Accurate subtyping of lung cancers by modelling class dependencies
Identifying subtypes and histological patterns is crucial for lung cancer diagnosis and treatment. Nevertheless, datasets with complete subtyping annotations are scarce, and most existing work primarily focuses on categorising lung cancers into fundamental types, omitting the distinction of adenocar...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2024
|
| _version_ | 1826314378523181056 |
|---|---|
| author | Batchkala, G Li, B Fan, M McCole, M Brambilla, C Gleeson, F Rittscher, J |
| author_facet | Batchkala, G Li, B Fan, M McCole, M Brambilla, C Gleeson, F Rittscher, J |
| author_sort | Batchkala, G |
| collection | OXFORD |
| description | Identifying subtypes and histological patterns is crucial for
lung cancer diagnosis and treatment. Nevertheless, datasets
with complete subtyping annotations are scarce, and most
existing work primarily focuses on categorising lung cancers into fundamental types, omitting the distinction of
adenocarcinoma patterns. We present a computational approach for a more comprehensive lung cancer subtyping
from histology by modelling the dependencies between
cancer subtypes and histological patterns in a multi-label
setting. Our approach utilises slide-level labels indicating cancer subtypes as well as the presence of cancerassociated patterns, thereby alleviating the need for labourintensive region-based annotations. A new dataset with
cancer-associated pattern labels is constructed and combined
with publicly available datasets. We evaluate our model’s
ability to simultaneously differentiate cancer subtypes and
cancer-associated patterns. The result demonstrates that
our modules enable conventional weakly-supervised classification models on multi-label problems, achieving subset
accuracy of 84% when differentiating lung cancer subtypes
and cancer-associated histological patterns. |
| first_indexed | 2024-04-23T08:25:24Z |
| format | Conference item |
| id | oxford-uuid:4966840e-ccef-4fbf-b5fb-6cf0376d9aaa |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:31:39Z |
| publishDate | 2024 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:4966840e-ccef-4fbf-b5fb-6cf0376d9aaa2024-08-31T20:03:30ZAccurate subtyping of lung cancers by modelling class dependenciesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:4966840e-ccef-4fbf-b5fb-6cf0376d9aaaEnglishSymplectic ElementsIEEE2024Batchkala, GLi, BFan, MMcCole, MBrambilla, CGleeson, FRittscher, JIdentifying subtypes and histological patterns is crucial for lung cancer diagnosis and treatment. Nevertheless, datasets with complete subtyping annotations are scarce, and most existing work primarily focuses on categorising lung cancers into fundamental types, omitting the distinction of adenocarcinoma patterns. We present a computational approach for a more comprehensive lung cancer subtyping from histology by modelling the dependencies between cancer subtypes and histological patterns in a multi-label setting. Our approach utilises slide-level labels indicating cancer subtypes as well as the presence of cancerassociated patterns, thereby alleviating the need for labourintensive region-based annotations. A new dataset with cancer-associated pattern labels is constructed and combined with publicly available datasets. We evaluate our model’s ability to simultaneously differentiate cancer subtypes and cancer-associated patterns. The result demonstrates that our modules enable conventional weakly-supervised classification models on multi-label problems, achieving subset accuracy of 84% when differentiating lung cancer subtypes and cancer-associated histological patterns. |
| spellingShingle | Batchkala, G Li, B Fan, M McCole, M Brambilla, C Gleeson, F Rittscher, J Accurate subtyping of lung cancers by modelling class dependencies |
| title | Accurate subtyping of lung cancers by modelling class dependencies |
| title_full | Accurate subtyping of lung cancers by modelling class dependencies |
| title_fullStr | Accurate subtyping of lung cancers by modelling class dependencies |
| title_full_unstemmed | Accurate subtyping of lung cancers by modelling class dependencies |
| title_short | Accurate subtyping of lung cancers by modelling class dependencies |
| title_sort | accurate subtyping of lung cancers by modelling class dependencies |
| work_keys_str_mv | AT batchkalag accuratesubtypingoflungcancersbymodellingclassdependencies AT lib accuratesubtypingoflungcancersbymodellingclassdependencies AT fanm accuratesubtypingoflungcancersbymodellingclassdependencies AT mccolem accuratesubtypingoflungcancersbymodellingclassdependencies AT brambillac accuratesubtypingoflungcancersbymodellingclassdependencies AT gleesonf accuratesubtypingoflungcancersbymodellingclassdependencies AT rittscherj accuratesubtypingoflungcancersbymodellingclassdependencies |