Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status
Abstract The detection of tumour gene mutations by DNA or RNA sequencing is crucial for the prescription of effective targeted therapies. Recent developments showed promising results for tumoral mutational status prediction using new deep learning based methods on histopathological images. However,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-34016-y |
| _version_ | 1797836509898866688 |
|---|---|
| author | Louis-Oscar Morel Valentin Derangère Laurent Arnould Sylvain Ladoire Nathan Vinçon |
| author_facet | Louis-Oscar Morel Valentin Derangère Laurent Arnould Sylvain Ladoire Nathan Vinçon |
| author_sort | Louis-Oscar Morel |
| collection | DOAJ |
| description | Abstract The detection of tumour gene mutations by DNA or RNA sequencing is crucial for the prescription of effective targeted therapies. Recent developments showed promising results for tumoral mutational status prediction using new deep learning based methods on histopathological images. However, it is still unknown whether these methods can be useful aside from sequencing methods for efficient population diagnosis. In this retrospective study, we use a standard prediction pipeline based on a convolutional neural network for the detection of cancer driver genomic alterations in The Cancer Genome Atlas (TCGA) breast (BRCA, n = 719), lung (LUAD, n = 541) and colon (COAD, n = 459) cancer datasets. We propose 3 diagnostic strategies using deep learning methods as first-line diagnostic tools. Focusing on cancer driver genes such as KRAS, EGFR or TP53, we show that these methods help reduce DNA sequencing by up to 49.9% with a high sensitivity (95%). In a context of limited resources, these methods increase sensitivity up to 69.8% at a 30% capacity of DNA sequencing tests, up to 85.1% at a 50% capacity, and up to 91.8% at a 70% capacity. These methods can also be used to prioritize patients with a positive predictive value up to 90.6% in the 10% patient most at risk of being mutated. Limitations of this study include the lack of external validation on non-TCGA data, dependence on prevalence of mutations in datasets, and use of a standard DL method on a limited dataset. Future studies using state-of-the-art methods and larger datasets are needed for better evaluation and clinical implementation. |
| first_indexed | 2024-04-09T15:10:06Z |
| format | Article |
| id | doaj.art-d38070a7f6a04daf870471a42a6e9f4b |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T15:10:06Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-d38070a7f6a04daf870471a42a6e9f4b2023-04-30T11:16:12ZengNature PortfolioScientific Reports2045-23222023-04-0113111110.1038/s41598-023-34016-yPreliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational statusLouis-Oscar Morel0Valentin Derangère1Laurent Arnould2Sylvain Ladoire3Nathan Vinçon4Ummon HealthTechCentre Georges François LeclercCentre Georges François LeclercCentre Georges François LeclercUmmon HealthTechAbstract The detection of tumour gene mutations by DNA or RNA sequencing is crucial for the prescription of effective targeted therapies. Recent developments showed promising results for tumoral mutational status prediction using new deep learning based methods on histopathological images. However, it is still unknown whether these methods can be useful aside from sequencing methods for efficient population diagnosis. In this retrospective study, we use a standard prediction pipeline based on a convolutional neural network for the detection of cancer driver genomic alterations in The Cancer Genome Atlas (TCGA) breast (BRCA, n = 719), lung (LUAD, n = 541) and colon (COAD, n = 459) cancer datasets. We propose 3 diagnostic strategies using deep learning methods as first-line diagnostic tools. Focusing on cancer driver genes such as KRAS, EGFR or TP53, we show that these methods help reduce DNA sequencing by up to 49.9% with a high sensitivity (95%). In a context of limited resources, these methods increase sensitivity up to 69.8% at a 30% capacity of DNA sequencing tests, up to 85.1% at a 50% capacity, and up to 91.8% at a 70% capacity. These methods can also be used to prioritize patients with a positive predictive value up to 90.6% in the 10% patient most at risk of being mutated. Limitations of this study include the lack of external validation on non-TCGA data, dependence on prevalence of mutations in datasets, and use of a standard DL method on a limited dataset. Future studies using state-of-the-art methods and larger datasets are needed for better evaluation and clinical implementation.https://doi.org/10.1038/s41598-023-34016-y |
| spellingShingle | Louis-Oscar Morel Valentin Derangère Laurent Arnould Sylvain Ladoire Nathan Vinçon Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status Scientific Reports |
| title | Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status |
| title_full | Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status |
| title_fullStr | Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status |
| title_full_unstemmed | Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status |
| title_short | Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status |
| title_sort | preliminary evaluation of deep learning for first line diagnostic prediction of tumor mutational status |
| url | https://doi.org/10.1038/s41598-023-34016-y |
| work_keys_str_mv | AT louisoscarmorel preliminaryevaluationofdeeplearningforfirstlinediagnosticpredictionoftumormutationalstatus AT valentinderangere preliminaryevaluationofdeeplearningforfirstlinediagnosticpredictionoftumormutationalstatus AT laurentarnould preliminaryevaluationofdeeplearningforfirstlinediagnosticpredictionoftumormutationalstatus AT sylvainladoire preliminaryevaluationofdeeplearningforfirstlinediagnosticpredictionoftumormutationalstatus AT nathanvincon preliminaryevaluationofdeeplearningforfirstlinediagnosticpredictionoftumormutationalstatus |