Automatic renal interstitial fibrosis quantification system

Wei Keat Tey, Ye Chow Kuang, Joon Joon Khoo, Melanie Po Leen Ooi, Serge Demidenko

    Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

    Abstract

    Interstitial fibrosis in renal biopsies has shown a good correlation to the presence of chronic kidney disease, and it is therefore quantified by pathologists in the diagnosis of the disease. In the previous work, the developed automatic quantification system for the interstitial fibrosis was presented. It was based on the segmentation of tubular structures. This paper advances the development of the system by expanding the set of identifiable structures to include glomerulus, arteries, and urinary casts. In particular, it investigates two methods of the glomerular detection, namely the Bowman's space search and rLADTree classification. The quantification results of the final system incorporating segmentation of all commonly seen structures have shown a quantification matching that produced by the ground truth to within 8.8%, while the glomerulus structure detection by rLADTree classification method outperformed its alternative due to its higher robustness in tolerating the variance in the glomerulus appearance.

    Original languageEnglish
    Title of host publicationI2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    ISBN (Electronic)9781509035960
    DOIs
    Publication statusPublished - 5 Jul 2017
    EventIEEE International Instrumentation and Measurement Technology Conference 2017 - Torino, Italy
    Duration: 22 May 201725 May 2017
    http://2017.imtc.ieee-ims.org/

    Conference

    ConferenceIEEE International Instrumentation and Measurement Technology Conference 2017
    Abbreviated titleI2MTC 2017
    CountryItaly
    CityTorino
    Period22/05/1725/05/17
    Internet address

    Keywords

    • Glomerulus segmentation
    • Medical image analysis
    • Renal fibrosis
    • RLADTree

    Cite this

    Tey, W. K., Kuang, Y. C., Khoo, J. J., Ooi, M. P. L., & Demidenko, S. (2017). Automatic renal interstitial fibrosis quantification system. In I2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings [7969716] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/I2MTC.2017.7969716
    Tey, Wei Keat ; Kuang, Ye Chow ; Khoo, Joon Joon ; Ooi, Melanie Po Leen ; Demidenko, Serge. / Automatic renal interstitial fibrosis quantification system. I2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2017.
    @inproceedings{84873a3542944e8b80fa59faa271f760,
    title = "Automatic renal interstitial fibrosis quantification system",
    abstract = "Interstitial fibrosis in renal biopsies has shown a good correlation to the presence of chronic kidney disease, and it is therefore quantified by pathologists in the diagnosis of the disease. In the previous work, the developed automatic quantification system for the interstitial fibrosis was presented. It was based on the segmentation of tubular structures. This paper advances the development of the system by expanding the set of identifiable structures to include glomerulus, arteries, and urinary casts. In particular, it investigates two methods of the glomerular detection, namely the Bowman's space search and rLADTree classification. The quantification results of the final system incorporating segmentation of all commonly seen structures have shown a quantification matching that produced by the ground truth to within 8.8{\%}, while the glomerulus structure detection by rLADTree classification method outperformed its alternative due to its higher robustness in tolerating the variance in the glomerulus appearance.",
    keywords = "Glomerulus segmentation, Medical image analysis, Renal fibrosis, RLADTree",
    author = "Tey, {Wei Keat} and Kuang, {Ye Chow} and Khoo, {Joon Joon} and Ooi, {Melanie Po Leen} and Serge Demidenko",
    year = "2017",
    month = "7",
    day = "5",
    doi = "10.1109/I2MTC.2017.7969716",
    language = "English",
    booktitle = "I2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States of America",

    }

    Tey, WK, Kuang, YC, Khoo, JJ, Ooi, MPL & Demidenko, S 2017, Automatic renal interstitial fibrosis quantification system. in I2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings., 7969716, IEEE, Institute of Electrical and Electronics Engineers, IEEE International Instrumentation and Measurement Technology Conference 2017, Torino, Italy, 22/05/17. https://doi.org/10.1109/I2MTC.2017.7969716

    Automatic renal interstitial fibrosis quantification system. / Tey, Wei Keat; Kuang, Ye Chow; Khoo, Joon Joon; Ooi, Melanie Po Leen; Demidenko, Serge.

    I2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2017. 7969716.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

    TY - GEN

    T1 - Automatic renal interstitial fibrosis quantification system

    AU - Tey, Wei Keat

    AU - Kuang, Ye Chow

    AU - Khoo, Joon Joon

    AU - Ooi, Melanie Po Leen

    AU - Demidenko, Serge

    PY - 2017/7/5

    Y1 - 2017/7/5

    N2 - Interstitial fibrosis in renal biopsies has shown a good correlation to the presence of chronic kidney disease, and it is therefore quantified by pathologists in the diagnosis of the disease. In the previous work, the developed automatic quantification system for the interstitial fibrosis was presented. It was based on the segmentation of tubular structures. This paper advances the development of the system by expanding the set of identifiable structures to include glomerulus, arteries, and urinary casts. In particular, it investigates two methods of the glomerular detection, namely the Bowman's space search and rLADTree classification. The quantification results of the final system incorporating segmentation of all commonly seen structures have shown a quantification matching that produced by the ground truth to within 8.8%, while the glomerulus structure detection by rLADTree classification method outperformed its alternative due to its higher robustness in tolerating the variance in the glomerulus appearance.

    AB - Interstitial fibrosis in renal biopsies has shown a good correlation to the presence of chronic kidney disease, and it is therefore quantified by pathologists in the diagnosis of the disease. In the previous work, the developed automatic quantification system for the interstitial fibrosis was presented. It was based on the segmentation of tubular structures. This paper advances the development of the system by expanding the set of identifiable structures to include glomerulus, arteries, and urinary casts. In particular, it investigates two methods of the glomerular detection, namely the Bowman's space search and rLADTree classification. The quantification results of the final system incorporating segmentation of all commonly seen structures have shown a quantification matching that produced by the ground truth to within 8.8%, while the glomerulus structure detection by rLADTree classification method outperformed its alternative due to its higher robustness in tolerating the variance in the glomerulus appearance.

    KW - Glomerulus segmentation

    KW - Medical image analysis

    KW - Renal fibrosis

    KW - RLADTree

    UR - http://www.scopus.com/inward/record.url?scp=85026777480&partnerID=8YFLogxK

    U2 - 10.1109/I2MTC.2017.7969716

    DO - 10.1109/I2MTC.2017.7969716

    M3 - Conference Paper

    AN - SCOPUS:85026777480

    BT - I2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings

    PB - IEEE, Institute of Electrical and Electronics Engineers

    ER -

    Tey WK, Kuang YC, Khoo JJ, Ooi MPL, Demidenko S. Automatic renal interstitial fibrosis quantification system. In I2MTC 2017 - 2017 IEEE International Instrumentation and Measurement Technology Conference, Proceedings. IEEE, Institute of Electrical and Electronics Engineers. 2017. 7969716 https://doi.org/10.1109/I2MTC.2017.7969716