Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy

Worldwide, carcinomas are the second leading cause of death after cardiovascular diseases. Of these, more than 25 % are caused by cancer in the gastrointestinal tract. However, screening still misses about 20 % of carcinomas. An optimal solution would be a red flag technology to locate the suspiciou...

Whakaahuatanga katoa

I tiakina i:
Ngā taipitopito rārangi puna kōrero
Kaituhi matua: Hohmann, Martin
Hōputu: Online
Reo:Ingarihi
I whakaputaina: FAU University Press 2025
Ngā marau:
Urunga tuihono:ONIX_20251120T102856_9783961474462_28
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
_version_ 1869526691261448192
author Hohmann, Martin
author_browse Hohmann, Martin
author_facet Hohmann, Martin
author_sort Hohmann, Martin
collection Directory of Open Access Books
description Worldwide, carcinomas are the second leading cause of death after cardiovascular diseases. Of these, more than 25 % are caused by cancer in the gastrointestinal tract. However, screening still misses about 20 % of carcinomas. An optimal solution would be a red flag technology to locate the suspicious area. Despite the use of many optical technologies and advancements in traditional endoscopic technologies, most methods have failed to significantly improve the detectability of carcinomas in the GI. Therefore, it has been suggested in the literature to use spectroscopic quantitative measurements, which is achieved by hyperspectral imaging. However, in this work, a multispectral endoscope system for in vivo use is used for human (stomach) and mouse (colon) studies. In the human study, the tumours could only be found to a limited extent with the standard methods (MCC = 0.32; ACC2=0.68). Nevertheless, this is a significant improvement compared to previous results. The introduction of spectral spatial variation as a spatial-spectral feature improves the results significantly again. Compared to the human study, the results from the mouse model show better classification results: ACC2 = 0.73 and MCC = 0.47. Thus, for the development of an endoscopic red flag technique, a point technique for correct pre-labelling of the data is needed. Moreover, the results of this MSI in vivo study with spatial features are similar to the recent HSI ex vivo studies. Therefore, it is likely that MSI will remain part of future research.
format Online
id doab-20.500.12854ir-169126
institution Directory of Open Access Books
language eng
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher FAU University Press
publisherStr FAU University Press
record_format ojs
spelling doab-20.500.12854ir-1691262025-11-22T06:15:52Z Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy Hohmann, Martin Endoskopie Multispektral Hyperspektral Maschinenbau Tumor Produktionstechnik maschinelles Lernen Ingenieurwissenschaften thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials::TGB Mechanical engineering thema EDItEUR::P Mathematics and Science::PH Physics::PHV Applied physics::PHVD Medical physics thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TT Other technologies and applied sciences::TTB Applied optics::TTBM Imaging systems and technology Worldwide, carcinomas are the second leading cause of death after cardiovascular diseases. Of these, more than 25 % are caused by cancer in the gastrointestinal tract. However, screening still misses about 20 % of carcinomas. An optimal solution would be a red flag technology to locate the suspicious area. Despite the use of many optical technologies and advancements in traditional endoscopic technologies, most methods have failed to significantly improve the detectability of carcinomas in the GI. Therefore, it has been suggested in the literature to use spectroscopic quantitative measurements, which is achieved by hyperspectral imaging. However, in this work, a multispectral endoscope system for in vivo use is used for human (stomach) and mouse (colon) studies. In the human study, the tumours could only be found to a limited extent with the standard methods (MCC = 0.32; ACC2=0.68). Nevertheless, this is a significant improvement compared to previous results. The introduction of spectral spatial variation as a spatial-spectral feature improves the results significantly again. Compared to the human study, the results from the mouse model show better classification results: ACC2 = 0.73 and MCC = 0.47. Thus, for the development of an endoscopic red flag technique, a point technique for correct pre-labelling of the data is needed. Moreover, the results of this MSI in vivo study with spatial features are similar to the recent HSI ex vivo studies. Therefore, it is likely that MSI will remain part of future research. 2025-11-21T05:19:19Z 2025-11-21T05:19:19Z 2025-11-20T09:33:30Z 2021 book ONIX_20251120T102856_9783961474462_28 https://library.oapen.org/handle/20.500.12657/108240 9783961474462 9783961474455 https://directory.doabooks.org/handle/20.500.12854/169126 eng FAU Studien aus dem Maschinenbau open access image/jpeg Attribution-NonCommercial 4.0 International https://library.oapen.org/bitstream/20.500.12657/108240/1/9783961474462.pdf FAU University Press 10.25593/978-3-96147-446-2 10.25593/978-3-96147-446-2 2c600dea-eece-4066-87be-da335e323fdb 9783961474462 9783961474455 137 Erlangen open access
spellingShingle Endoskopie
Multispektral
Hyperspektral
Maschinenbau
Tumor
Produktionstechnik
maschinelles Lernen
Ingenieurwissenschaften
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials::TGB Mechanical engineering
thema EDItEUR::P Mathematics and Science::PH Physics::PHV Applied physics::PHVD Medical physics
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TT Other technologies and applied sciences::TTB Applied optics::TTBM Imaging systems and technology
Hohmann, Martin
Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy
title Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy
title_full Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy
title_fullStr Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy
title_full_unstemmed Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy
title_short Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy
title_sort machine learning and hyper spectral imaging multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy
topic Endoskopie
Multispektral
Hyperspektral
Maschinenbau
Tumor
Produktionstechnik
maschinelles Lernen
Ingenieurwissenschaften
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials::TGB Mechanical engineering
thema EDItEUR::P Mathematics and Science::PH Physics::PHV Applied physics::PHVD Medical physics
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TT Other technologies and applied sciences::TTB Applied optics::TTBM Imaging systems and technology
topic_facet Endoskopie
Multispektral
Hyperspektral
Maschinenbau
Tumor
Produktionstechnik
maschinelles Lernen
Ingenieurwissenschaften
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials::TGB Mechanical engineering
thema EDItEUR::P Mathematics and Science::PH Physics::PHV Applied physics::PHVD Medical physics
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TT Other technologies and applied sciences::TTB Applied optics::TTBM Imaging systems and technology
url ONIX_20251120T102856_9783961474462_28
work_keys_str_mv AT hohmannmartin machinelearningandhyperspectralimagingmultispectralendoscopyinthegastrointestinaltracttowardshyperspectralendoscopy