Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis
Abstract Background The ability to predict the prognosis of patients with ovarian cancer can greatly improve disease management. However, the knowledge on the mechanism of the prediction is limited. We sought to deconvolute the attention feature learnt by a deep learning convolutional neural network...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | Journal of Translational Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12967-024-06007-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585452507365376 |
|---|---|
| author | Chun Wai Ng Kwong-Kwok Wong Barrett C. Lawson Sammy Ferri-Borgogno Samuel C. Mok |
| author_facet | Chun Wai Ng Kwong-Kwok Wong Barrett C. Lawson Sammy Ferri-Borgogno Samuel C. Mok |
| author_sort | Chun Wai Ng |
| collection | DOAJ |
| description | Abstract Background The ability to predict the prognosis of patients with ovarian cancer can greatly improve disease management. However, the knowledge on the mechanism of the prediction is limited. We sought to deconvolute the attention feature learnt by a deep learning convolutional neural networks trained with whole-slide images (WSIs) of hematoxylin-and-eosin (H&E)–stained tumor samples using spatial transcriptomic data. Methods In this study, 773 WSIs of H&E-stained tumor sections from 335 patients with treatment naïve high-grade serous ovarian cancer who were included in The Cancer Genome Atlas (TCGA) Pan-Cancer study were used to train, and validate, and to test a ResNet101 CNN model modified with attention mechanism. WSIs from patients in an independent cohort were used to further evaluate the model. Results The prognostic value of the predicted H&E-based survival scores from the trained model on patient survival was evaluated. The attention signals learnt by the model were then examined their correlation with immune signatures using spatial transcriptome. After validating the model with the testing datasets, pathway enrichment analysis showed that the H&E—based survival score significantly correlated with certain immune signatures and this was validated spatially using spatial transcriptome data generated from ovarian cancer FFPE samples by correlating the selected signature and attention signal. Conclusions In conclusion, attention mechanism might be useful to identify regions for their specific immune activities. This could guide future pathological study for the useful immunological features that are important in modulating the prognosis of ovarian cancer patients. |
| format | Article |
| id | doaj-art-c61704f077f94603b5e1c03ba7d44854 |
| institution | Kabale University |
| issn | 1479-5876 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Translational Medicine |
| spelling | doaj-art-c61704f077f94603b5e1c03ba7d448542025-01-26T12:50:07ZengBMCJournal of Translational Medicine1479-58762025-01-0123111110.1186/s12967-024-06007-8Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosisChun Wai Ng0Kwong-Kwok Wong1Barrett C. Lawson2Sammy Ferri-Borgogno3Samuel C. Mok4Department of Gynecologic Oncology and Reproductive Medicine, Unit 1362, The University of Texas MD Anderson Cancer CenterDepartment of Gynecologic Oncology and Reproductive Medicine, Unit 1362, The University of Texas MD Anderson Cancer CenterDepartment of Anatomical Pathology, The University of Texas MD Anderson Cancer CenterDepartment of Gynecologic Oncology and Reproductive Medicine, Unit 1362, The University of Texas MD Anderson Cancer CenterDepartment of Gynecologic Oncology and Reproductive Medicine, Unit 1362, The University of Texas MD Anderson Cancer CenterAbstract Background The ability to predict the prognosis of patients with ovarian cancer can greatly improve disease management. However, the knowledge on the mechanism of the prediction is limited. We sought to deconvolute the attention feature learnt by a deep learning convolutional neural networks trained with whole-slide images (WSIs) of hematoxylin-and-eosin (H&E)–stained tumor samples using spatial transcriptomic data. Methods In this study, 773 WSIs of H&E-stained tumor sections from 335 patients with treatment naïve high-grade serous ovarian cancer who were included in The Cancer Genome Atlas (TCGA) Pan-Cancer study were used to train, and validate, and to test a ResNet101 CNN model modified with attention mechanism. WSIs from patients in an independent cohort were used to further evaluate the model. Results The prognostic value of the predicted H&E-based survival scores from the trained model on patient survival was evaluated. The attention signals learnt by the model were then examined their correlation with immune signatures using spatial transcriptome. After validating the model with the testing datasets, pathway enrichment analysis showed that the H&E—based survival score significantly correlated with certain immune signatures and this was validated spatially using spatial transcriptome data generated from ovarian cancer FFPE samples by correlating the selected signature and attention signal. Conclusions In conclusion, attention mechanism might be useful to identify regions for their specific immune activities. This could guide future pathological study for the useful immunological features that are important in modulating the prognosis of ovarian cancer patients.https://doi.org/10.1186/s12967-024-06007-8AttentionDeep learningH&EImmune signatureOvarian cancerPrognosis |
| spellingShingle | Chun Wai Ng Kwong-Kwok Wong Barrett C. Lawson Sammy Ferri-Borgogno Samuel C. Mok Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis Journal of Translational Medicine Attention Deep learning H&E Immune signature Ovarian cancer Prognosis |
| title | Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis |
| title_full | Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis |
| title_fullStr | Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis |
| title_full_unstemmed | Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis |
| title_short | Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis |
| title_sort | spatial transcriptome reveals histology correlated immune signature learnt by deep learning attention mechanism on h e stained images for ovarian cancer prognosis |
| topic | Attention Deep learning H&E Immune signature Ovarian cancer Prognosis |
| url | https://doi.org/10.1186/s12967-024-06007-8 |
| work_keys_str_mv | AT chunwaing spatialtranscriptomerevealshistologycorrelatedimmunesignaturelearntbydeeplearningattentionmechanismonhestainedimagesforovariancancerprognosis AT kwongkwokwong spatialtranscriptomerevealshistologycorrelatedimmunesignaturelearntbydeeplearningattentionmechanismonhestainedimagesforovariancancerprognosis AT barrettclawson spatialtranscriptomerevealshistologycorrelatedimmunesignaturelearntbydeeplearningattentionmechanismonhestainedimagesforovariancancerprognosis AT sammyferriborgogno spatialtranscriptomerevealshistologycorrelatedimmunesignaturelearntbydeeplearningattentionmechanismonhestainedimagesforovariancancerprognosis AT samuelcmok spatialtranscriptomerevealshistologycorrelatedimmunesignaturelearntbydeeplearningattentionmechanismonhestainedimagesforovariancancerprognosis |