Dimensionality reduction for deep learning in infrared microscopy: a comparative computational survey-Reference-Cited by-同舟云学术

Dimensionality reduction for deep learning in infrared microscopy: a comparative computational survey

Published:2023 Issue:20 Volume:148 Page:5022-5032
ISSN:0003-2654
Container-title:The Analyst
language:en
Short-container-title:Analyst

Author:

Müller Dajana¹²^ORCID,Schuhmacher David¹²,Schörner Stephanie¹³,Großerueschkamp Frederik¹³,Tischoff Iris⁴,Tannapfel Andrea¹⁴,Reinacher-Schick Anke¹⁵,Gerwert Klaus¹³^ORCID,Mosig Axel¹²

Affiliation:

1. Ruhr University Bochum, Center for Protein Diagnostics, Bochum, 44801, Germany

2. Ruhr University Bochum, Faculty of Biology and Biotechnology, Bioinformatics Group, 44801, Germany

3. Ruhr University Bochum, Faculty of Biology and Biotechnology, Department of Biophysics, 44801, Germany

4. Institute of Pathology, Ruhr-University Bochum, 44789 Bochum, Germany

5. Department of Hematology, Oncology and Palliative Care, Ruhr-University Bochum, Bochum, Germany

Abstract

We compare dimensionality reduction approaches and their effect on identifying cancer in infrared microscopic images. Neural networks trained on reduced spectra perform surprisingly well, indicating the importance of spatial information.

Funder

Ministerium für Kultur und Wissenschaft des Landes Nordrhein-Westfalen

Bundesministerium für Bildung und Forschung

Publisher

Royal Society of Chemistry (RSC)

Subject

Electrochemistry,Spectroscopy,Environmental Chemistry,Biochemistry,Analytical Chemistry

Link

http://pubs.rsc.org/en/content/articlepdf/2023/AN/D3AN00166K

Reference43 articles.

1. Infrared imaging in histopathology: Is a unified approach possible?

2. Spectropathology for the next generation: Quo vadis?

3. Immunohistochemistry, histopathology and infrared spectral histopathology of colon cancer tissue sections

4. Quantum Cascade Laser-Based Infrared Microscopy for Label-Free and Automated Cancer Classification in Tissue Sections

5. A framework for falsifiable explanations of machine learning models with an application in computational pathology

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Preliminary evaluation of an automated autoencoder-UNet pipeline for chemical image segmentation and compression with reference to serial ground truth pathology;Data Science for Photonics and Biophotonics;2024-06-18