Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 766627

Unsupervised segmentation of low-contrast multichannel images: discrimination of tissue components in microscopic images of unstained specimens


Kopriva, Ivica; Popović Hadžija, Marijana; Hadžija, Mirko; Aralica, Gorana
Unsupervised segmentation of low-contrast multichannel images: discrimination of tissue components in microscopic images of unstained specimens // Scientific Reports, 5 (2015), 11576-1 doi:10.1038/srep11576 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 766627 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Unsupervised segmentation of low-contrast multichannel images: discrimination of tissue components in microscopic images of unstained specimens

Autori
Kopriva, Ivica ; Popović Hadžija, Marijana ; Hadžija, Mirko ; Aralica, Gorana

Izvornik
Scientific Reports (2045-2322) 5 (2015); 11576-1

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
optical imaging; computational science

Sažetak
Low-contrast images, such as color microscopic images of unstained histological specimens, are composed of objects with highly correlated spectral profiles. Such images are very hard to segment. Here, we present a method that nonlinearly maps low-contrast color image into an image with an increased number of non-physical channels and a decreased correlation between spectral profiles. The method is a proof-of-concept validated on the unsupervised segmentation of color images of unstained specimens, in which case the tissue components appear colorless when viewed under the light microscope. Specimens of human hepatocellular carcinoma, human liver with metastasis from colon and gastric cancer and mouse fatty liver were used for validation. The average correlation between the spectral profiles of the tissue components was greater than 0.9985, and the worst case correlation was greater than 0.9997. The proposed method can potentially be applied to the segmentation of low-contrast multichannel images with high spatial resolution that arise in other imaging modalities.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Računarstvo, Kliničke medicinske znanosti



POVEZANOST RADA


Projekti:
HZZ 9.01/232

Ustanove:
Institut "Ruđer Bošković", Zagreb,
Medicinski fakultet, Zagreb,
Klinička bolnica "Dubrava"

Citiraj ovu publikaciju

Kopriva, Ivica; Popović Hadžija, Marijana; Hadžija, Mirko; Aralica, Gorana
Unsupervised segmentation of low-contrast multichannel images: discrimination of tissue components in microscopic images of unstained specimens // Scientific Reports, 5 (2015), 11576-1 doi:10.1038/srep11576 (međunarodna recenzija, članak, znanstveni)
Kopriva, I., Popović Hadžija, M., Hadžija, M. & Aralica, G. (2015) Unsupervised segmentation of low-contrast multichannel images: discrimination of tissue components in microscopic images of unstained specimens. Scientific Reports, 5, 11576-1 doi:10.1038/srep11576.
@article{article, year = {2015}, pages = {11576-1-11576-13}, DOI = {10.1038/srep11576}, keywords = {optical imaging, computational science}, journal = {Scientific Reports}, doi = {10.1038/srep11576}, volume = {5}, issn = {2045-2322}, title = {Unsupervised segmentation of low-contrast multichannel images: discrimination of tissue components in microscopic images of unstained specimens}, keyword = {optical imaging, computational science} }
@article{article, year = {2015}, pages = {11576-1-11576-13}, DOI = {10.1038/srep11576}, keywords = {optical imaging, computational science}, journal = {Scientific Reports}, doi = {10.1038/srep11576}, volume = {5}, issn = {2045-2322}, title = {Unsupervised segmentation of low-contrast multichannel images: discrimination of tissue components in microscopic images of unstained specimens}, keyword = {optical imaging, computational science} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus
  • MEDLINE


Citati





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font