Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides
Abstract Endometrial cancer (EC) diagnosis traditionally relies on tumor morphology and nuclear grade, but personalized therapy demands a deeper understanding of tumor mutational burden (TMB), i.e., a key biomarker for immune checkpoint inhibition and immunotherapy response. Traditional TMB predicti...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-024-00766-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846112944744562688 |
|---|---|
| author | Ching-Wei Wang Nabila Puspita Firdi Yu-Ching Lee Tzu-Chiao Chu Hikam Muzakky Tzu-Chien Liu Po-Jen Lai Tai-Kuang Chao |
| author_facet | Ching-Wei Wang Nabila Puspita Firdi Yu-Ching Lee Tzu-Chiao Chu Hikam Muzakky Tzu-Chien Liu Po-Jen Lai Tai-Kuang Chao |
| author_sort | Ching-Wei Wang |
| collection | DOAJ |
| description | Abstract Endometrial cancer (EC) diagnosis traditionally relies on tumor morphology and nuclear grade, but personalized therapy demands a deeper understanding of tumor mutational burden (TMB), i.e., a key biomarker for immune checkpoint inhibition and immunotherapy response. Traditional TMB prediction methods, such as sequencing exomes or whole genomes, are costly and often unavailable in clinical settings. We present the first TR-MAMIL deep learning framework to predict TMB status and classify the EC cancer subtype directly from H&E-stained WSIs, enabling effective personalized immunotherapy planning and prognostic refinement of EC patients. Our models were evaluated on a large dataset from The Cancer Genome Atlas. TR-MAMIL performed exceptionally well in classifying aggressive and non-aggressive EC, as well as predicting TMB, outperforming seven state-of-the-art approaches. It also performed well in classifying normal and abnormal p53 mutations in EC using H&E WSIs. Kaplan–Meier analysis further demonstrated TR-MAMIL’s ability to differentiate patients with longer survival in the aggressive EC. |
| format | Article |
| id | doaj-art-bb3c51a15c3c4580bec4fa38c4177af6 |
| institution | Kabale University |
| issn | 2397-768X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-bb3c51a15c3c4580bec4fa38c4177af62024-12-22T12:11:27ZengNature Portfolionpj Precision Oncology2397-768X2024-12-018111810.1038/s41698-024-00766-9Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slidesChing-Wei Wang0Nabila Puspita Firdi1Yu-Ching Lee2Tzu-Chiao Chu3Hikam Muzakky4Tzu-Chien Liu5Po-Jen Lai6Tai-Kuang Chao7Graduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyGraduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyGraduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyGraduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyGraduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyGraduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyGraduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyInstitute of Pathology and Parasitology, National Defense Medical CenterAbstract Endometrial cancer (EC) diagnosis traditionally relies on tumor morphology and nuclear grade, but personalized therapy demands a deeper understanding of tumor mutational burden (TMB), i.e., a key biomarker for immune checkpoint inhibition and immunotherapy response. Traditional TMB prediction methods, such as sequencing exomes or whole genomes, are costly and often unavailable in clinical settings. We present the first TR-MAMIL deep learning framework to predict TMB status and classify the EC cancer subtype directly from H&E-stained WSIs, enabling effective personalized immunotherapy planning and prognostic refinement of EC patients. Our models were evaluated on a large dataset from The Cancer Genome Atlas. TR-MAMIL performed exceptionally well in classifying aggressive and non-aggressive EC, as well as predicting TMB, outperforming seven state-of-the-art approaches. It also performed well in classifying normal and abnormal p53 mutations in EC using H&E WSIs. Kaplan–Meier analysis further demonstrated TR-MAMIL’s ability to differentiate patients with longer survival in the aggressive EC.https://doi.org/10.1038/s41698-024-00766-9 |
| spellingShingle | Ching-Wei Wang Nabila Puspita Firdi Yu-Ching Lee Tzu-Chiao Chu Hikam Muzakky Tzu-Chien Liu Po-Jen Lai Tai-Kuang Chao Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides npj Precision Oncology |
| title | Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides |
| title_full | Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides |
| title_fullStr | Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides |
| title_full_unstemmed | Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides |
| title_short | Deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides |
| title_sort | deep learning for endometrial cancer subtyping and predicting tumor mutational burden from histopathological slides |
| url | https://doi.org/10.1038/s41698-024-00766-9 |
| work_keys_str_mv | AT chingweiwang deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides AT nabilapuspitafirdi deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides AT yuchinglee deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides AT tzuchiaochu deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides AT hikammuzakky deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides AT tzuchienliu deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides AT pojenlai deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides AT taikuangchao deeplearningforendometrialcancersubtypingandpredictingtumormutationalburdenfromhistopathologicalslides |