Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging
Abstract Esophageal cancer is the sixth leading cause of cancer-related death worldwide. Histopathological confirmation is a key step in tumor diagnosis. Therefore, simplification in decision-making by discrimination between malignant and non-malignant cells of histological specimens can be provided...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-07524-6 |
| _version_ | 1818315451458912256 |
|---|---|
| author | Marianne Maktabi Yannis Wichmann Hannes Köhler Henning Ahle Dietmar Lorenz Michael Bange Susanne Braun Ines Gockel Claire Chalopin René Thieme |
| author_facet | Marianne Maktabi Yannis Wichmann Hannes Köhler Henning Ahle Dietmar Lorenz Michael Bange Susanne Braun Ines Gockel Claire Chalopin René Thieme |
| author_sort | Marianne Maktabi |
| collection | DOAJ |
| description | Abstract Esophageal cancer is the sixth leading cause of cancer-related death worldwide. Histopathological confirmation is a key step in tumor diagnosis. Therefore, simplification in decision-making by discrimination between malignant and non-malignant cells of histological specimens can be provided by combination of new imaging technology and artificial intelligence (AI). In this work, hyperspectral imaging (HSI) data from 95 patients were used to classify three different histopathological features (squamous epithelium cells, esophageal adenocarcinoma (EAC) cells, and tumor stroma cells), based on a multi-layer perceptron with two hidden layers. We achieved an accuracy of 78% for EAC and stroma cells, and 80% for squamous epithelium. HSI combined with machine learning algorithms is a promising and innovative technique, which allows image acquisition beyond Red–Green–Blue (RGB) images. Further method validation and standardization will be necessary, before automated tumor cell identification algorithms can be used in daily clinical practice. |
| first_indexed | 2024-12-13T09:05:45Z |
| format | Article |
| id | doaj.art-68982a5cd6a04356b2985d1e39e60ca1 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-13T09:05:45Z |
| publishDate | 2022-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-68982a5cd6a04356b2985d1e39e60ca12022-12-21T23:53:05ZengNature PortfolioScientific Reports2045-23222022-03-0112111410.1038/s41598-022-07524-6Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imagingMarianne Maktabi0Yannis Wichmann1Hannes Köhler2Henning Ahle3Dietmar Lorenz4Michael Bange5Susanne Braun6Ines Gockel7Claire Chalopin8René Thieme9Innovation Center Computer Assisted Surgery (ICCAS), Leipzig UniversityDepartment of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of LeipzigInnovation Center Computer Assisted Surgery (ICCAS), Leipzig UniversityDepartment of General and Visceral Surgery, Sana Clinic Offenbach GmbHDepartment of General, Visceral and Thoracic Surgery, Municipal Hospital of Darmstadt GmbHInstitute of Pathology, Sana Clinic Offenbach GmbHInstitute of Pathology, Sana Clinic Offenbach GmbHDepartment of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of LeipzigInnovation Center Computer Assisted Surgery (ICCAS), Leipzig UniversityDepartment of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of LeipzigAbstract Esophageal cancer is the sixth leading cause of cancer-related death worldwide. Histopathological confirmation is a key step in tumor diagnosis. Therefore, simplification in decision-making by discrimination between malignant and non-malignant cells of histological specimens can be provided by combination of new imaging technology and artificial intelligence (AI). In this work, hyperspectral imaging (HSI) data from 95 patients were used to classify three different histopathological features (squamous epithelium cells, esophageal adenocarcinoma (EAC) cells, and tumor stroma cells), based on a multi-layer perceptron with two hidden layers. We achieved an accuracy of 78% for EAC and stroma cells, and 80% for squamous epithelium. HSI combined with machine learning algorithms is a promising and innovative technique, which allows image acquisition beyond Red–Green–Blue (RGB) images. Further method validation and standardization will be necessary, before automated tumor cell identification algorithms can be used in daily clinical practice.https://doi.org/10.1038/s41598-022-07524-6 |
| spellingShingle | Marianne Maktabi Yannis Wichmann Hannes Köhler Henning Ahle Dietmar Lorenz Michael Bange Susanne Braun Ines Gockel Claire Chalopin René Thieme Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging Scientific Reports |
| title | Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging |
| title_full | Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging |
| title_fullStr | Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging |
| title_full_unstemmed | Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging |
| title_short | Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging |
| title_sort | tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging |
| url | https://doi.org/10.1038/s41598-022-07524-6 |
| work_keys_str_mv | AT mariannemaktabi tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT yanniswichmann tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT hanneskohler tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT henningahle tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT dietmarlorenz tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT michaelbange tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT susannebraun tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT inesgockel tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT clairechalopin tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging AT renethieme tumorcellidentificationandclassificationinesophagealadenocarcinomaspecimensbyhyperspectralimaging |