Chemical imaging and machine learning for sub‐classification of oesophageal tissue histology
Abstract Fourier Transform Infrared (FTIR) based chemical imaging is a powerful, non‐destructive and label‐free biophotonic technique, which spatially acquires bio‐molecularly relevant information in histopathology. Cancer detection with objective chemical imaging techniques is relatively well estab...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2021-11-01
|
| Series: | Translational Biophotonics |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/tbio.202100004 |
| _version_ | 1828919754822254592 |
|---|---|
| author | Abigail Keogan Thi Nguyet Que Nguyen James J. Phelan Naoimh O'Farrell Niamh Lynam‐Lennon Brendan Doyle Dermot O'Toole John V. Reynolds Jacintha O'Sullivan Aidan D. Meade |
| author_facet | Abigail Keogan Thi Nguyet Que Nguyen James J. Phelan Naoimh O'Farrell Niamh Lynam‐Lennon Brendan Doyle Dermot O'Toole John V. Reynolds Jacintha O'Sullivan Aidan D. Meade |
| author_sort | Abigail Keogan |
| collection | DOAJ |
| description | Abstract Fourier Transform Infrared (FTIR) based chemical imaging is a powerful, non‐destructive and label‐free biophotonic technique, which spatially acquires bio‐molecularly relevant information in histopathology. Cancer detection with objective chemical imaging techniques is relatively well established, though detection of pre‐cancer stages within a continuum from normal tissue to cancer remains challenging. Here machine learning with chemical imaging was used to provide an objective classification pipeline for oesophageal tissues pathologically classified as normal, oesophagitis, dysplasia, Barrett's disease and cancer. Spectral images were segmented using a k‐means cluster validity indices approach and clustered spectra were classified using partial least squares discriminant analysis. Classification performances approached a receiver operator characteristic area‐under‐the‐curve (ROC‐AUC) of 0.90 for binary classification tasks (eg, normal vs Barrett's). Isolated histopathological substructures were identified which delivered a ROC‐AUC in of ~0.69 in classifying into each of the five‐classes. This work may provide the means to assist pathologist diagnoses of intermediate pre‐cancer stages. |
| first_indexed | 2024-12-13T21:34:20Z |
| format | Article |
| id | doaj.art-63b24369954a41efb8aabbedac63d2eb |
| institution | Directory Open Access Journal |
| issn | 2627-1850 |
| language | English |
| last_indexed | 2024-12-13T21:34:20Z |
| publishDate | 2021-11-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Translational Biophotonics |
| spelling | doaj.art-63b24369954a41efb8aabbedac63d2eb2022-12-21T23:30:44ZengWiley-VCHTranslational Biophotonics2627-18502021-11-0134n/an/a10.1002/tbio.202100004Chemical imaging and machine learning for sub‐classification of oesophageal tissue histologyAbigail Keogan0Thi Nguyet Que Nguyen1James J. Phelan2Naoimh O'Farrell3Niamh Lynam‐Lennon4Brendan Doyle5Dermot O'Toole6John V. Reynolds7Jacintha O'Sullivan8Aidan D. Meade9Radiation and Environmental Science Centre Focas Research Institute, Technological University Dublin Dublin IrelandRadiation and Environmental Science Centre Focas Research Institute, Technological University Dublin Dublin IrelandDepartment of Surgery Trinity Translational Medicine Institute, Trinity College Dublin Dublin IrelandDepartment of Surgery Trinity Translational Medicine Institute, Trinity College Dublin Dublin IrelandDepartment of Surgery Trinity Translational Medicine Institute, Trinity College Dublin Dublin IrelandDepartment of Histopathology Beaumont Hospital Dublin IrelandSchool of Clinical Medicine Trinity College Dublin Dublin IrelandDepartment of Surgery Trinity Translational Medicine Institute, Trinity College Dublin Dublin IrelandDepartment of Surgery Trinity Translational Medicine Institute, Trinity College Dublin Dublin IrelandRadiation and Environmental Science Centre Focas Research Institute, Technological University Dublin Dublin IrelandAbstract Fourier Transform Infrared (FTIR) based chemical imaging is a powerful, non‐destructive and label‐free biophotonic technique, which spatially acquires bio‐molecularly relevant information in histopathology. Cancer detection with objective chemical imaging techniques is relatively well established, though detection of pre‐cancer stages within a continuum from normal tissue to cancer remains challenging. Here machine learning with chemical imaging was used to provide an objective classification pipeline for oesophageal tissues pathologically classified as normal, oesophagitis, dysplasia, Barrett's disease and cancer. Spectral images were segmented using a k‐means cluster validity indices approach and clustered spectra were classified using partial least squares discriminant analysis. Classification performances approached a receiver operator characteristic area‐under‐the‐curve (ROC‐AUC) of 0.90 for binary classification tasks (eg, normal vs Barrett's). Isolated histopathological substructures were identified which delivered a ROC‐AUC in of ~0.69 in classifying into each of the five‐classes. This work may provide the means to assist pathologist diagnoses of intermediate pre‐cancer stages.https://doi.org/10.1002/tbio.202100004Barrett's OesophagusFTIR spectroscopyoesophageal adenocarcinomaPLSDA |
| spellingShingle | Abigail Keogan Thi Nguyet Que Nguyen James J. Phelan Naoimh O'Farrell Niamh Lynam‐Lennon Brendan Doyle Dermot O'Toole John V. Reynolds Jacintha O'Sullivan Aidan D. Meade Chemical imaging and machine learning for sub‐classification of oesophageal tissue histology Translational Biophotonics Barrett's Oesophagus FTIR spectroscopy oesophageal adenocarcinoma PLSDA |
| title | Chemical imaging and machine learning for sub‐classification of oesophageal tissue histology |
| title_full | Chemical imaging and machine learning for sub‐classification of oesophageal tissue histology |
| title_fullStr | Chemical imaging and machine learning for sub‐classification of oesophageal tissue histology |
| title_full_unstemmed | Chemical imaging and machine learning for sub‐classification of oesophageal tissue histology |
| title_short | Chemical imaging and machine learning for sub‐classification of oesophageal tissue histology |
| title_sort | chemical imaging and machine learning for sub classification of oesophageal tissue histology |
| topic | Barrett's Oesophagus FTIR spectroscopy oesophageal adenocarcinoma PLSDA |
| url | https://doi.org/10.1002/tbio.202100004 |
| work_keys_str_mv | AT abigailkeogan chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT thinguyetquenguyen chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT jamesjphelan chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT naoimhofarrell chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT niamhlynamlennon chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT brendandoyle chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT dermototoole chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT johnvreynolds chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT jacinthaosullivan chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology AT aidandmeade chemicalimagingandmachinelearningforsubclassificationofoesophagealtissuehistology |