Tissue classification of liver pathological tissue specimens image using spectral features

Emi Hashimoto, Masahiro Ishikawa, Kazuma Shinoda, Madoka Hasegawa, Hideki Komagata, Naoki Kobayashi, Naoki Mochidome, Yoshinao Oda, Chika Iwamoto, Kenoki Ouchida, Makoto Hashizume

研究成果: 著書/レポートタイプへの貢献会議での発言

4 引用 (Scopus)

抄録

In digital pathology diagnosis, accurate recognition and quantification of the tissue structure is an important factor for computer-aided diagnosis. However, the classification accuracy of cytoplasm is low in Hematoxylin and eosin (HE) stained liver pathology specimens because the RGB color values of cytoplasm are almost similar to that of fibers. In this paper, we propose a new tissue classification method for HE stained liver pathology specimens by using hyperspectral image. At first we select valid spectra from the image to make a clear distinction between fibers and cytoplasm, and then classify five types of tissue based on the bag of features (BoF). The average classification accuracy for all tissues was improved by 11% in the case of using BoF of RGB and selected spectra bands in comparison with using only RGB. In particular, the improvement reached to 24% for fibers and 5% for cytoplasm.

元の言語英語
ホスト出版物のタイトルMedical Imaging 2017
ホスト出版物のサブタイトルDigital Pathology
出版者SPIE
10140
ISBN(電子版)9781510607255
DOI
出版物ステータス出版済み - 1 1 2017
イベントMedical Imaging 2017: Digital Pathology - Orlando, 米国
継続期間: 2 12 20172 13 2017

その他

その他Medical Imaging 2017: Digital Pathology
米国
Orlando
期間2/12/172/13/17

Fingerprint

cytoplasm
liver
Liver
Cytoplasm
pathology
Pathology
Tissue
bags
Hematoxylin
Eosine Yellowish-(YS)
fibers
Fibers
Computer aided diagnosis
Color
color

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

これを引用

Hashimoto, E., Ishikawa, M., Shinoda, K., Hasegawa, M., Komagata, H., Kobayashi, N., ... Hashizume, M. (2017). Tissue classification of liver pathological tissue specimens image using spectral features. : Medical Imaging 2017: Digital Pathology (巻 10140). [101400Z] SPIE. https://doi.org/10.1117/12.2253818

Tissue classification of liver pathological tissue specimens image using spectral features. / Hashimoto, Emi; Ishikawa, Masahiro; Shinoda, Kazuma; Hasegawa, Madoka; Komagata, Hideki; Kobayashi, Naoki; Mochidome, Naoki; Oda, Yoshinao; Iwamoto, Chika; Ouchida, Kenoki; Hashizume, Makoto.

Medical Imaging 2017: Digital Pathology. 巻 10140 SPIE, 2017. 101400Z.

研究成果: 著書/レポートタイプへの貢献会議での発言

Hashimoto, E, Ishikawa, M, Shinoda, K, Hasegawa, M, Komagata, H, Kobayashi, N, Mochidome, N, Oda, Y, Iwamoto, C, Ouchida, K & Hashizume, M 2017, Tissue classification of liver pathological tissue specimens image using spectral features. : Medical Imaging 2017: Digital Pathology. 巻. 10140, 101400Z, SPIE, Medical Imaging 2017: Digital Pathology, Orlando, 米国, 2/12/17. https://doi.org/10.1117/12.2253818
Hashimoto E, Ishikawa M, Shinoda K, Hasegawa M, Komagata H, Kobayashi N その他. Tissue classification of liver pathological tissue specimens image using spectral features. : Medical Imaging 2017: Digital Pathology. 巻 10140. SPIE. 2017. 101400Z https://doi.org/10.1117/12.2253818
Hashimoto, Emi ; Ishikawa, Masahiro ; Shinoda, Kazuma ; Hasegawa, Madoka ; Komagata, Hideki ; Kobayashi, Naoki ; Mochidome, Naoki ; Oda, Yoshinao ; Iwamoto, Chika ; Ouchida, Kenoki ; Hashizume, Makoto. / Tissue classification of liver pathological tissue specimens image using spectral features. Medical Imaging 2017: Digital Pathology. 巻 10140 SPIE, 2017.
@inproceedings{101f5f4e40914af496ee7ba49affefb7,
title = "Tissue classification of liver pathological tissue specimens image using spectral features",
abstract = "In digital pathology diagnosis, accurate recognition and quantification of the tissue structure is an important factor for computer-aided diagnosis. However, the classification accuracy of cytoplasm is low in Hematoxylin and eosin (HE) stained liver pathology specimens because the RGB color values of cytoplasm are almost similar to that of fibers. In this paper, we propose a new tissue classification method for HE stained liver pathology specimens by using hyperspectral image. At first we select valid spectra from the image to make a clear distinction between fibers and cytoplasm, and then classify five types of tissue based on the bag of features (BoF). The average classification accuracy for all tissues was improved by 11{\%} in the case of using BoF of RGB and selected spectra bands in comparison with using only RGB. In particular, the improvement reached to 24{\%} for fibers and 5{\%} for cytoplasm.",
author = "Emi Hashimoto and Masahiro Ishikawa and Kazuma Shinoda and Madoka Hasegawa and Hideki Komagata and Naoki Kobayashi and Naoki Mochidome and Yoshinao Oda and Chika Iwamoto and Kenoki Ouchida and Makoto Hashizume",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2253818",
language = "English",
volume = "10140",
booktitle = "Medical Imaging 2017",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Tissue classification of liver pathological tissue specimens image using spectral features

AU - Hashimoto, Emi

AU - Ishikawa, Masahiro

AU - Shinoda, Kazuma

AU - Hasegawa, Madoka

AU - Komagata, Hideki

AU - Kobayashi, Naoki

AU - Mochidome, Naoki

AU - Oda, Yoshinao

AU - Iwamoto, Chika

AU - Ouchida, Kenoki

AU - Hashizume, Makoto

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In digital pathology diagnosis, accurate recognition and quantification of the tissue structure is an important factor for computer-aided diagnosis. However, the classification accuracy of cytoplasm is low in Hematoxylin and eosin (HE) stained liver pathology specimens because the RGB color values of cytoplasm are almost similar to that of fibers. In this paper, we propose a new tissue classification method for HE stained liver pathology specimens by using hyperspectral image. At first we select valid spectra from the image to make a clear distinction between fibers and cytoplasm, and then classify five types of tissue based on the bag of features (BoF). The average classification accuracy for all tissues was improved by 11% in the case of using BoF of RGB and selected spectra bands in comparison with using only RGB. In particular, the improvement reached to 24% for fibers and 5% for cytoplasm.

AB - In digital pathology diagnosis, accurate recognition and quantification of the tissue structure is an important factor for computer-aided diagnosis. However, the classification accuracy of cytoplasm is low in Hematoxylin and eosin (HE) stained liver pathology specimens because the RGB color values of cytoplasm are almost similar to that of fibers. In this paper, we propose a new tissue classification method for HE stained liver pathology specimens by using hyperspectral image. At first we select valid spectra from the image to make a clear distinction between fibers and cytoplasm, and then classify five types of tissue based on the bag of features (BoF). The average classification accuracy for all tissues was improved by 11% in the case of using BoF of RGB and selected spectra bands in comparison with using only RGB. In particular, the improvement reached to 24% for fibers and 5% for cytoplasm.

UR - http://www.scopus.com/inward/record.url?scp=85020255639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020255639&partnerID=8YFLogxK

U2 - 10.1117/12.2253818

DO - 10.1117/12.2253818

M3 - Conference contribution

VL - 10140

BT - Medical Imaging 2017

PB - SPIE

ER -