Segmentation of black ink and melanin in skin histopathological images

被引:2
|
作者
Kleczek, Pawel [1 ]
Lech, Martyna [2 ]
Jaworek-Korjakowska, Joanna [1 ]
Dyduch, Grzegorz [2 ]
Tadeusiewicz, Ryszard [3 ]
机构
[1] AGH Univ Sci & Technol, Dept Automat & Robot, Al Mickiewicza 30, PL-30059 Krakow, Poland
[2] Jagiellonian Univ, Coll Med, Dept Pathomorphol, Ul Grzegorzecka 16, PL-31531 Krakow, Poland
[3] AGH Univ Sci & Technol, Dept Biocybernet & Biomed Engn, Al Mickiewicza 30, PL-30059 Krakow, Poland
来源
关键词
Histopathology; Image analysis; Melanin; Ink; Segmentation;
D O I
10.1117/12.2292859
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
The black ink (India ink) and melanin are substances often found in histopathological images of skin specimens. If present in abundant quantity, they negatively affect the outcome of automatic stain deconvolution methods. We propose an automatic black ink and melanin segmentation method based on global color thresholding in CIELAB color space combined with a novel region growing approach. Our technique achieved sensitivity of 87 %, specificity of 99 %, and precision of 94 % for black ink detection. It segmented melanin with sensitivity of 93 %, specificity of 99 %, and precision of 84 %. When excluding certain regions of images before performing color deconvolution, we observed better approximation of the stain unmixing matrix.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Automated Segmentation of the Melanocytes in Skin Histopathological Images
    Lu, Cheng
    Mahmood, Muhammad
    Jha, Naresh
    Mandal, Mrinal
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2013, 17 (02) : 284 - 296
  • [2] Hardware Implementation of Epidermis Segmentation in Skin Histopathological Images
    Machupalli, Raju
    de Oliveira, Luiz Antonio, Jr.
    Hossain, Masum
    Mandal, Mrinal
    [J]. ADVANCES IN SIGNAL PROCESSING AND COMMUNICATION ENGINEERING, ICASPACE 2021, 2022, 929 : 75 - 82
  • [3] Efficient Epidermis Segmentation for Whole Slide Skin Histopathological Images
    Lu, Cheng
    Mandal, Mrinal
    [J]. 2014 36TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2014, : 5546 - 5549
  • [4] Automated Segmentation and Analysis of the Epidermis Area in Skin Histopathological Images
    Lu, Cheng
    Mandal, Mrinal
    [J]. 2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2012, : 5355 - 5359
  • [5] Nuclear Segmentation For Skin Cancer Diagnosis From Histopathological Images
    Ray, Pravda Jith
    Priya, S.
    Kumar, Ashok T.
    [J]. 2015 GLOBAL CONFERENCE ON COMMUNICATION TECHNOLOGIES (GCCT), 2015, : 393 - 397
  • [6] Efficient Segmentation of Skin Epidermis in Whole Slide Histopathological Images
    Xu, Hongming
    Mandal, Mrinal
    [J]. 2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2015, : 3855 - 3858
  • [7] Automated segmentation of the epidermis area in skin whole slide histopathological images
    Lu, Cheng
    Ma, Zhen
    Mandal, Mrinal
    [J]. IET IMAGE PROCESSING, 2015, 9 (09) : 735 - 742
  • [8] Automated Segmentation of Regions of Interest in Whole Slide Skin Histopathological Images
    Xu, Hongming
    Lu, Cheng
    Mandal, Mrinal
    [J]. 2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2015, : 3869 - 3872
  • [9] Automated epidermis segmentation in histopathological images of human skin stained with hematoxylin and eosin
    Kleczek, Pawel
    Dyduch, Grzegorz
    Jaworek-Korjakowska, Joanna
    Tadeusiewicz, Ryszard
    [J]. MEDICAL IMAGING 2017: DIGITAL PATHOLOGY, 2017, 10140
  • [10] Hemoglobin and Melanin Quantification on Skin Images
    Gong, Hao
    Desvignes, Michel
    [J]. IMAGE ANALYSIS AND RECOGNITION, PT II, 2012, 7325 : 198 - 205