Deep Learning for Subtypes Identification of Pure Seminoma of the Testis
The most critical step in the clinical diagnosis workflow is the pathological evaluation of each tumor sample. Deep learning is a powerful approach that is widely used to enhance diagnostic accuracy and streamline the diagnosis process. In our previous study using omics data, we identified 2 distinc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2024-02-01
|
| Series: | Clinical Pathology |
| Online Access: | https://doi.org/10.1177/2632010X241232302 |
| _version_ | 1797302786476474368 |
|---|---|
| author | Kirill E Medvedev Paul H Acosta Liwei Jia Nick V Grishin |
| author_facet | Kirill E Medvedev Paul H Acosta Liwei Jia Nick V Grishin |
| author_sort | Kirill E Medvedev |
| collection | DOAJ |
| description | The most critical step in the clinical diagnosis workflow is the pathological evaluation of each tumor sample. Deep learning is a powerful approach that is widely used to enhance diagnostic accuracy and streamline the diagnosis process. In our previous study using omics data, we identified 2 distinct subtypes of pure seminoma. Seminoma is the most common histological type of testicular germ cell tumors (TGCTs). Here we developed a deep learning decision making tool for the identification of seminoma subtypes using histopathological slides. We used all available slides for pure seminoma samples from The Cancer Genome Atlas (TCGA). The developed model showed an area under the ROC curve of 0.896. Our model not only confirms the presence of 2 distinct subtypes within pure seminoma but also unveils the presence of morphological differences between them that are imperceptible to the human eye. |
| first_indexed | 2024-03-07T23:44:00Z |
| format | Article |
| id | doaj.art-29a50be5aa72457cb45163381907d752 |
| institution | Directory Open Access Journal |
| issn | 2632-010X |
| language | English |
| last_indexed | 2024-03-07T23:44:00Z |
| publishDate | 2024-02-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Clinical Pathology |
| spelling | doaj.art-29a50be5aa72457cb45163381907d7522024-02-19T18:03:18ZengSAGE PublishingClinical Pathology2632-010X2024-02-011710.1177/2632010X241232302Deep Learning for Subtypes Identification of Pure Seminoma of the TestisKirill E Medvedev0Paul H Acosta1Liwei Jia2Nick V Grishin3Department of Biophysics, University of Texas Southwestern Medical Center, Dallas, TX, USALyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USADepartment of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USADepartment of Biochemistry, University of Texas Southwestern Medical Center, Dallas, TX, USAThe most critical step in the clinical diagnosis workflow is the pathological evaluation of each tumor sample. Deep learning is a powerful approach that is widely used to enhance diagnostic accuracy and streamline the diagnosis process. In our previous study using omics data, we identified 2 distinct subtypes of pure seminoma. Seminoma is the most common histological type of testicular germ cell tumors (TGCTs). Here we developed a deep learning decision making tool for the identification of seminoma subtypes using histopathological slides. We used all available slides for pure seminoma samples from The Cancer Genome Atlas (TCGA). The developed model showed an area under the ROC curve of 0.896. Our model not only confirms the presence of 2 distinct subtypes within pure seminoma but also unveils the presence of morphological differences between them that are imperceptible to the human eye.https://doi.org/10.1177/2632010X241232302 |
| spellingShingle | Kirill E Medvedev Paul H Acosta Liwei Jia Nick V Grishin Deep Learning for Subtypes Identification of Pure Seminoma of the Testis Clinical Pathology |
| title | Deep Learning for Subtypes Identification of Pure Seminoma of the Testis |
| title_full | Deep Learning for Subtypes Identification of Pure Seminoma of the Testis |
| title_fullStr | Deep Learning for Subtypes Identification of Pure Seminoma of the Testis |
| title_full_unstemmed | Deep Learning for Subtypes Identification of Pure Seminoma of the Testis |
| title_short | Deep Learning for Subtypes Identification of Pure Seminoma of the Testis |
| title_sort | deep learning for subtypes identification of pure seminoma of the testis |
| url | https://doi.org/10.1177/2632010X241232302 |
| work_keys_str_mv | AT kirillemedvedev deeplearningforsubtypesidentificationofpureseminomaofthetestis AT paulhacosta deeplearningforsubtypesidentificationofpureseminomaofthetestis AT liweijia deeplearningforsubtypesidentificationofpureseminomaofthetestis AT nickvgrishin deeplearningforsubtypesidentificationofpureseminomaofthetestis |