Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images
<p>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...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Elsevier
2022
|
| _version_ | 1826311067903459328 |
|---|---|
| author | Denholm, J Schreiber, BA Evans, SC Crook, OM Sharma, A Watson, JL Bancroft, H Langman, G Gilbey, JD Schönlieb, C-B Arends, MJ Soilleux, EJ |
| author_facet | Denholm, J Schreiber, BA Evans, SC Crook, OM Sharma, A Watson, JL Bancroft, H Langman, G Gilbey, JD Schönlieb, C-B Arends, MJ Soilleux, EJ |
| author_sort | Denholm, J |
| collection | OXFORD |
| description | <p>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.</p>
<p>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 <em>same-source</em> 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 <em>different-source</em> 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.</p> |
| first_indexed | 2024-03-07T08:02:54Z |
| format | Journal article |
| id | oxford-uuid:f256f4b4-3e07-4c3d-b14d-80e54955f10f |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:02:54Z |
| publishDate | 2022 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:f256f4b4-3e07-4c3d-b14d-80e54955f10f2023-10-03T13:23:26ZMultiple-instance-learning-based detection of coeliac disease in histological whole-slide imagesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:f256f4b4-3e07-4c3d-b14d-80e54955f10fEnglishSymplectic ElementsElsevier2022Denholm, JSchreiber, BAEvans, SCCrook, OMSharma, AWatson, JLBancroft, HLangman, GGilbey, JDSchönlieb, C-BArends, MJSoilleux, EJ<p>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.</p> <p>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 <em>same-source</em> 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 <em>different-source</em> 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.</p> |
| spellingShingle | Denholm, J Schreiber, BA Evans, SC Crook, OM Sharma, A Watson, JL Bancroft, H Langman, G Gilbey, JD Schönlieb, C-B Arends, MJ Soilleux, EJ Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images |
| title | Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images |
| title_full | Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images |
| title_fullStr | Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images |
| title_full_unstemmed | Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images |
| title_short | Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images |
| title_sort | multiple instance learning based detection of coeliac disease in histological whole slide images |
| work_keys_str_mv | AT denholmj multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT schreiberba multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT evanssc multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT crookom multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT sharmaa multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT watsonjl multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT bancrofth multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT langmang multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT gilbeyjd multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT schonliebcb multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT arendsmj multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages AT soilleuxej multipleinstancelearningbaseddetectionofcoeliacdiseaseinhistologicalwholeslideimages |