Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging
Abstract Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ign...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-024-00772-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595068749348864 |
|---|---|
| author | Abigail Keogan Thi Nguyet Que Nguyen Pascaline Bouzy Nicholas Stone Karin Jirstrom Arman Rahman William M. Gallagher Aidan D. Meade |
| author_facet | Abigail Keogan Thi Nguyet Que Nguyen Pascaline Bouzy Nicholas Stone Karin Jirstrom Arman Rahman William M. Gallagher Aidan D. Meade |
| author_sort | Abigail Keogan |
| collection | DOAJ |
| description | Abstract Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ignore the spatial context of the cellular material and are, therefore, of limited value in the development of mechanistic models. In this study, Fourier-transform infrared (FTIR) chemical images of BC tissue were used to train deep learning models to predict future disease recurrence. A number of deep learning models were employed, with champion models employing two-dimensional and two-dimensional-separable convolutional networks found to have predictive performance of a ROC AUC of approximately 0.64, which compares well to other clinically used prognostic assays in this space. All-digital chemical imaging may therefore provide a label-free platform for histopathological prognosis in breast cancer, opening new horizons for future deployment of these technologies. |
| format | Article |
| id | doaj-art-ba598c7a211743f58cbdc072741d6d01 |
| institution | Kabale University |
| issn | 2397-768X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-ba598c7a211743f58cbdc072741d6d012025-01-19T12:08:18ZengNature Portfolionpj Precision Oncology2397-768X2025-01-019111110.1038/s41698-024-00772-xPrediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imagingAbigail Keogan0Thi Nguyet Que Nguyen1Pascaline Bouzy2Nicholas Stone3Karin Jirstrom4Arman Rahman5William M. Gallagher6Aidan D. Meade7Radiation and Environmental Science Centre, Physical to Life Sciences Research Hub, Technological University DublinDigital Futures Research Hub, Technological University DublinDepartment of Physics and Astronomy, University of ExeterDepartment of Physics and Astronomy, University of ExeterDivision of Oncology and Therapeutic Pathology, Department of Clinical Sciences, Lund UniversityUCD School of Biomolecular and Biomedical Science, UCD Conway Institute, University College DublinUCD School of Biomolecular and Biomedical Science, UCD Conway Institute, University College DublinRadiation and Environmental Science Centre, Physical to Life Sciences Research Hub, Technological University DublinAbstract Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ignore the spatial context of the cellular material and are, therefore, of limited value in the development of mechanistic models. In this study, Fourier-transform infrared (FTIR) chemical images of BC tissue were used to train deep learning models to predict future disease recurrence. A number of deep learning models were employed, with champion models employing two-dimensional and two-dimensional-separable convolutional networks found to have predictive performance of a ROC AUC of approximately 0.64, which compares well to other clinically used prognostic assays in this space. All-digital chemical imaging may therefore provide a label-free platform for histopathological prognosis in breast cancer, opening new horizons for future deployment of these technologies.https://doi.org/10.1038/s41698-024-00772-x |
| spellingShingle | Abigail Keogan Thi Nguyet Que Nguyen Pascaline Bouzy Nicholas Stone Karin Jirstrom Arman Rahman William M. Gallagher Aidan D. Meade Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging npj Precision Oncology |
| title | Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging |
| title_full | Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging |
| title_fullStr | Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging |
| title_full_unstemmed | Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging |
| title_short | Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging |
| title_sort | prediction of post treatment recurrence in early stage breast cancer using deep learning with mid infrared chemical histopathological imaging |
| url | https://doi.org/10.1038/s41698-024-00772-x |
| work_keys_str_mv | AT abigailkeogan predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging AT thinguyetquenguyen predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging AT pascalinebouzy predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging AT nicholasstone predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging AT karinjirstrom predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging AT armanrahman predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging AT williammgallagher predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging AT aidandmeade predictionofposttreatmentrecurrenceinearlystagebreastcancerusingdeeplearningwithmidinfraredchemicalhistopathologicalimaging |