Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images
Background: Tumor programmed death-ligand 1 (PD-L1) status is useful in determining which patients may benefit from programmed death-1 (PD-1)/PD-L1 inhibitors. However, little is known about the association between PD-L1 status and tumor histopathological patterns. Using deep learning, we predicted...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2019;volume=10;issue=1;spage=24;epage=24;aulast=Sha |
| _version_ | 1818230402747203584 |
|---|---|
| author | Lingdao Sha Boleslaw L Osinski Irvin Y Ho Timothy L Tan Caleb Willis Hannah Weiss Nike Beaubier Brett M Mahon Tim J Taxter Stephen S F Yip |
| author_facet | Lingdao Sha Boleslaw L Osinski Irvin Y Ho Timothy L Tan Caleb Willis Hannah Weiss Nike Beaubier Brett M Mahon Tim J Taxter Stephen S F Yip |
| author_sort | Lingdao Sha |
| collection | DOAJ |
| description | Background: Tumor programmed death-ligand 1 (PD-L1) status is useful in determining which patients may benefit from programmed death-1 (PD-1)/PD-L1 inhibitors. However, little is known about the association between PD-L1 status and tumor histopathological patterns. Using deep learning, we predicted PD-L1 status from hematoxylin and eosin (H and E) whole-slide images (WSIs) of nonsmall cell lung cancer (NSCLC) tumor samples. Materials and Methods: One hundred and thirty NSCLC patients were randomly assigned to training (n = 48) or test (n = 82) cohorts. A pair of H and E and PD-L1-immunostained WSIs was obtained for each patient. A pathologist annotated PD-L1 positive and negative tumor regions on the training samples using immunostained WSIs for reference. From the H and E WSIs, over 145,000 training tiles were generated and used to train a multi-field-of-view deep learning model with a residual neural network backbone. Results: The trained model accurately predicted tumor PD-L1 status on the held-out test cohort of H and E WSIs, which was balanced for PD-L1 status (area under the receiver operating characteristic curve [AUC] =0.80, P << 0.01). The model remained effective over a range of PD-L1 cutoff thresholds (AUC = 0.67–0.81, P ≤ 0.01) and when different proportions of the labels were randomly shuffled to simulate interpathologist disagreement (AUC = 0.63–0.77, P ≤ 0.03). Conclusions: A robust deep learning model was developed to predict tumor PD-L1 status from H and E WSIs in NSCLC. These results suggest that PD-L1 expression is correlated with the morphological features of the tumor microenvironment. |
| first_indexed | 2024-12-12T10:33:56Z |
| format | Article |
| id | doaj.art-c38c7fa27aac4ae58bd530eaed8dbca4 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 2153-3539 |
| language | English |
| last_indexed | 2024-12-12T10:33:56Z |
| publishDate | 2019-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-c38c7fa27aac4ae58bd530eaed8dbca42022-12-22T00:27:17ZengElsevierJournal of Pathology Informatics2153-35392153-35392019-01-01101242410.4103/jpi.jpi_24_19Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin imagesLingdao ShaBoleslaw L OsinskiIrvin Y HoTimothy L TanCaleb WillisHannah WeissNike BeaubierBrett M MahonTim J TaxterStephen S F YipBackground: Tumor programmed death-ligand 1 (PD-L1) status is useful in determining which patients may benefit from programmed death-1 (PD-1)/PD-L1 inhibitors. However, little is known about the association between PD-L1 status and tumor histopathological patterns. Using deep learning, we predicted PD-L1 status from hematoxylin and eosin (H and E) whole-slide images (WSIs) of nonsmall cell lung cancer (NSCLC) tumor samples. Materials and Methods: One hundred and thirty NSCLC patients were randomly assigned to training (n = 48) or test (n = 82) cohorts. A pair of H and E and PD-L1-immunostained WSIs was obtained for each patient. A pathologist annotated PD-L1 positive and negative tumor regions on the training samples using immunostained WSIs for reference. From the H and E WSIs, over 145,000 training tiles were generated and used to train a multi-field-of-view deep learning model with a residual neural network backbone. Results: The trained model accurately predicted tumor PD-L1 status on the held-out test cohort of H and E WSIs, which was balanced for PD-L1 status (area under the receiver operating characteristic curve [AUC] =0.80, P << 0.01). The model remained effective over a range of PD-L1 cutoff thresholds (AUC = 0.67–0.81, P ≤ 0.01) and when different proportions of the labels were randomly shuffled to simulate interpathologist disagreement (AUC = 0.63–0.77, P ≤ 0.03). Conclusions: A robust deep learning model was developed to predict tumor PD-L1 status from H and E WSIs in NSCLC. These results suggest that PD-L1 expression is correlated with the morphological features of the tumor microenvironment.http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2019;volume=10;issue=1;spage=24;epage=24;aulast=ShaArtificial intelligencedeep learningdigital pathologylung cancer |
| spellingShingle | Lingdao Sha Boleslaw L Osinski Irvin Y Ho Timothy L Tan Caleb Willis Hannah Weiss Nike Beaubier Brett M Mahon Tim J Taxter Stephen S F Yip Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images Journal of Pathology Informatics Artificial intelligence deep learning digital pathology lung cancer |
| title | Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images |
| title_full | Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images |
| title_fullStr | Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images |
| title_full_unstemmed | Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images |
| title_short | Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images |
| title_sort | multi field of view deep learning model predicts nonsmall cell lung cancer programmed death ligand 1 status from whole slide hematoxylin and eosin images |
| topic | Artificial intelligence deep learning digital pathology lung cancer |
| url | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2019;volume=10;issue=1;spage=24;epage=24;aulast=Sha |
| work_keys_str_mv | AT lingdaosha multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT boleslawlosinski multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT irvinyho multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT timothyltan multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT calebwillis multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT hannahweiss multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT nikebeaubier multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT brettmmahon multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT timjtaxter multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages AT stephensfyip multifieldofviewdeeplearningmodelpredictsnonsmallcelllungcancerprogrammeddeathligand1statusfromwholeslidehematoxylinandeosinimages |