Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy
Currently, colorectal cancer (CRC) is mainly identified via a visual assessment during colonoscopy, increasingly used artificial intelligence algorithms, or surgery. Subsequently, CRC is confirmed through a histopathological examination by a pathologist. Hyperspectral imaging (HSI), a non-invasive o...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-02-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/13/5/967 |
id |
doaj-42114d0126c445d0985918359c6734e6 |
---|---|
record_format |
Article |
spelling |
doaj-42114d0126c445d0985918359c6734e62021-02-26T00:06:47ZengMDPI AGCancers2072-66942021-02-011396796710.3390/cancers13050967Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical BiopsyBoris Jansen-Winkeln0Manuel Barberio1Claire Chalopin2Katrin Schierle3Michele Diana4Hannes Köhler5Ines Gockel6Marianne Maktabi7Department of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of Leipzig, 04103 Leipzig, GermanyDepartment of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of Leipzig, 04103 Leipzig, GermanyInnovation Center Computer-Assisted Surgery (ICCAS), University of Leipzig, 04103 Leipzig, GermanyInstitute of Pathology, University Hospital Leipzig, 04103 Leipzig, GermanyInstitute for Research against Digestive Cancer (IRCAD), 67091 Strasbourg, FranceInnovation Center Computer-Assisted Surgery (ICCAS), University of Leipzig, 04103 Leipzig, GermanyDepartment of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of Leipzig, 04103 Leipzig, GermanyInnovation Center Computer-Assisted Surgery (ICCAS), University of Leipzig, 04103 Leipzig, GermanyCurrently, colorectal cancer (CRC) is mainly identified via a visual assessment during colonoscopy, increasingly used artificial intelligence algorithms, or surgery. Subsequently, CRC is confirmed through a histopathological examination by a pathologist. Hyperspectral imaging (HSI), a non-invasive optical imaging technology, has shown promising results in the medical field. In the current study, we combined HSI with several artificial intelligence algorithms to discriminate CRC. Between July 2019 and May 2020, 54 consecutive patients undergoing colorectal resections for CRC were included. The tumor was imaged from the mucosal side with a hyperspectral camera. The image annotations were classified into three groups (cancer, CA; adenomatous margin around the central tumor, AD; and healthy mucosa, HM). Classification and visualization were performed based on a four-layer perceptron neural network. Based on a neural network, the classification of CA or AD resulted in a sensitivity of 86% and a specificity of 95%, by means of leave-one-patient-out cross-validation. Additionally, significant differences in terms of perfusion parameters (e.g., oxygen saturation) related to tumor staging and neoadjuvant therapy were observed. Hyperspectral imaging combined with automatic classification can be used to differentiate between CRC and healthy mucosa. Additionally, the biological changes induced by chemotherapy to the tissue are detectable with HSI.https://www.mdpi.com/2072-6694/13/5/967hyperspectral imaging (HSI), colorectal cancer (CRC), machine learningdeep learningoptical biopsyoptical imaging |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Boris Jansen-Winkeln Manuel Barberio Claire Chalopin Katrin Schierle Michele Diana Hannes Köhler Ines Gockel Marianne Maktabi |
spellingShingle |
Boris Jansen-Winkeln Manuel Barberio Claire Chalopin Katrin Schierle Michele Diana Hannes Köhler Ines Gockel Marianne Maktabi Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy Cancers hyperspectral imaging (HSI), colorectal cancer (CRC), machine learning deep learning optical biopsy optical imaging |
author_facet |
Boris Jansen-Winkeln Manuel Barberio Claire Chalopin Katrin Schierle Michele Diana Hannes Köhler Ines Gockel Marianne Maktabi |
author_sort |
Boris Jansen-Winkeln |
title |
Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy |
title_short |
Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy |
title_full |
Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy |
title_fullStr |
Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy |
title_full_unstemmed |
Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy |
title_sort |
feedforward artificial neural network-based colorectal cancer detection using hyperspectral imaging: a step towards automatic optical biopsy |
publisher |
MDPI AG |
series |
Cancers |
issn |
2072-6694 |
publishDate |
2021-02-01 |
description |
Currently, colorectal cancer (CRC) is mainly identified via a visual assessment during colonoscopy, increasingly used artificial intelligence algorithms, or surgery. Subsequently, CRC is confirmed through a histopathological examination by a pathologist. Hyperspectral imaging (HSI), a non-invasive optical imaging technology, has shown promising results in the medical field. In the current study, we combined HSI with several artificial intelligence algorithms to discriminate CRC. Between July 2019 and May 2020, 54 consecutive patients undergoing colorectal resections for CRC were included. The tumor was imaged from the mucosal side with a hyperspectral camera. The image annotations were classified into three groups (cancer, CA; adenomatous margin around the central tumor, AD; and healthy mucosa, HM). Classification and visualization were performed based on a four-layer perceptron neural network. Based on a neural network, the classification of CA or AD resulted in a sensitivity of 86% and a specificity of 95%, by means of leave-one-patient-out cross-validation. Additionally, significant differences in terms of perfusion parameters (e.g., oxygen saturation) related to tumor staging and neoadjuvant therapy were observed. Hyperspectral imaging combined with automatic classification can be used to differentiate between CRC and healthy mucosa. Additionally, the biological changes induced by chemotherapy to the tissue are detectable with HSI. |
topic |
hyperspectral imaging (HSI), colorectal cancer (CRC), machine learning deep learning optical biopsy optical imaging |
url |
https://www.mdpi.com/2072-6694/13/5/967 |
work_keys_str_mv |
AT borisjansenwinkeln feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy AT manuelbarberio feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy AT clairechalopin feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy AT katrinschierle feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy AT michelediana feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy AT hanneskohler feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy AT inesgockel feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy AT mariannemaktabi feedforwardartificialneuralnetworkbasedcolorectalcancerdetectionusinghyperspectralimagingasteptowardsautomaticopticalbiopsy |
_version_ |
1724250213829312512 |