuss generalising our approach to screen for a range of pathologies.
KW - computational pathology
KW - deep learning
KW - weakly supervised learning
KW - computer vision
KW - coeliac disease
U2 - 10.1016/j.jpi.2022.100151
DO - 10.1016/j.jpi.2022.100151
M3 - Article
SN - 2153-3539
VL - 13
JO - Journal of Pathology Informatics
JF - Journal of Pathology Informatics
M1 - 100151
ER -